A methodology for identity verification from contactless finger images using ridge orientation profiles and bispectral invariant features is extended to use fusion at data, feature levels and combination of both levels using multiple finger segments. Performance is evaluated on 1341 images (selected 24 Megapixel video frames obtained with the finger to camera distance between 12 and 20cms, reduced to finger regions of about 1250 x 3000 pixels) from 41 individuals of different ethnicities. Features are extracted from profiles along key lines between landmarks that facilitate segmentation. The methodology is designed by means of the segmentation procedure, the invariant features and fusion techniques to be robust to geometric and photometric transformations and partial occlusion. Feature fusion, data fusion and a combination of the two are tested. The methodology yields around 5% EER with a combination of data and feature fusion providing the best performance. It can be applied to soft, on-the-move biometric systems.

A new method of biometric identity verification using images of fingers (contact-less sensing) is presented. The method utilizes ridge orientation along lines between easily and reliably extracted key points and bispectral invariant features from the ridge orientation profiles. Rotation is corrected in the pre-processing stage after extraction of key points. Robustness to translation and scale are incorporated in the feature extraction. The method does not rely on minutiae extraction and has potential for feature fusion from multiple fingers for improved performance. A radial basis function Support Vector Machine is trained to perform each identity verification. Results were obtained using 1341 index finger images from 41 individuals with 10-fold cross validation. The system shows about 12% misses at a setting of 1% false alarms and the classification accuracy of the fused system is 92.99%. The performance can be improved with the use of multiple fingers. The proposed methodology can facilitate high traffic, soft identity verification in busy premises such as shopping centres with presentation of the hand as a person walks through.

This paper proposes the use of posterior-adapted class-based weighted decision fusion to effectively combine multiple accelerometer data for improving physical activity recognition. The cutting-edge performance of this method is benchmarked against model-based weighted fusion and class-based weighted fusion without posterior adaptation, based on two publicly available datasets, namely PAMAP2 and MHEALTH. Experimental results show that: 1) posterior-adapted class-based weighted fusion outperformed model-based and class-based weighted fusion; 2) decision fusion with two accelerometers showed statistically significant improvement in average performance compared to the use of a single accelerometer; 3) generally, decision fusion from three accelerometers did not show further improvement from the best combination of two accelerometers; and 4) a combination of ankle and wrist located accelerometers showed the best overall performance compared to any combination of two or three accelerometers.

A method for segmenting HEp-2 cells in Indirect Immuno Fluorescence microscope (IIF) images is implemented and evaluated. Challenges to accurate segmentation include the complexity of the data acquired at multiple wavelengths, overlapping cells, and variations in staining. Level set methods via geometric active contours are used to solve this problem. Level set methods use morphological operations to estimate an initial cell boundary and are fully automated. Geometric active contours are able to adapt to the curve topology of the cell boundary. Segmentation performance is evaluated using six indices: boundary displacement error, global consistency error, variation of information, Jaccard distance error, rand index and F-index.

Classification of viewer interest using facial expression and heart rate facilitates automatic identification of interest evoking video segments. Sports video is suitable for testing the effectiveness of such a system as it has structured segments with distinguishable highlight events. Previous work has not investigated the differences in viewer interest characteristics from one sports type to another, which is crucial for appropriate classification methodology. Thus, it is still unclear whether a universal classification model can be used for analyzing viewer interest for all types of sports. This paper addresses this gap by demonstrating a significant difference (p < 0.05) in the distributions of viewer interest data in soccer compared to tennis. Based on this finding, this paper proposes an adoption of Gaussian mixture models (GMM) to integrate sports-specific and sports-independent approaches for identifying video segments, which would be of potential interest to individual viewers. The approaches achieve 52% to 64% accuracy, demonstrating that sports-specific approach gets better performance.

The increased availability of image capturing devices has enabled collections of digital images to rapidly expand in both size and diversity. This has created a constantly growing need for efficient and effective image browsing, searching, and retrieval tools. Pseudo-relevance feedback (PRF) has proven to be an effective mechanism for improving retrieval accuracy. An original, simple yet effective rank-based PRF mechanism (RB-PRF) that takes into account the initial rank order of each image to improve retrieval accuracy is proposed. This RB-PRF mechanism innovates by making use of binary image signatures to improve retrieval precision by promoting images similar to highly ranked images and demoting images similar to lower ranked images. Empirical evaluations based on standard benchmarks, namely Wang, Oliva & Torralba, and Corel datasets demonstrate the effectiveness of the proposed RB-PRF mechanism in image retrieval.

