Defect classification and detection have been explored using convolutional neural networks (CNNs). Normally, a large set of training images containing defects and the associated annotation data are required by these approaches. However, such a large set of images is usually difficult to collect because defects are rare and annotation is time-consuming and expensive. To address these issues, we propose to use a multitask deep one-class CNN for defect classification. Compared with supervised classification methods, this CNN does not require abnormal images and annotated data for training. Specifically, we build a stacked encoder–decoder autoencoder for learning feature representation from normal images. The encoder is used as a feature extractor based on the hard sharing scheme of multitask learning. A one-class classification (OCC) objective learned as a hypersphere using minimum volume estimation is appended to it. Together the encoder and the OCC objective lead to a deep one-class classifier. To train both the autoencoder and one-class classifier end-to-end, a multitask loss function is built. Given an unknown sample, the distance between its feature representation and the center of the hypersphere is used as the anomaly score. Furthermore, defect detection is implemented using a moving-window scanning method on top of the deep one-class classifier. The proposed approach achieves better performance than its counterparts trained using a two-stage method. For defect detection, our approach achieves results almost as good as the supervised method even without using any annotated data. We attribute the promising results to the advantages of multitask learning.Note to Practitioners—Building and evaluating vision-based nondestructive testing (NDT) techniques require many examples of abnormal images, which may not be easy to acquire. This article describes a method that does not require abnormal images for training a convolutional neural network (CNN) in order to perform one-class defect classification (outlier detection). We also applied the method to defect detection with promising results. We include results of experiments demonstrating that better performance can be obtained using our method compared to a set of baselines. Although the proposed method does not use abnormal images for training, it still produces results that are almost as good as the supervised learning-based CNN approaches. This study provides a solution to the challenge encountered by the industrial inspection community when enough abnormal samples are hard to obtain.

In the aerospace manufacturing industry, nondestructive evaluation (NDE) of components plays an important role. Porosities and other defects usually occur in the welds of these components. If such defects end up in the aircraft, the fatigue life of components is lessened, which may cause disastrous accidents. At present, those welds are manually evaluated by human inspectors via reviewing X-ray images. To reduce the workload of inspectors, we have developed an automatic inspection system for identifying defects in linear thin welds. For an X-ray image, this system starts with localizing the central line of the weld using a random forest (RF) regressor. A region surrounding the line is then investigated using an RF classifier in order to detect defects. After extensive experiments, the results demonstrate that the weld can be precisely localized from X-ray images, and the defect detection module can find 80% of defects that have been identified by human inspectors (i.e., true positives), while fewer than 1.6 false positives per image are returned. It is suggested that the system may be beneficial to human inspectors by reducing their workload. In addition, our system produces encouraging results on the publicly available weld X-ray image data set and a magnetic tile image data set.Note to Practitioners—This work was motivated by the challenge of inspecting aerospace components, which is almost entirely done manually at present. Rather than replacing human inspectors, this work aims at reducing their workload by providing them with an initial inspection result for each component. Especially, the proposed system is able to first localize the Region of Interest (RoI) from an X-ray image of a component and then identify potential defects contained in the RoI. To the best of our knowledge, few existing studies perform defect detection on raw component images. Normally, researchers manually cropped an RoI from these images. The output of our system is the pixelwise location information on potential defects. Our results demonstrate that the proposed system is able to accurately localize the weld and identify 80% of defects contained in abnormal weld images with very few false positives. Given that large weld images ($2304\times1920$pixels) were processed, our system located the weld in 6.6± 1.3 s/image and fulfilled defect detection on each localized weld region in 0.8± 0.1 s. The proposed system was also tested with the publicly available X-ray weld image data set: GDXray and a magnetic tile image data set. Although only a small number of training images were available, promising results were obtained. This suggests that our system is suitable for both X-ray weld images and other images though more work is needed to reduce false positives.

The non-destructive testing (NDT) of components is very important to the aerospace industry. Welds in these components may contain porosities and other defects. These reduce the fatigue life of components and may result in catastrophic accidents if they end up in the aircraft. Currently such welds are inspected by humans studying radiographs of the welds. We describe an automatic system for detecting defects in welds, with the aim of creating a triage system to reduce the workload on human inspectors. Given an X-ray image of the aerospace weld, the system locates the weld line, then analyses the region around the line to identify abnormalities. Our results show that the weld can be precisely extracted from X-ray images and the defect detection operation can identify 83% of defects with fewer than 3 false positives per image, and thus may be useful for prompting human inspectors to reduce their workload.

Nailfold capillaroscopy (NC) allows non-invasive imaging of systemic sclerosis (SSc) related microvascular disease. We have developed a state-of-the-art NC system that enables fast, panoramic imaging of the whole nailfold at high-magnification, and incorporates novel software to make fully automated estimates of capillary structure and blood flow velocity. We present the first results of a study in which 50 patients with SSc, 12 with primary Raynauds phenomenon (PRP) and 50 healthy controls (HC) were imaged using the new system, and show that a combined model of capillary measurements strongly separates SSc from HC/PRP (ROC $$A_z$$=0.93). Including capillary flow improves model performance, suggesting flow provides complementary information to capillary structure for diagnosing SSc.

Active Appearance Models (AAMs) are widely used to fit shape models to new images.Recently it has been demonstrated that non-linear regression methods and sequences of AAMs can significantly improve performance over the original linear formulation.In this paper we focus on the ability of a model trained on one dataset to generalise to other sets with different conditions.In particular we compare two non-linear, discriminative regression strategies for predicting shape updates, a boosting approach and variants of Random Forest regression.We investigate the use of these regression methods within a sequential model fitting framework, where each stage in the sequence consists of a shape model and a corresponding regression model.The performance of the framework is assessed by both testing on unseen data taken from within the training databases, as well as by investigating the more difficult task of generalising to unrelated datasets.We present results that show that (a) the generalisation performance of the Random Forest is superior to that of the linear or boosted regression procedure and that (b) using a simple feature selection procedure, the Random Forest can be made to be as efficient as the boosting procedure without significant reduction in accuracy.

In statistical modeling, there are various techniques used to build models from training data. Quantitative comparison of modeling techniques requires a method for evaluating the quality of the fit between the model probability density function (pdf) and the training data. One graph-based measure that has been used for this purpose is the specificity. We consider the large-numbers limit of the specificity, and derive expressions which show that it can be considered as an estimator of the divergence between the unknown pdf from which the training data was drawn and the model pdf built from the training data. Experiments using artificial data enable us to show that these limiting large-number relations enable us to obtain good quantitative and qualitative predictions of the behavior of the measured specificity, even for small numbers of training examples and in some extreme cases. We demonstrate that specificity can provide a more sensitive measure of difference between various modeling methods than some previous graph-based techniques. Key points are illustrated using real data sets. We thus establish a proper theoretical basis for the previously ad hoc concept of specificity, and obtain useful insights into the application of specificity in the analysis of real data.

