Hong Ren Wu

Facial Expression Recognition in Perceptual Color Space

This paper introduces a tensor perceptual color framework (TPCF) for facial expression recognition (FER), which is based on information contained in color facial images. The TPCF enables multilinear image analysis in different color spaces, and demonstrates that color components provide additional information for robust FER. Using this framework, the components (in either RGB, YCbCr, CIELab or CIELuv space) of color images are unfolded to 2-D tensors based on multilinear algebra and tensor concepts, from which the features are extracted by Log-Gabor filters. The mutual information quotient method is employed for feature selection. These features are classified using a multiclass linear discriminant analysis classifier. The effectiveness of color information on FER using low-resolution and facial expression images with illumination variations is assessed for performance evaluation. Experimental results demonstrate that color information has significant potential to improve emotion recognition performance due to the complementary characteristics of image textures. Furthermore, the perceptual color spaces (CIELab and CIELuv) are better overall for FER than other color spaces, by providing more efficient and robust performance for FER using facial images with illumination variation.

Perceptually lossless medical image coding

A novel perceptually lossless coder is presented for the compression of medical images. Built on the JPEG 2000 coding framework, the heart of the proposed coder is a visual pruning function, embedded with an advanced human vision model to identify and to remove visually insignificant/irrelevant information. The proposed coder offers the advantages of simplicity and modularity with bit-stream compliance. Current results have shown superior compression ratio gains over that of its information lossless counterparts without any visible distortion. In addition, a case study consisting of 31 medical experts has shown that no perceivable difference of statistical significance exists between the original images and the images compressed by the proposed coder.

Perceptual Color Image Coding With JPEG2000

A perceptual color image coder (PCIC) is presented for the YCbCr color space within the framework of JPEG2000. This coder employs a vision model based perceptual distortion metric (PDM) to approximate perceived error for rate-distortion (R-D) optimization in order to maximize the visual quality of coded images. The vision model employed in the PCIC is structurally based on an existing monochromatic multichannel vision model, which is extended for color image coding. Subjective tests with 30 viewers show that the PCIC provides superior picture quality at low to intermediate bitrates in comparison with a JPEG2000 compliant coder employing the mean squared error (MSE) and the visual distortion metric (Cvis) as distortion measures, respectively.

Geometric Features-Based Filtering for Suppression of Impulse Noise in Color Images

A geometric features-based filtering technique, named as the adaptive geometric features based filtering technique (AGFF), is presented for removal of impulse noise in corrupted color images. In contrast with the traditional noise detection techniques where only 1D statistical information is used for noise detection and estimation, a novel noise detection method is proposed based on geometric characteristics and features (i.e., the 2-D information) of the corrupted pixel or the pixel region, leading to effective and efficient noise detection and estimation outcomes. A progressive restoration mechanism is devised using multipass nonlinear operations which adapt to the intensity and the types of the noise. Extensive experiments conducted using a wide range of test color images have shown that the AGFF is superior to a number of existing well-known benchmark techniques, in terms of standard image restoration performance criteria, including objective measurements, the visual image quality, and the computational complexity.

Colour image enhancement by virtual histogram approach

This paper introduces a new hybrid image enhancement approach driven by both global and local processes on luminance and chrominance components of the image. This approach, based on the parameter-controlled virtual histogram distribution method, can enhance simultaneously the overall contrast and the sharpness of an image. The approach also increases the visibility of specified portions or aspects of the image whilst better maintaining image colour. The approach was compared with other well-known image enhancement techniques. The experimental results have shown the superiority of the proposed approach.

Robust Shape-Feature-Vector-Based Face Recognition System

This paper presents a feature-based approach for fast face recognition. A novel shape-based automatic reference control point and feature extraction technique is proposed for face representation, whereby the difference between two faces is measured by a set of extracted features, and 3-D features from a set of 2-D images are used for face template registration. Unlike holistic face recognition algorithms, the feature-based algorithm is relatively robust to variations of face expressions, illumination, and pose, due to invariance of its facial feature vector. The theoretical performance analysis of the proposed technique was provided by a probabilistic and statistical approach. The proposed approach is shown to achieve promising performance for face recognition using several subsets of face recognition databases.

Smart video surveillance system

A new approach is proposed for a smart video surveillance system in this paper. The proposed surveillance system uses cononical stereo configuration to set up a pair of statical cameras to support a salient map to control a Pan-Tilt-Zoom(PTZ) camera/cameras, which captures high definition image /video of the interesting moving object in the surveillance area for further forensic investigations. The other contribution of the proposed approach is that, 3D information generated by the set of static cameras is used to support reliable spatial-temporal based image segmentation and object detection. For object tracking, velocity field computation from two consecutive images is based on correspondence salient feature (points). Due to its low computational cost, it is potential to support a real time system to make a loop control for further using the information from the PTZ camera to support the object tracking in video captured by the static cameras.

Statistical Analysis of Impulse Noise Model for Color Image Restoration

In the area of color image restoration, many state-of-the-art filters consist of two main processes, classification and reconstruction. Classification is used to separate clean pixels from corrupted pixels. Reconstruction involves using values from corrupted pixels to interpolate values for pixels believed to have been corrupted. In this paper, two statistical analyses are carried out to determine how salt and pepper and random impulse noise behave in images. By computing the cluster count and probability of occurrence in a database of 1000 single color noisy images for each noise model, we found that the results will benefit the classification and reconstruction process in color image filters.

Features Based Spatial and Temporal Blotch Detection for Archive Video Restoration

In order to restore blotched archive video without causing distortion to areas of the frames that are not corrupted, the locations of the blotches must be identified. Blotch detection usually needs reliable motion estimation to avoid false detection of uncorrupted regions in existing techniques. In this paper a blotch artifacts detection technique, which is based on spatiotemporal blotch image features extraction to avoid the dependence on the motion estimation, is proposed. In order to greatly reduce false alarms due to motion estimation errors the proposed detection technique is first to detect blotch candidates based on their spatial features and then to detect blotches from the blotch candidates by their temporal intensity discontinuities. Experimental results show that the proposed technique significantly improves detection performance and outperforms existing techniques.

A non-linear post filtering method for flicker reduction in H.264/AVC coded video sequences

The H.264/AVC coding standard reduces the blocking artifact by applying a spatial loop-filter in the encoder and in the decoder. However, the temporal fluctuation or flickering artifact is still noticeable between intra-coded frames or between an intra (I) frame and the preceding or subsequent inter prediction (P) frames. This paper proposes a non-linear temporal filter to reduce the flickering artifact and preserve image sharpness of the reconstructed video, by using a robust prior model. Performance of the flickering reduction with proposed filter is evaluated by a temporal metric, namely the sum of square difference (SSD), and the traditional measure, the peak signal to noise ratio (PSNR).