Viewer interest, evoked by video content, can potentially identify the highlights of the video. This paper explores the use of facial expressions (FE) and heart rate (HR) of viewers captured using camera and non-strapped sensor for identifying interesting video segments. The data from ten subjects with three videos showed that these signals are viewer dependent and not synchronized with the video contents. To address this issue, new algorithms are proposed to effectively combine FE and HR signals for identifying the time when viewer interest is potentially high. The results show that, compared with subjective annotation and match report highlights, 'non-neutral' FE and 'relatively higher and faster' HR is able to capture 60%-80% of goal, foul, and shot-on-goal soccer video events. FE is found to be more indicative than HR of viewer interest, but the fusion of these two modalities outperforms each of them.

The proliferation of news reports published in online websites and news information sharing among social media users necessitates effective techniques for analysing the image, text and video data related to news topics. This paper presents the first study to classify affective facial images on emerging news topics. The proposed system dynamically monitors and selects the current hot (of great interest) news topics with strong affective interestingness using textual keywords in news articles and social media discussions. Images from the selected hot topics are extracted and classified into three categorized emotions, positive, neutral and negative, based on facial expressions of subjects in the images. Performance evaluations on two facial image datasets collected from realworld resources demonstrate the applicability and effectiveness of the proposed system in affective classification of facial images in news reports. Facial expression shows high consistency with the affective textual content in news reports for positive emotion, while only low correlation has been observed for neutral and negative. The system can be directly used for applications, such as assisting editors in choosing photos with a proper affective semantic for a certain topic during news report preparation.

Feature extraction and selection are critical processes in developing facial expression recognition (FER) systems. While many algorithms have been proposed for these processes, direct comparison between texture, geometry and their fusion, as well as between multiple selection algorithms has not been found for spontaneous FER. This paper addresses this issue by proposing a unified framework for a comparative study on the widely used texture (LBP, Gabor and SIFT) and geometric (FAP) features, using Adaboost, mRMR and SVM feature selection algorithms. Our experiments on the Feedtum and NVIE databases demonstrate the benefits of fusing geometric and texture features, where SIFT+FAP shows the best performance, while mRMR outperforms Adaboost and SVM. In terms of computational time, LBP and Gabor perform better than SIFT. The optimal combination of SIFT+FAP+mRMR also exhibits a state-of-the-art performance.

Occlusion is a big challenge for facial expression recognition (FER) in real-world situations. Previous FER efforts to address occlusion suffer from loss of appearance features and are largely limited to a few occlusion types and single testing strategy. This paper presents a robust approach for FER in occluded images and addresses these issues. A set of Gabor based templates is extracted from images in the gallery using a Monte Carlo algorithm. These templates are converted into distance features using template matching. The resulting feature vectors are robust to occlusion. Occluded eyes and mouth regions and randomly places occlusion patches are used for testing. Two testing strategies analyze the effects of these occlusions on the overall recognition performance as well as each facial expression. Experimental results on the Cohn-Kanade database confirm the high robustness of our approach and provide useful insights about the effects of occlusion on FER. Performance is also compared with previous approaches.

Spectrum sensing optimisation techniques maximise the efficiency of spectrum sensing while satisfying a number of constraints. Many optimisation models consider the possibility of the primary user changing activity state during the secondary user's transmission period. However, most ignore the possibility of activity change during the sensing period and assume the activity state is constant without validating or enforcing this assumption. The observed primary user signal during sensing can exhibit a duty cycle which has been shown to severely degrade detection performance. This paper shows that (a) the probability of state change during sensing cannot be neglected and (b) the true detection performance obtained when incorporating the duty cycle of the primary user signal can deviate significantly from the results expected with the assumption of no such duty cycle.

