High Resolution Peripheral Quantitative Computed Tomography (HRpQCT) is a modern form of medical imaging that is used to extract detailed internal texture and structure information from non-invasive scans. This greater resolution means HRpQCT images are more vulnerable to motion artefact than other existing bone imaging methods. Current practice is for scan images to be manually reviewed and graded on a one to five scale for movement artefact, where analysis of scans with the most severe grades of movement artefact may not be possible. Various approaches to automatically detecting motion artefact in HRpQCT images have been described, but these typically rely on classifying scans based on the qualitative manual gradings instead of determining the amount of artefact. This paper describes research into quantitatively calculating the degree of motion affecting an HRpQCT. This is approached by analysing the jumps and shifts present in the raw projection data produced by the HRpQCT instrument scanner, rather than using the reconstructed cross-sectional images. The motivation and methods of this approach are described, and results are provided, along with comparisons to existing work.

The UNet model consists of fully convolutional network (FCN) layers arranged as contracting encoder and upsampling decoder maps. Nested arrangements of these encoder and decoder maps give rise to extensions of the UNet model, such as UNete and UNet++. Other refinements include constraining the outputs of the convolutional layers to discriminate between segment labels when trained end to end, a property called deep supervision. This reduces feature diversity in these nested UNet models despite their large parameter space. Furthermore, for texture segmentation , pixel correlations at multiple scales contribute to the classification task ; hence, explicit deep supervision of shallower layers is likely to enhance performance. In this paper, we propose ADS_UNet, a stage-wise additive training algorithm that incorporates resource-efficient deep supervision in shallower layers and takes performance-weighted combinations of the sub-UNets to create the segmentation model. We provide empirical evidence on three histopathology datasets to support the claim that the proposed ADS_UNet reduces correlations between constituent features and improves performance while being more resource efficient. We demonstrate that ADS_UNet outperforms state-of-the-art Transformer-based models by 1.08 and 0.6 points on CRAG and BCSS datasets, and yet requires only 37% of GPU consumption and 34% of training time as that required by Transformers. The source code is available at: .

Continuous development in surveillance systems is increasingly motivating research in biometrics to articulate unconstrained recognition of human faces. Comparative soft biometric has recently been employed to characterize eyewitness testimonies for use in a biometric system to improve the recognition accuracies of the traditional biometric systems. In this paper, we present a face profile recognition system by fusing features extracted in a traditional face recognition system and eyewitness testimonies processed in a soft biometric system to improve recognition accuracies. Here we have also demonstrated an association between our traditional face profile biometric system and the soft biometric system by numerically mapping the features extracted from a face profile to its soft biometric attributes. Our experiments on 230 subjects in XM2VTSDB dataset demonstrate 84% accuracy for traditional biometrics. The recognition rate is further improved to 98% accuracy when soft and traditional biometrics are fused.

3D local binary pattern (LBP) shows significant performance in many domains such as solid textures analysis, face recognition and tumor detection. In recent years, rotation invariant 3D LBP texture descriptors have received increasing attention and several variants have been proposed. However, they are sensitive to the noise present in the image. In this paper, we propose an efficient rotation invariant texture descriptor known as robust extended 3D LBP (RELBP) for volumetric texture classification. Unlike the current 3D LBP framework, our descriptor uses the information of neighboring voxels to reduce noise. First, the 3D weighted average filter is employed to process each voxel in the image, in which the center voxel is replaced by the average local gray level based on weights. Besides, equidistant points on a sphere are sampled to construct a set of rotation invariant features. Our experiments demonstrate that the RELBP proposed here shows superior classification performance in texture classification tasks and our method is highly robust to image noise on benchmark datasets.