This paper tackles the problem of accurately matching a 3D deformable face model to sequences of images in challenging real-world scenarios with large amounts of head movement, occlusion, and difficult lighting conditions. A baseline system involves searching with a set of view-dependent local patches to locate image features, and using these to update the face shape model parameters. We show here two modifications that lead to improvements in performance and can be applied in other similar systems. These are: explicitly searching for occluding boundaries, which prevents the model from rotating rather than changing shape; and a simple method for weighting the relative importance of each located match for model fit. We demonstrate the improvements on both standard test sets and on a series of difficult in-car driver videos, showing more accurate matching and fewer search failures. © 2010. The copyright of this document resides with its authors.

Groupwise image registration algorithms seek to establish dense correspondences between sets of images. Typically, they involve iteratively improving the registration between each image and an evolving mean. A variety of methods have been proposed, which differ in their choice of objective function, representation of deformation field, and optimization methods. Given the complexity of the task, the final accuracy is significantly affected by the choices made for each component. Here, we present a groupwise registration algorithm which can take advantage of the statistics of both the image intensities and the range of shapes across the group to achieve accurate matching. By testing on large sets of images (in both 2D and 3D), we explore the effects of using different image representations and different statistical shape constraints. We demonstrate that careful choice of such representations can lead to significant improvements in overall performance.

Statistical shape models are powerful tools for image interpretation and shape analysis. A simple, yet effective, way of building such models is to capture the statistics of sampled point coordinates over a training set of example shapes. However, a major drawback of this approach is the need to establish a correspondence across the training set. In 2-D, a correspondence is often defined using a set of manually placed 'landmarks' and linear interpolation to sample the shape in between. Such annotation is, however, time-consuming and subjective, particularly when extended to 3-D. In this paper, we show that it is possible to establish a dense correspondence across the whole training set automatically by treating correspondence as an optimization problem. The objective function we use for the optimization is based on the minimum description length principle, which we argue is a criterion that leads to models with good compactness, specificity, and generalization ability. We manipulate correspondence by reparameterizing each training shape. We describe an explicit representation of reparameterization for surfaces in 3-D that makes it impossible to generate an illegal (i.e., not one-to-one) correspondence. We also describe several large-scale optimization strategies for model building, and perform a detailed analysis of each approach. Finally, we derive quantitative measures of model quality, allowing meaningful comparison between models built using different methods. Results are given for several different training sets of 3-D shapes, which show that the minimum description length models perform significantly better than other approaches.

Magnetic resonance imaging (MRI) is emerging as the method of choice for measuring cartilage loss in osteoarthritis (OA), but current methods of analysis are imperfect for therapeutic clinical trials. In this paper, we present and evaluate, in two multicenter multivendor studies, a new method for anatomically corresponded regional analysis of cartilage (ACRAC) that allows analysis of knee cartilage morphology in anatomically corresponding focal regions defined on the bone surface. In our first study, 3-D knee MR Images were obtained from 19 asymptomatic female volunteers, followed by segmentations of the bone and cartilage. Minimum description length (MDL) statistical shape models (SSMs) were constructed from the segmented bone surfaces, providing mean bone shapes and a dense set of anatomically corresponding positions on each individual bone, the accuracy of which were measured using repeat images from a subset of the volunteers. Cartilage thicknesses were measured at these locations along 3-D normals to the bone surfaces, yielding corresponded cartilage thickness maps. Functional subregions of the joint were defined on the mean bone shapes, and propagated, using the correspondences, to each individual. ACRAC improved reproducibility, particularly in the central, load bearing subregions of the joint, compared with measures of volume obtained directly from the segmented cartilage surfaces. In our second study, MR Images were obtained from 31 female patient-volunteers with knee OA at baseline and six months. We obtained manual segmentations of the cartilage, and automatic segmentations of the bone using active appearance models (AAMs) built from the bone SSMs of the first study. ACRAC enabled the detection of significant thickness loss in the central, load-bearing regions of the whole femur (-5.57% p = 0.01, annualized) and the medial condyle (-13.08% , p = 0.024 Bonferroni corrected, annualized). We conclude that statistical shape modelling of bone surfaces defines correspondences invariant to individual joint size or shape, providing focal measures of cartilage with improved reproducibility compared to whole compartment measures. It permits the identification of anatomically equivalent regions, and provides the ability to identify the main load-bearing regions of the joint, based on the imputed premorbid state. The method permitted detection of tiny morphological change in cartilage thickness over six months in a small study, and may be useful for OA disease analysis and treatment monitoring.

We describe a method for modelling and locating deformable objects using a combination of global and local shape models. An object is represented as a set of patches together with a geometric model of their relative positions. The geometry is modelled with a global pose and linear shape model, together with a Markov Random Field (MRF) model of local displacements from the global model. Matching to a new image involves an alternating scheme in which an MRF inference technique selects the best candidates for each point, which are then used to update the parameters of the global pose and shape model. A cascade of increasingly complex models is used to achieve robust matching to new images. We explore the effect of model parameters on system performance and show that the proposed method achieves better accuracy than other widely used methods on standard datasets. © 2009. The copyright of this document resides with its authors.

We describe an approach for automated analysis of deformable objects which extracts structure information from groups of images containing different examples of the object with a particular application to human imaging. The proposed analysis framework simultaneously segments and registers a set of images, incrementally constructing a model of the composition of the object. By fitting an appropriate intensity distribution model to the image we obtain a soft segmentation which allows us to explicitly model the construction of each pixel from constituent image segments, rather than its expected intensity. This effectively decouples the model from the effects of the imaging system and varying statistics in different examples. When estimating the optimal deformation field for each example, the original image is compared to a reconstruction, generated using the composition model and its intensity distribution parameters for each segment (i.e. an estimate of how the model would appear given the imaging conditions for that image). In the paper we describe the algorithm in detail and show results of applying it to two sets of medical images of different anatomies taken with different imaging modalities. We present quantitative results demonstrating that the proposed algorithm is more powerful than current state of the art methods at extracting structural information such as spatial correspondences across groups of images with varying statistics. 1

Active Appearance Models [5] are widely used to match statistical models of shape and appearance to new images rapidly. They work by finding model parameters which minimise the sum of squares of residual differences between model and target image. Their efficiency is achieved by pre-computing the Jacobian describing how the residuals are expected to change as the parameters vary. This leads to a method of predicting the position of the minima based on a single measurement of the residuals (though in practise the algorithm is iterated to refine the estimate). However, the estimate of the Jacobian from the training set will only be an approximation for any given target image, and may be a poor one if the target image is significantly different from the training images. This paper describes a simple method of updating a representation of the Jacobian as the search progresses. This allows us to tune the AAM to the current example. Though useful for matching to a single image, it is particularly powerful when tracking objects through sequences, as it gives a method of tuning the AAM as the search progresses. We demonstrate the power of the technique on a variety of datasets. 1

