Albert Chi Shing Chung

Dominant Local Binary Patterns for Texture Classification

This paper proposes a novel approach to extract image features for texture classification. The proposed features are robust to image rotation, less sensitive to histogram equalization and noise. It comprises of two sets of features: dominant local binary patterns (DLBP) in a texture image and the supplementary features extracted by using the circularly symmetric Gabor filter responses. The dominant local binary pattern method makes use of the most frequently occurred patterns to capture descriptive textural information, while the Gabor-based features aim at supplying additional global textural information to the DLBP features. Through experiments, the proposed approach has been intensively evaluated by applying a large number of classification tests to histogram-equalized, randomly rotated and noise corrupted images in Outex, Brodatz, Meastex, and CUReT texture image databases. Our method has also been compared with six published texture features in the experiments. It is experimentally demonstrated that the proposed method achieves the highest classification accuracy in various texture databases and image conditions.

Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux

This paper proposes a novel curvilinear structure detector, called Optimally Oriented Flux (OOF). OOF finds an optimal axis on which image gradients are projected in order to compute the image gradient flux. The computation of OOF is localized at the boundaries of local spherical regions. It avoids considering closely located adjacent structures. The main advantage of OOF is its robustness against the disturbance induced by closely located adjacent objects. Moreover, the analytical formulation of OOF introduces no additional computation load as compared to the calculation of the Hessian matrix which is widely used for curvilinear structure detection. It is experimentally demonstrated that OOF delivers accurate and stable curvilinear structure detection responses under the interference of closely located adjacent structures as well as image noise.

Facial Expression Recognition using Advanced Local Binary Patterns, Tsallis Entropies and Global Appearance Features

This paper proposes a novel facial expression recognition approach based on two sets of features extracted from the face images: texture features and global appearance features. The first set is obtained by using the extended local binary patterns in both intensity and gradient maps and computing the Tsallis entropy of the Gabor filtered responses. The second set of features is obtained by performing null-space based linear discriminant analysis on the training face images. The proposed method is evaluated by extensive experiments on the JAFFE database, and compared with two widely used facial expression recognition approaches. Experimental results show that the proposed approach maintains high recognition rate in a wide range of resolution levels and outperforms the other alternative methods.

Multi-modal Image Registration by Minimising Kullback-Leibler Distance

In this paper, we propose a multi-modal image registration method based on the a priori knowledge of the expected joint intensity distribution estimated from aligned training images. The goal of the registration is to find the optimal transformation such that the discrepancy between the expected and the observed joint intensity distributions is minimised. The difference between distributions is measured using the Kullback-Leibler distance (KLD). Experimental results in 3D-3D registration show that the KLD based registration algorithm is less dependent on the size of the sampling region than the Maximum log-Likelihood based registration method. We have also shown that, if manual alignment is unavailable, the expected joint intensity distribution can be estimated based on the segmented and corresponding structures from a pair of novel images. The proposed method has been applied to 2D-3D registration problems between digital subtraction angiograms (DSAs) and magnetic resonance angiographic (MRA) image volumes.

Statistical 3D Vessel Segmentation Using a Rician Distribution

This paper presents an extended version of the fully automated 3D cerebral vessel reconstruction algorithm developed by Wilson and Noble [11] which is applicable to time-of-flight (TOF) and phase contrast (PC) magnetic resonance angiography (MRA) images. We introduce a Rician distribution for background noise modelling and use a modified EM (Expectation-Maximization) algorithm for the parameter estimation procedure. The proposed algorithm is applied to PC-MRA images. It is shown that the estimated Rician distribution gives a better quality-of-fit to the observed background noise distribution than a Gaussian distribution. In the experiments reported, the segmented 3D vasculature is shown to be qualitatively comparable with the results obtained from higher resolution TOF MRA images.