Road surface macrotexture is identified as one of the factors contributing to the surface's skid resistance. Existing methods of quantifying the surface macrotexture, such as the sand patch test and the laser profilometer test, are either expensive or intrusive, requiring traffic control. High-resolution cameras have made it possible to acquire good quality images from roads for the automated analysis of texture depth. In this paper, a granulometric method based on image processing is proposed to estimate road surface texture coarseness distribution from their edge profiles. More than 1300 images were acquired from two different sites, extending to a total of 2.96 km. The images were acquired using camera orientations of 60°and 90°. The road surface is modeled as a texture of particles, and the size distribution of these particles is obtained from chord lengths across edge boundaries. The mean size from each distribution is compared with the sensor measured texture depth obtained using a laser profilometer. By tuning the edge detector parameters, a coefficient of determination of up toR2= 0.94 between the proposed method and the laser profilometer method was obtained. The high correlation is also confirmed by robust calibration parameters that enable the method to be used for unseen data after the method has been calibrated over road surface data with similar surface characteristics and under similar imaging conditions.

A method of improving the security of biometric templates which satisfies desirable properties such as (a) irreversibility of the template, (b) revocability and assignment of a new template to the same biometric input, (c) matching in the secure transformed domain is presented. It makes use of an iterative procedure based on the bispectrum that serves as an irreversible transformation for biometric features because signal phase is discarded each iteration. Unlike the usual hash function, this transformation preserves closeness in the transformed domain for similar biometric inputs. A number of such templates can be generated from the same input. These properties are illustrated using synthetic data and applied to images from the FRGC 3D database with Gabor features. Verification can be successfully performed using these secure templates with an EER of 5.85%.

The development and use of a virtual assessment tool for a signal processing unit is described. It allows students to take a test from anywhere using a web browser to connect to the university server that hosts the test. While student responses are of the multiple choice type, they have to work out problems to arrive at the answer to be entered. CGI programming is used to verify student identification information and record their scores as well as provide immediate feedback after the test is complete. The tool has been used at QUT for the past 3 years and student feedback is discussed. The virtual assessment tool is an efficient alternative to marking written assignment reports that can often take more hours than actual lecture hall contact from a lecturer or tutor. It is especially attractive for very large classes that are now the norm at many universities in the first two years.

The eigenfaces algorithm has long been a mainstay in the field of face recognition due to the high dimensionality of face images. While providing minimal reconstruction error, the eigenface-based transform space de-emphasizes high-frequency information, effectively reducing the information available for classification. Methods such as linear discriminant analysis (also known as fisherfaces) allow the construction of subspaces which preserve the discriminatory information. In this article, multiscale techniques are used to partition the information contained in the frequency domain prior to dimensionality reduction. In this manner, it is possible to increase the information available for classification and, hence, increase the discriminative performance of both eigenfaces and fisherfaces techniques. Motivated by biological systems, Gabor filters are a natural choice for such a partitioning scheme. However, a comprehensive filter bank will dramatically increase the already high dimensionality of extracted features. In this article, a new method for intelligently reducing the dimensionality of Gabor features is presented. The face recognition grand challenge dataset of 3-D face images is used to examine the performance of Gabor filter banks for face recognition and to compare them against other multiscale partitioning methods such as the discrete wavelet transform and the discrete cosine transform.

The addition of Three Dimensional (3D) data has the potential to greatly improve the accuracy of Face Recognition Technologies by providing complementary information. In this paper a new method combining intensity and range images and providing insensitivity to expression variation based on Log-Gabor Templates is presented. By breaking a single image into 75 semi-independent observations the reliance of the algorithm upon any particular part of the face is relaxed allowing robustness in the presence of occulusions, distortions and facial expressions. Also presented is a new distance measure based on the Mahalanobis Cosine metric which has desirable discriminatory characteristics in both the 2D and 3D domains. Using the 3D database collected by University of Notre Dame for the Face Recognition Grand Challenge (FRGC), benchmarking results are presented demonstrating the performance of the proposed methods.

Tracking systems are typically targeted towards tracking a single class of object. In many real world situations, and in the ETISEO evaluation, it is advantageous to be able to track multiple classes of objects. In this paper we describe the adaptation of a single class tracking system to a multi-class tracking system, and describe a modified version of the condensation filter that can be used to track all objects, of all classes. We show that by using simple targeted detectors, we can achieve accurate tracking and can accurately distinguish between classes.