There are various methods for building statistical models of shape or shape and appearance from training data. Quantitative comparison of such methods requires a method of evaluating the quality of the fit between the model pdf and the training data. One quantitative graph-based measure which has been used for this purpose is the specificity, and the associated measure of generalisation. In this paper we consider the large-numbers limit of the specificity, and derive expressions which show that specificity can be considered as a graph-based estimator of cross-entropy. We also give explicit expressions for the various constants involved. We perform simple experiments using artificial data, and show that these limiting relations hold good even for relatively small numbers of training examples. We hence establish a proper theoretical context for the previously ad hoc concept of specificity. 1

We describe an algorithm for obtaining correspondences across a group of images of deformable objects. The approach is to construct a statistical model of appearance which can encode the training images as compactly as possible (a Minimum Description Length framework). Correspondences are defined by piece-wise linear interpolation between a set of control points defined on each image. Given such points a model can be constructed, which can approximate every image in the set. The description length encodes the cost of the model, the parameters and most importantly, the residuals not explained by the model. By modifying the positions of the control points we can optimise the description length, leading to good correspondence. We describe the algorithm in detail and give examples of its application to MR brain images and to faces. We also describe experiments which use a recently-introduced specificity measure to evaluate the performance of different components of the algorithm. 1

The principled non-rigid registration of groups of images requires a fully groupwise objective function. We consider the problem as one of finding the optimal dense correspondence between the images in the set, where optimality is defined using the Minimum Description Length (MDL) principle, that the transmission of a model of the data, together with the parameters of that model, should be as short as possible. We demonstrate that this approach provides a suitable objective function by applying it to the task of non-rigid registration of a set of 2D T1-weighted MR images of the human brain. Furthermore, we show that even in the case when substantial portions of the images are missing, the algorithm not only converges to the correct solution, but also allows meaningful integration of image data across the training set, allowing the original image to be reconstructed. 1

We describe methods for detecting linear structures in mammograms, and for classifying them into anatomical types (vessels, spicules, ducts, etc). Several different detection methods are compared, using realistic synthetic images and receiver operating characteristic (ROC) analysis. There are significant differences (p < 0.001) between the methods, with the best giving an Az value for pixel-level detection of 0.943. We also investigate methods for classifying the detected linear structures into anatomical types, using their cross-sectional profiles, with particular emphasis on recognising the "spicules" and "ducts" associated with some of the more subtle abnormalities. Automatic classification results are compared with expert annotations using ROC analysis, demonstrating useful discrimination between anatomical classes (Az = 0.746). Some of this discrimination relies on simple attributes such as profile width and contrast, but important information is also carried by the shape of the profile (Az = 0.653). The methods presented have potentially wide application in improving the specificity of abnormality detection by exploiting additional anatomical information.

We describe a generative model of ‘talking head ’ facial behaviour, intended for use in both video synthesis and model-based interpretation. The model is learnt, without supervision, from talking head video, parameterised by tracking with an Active Appearance Model (AAM). We present a integrated probabilistic framework for capturing both the short-term visual dynamics and longer-term behavioural structure. We demonstrate that the approach leads to a compact model, capable of generating realistic and relatively subtle talking head behaviour in real time. The results of a forcedchoice psychophysical experiment show that the quality of the generated sequences is significantly better than that obtained using alternative approaches, and is indistinguishable from that of the original training sequence. 1

We consider the problem of learning how a person's face behaves in a long video sequence, with the aim of synthesising convincing sequences demonstrating the same behaviours. We describe a novel approach to segment a sequence into short sections, each representing a distinct action (or a part of an action). These sections are grouped and a model of the variability of the action learnt. A variable length Markov model is trained on the sequence of such actions to learn the temporal relationships. The result is a system that can generate realistic sequences of an individual face.

Statistical models of shape and appearance have been successfully used in face modeling, tracking and synthesis. In this paper we describe ex-periments using appearance models for face verification. We compare a variety of different algorithms on a standard face database (XM2VTS). We demonstrate that simple methods of correction for head pose and face expression can significantly improve results. 1

This paper considers the problem of measuring the differences between deformations. It is intended to be applied in the context of applications such as the analysis of sets of non-rigidly registered medical images, where diffeomorphic warps between pairs of images establish a dense pixel-to-pixel correspondence. We introduce a new spline with explicit boundary conditions, and show how this can be used to generate general flows of bounded diffeomorphisms. Techniques are developed to describe an arbitrary continuous diffeomorphism and to invert and interpolate between such diffeomorphisms. We show how these constructions and the geodesic distance can be used in the analysis of training sets of general diffeomorphic warps.

The process of aging causes significant alterations in the facial appearance of individuals. When compared with other sources of variation in face images, appearance variation due to aging displays some unique characteristics. Changes in facial appearance due to aging can even affect discriminatory facial features, resulting in deterioration of the ability of humans and machines to identify aged individuals. We describe how the effects of aging on facial appearance can be explained using learned age transformations and present experimental results to show that reasonably accurate estimates of age can be made for unseen images. We also show that we can improve our results by taking into account the fact that different individuals age in different ways and by considering the effect of lifestyle. Our proposed framework can be used for simulating aging effects on new face images in order to predict how an individual might look like in the future or how he/she used to look in the past. The methodology presented has also been used for designing a face recognition system, robust to aging variation. In this context, the perceived age of the subjects in the training and test images is normalized before the training and classification procedure so that aging variation is eliminated. Experimental results demonstrate that, when age normalization is used, the performance of our face recognition system can be improved.

We describe a method for automatically building statistical shape models from a training set of example boundaries/surfaces. These models show considerable promise as a basis for segmenting and interpreting images. One of the drawbacks of the approach is, however, the need to establish a set of dense correspondences between all members of a set of training shapes. Often this is achieved by locating a set of "landmarks" manually on each training image, which is time consuming and subjective in two dimensions and almost impossible in three dimensions. We describe how shape models can be built automatically by posing the correspondence problem as one of finding the parameterization for each shape in the training set. We select the set of parameterizations that build the "best" model. We define "best" as that which minimizes the description length of the training set, arguing that this leads to models with good compactness, specificity and generalization ability. We show how a set of shape parameterizations can be represented and manipulated in order to build a minimum description length model. Results are given for several different training sets of two-dimensional boundaries, showing that the proposed method constructs better models than other approaches including manual landmarking-the current gold standard. We also show that the method can be extended straightforwardly to three dimensions.