Chronic obstructive pulmonary disease (COPD) has long been one of the leading causes of morbidity and mortality worldwide. Numerous studies have shown that CT image analysis is an effective way to diagnose patients with COPD. Automatic diagnosis of CT images using computer vision will shorten the time a patient takes to confirm COPD. This enables patients to receive timely treatment. CT images are three-dimensional data. The extraction of 3D texture features is the core of classification problem. However, the classification accuracy of the current computer vision models is still not high when extracting these features. Therefore, computer vision assisted diagnosis has not been widely used. In this paper, we proposed MV-DCNN, a multi-view deep neural network based on 15 directions. The experimental results show that compared with the state-of-art methods, this method significantly improves the accuracy of COPD classification, with an accuracy of 97.7%. The model proposed here can be used in the medical institutions for diagnosis of COPD.

This paper proposes new descriptors based on three-dimensional Gaussian Markov random fields (3D-GMRF) for volumetric texture classification. The estimated parameters of 3DGMRF are decomposed into sign and magnitude components and then are encoded into a single binary code to describe the local texture. Our experiments on a synthetic dataset of volumetric texture show that this approach leads to significant reduction in descriptor size, while preserving the discriminative power of 3D-GMRF features. The descriptors proposed here demonstrate strong performance in distinguishing between healthy and chronic obstructive pulmonary disease (COPD) subjects, using a medical dataset. These descriptors are successfully employed to measure the differences between various groups from the medical dataset, in order to determine which group is at risk of COPD.

Region tracking becomes a challenging problem at the presence of low contrast and textured images such as cilia video images where beating cilia appear as moving texture. Tracking such patterns requires extracting of features that are capable of discriminating them effectively. In this paper, a method based on texture features for region tracking is proposed. The texture features are extracted from a sequence of images using Gaussian Markov Random Fields (GMRF). These features are employed to track the motion of a given region and extract its trajectory. The proposed method is evaluated on synthetic samples generated for this purpose and demonstrates good tracking performance depending only on texture features. Our proposed method is successfully utilized to extract the trajectory of the cilia motion which could help to analyze the beating behavior of cilia.

We propose an innovative similarity registration method for volumetric shapes in this paper. This characteristic function-based method is intended to tackle the registration problem for the shapes containing sub-shapes in the presence of noise, and to strike a desirable balance between alignment performance and efficiency. In order to obtain the optimal parameters for scaling, rotation and translation in a reasonable time, radial moments and spherical coordinate system-based cross-correlation are exploited here. Moreover, an iterative method and principal component analysis are also employed to improve robustness of our algorithm. The shapes containing sub-shapes and the lung shapes from a CT dataset are employed in the experiments for validation. Compared with state-of-the-art algorithms, the characteristic function-based method manages to achieve excellent robustness at very low signal-to-noise ratio as well as superior registration speed, accuracy and stability in the medical shape data processing.

This study presents a fast algorithm for the registration of shapes implicitly represented by their characteristic functions. The algorithm proposed here aims to recover the registration parameters (scaling, rotation and translation) by minimising a dissimilarity term between the two shapes. The proposed algorithm is based on phase correlation and statistical shape moments to compute the registration parameters individually. The registration method proposed here is applied to various registration problems, to address issues such as the registration of shapes with various topologies and registration of complex shapes containing various numbers of sub‐shapes. The method proposed here is characterised with a better accuracy, a higher convergence speed, robustness at the presence of excessive noise and a better performance for registration over large databases of shapes, in comparison with other state‐of‐the‐art shape registration techniques in the literature.

In statistical model based texture feature extraction, features based on spatially varying parameters achieve higher discriminative performances compared to spatially constant parameters. In this paper we formulate a novel Bayesian framework which achieves texture characterization by spatially varying parameters based on Gaussian Markov random fields. The parameter estimation is carried out by Metropolis-Hastings algorithm. The distributions of estimated spatially varying parameters are then used as successful discriminant texture features in classification and segmentation. Results show that novel features outperform traditional Gaussian Markov random field texture features which use spatially constant parameters. These features capture both pixel spatial dependencies and structural properties of a texture giving improved texture features for effective texture classification and segmentation.