Although the use of super-resolution techniques has demonstrated the ability to improve face recognition accuracy when compared to traditional upsampling techniques, they are difficult to implement for real-time use due to their complexity and high computational demand. As a large portion of processing time is dedicated to registering the lowresolution images, many have adopted global motion models in order to improve efficiency. The drawback of such global models is that they can not accommodate for complex local motions, such as multiple objects moving independently across and static or dynamic background as frequently occurs in a surveillance environment. Local methods like optical flow can compensate for these situations, although it is achieved at the expense of computation time. In this paper, experiments have been carried out to investigate how motion models of different super-resolution reconstruction algorithms affect reconstruction error and face recognition rates in a surveillance environment. Results show that lower reconstruction error doesn't necessarily imply better recognition rates and the use of local motion models yields better recognition rates than global motion models.

This paper examines the the effectiveness of feature modelling to conduct 2D and 3D face recognition. In particular, PCA difference vectors are modelled using Gaussian Mixture Models (GMMs) which describe Intra-Personal (IP) and Extra-Personal (EP) variations. Two classifiers, an IP and IPEP classifier, are formed using these GMMs and their performance is compared to that of the Mahalanobis cosine metric (MahCosine). The best results for the 2D and 3D face modalities are obtained with the IP and IPEP classifiers respectively. The multi-modal fusion of these two systems provided consistent performance improvement across the FRGC database v2.0.

The use of Three Dimensional (3D) data allows new facial recognition algorithms to overcome factors such as pose and illumination variations which have plagued traditional 2D Face Recognition. In this paper a new method for providing insensitivity to expression variation in range images based on Log-Gabor Templates is presented. By decomposing a single image of a subject into 147 observations the reliance of the algorithm upon any particular part of the face is relaxed allowing high accuracy even in the presence of occulusions, distortions and facial expressions. Using the 3D database collected by University of Notre Dame for the Face Recognition Grand Challenge (FRGC), benchmarking results are presented showing superior performance of the proposed method. Comparisons showing the relative strength of the algorithm against two commercial and two academic 3D face recognition algorithms are also presented. algoritms are also presented. 1 Introduction

The use of ground penetrating radar (GPR) for detecting near-surface interfaces is a scenario of special interest to the underground coal mining industry. The problem is difficult to solve in practice because the radar echo is often dominated by unwanted components such as antenna crosstalk and ringing, ground-bounce effects, clutter, and severe attenuation. These nuisance components are also highly sensitive to subtle variations in ground conditions, rendering the application of standard signal pre-processing techniques largely ineffective in the unsupervised case. As a solution to this problem, we develop a novel algorithm which utilizes a pattern recognition-based approach using features derived from the bispectrum of the radar data. We show that, unlike traditional second order correlation based methods such as matched filtering which fail in known conditions, the new method reliably allows the determination of layer interfaces using GPR to be extended to the near surface region.

In this paper, an in-depth analysis is undertaken into effective strategies for integrating the audio-visual speech modalities with respect to two major questions. Firstly, at what level should integration occur? Secondly, given a level of integration how should this integration be implemented? Our work is based around the well-known hidden Markov model (HMM) classifier framework for modeling speech. A novel framework for modeling the mismatch between train and test observation sets is proposed, so as to provide effective classifier combination performance between the acoustic and visual HMM classifiers. From this framework, it can be shown that strategies for combining independent classifiers, such as the weighted product or sum rules, naturally emerge depending on the influence of the mismatch. Based on the assumption that poor performance in most audio-visual speech processing applications can be attributed to train/test mismatches we propose that the main impetus of practical audio-visual integration is to dampen the independent errors, resulting from the mismatch, rather than trying to model any bimodal speech dependencies. To this end a strategy is recommended, based on theory and empirical evidence, using a hybrid between the weighted product and weighted sum rules in the presence of varying acoustic noise for the task of text-dependent speaker recognition.

This paper presents an improved technique for determining the 3D structure of the human face form stereo images. The approach targets specific regions of the face individually. An application of the approach to estimate the 3D structure of the nose is presented. Stereo matching is extended and applied to colour in addition to grayscale, which improves matching in a low texture image like parts of the skin of a human face. Left-right consistency check is used to determine erroneous disparity estimates. Prior knowledge of the nose structure is used in conjunction to improve the quality of the 3D nose estimates.

The use of visual attention (VA) spatial and temporal characteristics, monitored by a gaze-tracking device, to generate a region of interest (ROI) 'importance' map is proposed. A K-means clustering approach is adopted to group gaze location points into a number of clusters to represent the loci of regions of VA (or ROIs). Several metrics are then derived from the gaze positions and sequences to quantify the relative importance of the K-means clusters. An entropy-weighting strategy is adopted for the combination of these metrics to generate the ROI map. Results show that the ROI map is robust to the number of clusters and different gaze patterns, and can be used in progressive image coding/decoding to enhance the image quality in regions of interest.

