King Ngi Ngan

Face segmentation using skin-color map in videophone applications

This paper addresses our proposed method to automatically segment out a persons face from a given image that consists of a head-and-shoulders view of the person and a complex background scene. The method involves a fast, reliable, and effective algorithm that exploits the spatial distribution characteristics of human skin color. A universal skin-color map is derived and used on the chrominance component of the input image to detect pixels with skin-color appearance. Then, based on the spatial distribution of the detected skin-color pixels and their corresponding luminance values, the algorithm employs a set of novel regularization processes to reinforce regions of skin-color pixels that are more likely to belong to the facial regions and eliminate those that are not. The performance of the face-segmentation algorithm is illustrated by some simulation results carried out on various head-and-shoulders test images. The use of face segmentation for video coding in applications such as videotelephony is then presented. We explain how the face-segmentation results can be used to improve the perceptual quality of a videophone sequence encoded by the H.261-compliant coder.

Unsupervised extraction of visual attention objects in color images

This paper proposes a generic model for unsupervised extraction of viewers attention objects from color images. Without the full semantic understanding of image content, the model formulates the attention objects as a Markov random field (MRF) by integrating computational visual attention mechanisms with attention object growing techniques. Furthermore, we describe the MRF by a Gibbs random field with an energy function. The minimization of the energy function provides a practical way to obtain attention objects. Experimental results on 880 real images and user subjective evaluations by 16 subjects demonstrate the effectiveness of the proposed approach.

Automatic segmentation of moving objects for video object plane generation

The new video coding standard MPEG-4 is enabling content-based functionalities. It takes advantage of a prior decomposition of sequences into video object planes (VOPs) so that each VOP represents one moving object. A comprehensive review summarizes some of the most important motion segmentation and VOP generation techniques that have been proposed. Then, a new automatic video sequence segmentation algorithm that extracts moving objects is presented. The core of this algorithm is an object tracker that matches a two-dimensional (2-D) binary model of the object against subsequent frames using the Hausdorff distance. The best match found indicates the translation the object has undergone, and the model is updated every frame to accommodate for rotation and changes in shape. The initial model is derived automatically, and a new model update method based on the concept of moving connected components allows for comparatively large changes in shape. The proposed algorithm is improved by a filtering technique that removes stationary background. Finally, the binary model sequence guides the extraction objects of the VOPs from the sequence. Experimental results demonstrate the performance of our algorithm.

Video segmentation for content-based coding

To provide multimedia applications with new functionalities, the new video coding standard MPEG-4 relies on a content-based representation. This requires a prior decomposition of sequences into semantically meaningful, physical objects. We formulate this problem as one of separating foreground objects from the background based on motion information. For the object of interest, a 2D binary model is derived and tracked throughout the sequence. The model points consist of edge pixels detected by the Canny operator. To accommodate rotation and changes in shape of the tracked object, the model is updated every frame. These binary models then guide the actual video object plane (VOP) extraction. Thanks to our new boundary postprocessor and the excellent edge localization properties of the Canny operator, the resulting VOP contours are very accurate. Both the model initialization and update stages exploit motion information. The main assumption underlying our approach is the existence of a dominant global motion that can be assigned to the background. Areas that do not follow this background motion indicate the presence of independently moving physical objects. Two alternative methods to identify such objects are presented. The first one employs a morphological motion filter with a new filter criterion, which measures the deviation of the locally estimated optical flow from the corresponding global motion. The second method computes a change detection mask by taking the difference between consecutive frames. The first version is more suitable for sequences with little motion, whereas the second version is better at dealing with faster moving or changing objects. Experimental results demonstrate the performance of our algorithm.