When attempting to code faces for modelling or recognition, estimates of dimensions are typically obtained from an ensemble. These tend to be significantly sub-optimal. Each face contains both predictable and non-predictable qualities

Statistical shape models have been used widely as a basis for segmenting and interpreting images. A major drawback of the approach is the need to establish a set of dense correspondences across a training set of segmented shapes. By posing the problem as one of minimising the description length of the model, we develop an efficient method that automatically defines correspondences across a set of shapes. Results are given for several different training sets of shapes, showing that the automatic method constructs significantly better models than those built by hand- the current gold standard. 1

The use of Kernel Principal Component Analysis (KPCA) to model data distributions in high-dimensional spaces is described. Of the many potential applications, we focus on the problem of modelling the variability in a class of shapes. We show that a previous approach to representing non-linear shape constraints using KPCA is not generally valid, and introduce a new ‘proximity to data ’ measure that behaves correctly. This measure is applied to the building of models of both synthetic and real shapes of nematode worms. It is shown that using such a model to impose shape constraints during Active Shape Model (ASM) search gives improved segmentations of worm images than those obtained using linear shape constraints. 1

We show how a novel, non-linear representation of edge structure can be used to improve the performance of model matching algorithms and object verification/recognition tasks. Rather than represent the image structure using intensity values or gradients, we use a measure which indicates the orientation of structures at each pixel, together with an indication of how reliable the orientation estimate is. Orientations in flat, noisy regions tend to be penalised whereas those near strong edges are favoured. We demonstrate that this representation leads to more accurate and reliable matching between models and new images, and leads to better recognition/verification of faces in an access control task.

. We demonstrate a novel method of interpreting images using an Active Appearance Model (AAM). An AAM contains a statistical model of the shape and grey-level appearance of the object of interest which can generalise to almost any valid example. During a training phase we learn the relationship between model parameter displacements and the residual errors induced between a training image and a synthesised model example. To match to an image we measure the current residuals and use the model to predict changes to the current parameters, leading to a better fit. A good overall match is obtained in a few iterations, even from poor starting estimates. We describe the technique in detail and give results of quantitative performance tests. We anticipate that the AAM algorithm will be an important method for locating deformable objects in many applications. 1 Introduction Model-based approaches to the interpretation of images of variable objects are now attracting considerable interest [6][8...

This paper describes building models which represent the appearance of an object (in particular, a face) as seen from two or more dierent viewpoints simultaneously. A small number of 2D linear statistical models are suÆcient to capture the shape and appearance of a face from a wide range of viewpoints. Given multiple images of the same face we can learn a coupled model describing the relationship between the frontal appearance and the prole of a face. This relationship can be used to predict new views of a face seen from one view. Such a coupled model can be used to constrain search algorithms which seek to locate a face in multiple views simultaneously, leading to more robust results than searching each view independently. 1

When attempting to code faces for modeling or recognition, estimates of di-mensions are typically obtained from an ensemble. These tend to be signif-icantly sub-optimal. Firstly, ensembles are rarely balanced with regard to identity and expression. This can be overcome by dividing the ensemble by type of variation and rotating sub-spaces relative to one another. Secondly, each face contains both predictable and non-predictable qualities; only the predictable aspects are useful for defining coding systems for other faces. Variance-based methods of defining codes (PCA) will provide eigenvectors which are themselves potential faces. Predictable aspects will induce eigen-vectors with comparable levels of spatial redundancy to the ensemble. We show that this gives relatively short and consistent codes, and allows fast and accurate fitting of codes to faces. 1

We demonstrate that a small number of 2D statistical models are sufficient to capture the shape and appearance of a face from any viewpoint (full profile to front-to-parallel). Each model is linear and can be matched rapidly to new images using the active appearance model algorithm. We show how such a set of models can be used to estimate head pose, to track faces through large angles of head rotation and to synthesize faces from unseen viewpoints.

A large number of high-performance automatic face recognition systems have been reported in the literature. Many of them are robust to within class appearance variation of subjects such as variation in expression, lighting of subjects such as variation in expression, lighting and pose. However, most of the face identification systems developed are sensitive to changes in the age of individuals. We present experimental results to prove that the performance of automatic face recognition systems depends on the age difference of subjects between the training and test images. We also demonstrate that automatic age simulation techniques can be used for designing face recognition systems, robust to ageing variation. In this context, the perceived age of the subjects in the training and test images is modified before the training and classification procedures, so that ageing variation is eliminated. Experimental results demonstrate that the performance of our face recognition system can be improved significantly, when this approach is adopted.

In order to build a statistical model of facial appearance we require a set of images, each with a consistent set of landmarks. We address the problem of automatically placing a set of landmarks to define the correspondences across an image set. We can estimate correspondences between any pair of images by locating salient points on one and finding their corresponding position in the second. However, we wish to determine a globally consistent set of correspondences across all the images. We present an iterative scheme in which these pairwise correspondences are used to determine a global correspondence across the entire set. We show results on several training sets, and demonstrate that an appearance model trained on the correspondences is of higher quality than one built from hand-marked images.

In recent years there has been much progress in the development of facial recognition systems. The FERET series of tests reported the black box performance of several such systems working on stored face images. Much less effort has been spent in studying the behaviour of systems under realistic conditions of use. We describe and analyse the result of a trial of a door access control system based on a model-based approach. The trial consisted of 10 registered users making over 200 accesses during a 2 week period. We describe the internal failure modes and the performance characteristics of the system, identify inter- and intra-person dependencies and make recommendations for future work.

A framework for automatic landmark identification is presented based on an algorithm for corresponding the boundaries of two shapes. The auto-landmarking framework employs a binary tree of corresponded pairs of shapes to generate landmarks automatically on each of a set of example shapes. The landmarks are used to train statistical shape models, known as point distribution models. The correspondence algorithm locates a matching pair of sparse polygonal approximations, one for each of a pair of boundaries by minimizing a cost function, using a greedy algorithm. The cost function expresses the dissimilarity in both the shape and representation error (with respect to the defining boundary) of the sparse polygons. Results are presented for three classes of shape which exhibit various types of nonrigid deformation.

Statistical models of the shape and appearance of image structures can be matched to new images using both the Active Shape Model [7] algorithm and the Active Appearance Model algorithm [2]. The former searches along profiles about the current model point positions to update the current estimate of the shape of the object. The latter samples the image data under the current instance and uses the difference between model and sample to update the appearance model parameters. In this paper we compare and contrast the two algorithms, giving the results of experiments testing their performance on two data sets, one of faces, the other of structures in MR brain sections. We find that the ASM is faster and achieves more accurate feature point location than the AAM, but the AAM gives a better match to the texture. 1 Introduction Interpretting images containing objects whose appearance can vary is difficult. A powerful approach has been to use deformable models, which can represent the variati...

Facial variation divides into a number of functional subspaces, and ensemble-specific variation. An improved method of measuring these is presented, within the space defined by an Appearance Model. Initial estimates of the subspaces (lighting, pose, identity and expression) are obtained by Principal Components Analysis on appropriate groups of faces. An expectation-maximization algorithm is applied to image codings to maximise the probability of coding across these non-orthogonal subspaces. Ensemble specific variation is then removed by measuring the spatial predictability of the eigenvectors excluding those which are less predictable than the ensemble. These procedures significantly enhance identity recognition for a disjoint test set.

