Pheng-Ann Heng

A new method of feature fusion and its application in image recognition

A new method of feature extraction, based on feature fusion, is proposed in this paper according to the idea of canonical correlation analysis (CCA). At first, the theory framework of CCA used in pattern recognition and its reasonable description are discussed. The process can be explained as follows: extract two groups of feature vectors with the same pattern; establish the correlation criterion function between the two groups of feature vectors; and extract their canonical correlation features to form effective discriminant vector for recognition. Then, the problem of canonical projection vectors is solved when two total scatter matrixes are singular, such that it fits for the case of high-dimensional space and small sample size, in this sense, the applicable range of CCA is extended. At last, the inherent essence of this method used in recognition is analyzed further in theory. Experimental results on Concordia University CENPARMI database of handwritten Arabic numerals and Yale face database show that recognition rate is far higher than that of the algorithm adopting single feature or the existing fusion algorithm.

Stability of fuzzy control systems with bounded uncertain delays

Global exponential stability of fuzzy control systems with delays is studied. These delays in the fuzzy control systems are assumed to be any uncertain bounded continuous functions. Stability of systems with uncertain delays is interesting since in practical applications it is not easy to know the delays exactly. Conditions for global exponential stability of free fuzzy systems with uncertain delays are derived. Criteria for design of nonlinear fuzzy controllers to feedback control the stability of global nonlinear fuzzy systems are given. Theorems are proved via the method of functional differential inequalities analysis.

Sampling with Hammersley and Halton points

Abstract The Hammersley and Halton point sets, two well-known, low discrepancy sequences, have been used for quasi-Monte Carlo integration in previous research. A deterministic formula generates a uniformly distributed and stochasticlooking sampling pattern at low computational cost. The Halton point set is also useful for incremental sampling. In this paper, we discuss detailed implementation issues and our experience of choosing suitable bases for the point sets, not just on the two-dimensional plane but also on a spherical surface. The sampling scheme is also applied to ray tracing, with a significant improvement in error over standard sampling techniques.

Convergence analysis of cellular neural networks with unbounded delay

Cellular neural networks (CNNs) have been successfully applied in many areas such as classification of patterns, image processing, associative memories, etc. Since they are inherently local in nature, they can be easily implemented in very large scale integration. In the processing of static images, CNNs without delay are often applied whereas in the processing of moving images, CNNs with delay have been found more suitable. This paper proposes a more general model of CNNs with unbounded delay, which may have potential applications in processing such motion related phenomena as moving images, and studies global convergence properties of this model. The dynamic behaviors of CNNs, especially their convergence properties, play important roles in applications. This paper: (1) introduces a class of CNNs with unbounded delay; (2) gives some interesting properties of a networks output function; (3) establishes relationships between a networks state stability and its output stability; and (4) obtains simple and easily checkable conditions for global convergence by functional differential equation methods.

Manga colorization

This paper proposes a novel colorization technique that propagates color over regions exhibiting pattern-continuity as well as intensity-continuity. The proposed method works effectively on colorizing black-and-white manga which contains intensive amount of strokes, hatching, halftoning and screening. Such fine details and discontinuities in intensity introduce many difficulties to intensity-based colorization methods. Once the user scribbles on the drawing, a local, statistical based pattern feature obtained with Gabor wavelet filters is applied to measure the pattern-continuity. The boundary is then propagated by the level set method that monitors the pattern-continuity. Regions with open boundaries or multiple disjointed regions with similar patterns can be sensibly segmented by a single scribble. With the segmented regions, various colorization techniques can be applied to replace colors, colorize with stroke preservation, or even convert pattern to shading. Several results are shown to demonstrate the effectiveness and convenience of the proposed method.

Intrinsic colorization

In this paper, we present an example-based colorization technique robust to illumination differences between grayscale target and color reference images. To achieve this goal, our method performs color transfer in an illumination-independent domain that is relatively free of shadows and highlights. It first recovers an illumination-independent intrinsic reflectance image of the target scene from multiple color references obtained by web search. The reference images from the web search may be taken from different vantage points, under different illumination conditions, and with different cameras. Grayscale versions of these reference images are then used in decomposing the grayscale target image into its intrinsic reflectance and illumination components. We transfer color from the color reflectance image to the grayscale reflectance image, and obtain the final result by relighting with the illumination component of the target image. We demonstrate via several examples that our method generates results with excellent color consistency.