Skin detection often forms part of both face detectors and pornography detectors for Internet filters. This paper introduces a trivial skin detection algorithm that uses Gaussian Mixture Models to classify 8 × 8 blocks according to their skin-likeness. The absence of structural features in skin regions means luminance information alone is unsuitable for accurate skin detection. Therefore, the affect of the chosen colour components on the classification accuracy is investigated. Fused features vectors extracted from the Cb and Cr chrominance components were found to give the best results, achieving an equal error rate of 5.5%. By utilising these components and an 8 × 8 block size, skin regions in JPEG and MPEG files can be located without full decompression.

The weighted product rule has been shown empirically to be of great benefit in audio-visual speech recognition (AVSR), for isolated word recognition tasks. A firm theoretical ba-sis for the selection of effective weights is of considerable interest to the audio-visual speech processing community. In this paper a clear link is established between the selec-tion of effective weightings and the approximately isotropic shrinkage that the distribution of acoustic cepstral features undergo in the presence of additive noise. An elucidation of the theoretical relationship between the cepstral shrinkage and the variance of the HMM audio log-likelihoods is then explored. 1.

In this paper we propose a new method for face recognition using fractal codes. Fractal codes represent local contractive, affine transformations which when iteratively applied to range-domain pairs in an arbitrary initial image result in a fixed point close to a given image. The transformation parameters such as brightness offset, contrast factor, orientation and the address of the corresponding domain for each range are used directly as features in our method. Features of an unknown face image are compared with those pre-computed for images in a database. There is no need to iterate, use fractal neighbor distances or fractal dimensions for comparison in the proposed method. This method is robust to scale change, frame size change and rotations as well as to some noise, facial expressions and blur distortion in the image.

Recently, the use of chromatic segmentation has come very much into vogue for mouth tracking. Our recent work has endeavored to show under what conditions and representations chromatic segmentation works. Results are presented showing that, for some members of the population, chromatic segmentation does not work satisfactorily, irrespective of recording conditions. A suitability metric is proposed that can give a quantitative measure on how well chromatic mouth tracking will work for a given subject.

The paper proposes a general framework for the importance coding of still images to maximise the interpretability versus bitrate performance. The interpretability of an image to achieve maximum content recognition is important in a diverse range of applications such as surveillance and medical. Importance coding aims to address this problem by prioritisation of the encoded image bit-stream based on the importance of regions in an image. Consequently, the most important features required for interpretability are encoded and transmitted earlier in the encoded image bit-stream. The notion of importance maps, which provide a systematic approach for the assignment of relative importance of regions in an image, are presented and its use in importance coding is developed. One highly desirable advantage of the proposed importance coding framework is that it can be implemented by the EBCOT (embedded block coding with optimised truncation) coder, which has been selected as the core-coding algorithm in JPEG 2000.

An application of image processing techniques to recognition of hand-drawn circuit diagrams is presented. The scanned image of a diagram is pre-processed to remove noise and converted to bilevel. Morphological operations are applied to obtain a clean, connected representation using thinned lines. The diagram comprises of nodes, connections and components. Nodes and components are segmented using appropriate thresholds on a spatially varying object pixel density. Connection paths are traced using a pixel-stack. Nodes are classified using syntactic analysis. Components are classified using a combination of invariant moments, scalar pixel-distribution features, and vector relationships between straight lines in polygonal representations. A node recognition accuracy of 82% and a component recognition accuracy of 86% was achieved on a database comprising 107 nodes and 449 components. This recogniser can be used for layout "beautification" or to generate input code for circuit analysis and simulation packages.

An overview of the requirements of digital covert audio acquisition (DCAA) is provided and a scalable hybrid coder tuned for the coding of intelligible speech in a covert environment is proposed. The codec incorporates linear predictive coding (LPC) and an M-band discrete wavelet transform (DWT) to offer effective intelligible speech coding in the presence of multiple signal sources at bit rates between 8 kbps and 32 kbps. The results of informal intelligibility testing and an analysis of the algorithm's complexity are presented to demonstrate the performance of the proposed coder.