Our previous work in computer-aided mammography has used scaleorientation pixel signatures that provide a rich description of local structure. We describe work using the transportation (`earth mover') algorithm to de ne a measure of similarity between two signatures that recognises similar structures whilst remaining robust to background variability and the presence of other structures. Speci cally, we investigate an un-normalised, normalised and novel best-partialmatching (BPM) approach to measuring this transportation distance and compare it with Euclidean distance. Receiver operating characteristic (ROC) methodology is used to compare performance and an example of clinical application is given. The BPM approach outperforms the other methods.

We address the problem of automatically placing landmarks across an image sequence to define correspondences between frames. The marked up sequence is then used to build a statistical model of the appearance of the object within the sequence. We locate the most salient object features from within the first frame and attempt to track them throughout the sequence. Salient features are those which have a low probability of being mis-classified as any other feature, and are therefore more likely to be robustly tracked throughout the sequence. The method automatically builds statistical models of the objects shape and the salient features appearance as the sequence is tracked. These models are used in subsequent frames to further improve the probability of finding accurate matches. Results are shown for several face image sequences. The quality of the model is comparable with that generated from hand labelled images.

Active Appearance Models (AAMs) provide a method of modelling the appearance of objects in images and locating them automatically. Although the AAM approach is computationally eAEcient, the models used to search unseen images for the structures of interest are large typically the size of 100 images. This is perfectly practical for most 2-D images, but is currently impractical for 3-D images. We present a method for compressing the model information using a wavelet transform. The transform is applied to a set of training images in a shapenormalised frame, and coeAEcients of low variance across the training set are removed to reduce the information stored. An AAM is built from the training set using the wavelet coeAEcients rather than the raw intensities. We show that reliable image interpretation results can be obtained at a compression ratio of 20:1, which is suAEcient to make 3-D AAMs a practical proposition.

Facial variation divides into a number of functional subspaces. An improved method of measuring these was designed within the space defined by an Appearance Model. Initial estimates of the subspaces (lighting, pose, identity, expression) were obtained by Principal Components Analysis on appropriate groups of faces. An iterative algorithm was applied to image codings to maximise the probability of coding across these non-orthogonal subspaces before obtaining the projection on each sub-space and recalculating the spaces. This procedure enhances identity recognition, reduces overall sub-space variance and produces Principal Components with greater span and less contamination.

We present a quantitative evaluation of an algorithm for model-based face recognition. The algorithm actively learns how individual faces vary through video sequences, providing on-line suppression of confounding factors such as expression, lighting and pose. By actively decoupling sources of image variation, the algorithm provides a framework in which identity evidence can be integrated over a sequence. We demonstrate that face recognition can be considerably improved by the analysis of video sequences. The method presented is widely applicable in many multi-class interpretation problems.

This paper presents advances in the construction and use of Active Appearance Models (AAMs) for image interpretation. AAMs are photo-realistic generative models of object appearance that can be used to rapidly locate deformable objects in images. We extend the AAM method to include coloured texture and present an enhanced search algorithm with the ability to locate partially occluded objects. Previously, AAMs have been limited by the need for good manual initialisation. In this paper, we describe a hierarchical search algorithm that overcomes this drawback. The extended AAM method provides a complete, unified scheme for model based image interpretation. We demonstrate the application of the scheme to the task of locating faces in images.

The process of ageing causes significant alterations in the facial appearance of individuals. When compared with other sources of variation in face images (e.g. variation due to changes in pose and expression), appearance variation due to ageing displays some unique characteristics. For example ageing variation is specific to a given individual, it occurs slowly and it is affected significantly by other factors, such as the health, gender and the lifestyle of the individual. In this paper we describe how the effects of ageing on facial appearance can be explained using a parameterized statistical model. We present experimental results to show that reasonably accurate estimates of age can be made for unseen images. We also show that we can improve our results significantly by taking into account the fact that different individuals age in different ways and by considering the effect of lifestyle. We also demonstrate how the proposed framework can be used for simulating ageing effects on new face images, in order to predict how an individual might look like in the future, or how he/she used to look in the past. Experimental and visual results on simulation of age effects are presented.

Analysis of the condition of blood capillaries in the nailfold is complicated by the fact that gaps in the flow of blood cells results in temporal variability in their appearance. At a single instant the capillaries may be incomplete, but integration of the information from several successive video frames renders the whole capillary visible. This paper shows that combining the information from the video frame sequence by subtracting a multiple of the standard deviation from the mean value for each pixel, improves the signal to noise ratio of variable features when compared with the mean image or using minimum projection.

A previous publication has described a method of pairwise 3D surface correspondence for the automated generation of landmarks on a set of examples from a class of shape [3]. In this paper we describe a set of improved algorithms which give more accurate and more robust results. We show how the pairwise corresponder can be used in a extension of an existing framework for establishing dense correspondences between a set of training examples [4] to build a 3D Point Distribution Model. Examples are given for both synthetic and real data.

An Active Appearance Model (AAM) allows complex models of shape and appearance to be matched to new images rapidly. An AAM contains a statistical model of the shape and grey-level appearance of an object of interest The associated search algorithm exploits the locally linear relationship between model parameter displacements and the residual errors between model instance and image. This relationship can be learnt during a training phase. To match to an image we measure the current residuals and use the model to predict changes to the current parameters. The algorithm converges in a few iterations. In this paper we describe variations of the basic algorithm aimed at improving the speed and robustness of search. These include subsampling and using image residuals to drive the shape rather than full appearance model. We show examples of search and give the results of experiments comparing the performance of the different algorithms. 1 Introduction Model based methods are now widely used ...

We present a method for locating salient object features. Salient features are those which have a low probability of being mis-classified with any other feature, and are therefore more easily found in a similar image containing an example of the object. The local image structure can be described by vectors extracted using a standard `feature extractor' at a range of scales. We train statistical models for each feature, using vectors taken from a number of training examples. The feature models can then be used to find the probability of misclassifying a feature with all other features. Low probabilities indicate a salient feature. Results are presented showing that salient features can be relocated more reliably than features chosen using previous methods, including hand picked features.

In this paper we present the first steps in the development of a statistical shape model, specifically a point distribution model (PDM), of the cortical surface of the brain. This will ultimately be used to locate, label, and describe the cortex, for visualisation, diagnosis, and quantification. In order to produce the model it was necessary to find and label the sulcal fissures on a series of MR images. Due to the complexity of the surface, an automated method was developed to facilitate development of a full surface model. Automating the marking process introduced the problem of identifying correspondences between examples, the knowledge of which is essential to the development of a PDM. Various methods were investigated to solve this problem including simple point matching and more complex curve matching. Each is outlined and discussed. The models obtained so far provide interesting insights into the shape and cortical pattern variations over a group of normal subjects.