A nonlinear discontinuity-preserving method for noise removal for band pass signals such as signals modulated with Binary Phase-Shift Keying (BPSK) modulation is proposed in this paper. This method is inspired by the anisotropic diffusion algorithm to remove noise and preserve discontinuities in band pass signals modulated with a single frequency. It is demonstrated here that nonlinear noise removal method for a real valued band pass signal requires a solution for a nonlinear partial differential equation which is of fourth order in space and second order in time. The results presented in this work show better performance in nonlinear noise removal for real valued band pass signals in comparison with the previous work in the literature.

In this paper, local distributions of low order Gaussian Markov Random Field (GMRF) model parameters are proposed as texture features for unsupervised texture segmentation. Instead of using model parameters as texture features, we exploit the variations in parameter estimates found by model fitting in local region around the given pixel. The spatially localized estimation process is carried out by maximum likelihood method employing a moderately small estimation window which leads to modeling of partial texture characteristics belonging to the local region. Hence significant fluctuations occur in the estimates which can be related to texture pattern complexity. The variations occurred in estimates are quantified by normalized local histograms. Selection of an accurate window size for histogram calculation is crucial and is achieved by a technique based on the entropy of textures. These texture features expand the possibility of using relatively low order GMRF model parameters for segmenting fine to very large texture patterns and offer lower computational cost. Small estimation windows result in better boundary localization. Unsupervised segmentation is performed by integrated active contours, combining the region and boundary information. Experimental results on statistical and structural component textures show improved discriminative ability of the features compared to some recent algorithms in the literature.

In this paper, we propose an edge detection algorithm based on the Green function associated with the Mumford–Shah segmentation model. This Green function has a singularity at its center. A regularization method is therefore proposed here to obtain an edge detection filter known here as the Bessel filter. This filter is robust in the presence of noise, and its implementation is simple. It is demonstrated here that this filter is scale invariant. A mathematical argument is also provided to prove that the gradient magnitude of the convolved image with this filter has local maxima in discontinuities of the original image. The Bessel filter enjoys better overall performance (the product of the detection performance and localization indices) in Canny-like criteria than the state-of-the-art filters in the literature. Quantitative and qualitative evaluations of the edge detection algorithms investigated in this paper on synthetic and real world benchmark images confirm the theoretical results presented here, indicating the scale invariant property of the Bessel filter. The numerical complexity of the algorithm proposed here is as low as any convolution-based edge detection algorithm.

Many studies have shown that it is possible to recognize people by the way they walk. However, there are a number of covariate factors that affect recognition performance. The time between capturing the gallery and the probe has been reported to affect recognition the most. To date, no study has isolated the effect of time, irrespective of other covariates. Here, we present the first principled study that examines the effect of elapsed time on gait recognition. Using empirical evidence we show for the first time that elapsed time does not affect recognition significantly in the short-medium term. This finding challenges the existing view in the literature that time significantly affects gait recognition. We employ existing gait representations on a novel dataset captured specifically for this study. By controlling the clothing worn by the subjects and the environment, a Correct Classification Rate (CCR) of 95% has been achieved over the longest time period yet considered for gait on the largest ever temporal dataset. Our results show that gait can be used as a reliable biometric over time and at a distance if we were able to control all other factors such as clothing, footwear etc. We have also investigated the effect of different type of clothes, variations in speed and footwear on the recognition performance. The purpose of these experiments is to provide an indication of why previous studies (employing the same techniques as this study) have achieved significantly lower recognition performance over time. Our experimental results show that clothing and other covariates have been confused with elapsed time previously in the literature. We have demonstrated that clothing drastically affects the recognition performance regardless of elapsed time and significantly more than any of the other covariates that we have considered here.