Investigates the use of temporal lip information, in conjunction with speech information, for robust, text-dependent speaker identification. We propose that significant speaker-dependent information can be obtained from moving lips, enabling speaker recognition systems to be highly robust in the presence of noise. The fusion structure for the audio and visual information is based around the use of multi-stream hidden Markov models (MSHMM), with audio and visual features forming two independent data streams. Recent work with multi-modal MSHMMs has been performed successfully for the task of speech recognition. The use of temporal lip information for speaker identification has been performed previously (T.J. Wark et al., 1998), however this has been restricted to output fusion via single-stream HMMs. We present an extension to this previous work, and show that a MSHMM is a valid structure for multi-modal speaker identification.

Signals can be treated as ordered sets and shape as a property of the order. It is shown that the degree of asymmetry or relative contrast of various ordered subsets is a good measure of this property. Statistical measures provide robustness while shape measures provide sensitivity to changes in order. The concept of phase is examined within this framework. What shape information is found in the instantaneous phase? A relationship between instantaneous phase and a measure of shape is derived. Moments, Fourier and wavelet transforms, edges and segments are examined from the new perspective on measures of shape and robustness.

Multimodal speech processing in which visual facial features are jointly processed with audio features is a rapidly advancing field. Lip movements and configurations provide useful information to improve speech and speaker recognition. However, the use of this visual information requires accurate and fast lip tracking algorithms. A new technique is outlined that is able to estimate the outer lip contour directly from a given lip intensity image via linear regression. This estimate can be improved by a active shape model that is able to track a speakers lips without requiring time consuming iterative energy minimization techniques. Results of performance are presented against known tracking algorithms using the M2VTS database.

Gaussian mixture models (GMMs) have become an established means of modeling feature distributions in speaker recognition systems. It is useful for experimentation and practical implementation purposes to develop and test these models in an efficient manner particularly when computational resources are limited. A method of combining vector quantization (VQ) with single multi-dimensional Gaussians is proposed to rapidly generate a robust model approximation to the Gaussian mixture model. A fast method of testing these systems is also proposed and implemented. Results on the NIST 1996 Speaker Recognition Database suggest comparable and in some cases an improved verification performance to the traditional GMM based analysis scheme. In addition, previous research for the task of speaker identification indicated a similar system perfomance between the VQ Gaussian based technique and GMMs.

A new theory that qualitatively and quantitatively describes shape is presented. Signals are treated as ordered sets and shape as a property of the order. Measures of shape are derived starting from simple two element sets. It is shown that the degree of asymmetry of relative contrast at various scales is a sufficient descriptor of shape. The shape of a signal is a composite of the shape of all possible ordered subsets. A distinction is drawn between statistical and shape measures within a unified theoretical framework which may make it possible compare diverse pattern recognition approaches in terms robustness and discrimination power.

This paper investigates the use of lip information, in conjunction with speech information, for robust speaker verification in the presence of background noise. It has been previously shown in our own work, and in the work of others, that features extracted from a speaker's moving lips hold speaker dependencies which are complementary with speech features. We demonstrate that the fusion of lip and speech information allows for a highly robust speaker verification system which outperforms the performance of either sub-system. We present a new technique for determining the weighting to be applied to each modality so as to optimize the performance of the fused system. Given a correct weighting, lip information is shown to be highly effective for reducing the false acceptance and false rejection error rates in the presence of background noise.

This paper presents a novel technique for the tracking of moving lips for the purpose of speaker identification. In our system, a model of the lip contour is formed directly from chromatic information in the lip region. Iterative refinement of contour point estimates is not required. Colour features are extracted from the lips via concatenated profiles taken around the lip contour. Reduction of order in lip features is obtained via principal component analysis (PCA) followed by linear discriminant analysis (LDA). Statistical speaker models are built from the lip features based on the Gaussian mixture model (GMM). Identification experiments performed on the M2VTS/sup 1/ database, show encouraging results.

Features derived from the trispectra of DFT magnitude slices are used for multi-font digit recognition. These features are insensitive to translation, rotation, or scaling of the input. They are also robust to noise. Classification accuracy tests were conducted on a common data base of 256/spl times/256 pixel bilevel images of digits in 9 fonts. Randomly rotated and translated noisy versions were used for training and testing. The results indicate that the trispectral features are better than moment invariants and affine moment invariants. They achieve a classification accuracy of 95% compared to about 81% for Hu's (1962) moment invariants and 39% for the Flusser and Suk (1994) affine moment invariants on the same data in the presence of 1% impulse noise using a 1-NN classifier. For comparison, a multilayer perceptron with no normalization for rotations and translations yields 34% accuracy on 16/spl times/16 pixel low-pass filtered and decimated versions of the same data.