Face images are difficult to interpret because they are highly variable. Sources of variability include individual appearance, 3D pose, facial expression, and lighting. We describe a compact parametrized model of facial appearance which takes into account all these sources of variability. The model represents both shape and gray-level appearance, and is created by performing a statistical analysis over a training set of face images. A robust multiresolution search algorithm is used to fit the model to faces in new images. This allows the main facial features to be located, and a set of shape, and gray-level appearance parameters to be recovered. A good approximation to a given face can be reconstructed using less than 100 of these parameters. This representation can be used for tasks such as image coding, person identification, 3D pose recovery, gender recognition, and expression recognition. Experimental results are presented for a database of 690 face images obtained under widely varying conditions of 3D pose, lighting, and facial expression. The system performs well on all the tasks listed above.

Active Shape Models (ASMs) provide an efficient means of locating objects in images. By statistically modelling the shape variations in a class of objects they can rapidly and robustly fit to new examples. However, if an ASM does not represent all the shape variation exhibited by the object, the model may not be able to locate new examples accurately. This paper describes two complementary approaches to allowing additional freedom to the points which compromise the model, enabling them to fit to the image data more accurately. We present results for synthetic and real images and discuss how the methods can be used in an interactive 'bootstrap ' training scheme where problems with over-constrained models are particularly important.

In mammography the presence of subtle abnormalities such as stellate patterns and architectual distortions indicates possible malignancy. Radiologists do not always detect these abnormalities in screening mammograms; this has led to interest in computer--aided mammographic interpretation where the radiologist is presented with computer--generated 'prompts' for abnormalities. A first step in this process is the detection of the "orientation", "scale" and "strength" of linear structures in the mammograms. We discuss several generic methods for extracting this information from images and compare their performance using synthetic images intended to simulate the appearance of mammograms. We show significant differences in performance between the different methods. We also show results obtained for real mammograms. 1 Introduction The UK Breast Screening Programme alone generates 1.5 million mammograms per annum. Potential malignancies can be detected from subtle abnormalities in ...

We describe a method of locating hypotheses for the positions of faces in an image. We use statistical feature detectors to locate candidates for features, then use a statistical model of the shape and orientation of the features to test combinations of such features to find the most plausible. The best sets can be used as the initial position of an Active Shape Model, which can then accurately locate the full face.

Model based approaches to the interpretation of face images have proved very successful. We have previously described statistically based models of face shape and grey-level appearance and shown how they can be used to perform various coding and interpretation tasks (Lanitis et al., 1995). In the paper we describe improved methods of modelling, which couple shape and grey-level information more directly than our existing methods, isolate the changes in appearance due to different sources of variability (person, expression, pose, lighting) and deal with nonlinear shape variation. We show that the new methods are better suited to interpretation and tracking tasks.

The absolute orientation problem involves finding the Euclidean transformation which minimises the sum of the squared errors between two pointsets. In the standard form of the problem a confidence may be attached to each of the errors via a set of positive scalar weights. In this paper we consider a generalisation of the standard problem in which the components of the error vectors are coupled via a set of weight matrices. We show how problems of this type arise and derive two distinct forms of the problem. We present a closed-form solution to the first form of the 3-D problem and iterative solutions to the second form of the 2-D problem and both forms of the 3-D problem.

We describe a system that performs fully automatic analysis of total hip replacement (THR) radiographs using a model-based approach. Previous methods for analysis of this type of radiograph have been manual or semi-automatic and require considerable investment of skilled operators time. Our system works unsupervised and is the first of its type. Image search is carried out using a statistically defined deformable template used as an active shape model (ASM). The ASM, which is trained to model prosthetic, femoral, and pelvic structures within the image, iteratively modifies its pose and shape to fit to the evidence in a given image. We present the results of systematic experiments which show that the system can robustly locate relevant structures in routine post-operative radiographs accurately enough for practical applications.

Objects of the same class often exhibit variation in shape. This shape variation has previously been modelled by means of point distribution models (PDMs) in which there is a linear relationship between a set of shape parameters and the positions of points on the shape. Here we present a new form of PDM, which uses a multilayer perceptron (MLP) to carry out nonlinear principal component analysis. We demonstrate that MLP-PDMs can model the shape variability in classes of object for which the linear model fails. We describe the use of MLP-PDMs in image search and present quantitative results for a practical application (face recognition), demonstrating the ability to locate image structures accurately starting from a very poor initial approximation to their pose and shape.

The authors describe how active shape models (ASMs) have been used to accurately and robustly locate vertebrae in lateral dual energy X-ray absorptiometry (DXA) images of the spine. DXA images are of low spatial resolution, and contain significant random and structural noise, providing a difficult challenge for object location methods. All vertebrae in the image were searched for simultaneously, improving robustness in location of individual vertebrae by making use of constraints on shape provided by the position of other vertebrae. They show that the use of ASMs with minimal user interaction allows accuracy to be obtained which is as good as that achievable by human operators using a standard manual method.

Hand gesture recognition from video images is of considerable interest as a means of providing simple and intuitive man-machine interfaces. Possible applications range from replacing the mouse as a pointing device to virtual reality and communication with the deaf. We describe an approach to tracking a hand in an image sequence and recognising, in each video frame, which of five gestures it has adopted. A statistically based Point Distribution Model (PDM) is used to provide a compact parametrised description of the shape of the hand for any of the gestures or the transitions between them. The values of the resulting shape parameters are used in a statistical classifier to identify gestures. The model can be used as a deformable template to track a hand through a video sequence but this proves unreliable. We describe how a set of models, one for each of the five gestures, can be used for tracking with the appropriate model selected automatically. We show that this results in reliable tracking and gesture recognition for two 'unseen' video sequences in which all the gestures are used.

We describe how to build statistically-based flexible models of the 3D structure of variable objects, given a training set of uncalibrated images. We assume that for each example object there are two labelled images taken from different viewpoints. From each image pair a 3D structure can be reconstructed, up to either an affine or projective transformation, depending on which camera model is used. The reconstructions are aligned by choosing the transformations which minimise the distances between matched points across the training set. A statistical analysis results in an estimate of the mean structure of the training examples and a compact parameterised model of the variability in shape across the training set. Experiments have been performed using pinhole and affine camera models. Results are presented for both synthetic data and real images.

This paper presents a new method for modelling and locating objects in images for applications such as Printed Circuit Board (PCB) inspection. Objects of interest are assumed to exhibit little variation in size or shape from one example to the next, but may vary considerably in grey-level appearance. Simple correlation based approaches perform poorly on such examples. We demonstrate how a statistical model based approach combined with a multi-resolution search can accurately locate objects and reliably distinguish between good and bad components. We describe a 'bootstrap' approach to training and a method of automatically refining the final model to improve its performance. We demonstrate the method on PCB inspection, showing the approach is robust enough for use in a real production environment.