The Chinese Visible Human (CVH) datasets incorporate technical and imaging advances on earlier digital humans

We report the availability of a digitized Chinese male and a digitzed Chinese female typical of the population and with no obvious abnormalities. The embalming and milling procedures incorporate three technical improvements over earlier digitized cadavers. Vascular perfusion with coloured gelatin was performed to facilitate blood vessel identification. Embalmed cadavers were embedded in gelatin and cryosectioned whole so as to avoid section loss resulting from cutting the body into smaller pieces. Milling performed at −25 °C prevented small structures (e.g. teeth, concha nasalis and articular cartilage) from falling off from the milling surface. The male image set (.tiff images each of 36 Mb) has a section resolution of 3072 × 2048 pixels (∼170 µm, the accompanying magnetic resonance imaging and computer tomography data have a resolution of 512 × 512, i.e. ∼440 µm). The Chinese Visible Human male and female datasets are available at http://www.chinesevisiblehuman.com. (The male is 90.65 Gb and female 131.04 Gb). MPEG videos of direct records of real‐time volume rendering are at: http://www.cse.cuhk.edu.hk/~crc

Image-based Rendering with Controllable Illumination

A new image-based rendering method, based on the light field and Lumigraph system, allows illumination to be changed interactively. It does not try to recover or use any geometrical information (e.g., depth or surface normals) to calculate the illumination, but the resulting images are physically correct. The scene is first sampled from different viewpoints and under different illuminations. Treating each pixel on the back plane of the light slab as a surface element,the sampled images are used to find an apparent BRDF of each surface element. The tabular BRDF data of each pixel is further transformed to the spherical harmonic domain for efficient storage. Whenever the user changes the illumination setting, a certain number of views are reconstructed. The correct user perspective view is then displayed using the texture mapping technique of the Lumigraph system. Hence, the intensity, the type and the number of the light sources can be manipulated interactively.

Absolute periodicity and absolute stability of delayed neural networks

Proposes to study the absolute periodicity of delayed neural networks. A neural network is said to be absolutely periodic, if for every activation function in some suitable functional set and every input periodic vector function, a unique periodic solution of the network exists and all other solutions of the network converge exponentially to it. Absolute stability of delayed neural networks is also studied in this paper. Simple and checkable conditions for guaranteeing absolute periodicity and absolute stability are derived. Simulations for absolute periodicity are given.

Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks

Cerebral microbleeds (CMBs) are small haemorrhages nearby blood vessels. They have been recognized as important diagnostic biomarkers for many cerebrovascular diseases and cognitive dysfunctions. In current clinical routine, CMBs are manually labelled by radiologists but this procedure is laborious, time-consuming, and error prone. In this paper, we propose a novel automatic method to detect CMBs from magnetic resonance (MR) images by exploiting the 3D convolutional neural network (CNN). Compared with previous methods that employed either low-level hand-crafted descriptors or 2D CNNs, our method can take full advantage of spatial contextual information in MR volumes to extract more representative high-level features for CMBs, and hence achieve a much better detection accuracy. To further improve the detection performance while reducing the computational cost, we propose a cascaded framework under 3D CNNs for the task of CMB detection. We first exploit a 3D fully convolutional network (FCN) strategy to retrieve the candidates with high probabilities of being CMBs, and then apply a well-trained 3D CNN discrimination model to distinguish CMBs from hard mimics. Compared with traditional sliding window strategy, the proposed 3D FCN strategy can remove massive redundant computations and dramatically speed up the detection process. We constructed a large dataset with 320 volumetric MR scans and performed extensive experiments to validate the proposed method, which achieved a high sensitivity of 93.16% with an average number of 2.74 false positives per subject, outperforming previous methods using low-level descriptors or 2D CNNs by a significant margin. The proposed method, in principle, can be adapted to other biomarker detection tasks from volumetric medical data.