Texture Classification by using Advanced Local Binary Patterns and Spatial Distribution of Dominant Patterns

In this paper, we propose a new feature extraction method, which is robust against rotation and histogram equalization for texture classification. To this end, we introduce the concept of advanced local binary patterns (ALBP), which reflects the local dominant structural characteristics of different kinds of textures. In addition, to extract the global spatial distribution feature of the ALBP patterns, we incooperate ALBP with the aura matrix measure as the second layer to analyze texture images. The proposed method has three novel contributions, (a) The proposed ALBP approach captures the most essential local structure characteristics of texture images (i.e. edges, corners); (b) the proposed method extracts global information by using Aura matrix measure based on the spatial distribution information of the dominant patterns produced by ALBP; and (c) the proposed method is robust to rotation and histogram equalization. The proposed approach has been compared with other widely used texture classification techniques and evaluated by applying classification tests to randomly rotated and histogram equalized images in two different texture databases: Brodatz and CUReT. The experimental results show that the classification accuracy of the proposed method exceeds the ones obtained by other image features.

A Segmentation Model Using Compound Markov Random Fields Based on a Boundary Model

Markov random field (MRF) theory has been widely applied to the challenging problem of image segmentation. In this paper, we propose a new nontexture segmentation model using compound MRFs, in which the original label MRF is coupled with a new boundary MRF to help improve the segmentation performance. The boundary model is relatively general and does not need prior training on boundary patterns. Unlike some existing related work, the proposed method offers a more compact interaction between label and boundary MRFs. Furthermore, our boundary model systematically takes into account all the possible scenarios of a single edge existing in a 3times3 neighborhood and, thus, incorporates sophisticated prior information about the relation between label and boundary. It is experimentally shown that the proposed model can segment objects with complex boundaries and at the same time is able to work under noise corruption. The new method has been applied to medical image segmentation. Experiments on synthetic images and real clinical datasets show that the proposed model is able to produce more accurate segmentation results and satisfactorily keep the delicate boundary. It is also less sensitive to noise in both high and low signal-to-noise ratio regions than some of the existing models in common use

Trilateral filtering for biomedical images

Filtering is a core operation in low level computer vision. It is a preliminary process in many biomedical image processing applications. Bilateral filtering has been applied to smooth biomedical images while preserving the edges. However, to avoid oversmoothing structures of sizes comparable to the image resolutions, a narrow spatial window has to be used. This leads to the necessity of performing more iterations in the filtering process. In this paper, we propose a novel filtering technique namely trilateral filter, which can achieve edge-preserving smoothing with a narrow spatial window in only a few iterations. The experimental results have shown that our novel method provides greater noise reduction than bilateral filtering and smooths biomedical images without over-smoothing ridges and shifting the edge locations, as compared to other noise reduction methods.

Non-rigid image registration using graph-cuts

Non-rigid image registration is an ill-posed yet challenging problem due to its supernormal high degree of freedoms and inherent requirement of smoothness. Graph-cuts method is a powerful combinatorial optimization tool which has been successfully applied into image segmentation and stereo matching. Under some specific constraints, graph-cuts method yields either a global minimum or a local minimum in a strong sense. Thus, it is interesting to see the effects of using graph-cuts in non-rigid image registration. In this paper, we formulate non-rigid image registration as a discrete labeling problem. Each pixel in the source image is assigned a displacement label (which is a vector) indicating which position in the floating image it is spatially corresponding to. A smoothness constraint based on first derivative is used to penalize sharp changes in displacement labels across pixels. The whole system can be optimized by using the graph-cuts method via alpha-expansions. We compare 2D and 3D registration results of our method with two state-of-the-art approaches. It is found that our method is more robust to different challenging non-rigid registration cases with higher registration accuracy.

An active contour model for image segmentation based on elastic interaction

The task of image segmentation is to partition an image into non-overlapping regions based on intensity or textural information. The active contour methods provide an effective way for segmentation, in which the boundaries of the objects are detected by evolving curves. In this paper, we propose a new edge-based active contour method, which uses a long-range and orientation-dependent interaction between image boundaries and the moving curves while maintaining the edge fidelity. As a result, this method has a large capture range, and is able to detect sharp features of the images. The velocity field for the moving curves generated by this elastic interaction is calculated using the fast Fourier transform (FFT) method. Level set representation is used for the moving curves so that the topological changes during the evolution are handled automatically. This new method is derived based on the elastic interaction between line defects in solids (dislocations). Although it is derived originally for two dimensional segmentation, we also extend it to three dimensions. The features of the new method are examined by experiments on both synthetic images and medical images of blood vessels. Comparisons are made with the existing active contour methods.