Shape-from-shading algorithms that use a single image often find incorrect solutions because of ambiguity in the image shading. We describe a robust shape-from-shading algorithm using scale space tracking that can resolve most of these ambiguities by using two images taken from slightly different positions. Further improvements are obtained by combining stereo with shape-fromshading. Results are shown for synthetic test images (with and without added noise) for a Scanning Electron Microscope stereo pair, and for a stereo pair taken using a video camera. 1

Morphological granulometry has been shown to be effective in a range of texture analysis applications. We describe an extension to the standard approach which allows truly local properties of the texture to be measured at each pixel. The result is a set of texture features which are analogous to those which could be measured for individual texture primitives, if they could be isolated. We demonstrate the ability of the method to estimate the known properties of the primitives in synthetic texture images and show that reasonably accurate results can be obtained over a range of practically useful conditions. We describe the application of the method to a difficult texture analysis problem - grading the degree of osteoporosis in radiographs of the femoral neck - and show that better results can be obtained than with either Laws' texture features or conventional granulometry. 1 Introduction Textures are image intensity patterns which normally arise because of the presence of microstructu...

Objects of the same class sometimes exhibit variation in shape. This shape variation has previously been modelled by means of point distribution models (PDMs) in which there is a linear relationship between a set of shape parameters and the positions of points on the shape. A polynomial regression generalization of PDMs, which succeeds in capturing certain forms of non-linear shape variability, has also been described. Here we present a new form of PDM, which uses a multi-layer perceptron to carry out non-linear principal component analysis. We compare the performance of the new model with that of the existing models on two classes of variable shape: one exhibits bending, and the other exhibits complete rotation. The linear PDM fails on both classes of shape; the polynomial regression model succeeds for the first class of shapes but fails for the second; the new multi-layer perceptron model performs well for both classes of shape. The new model is the most general formulation for PDMs which has been proposed to date. 1.

Face images are difficult to interpret because they are highly variable. Sources of variability include individual appearance, 3D pose, facial expression and lighting. We describe a compact parametrised model of facial appearance which takes into account all these sources of variability. The model represents both shape and grey-level appearance and is created by performing a statistical analysis over a training set of face images. A robust multi-resolution search algorithm is used to fit the model to faces in new images. This allows the main facial features to be located and a set of shape and grey-level appearance parameters to be recovered. A good approximation to a given face can be reconstructed using less than 100 of these parameters. This representation can be used for tasks such as image coding, person identification, pose recovery, gender recognition and expression recognition. The system performs well on all the tasks listed above.>

This paper describes a method of combining two approaches to modelling flexible objects. Modal Analysis using Finite Element Methods (FEMs) generates a set of vibrational modes for a single shape. Point Distribution Models (PDMs) generate a statistical model of shape and shape variation from a set of example shapes. A new approach is described which generates vibrational modes when few example shapes are available and changes smoothly to using more statistical modes of variation when a large data set is presented. Results are given for both synthetic and real examples. Experiments using the models for image search show that the combined version performs better than either the PDM or FEM models alone. 1

We describe a new approach to modelling the appearance of structures in grey-level images. We assume that both the shape and grey-levels of the structures can vary from one image to another, and that a number of example images are available for training. A 2-D image can be thought of as a surface in 3 dimensions, with the third dimension being the grey-level intensity at each image point. We can represent the shape of this surface by planting landmark points across it. By examining the way such collections of points vary across different examples we can build a statistical model of the shape, which can be used to generate new examples, and to locate examples of the modelled structure in new images. We show examples of these composite appearance models and demonstrate their use in image interpretation.

We describe a multi-resolution technique for locating for variable structures in images. This is an extension of work on Active Shape Models (ASMs)- statistical models which iteratively deform to match image data. An ASM consists of a shape model controlling a set of landmark points, together with a statistical model of the grey-levels expected around each landmark. Both the shape model and the grey-level models are trained on sets of labelled example images. In order to apply a coarse-to-fine search strategy it is necessary to train a set of grey-level models for each landmark, one for every level of a multi-resolution image pyramid. During image search the model is started on the coarsest resolution image. As the search progresses it moves to finer and finer resolutions until no further improvement can be made. We describe an automatic technique for deciding when to:ss has converged. We demonstrate the ntitative experiments which show a sigi speed and quality of fit compared to previous methods.

Methods for automatic image interpretation based on the use of deformable template models have proved very successful. Whatever deformable template scheme is used, one of the basic requirements is a method for assessing the likelihood that a particular model instance is the correct interpretation of a given image. We describe a Bayesian `fitness' measure which combines the likelihood of the model shape with the evidential support in a principled way. Image search is carried out by minimising the fitness measure using multi-scale quasi-Newtonian optimisation. We have previously compared the perform# ance of different fitness measures. Here we give results for the new method and show that, by making optimal use of the image evidence, it achieves more accurate interpreta# tion than the best of the methods we have previously tested. Introduction Flexible template models have been used successfully for many applications of automatic image interpretation[1,2,3,4]. The template embodies ÁÂÄ...

Point Distribution Models (PDMs) are statistically derived flexible templates which are trained on sets of examples of the object(s) to be modelled. They require that each example is represented by a set of points (landmaiks) and that each landmark represents the same location on each of the examples. Generating the landmarks from 2D boundaries or 3D surfaces has previously been a manual process. Here, we describe a method for automatically generating PDMs from a training set of pixellated boundaries in 2D. The algorithm is a two-stage process in which a pair-wise corresponder is first used to establish an approximate set of landmarks on each of the example boundaries; in the second phase the landmarks are refined using an iterative non-linear optimisation scheme to generate a more compact PDM. We present results for two objects- the right hand and a chamber of the heart. The models generated using the automatically placed landmarks are shown to be better than those derived from landmarks located manually. 1

The usefulness of advanced machine vision techniques for automated inspection is restricted by long development cycles for the inspection software and a lack of general applicability of the resulting system. These difficulties arise because in the majority of cases the particulars of the inspection are embedded in the software structure resulting in severe restrictions on user reconfiguration. This paper describes the structure and major components of an inspection system which is capable of tackling a wide range of inspection problems without reprogramming. User configurability is based around a simple, interpreted geometric description language which provides support for both dimensional and surface quality measurements. The operation of the system is illustrated using the inspection of automotive brake assemblies as an example. 1 Introduction There is considerable potential for the use of automated visual inspection in manufacturing industry. Some inspection problems require specif...

We describe the use of flexible models for representing the shape and grey-level appearance of human faces. These models are controlled by a small number of parameters which can be used to code the overall appearance of a face for image compression and classification purposes. The model parameters control both inter-class and within-class variation. Discriminant analysis techniques are employed to enhance the effect of those parameters affecting inter-class variation, which are useful for classification. We have performed experiments on face coding and reconstruction and automatic face identification. Good recognition rates are obtained even when significant variation in lighting, expression and 3D viewpoint, is allowed. Human faces display significant variation in appearance due to changes in expression, 3D orientation, lighting conditions, hairstyles and so on. A successful automatic face identification system should be capable of suppressing the effect of these factors allowing any face image to be rendered expression-free with standardised 3D orientation and lighting. We describe how the variations in shape and grey-level appearance in face images can be modelled, and present results for a fully automatic face identification system which tolerates changes in expression, viewpoint and lighting.