A new algorithm for extracting features from images for object recognition is described. The algorithm uses higher order spectra to provide desirable invariance properties, to provide noise immunity, and to incorporate nonlinearity into the feature extraction procedure thereby allowing the use of simple classifiers. An image can be reduced to a set of 1D functions via the Radon transform, or alternatively, the Fourier transform of each 1D projection can be obtained from a radial slice of the 2D Fourier transform of the image according to the Fourier slice theorem. A triple product of Fourier coefficients, referred to as the deterministic bispectrum, is computed for each 1D function and is integrated along radial lines in bifrequency space. Phases of the integrated bispectra are shown to be translation- and scale-invariant. Rotation invariance is achieved by a regrouping of these invariants at a constant radius followed by a second stage of invariant extraction. Rotation invariance is thus converted to translation invariance in the second step. Results using synthetic and actual images show that isolated, compact clusters are formed in feature space. These clusters are linearly separable, indicating that the nonlinearity required in the mapping from the input space to the classification space is incorporated well into the feature extraction stage. The use of higher order spectra results in good noise immunity, as verified with synthetic and real images. Classification of images using the higher order spectra-based algorithm compares favorably to classification using the method of moment invariants.

This paper discusses the principal domains of auto- and cross-trispectra. It is shown that the cumulant and moment based trispectra are identical except on certain planes in trifrequency space. If these planes are avoided, their principal domains can be derived by considering the regions of symmetry of the fourth order spectral moment. The fourth order averaged periodogram will then serve as an estimate for both cumulant and moment trispectra. Statistics of estimates of normalised trispectra or tricoherence are also discussed.>

The School of Electrical and Electronic Systems Engineering of Queensland University of Technology (like many other universities around the world) has recognised the importance of complementing the teaching of signal processing with computer based experiments. A laboratory has been developed to provide a "hands-on" approach to the teaching of signal processing techniques. The motivation for the development of this laboratory was the cliche "What I hear I remember but what I do I understand." The laboratory has been named as the "Signal Computing and Real-time DSP Laboratory" and provides practical training to approximately 150 final year undergraduate students each year. The paper describes the novel features of the laboratory, techniques used in the laboratory based teaching, interesting aspects of the experiments that have been developed and student evaluation of the teaching techniques.>

A new method for the detection of abnormal vehicle trajectories is proposed. It couples optical flow extraction of vehicle velocities with a neural network classifier. Abnormal trajectories are indicative of drunk or sleepy drivers. A single feature of the vehicle, e.g., a tail light, is isolated and the optical flow computed only around this feature rather than at each pixel in the image. The velocity fields are accurately extracted using a modification of the basic optical flow method (Horn and Schunck, 1981, and Barron et al., 1994). Trajectories are extracted in the form of direction of motion in each frame. A back-propagation neural network is used to classify the vehicle trajectories as either normal or abnormal. The neural network is shown to perform accurate classification on simulated trajectories.>

A new approach to recognition of images using invariant features based on higher-order spectra is presented. Higher-order spectra are translation invariant because translation produces linear phase shifts which cancel. Scale and amplification invariance are satisfied by the phase of the integral of a higher-order spectrum along a radial line in higher-order frequency space because the contour of integration maps onto itself and both the real and imaginary parts are affected equally by the transformation. Rotation invariance is introduced by deriving invariants from the Radon transform of the image and using the cyclic-shift invariance property of the discrete Fourier transform magnitude. Results on synthetic and actual images show isolated, compact clusters in feature space and high classification accuracies.>

An approach to pattern recognition using invariant parameters based on higher-order spectra is presented. In particular, bispectral invariants are used to classify one-dimensional shapes. The bispectrum, which is translation invariant, is integrated along straight lines passing through the origin in bifrequency space. The phase of the integrated bispectrum is shown to be scale- and amplification-invariant. A minimal set of these invariants is selected as the feature vector for pattern classification. Pattern recognition using higher-order spectral invariants is fast, suited for parallel implementation, and works for signals corrupted by Gaussian noise. The classification technique is shown to distinguish two similar but different bolts given their one-dimensional profiles.>