We present an experimental study to demonstrate the effect of the time difference in image acquisition for gallery and probe on the performance of ear recognition. This experimental research is the first study on the time effect on ear biometrics. For the purpose of recognition, we convolve banana wavelets with an ear image and then apply local binary pattern on the convolved image. The histograms of the produced image are then used as features to describe an ear. A histogram intersection technique is then applied on the histograms of two ears to measure the ear similarity for the recognition purposes. We also use analysis of variance (ANOVA) to select features to identify the best banana wavelets for the recognition process. The experimental results show that the recognition rate is only slightly reduced by time. The average recognition rate of 98.5% is achieved for an eleven month-difference between gallery and probe on an un-occluded ear dataset of 1491 images of ears selected from Southampton University ear database.

A functional for unsupervised texture segmentation is investigated in this paper. An auto-normal model based on Markov Random Fields is employed here to represent textures. The functional investigated here is optimized with respect to the auto-normal model parameters and the evolving contour to simultaneously estimate auto-normal model parameters and find the evolving contour. Experimental results applied on the textures of the Brodatz album demonstrate the higher speed of convergence of this algorithm in comparison with a traditional stochastic algorithm in the literature.

We propose a learning method for gait synthesis from a sequence of shapes(frames) with the ability to extrapolate to novel data. It involves the application of PCA, first to reduce the data dimensionality to certain features, and second to model corresponding features derived from the training gait cycles as a Gaussian distribution. This approach transforms a non Gaussian shape deformation problem into a Gaussian one by considering features of entire gait cycles as vectors in a Gaussian space. We show that these features which we formulate as continuous functions can be modeled by PCA. We also use this model to in-between (generate intermediate unknown) shapes in the training cycle. Furthermore, this paper demonstrates that the derived features can be used in the identification of pedestrians.

In this letter, we propose a shape-based active contours method for segmentation, based on a piecewise-constant approximation of the Mumford-Shah (M-S) functional. The Chan-Vese (C-V) formalism in a level set framework is used to formulate our method; however no sign distance function (SDF) is employed in the method proposed here. This method has the topology-free segmentation associated with the C-V algorithm and adds faster convergence, less memory requirement and fast re-initialization. These properties make the algorithm very attractive for video segmentation.

The contour alignment problem, considered in this letter, is to compute the minimal distance in a least-squares sense, between two explicitly represented contours, specified by corresponding points, after arbitrary rotation, scaling, and translation of one of the contours. This is a constrained nonlinear optimization problem with respect to the translation, rotation, and scaling parameters; however, it is transformed into an equivalent linear least-squares problem by a nonlinear change of variables. Therefore, a global solution of the contour alignment problem can be computed efficiently. It is shown that a normalized minimum value of the cost function is invariant to ordering and affine transformation of the contours and can be used as a measure for the distance between the contours. A solution is proposed to the problem of finding a point correspondence between the contours.

An automated knowledge-based vision system for skeletal growth estimation in children is reported in this paper. Images were obtained from hand radiographs of 32 male and 25 female children of age 1-16 yr. Phalanx bones were automatically localized and segmented using hierarchical inferences and active shape models, respectively. A number of shape descriptors were obtained from the segmented bone contour to quantify skeletal growth. From these descriptors, a feature vector was selected for a regression model and a Bayesian estimator. The estimation accuracy was 84% for females and 82% for males. This level of accuracy is comparable to that of expert pediatric radiologists, which suggests that the proposed approach has a potential application in pediatric medicine.

A robust contour detection algorithm is presented for noisy images characterised by close objects. The proposed approach uses an adaptive multi-scale edge tracking scheme based on active shape models and the wavelet transform. This adaptive method effectively adjusts the appropriate Gaussian function bandwidth according to the noise level so that close object edges can be detected before they are merged by excessive smoothing. This gives an improved performance over a single scale approach, where an incorrect Gaussian function bandwidth can lead to erroneous edge detection. The results obtained show an adaptive multi-scale scheme is robust regardless of the image signal to noise ratio.