We have previously described how to model shape variability by means of point distribution models (TDMs,) in which there is a linear relationship between a set of shape parameters and the positions of points on the shape. This linear formulation can fail for shapes which articulate or bend. ' we show examples of such failure for both real and synthetic classes of shape. A new, more general formulation for PDMs, based on polynomial regression, is presented. The resulting Polynomial Regression PDMs (PRPDMsj perform well on the data for which the linear method failed. 1.

We describe methods for using flexible models to locate structures in images. We have previously described statistical models of shape and shape variability which can be used for this purpose (active shape models). In this paper we show how statistical models of grey-level appearance can be incorporated, leading to improved reliability and accuracy. We describe experiments designed to: 1) test how well an active shape model can locate an object in a new image; 2) to assess the effects on performance of varying the model parameters; and 3) to compare the results using grey-level models with those using a search for strongest edges. The results demonstrate that the addition of grey-level models leads to considerable improvement over earlier schemes.

We describe a multiresolution approach to image search using flexible shape models. This is an extension of work on active shape models (ASMs)-statistical models which iteratively deform to match image data. An ASM consists of a shape model controlling a set of landmark points, together with a statistical model of the grey-levels expected around each landmark. Both the shape model and the grey-level models are trained on sets of labelled example images. In order to apply a coarse-to-fine search strategy it is necessary to train a set of grey-level models for each landmark, one for every level of a multiresolution image pyramid. We demonstrate the approach and give results of quantitative experiments which show a significant increase in both speed, robustness and quality of fit compared to previous methods.

Abstract We describe a technique for improving the classification of fragmented cues for cracks. Evidence propagation on Bayesian networks represents search within the context of each cue. The algorithm was applied to a data-set of cracks, and results demonstrate that contextual classification of the cues leads to significantly improved error rates.

We describe methods for locating known structures in images. We have previously described statistical models of shape and shape variability which can be used for this purpose (Active Shape Models). In this paper we show how statistical models of grey-level appearance can be incorporated, leading to improved reliability and accuracy. We describe experiments designed to (i) test how well an ASM can locate an object in a new image, (ii) to assess the effects on performance of varying the model parameters, and (iii) to compare the results using grey-level models with those using a search for strongest edges. The results demonstrate that the addition of grey-level models leads to considerable improvement over earlier schemes.

The automatic segmentation and labelling of anatomical structures in 3D medical imagesis a challenging task of practical importance. We describe amodel- based approach which allows robust and accurate interpretation using explicit anatomical knowledge. Our method is based on the extension to 3D of Point Distribution Models (PDMs) and associated image search algorithms. Acombination of global, GeneticAlgorithm (GA), and local, Active Shape Model (ASM), search is used. We have built a 3D PDM of the human brain describing a number of major structures. Using this model we have obtained automatic interpretations for 30 3D Magnetic Resonance head images from different individuals. The results have been evaluated quantitativelyand support our claim of robust and accurate interpretation.

Existing Shape from Shading algorithms are not robust enough to work reliably with real images. We present a new paradigm for Shape from Shading based upon & scale space surface representation. Using this representation, the Shape from Shading problem becomes one of forming a surface from gaussian basis functions in such a way that the shading in the original image is explained. The algorithm is both fast and robust, producing convincing results. In its current form, the algorithm requires the reflectance function to be approximately circularly symmetric. We show results for synthetic images, both with and without added noise, and for real Scanning Electron Microscope images.

A technique for classifying variable objects using flexible template models is described.: is recognised as the input, plant seeds, handprinted characters and human faces; quantitative results are presented. 1

We address the problem of finding a consistent interpretation of an image when a number of object features may be detected independently, but unreliably, and their relative positions are known to be constrained. Our method treats feature detection and the application of spatial constraints as co-operating processes. We show that a Point Distribution Model can be used to model constraints on the configuration of features and that the model parameters define a convenient configuration space in which a region representing the set of currently feasible configurations can be maintained. We also introduce the idea of dealing with spatially compact groups of feature hypotheses rather than single hypotheses. We describe two reasoning strategies for dealing with hypothesis groups and feasible configuration regions. These lead to an efficient and exact solution to combinatorially explosive image interpretation problems. We demonstrate the feasibility of the approach by showing results for a system designed to interpret lateral skull radiographs.

The authors describe a technique for building compact models of the shape and appearance of flexible objects seen in 2-D images. The models are derived from the statistics of sets of labeled images of example objects. Each model consists of a flexible shape template, describing how important points of the object can vary, and a statistical model of the expected grey levels in regions around each model point. Such models have proved useful in a wide variety of applications. A description is given on how the models can be used in local image search, and examples of their application are included.>

An automatic analysis of angiographic retinal images is discussed. A detection method based on textural differences between perfused and nonperfused regions is described. The image is tessellated into a large number of primary regions using the positions of major vessels. For each region the degree of nonperfusion is estimated by measuring textural properties using mathematical morphology. The image is represented as a region adjacency graph. Adjacent regions are subsequently merged using information on the degree of perfusion. Comparison with manual grading is presented. It is shown that the algorithm for tessellating the image into regions conforms well to the manual delineation of nonperfused regions. The only parameter in the algorithm selects what size of vessels are used for region detection. The features used for grading the images are sensitive enough to detect nonperfused regions.>

Screening for breast cancer involves searching for subtle abnormalities in a large number of complex images, a task for which the specificity of human interpreters is known to be poor. We are aiming to improve screening performance by providing radiologists with machine assistance in the detection of clinically significant features. The first stage of the detection process is the generation of a set of cues to indicate potential abnormalities. We generally select a cue method for a particular task because it responds to a known property of the target. However, cue generators also respond to non-targets which share that target property. By combining evidence from a range of cues associated with different target properties we can increase the specificity of detection in noisy or cluttered images. We

This paper describes research into structured, knowledge-based image interpretation. An integrated framework has been developed, within which most tasks associated with the automatic interpretation and analysis of lateral skull X-ray images (cephalometry) can be performed. A model-based image analysis system makes use of a blackboard architecture and multiple knowledge sources. Its performance compares favourably to previously published attempts to automate cephalometric analysis.

Abstract The ability to make 3D measurements of surface topography is important to the control of quality in the fabrication of IC wafers. We describe a technique using shape from shading to produce a dense depth map from ICs imaged in the scanning electron microscope. The method minimizes error terms to ensure the resultant surface is everywhere continuous and accurately explains the observed image intensities. We describe how this method is extended when stereo images are available, and show results for synthetic and real images.

This paper addresses the problem of2D shape representation and its application to object verification. We show how knowledge of shape can be integrated in a principled manner with low-level evidence such as an estimate of object position and an edge strength map. We begin by considering the role of shape in image interpretation and discuss the criteria which should be applied in assessing representations of shape. We propose new criteria, particularly as regards the ability to model variability, and describe a Chord Length Distribution (CLD) representation of shape which possesses many desirable properties. We show how the CLD representation can be used in an iterative belief-updating scheme for object location and verification. We give experimental results which demonstrate the feasibility of the method and discuss future developments.