A Co-Saliency Model of Image Pairs

In this paper, we introduce a method to detect co-saliency from an image pair that may have some objects in common. The co-saliency is modeled as a linear combination of the single-image saliency map (SISM) and the multi-image saliency map (MISM). The first term is designed to describe the local attention, which is computed by using three saliency detection techniques available in literature. To compute the MISM, a co-multilayer graph is constructed by dividing the image pair into a spatial pyramid representation. Each node in the graph is described by two types of visual descriptors, which are extracted from a representation of some aspects of local appearance, e.g., color and texture properties. In order to evaluate the similarity between two nodes, we employ a normalized single-pair SimRank algorithm to compute the similarity score. Experimental evaluation on a number of image pairs demonstrates the good performance of the proposed method on the co-saliency detection task.

Spatio-Temporal Just Noticeable Distortion Profile for Grey Scale Image/Video in DCT Domain

In image and video processing field, an effective compression algorithm should remove not only the statistical redundancy information but also the perceptually insignificant component from the pictures. Just-noticeable distortion (JND) profile is an efficient model to represent those perceptual redundancies. Human eyes are usually not sensitive to the distortion below the JND threshold. In this paper, a DCT based JND model for monochrome pictures is proposed. This model incorporates the spatial contrast sensitivity function (CSF), the luminance adaptation effect, and the contrast masking effect based on block classification. Gamma correction is also considered to compensate the original luminance adaptation effect which gives more accurate results. In order to extend the proposed JND profile to video images, the temporal modulation factor is included by incorporating the temporal CSF and the eye movement compensation. Moreover, a psychophysical experiment was designed to parameterize the proposed model. Experimental results show that the proposed model is consistent with the human visual system (HVS). Compared with the other JND profiles, the proposed model can tolerate more distortion and has much better perceptual quality. This model can be easily applied in many related areas, such as compression, watermarking, error protection, perceptual distortion metric, and so on.

Admission control in IEEE 802.11e wireless LANs

Although IEEE 802.11 based wireless local area networks have become more and more popular due to low cost and easy deployment, they can only provide best effort services and do not have quality of service supports for multimedia applications. Recently, a new standard, IEEE 802.11e, has been proposed, which introduces a so-called hybrid coordination function containing two medium access mechanisms: contention-based channel access and controlled channel access. In this article we first give a brief tutorial on the various MAC-layer QoS mechanisms provided by 802.11e. We show that the 802.11e standard provides a very powerful platform for QoS supports in WLANs. Then we provide an extensive survey of recent advances in admission control algorithms/protocols in IEEE 802.11e WLANs. Our survey covers the research work in admission control for both EDCA and HCCA. We show that the new MAC-layer QoS schemes and parameters provided in EDCA and HCCA can be well utilized to fulfill the requirements of admission control so that QoS for multimedia applications can be provided in WLANs. Last, we give a summary of the design of admission control in EDCA and HCCA, and point out the remaining challenges.

Locating facial region of a head-and-shoulders color image

This paper addresses our proposed method to automatically locate the persons face from a given image that consists of a head-and-shoulders view of the person and a complex background scene. The method involves a fast, simple and yet robust algorithm that exploits the spatial distribution characteristics of human skin color. It first uses the chrominance component of the input image to detect pixels with skin color appearance. Then, bused on the spatial distribution of the detected skin-color pixels and their corresponding luminance values, the algorithm employs some regularization processes to reinforce regions of skin-color pixels that are more likely to belong to the facial regions and eliminate those that are not. The performance of the face localization algorithm is illustrated by some simulation results carried out on various head-and-shoulders test images.

Adaptive cosine transform coding of images in perceptual domain

An adaptive cosine transform coding scheme for color images which incorporates human visual properties into the coding scheme is described. It employs adaptive quantization to exploit the statistical nature of the coefficients and adaptive block distortion equalization to reduce the block edge structures inherent in block transform coding schemes. Results show that the subjective quality of the reconstructed images at a bit rate of 0.4 bit/pixel or a compression ratio of 60:1 is very good. >

Reduction of blocking artifacts in image and video coding

The discrete cosine transform (DCT) is the most popular transform for image and video compression. Many international standards such as JPEG, MPEG, and H.261 are based on a block-DCT scheme. High compression ratios are obtained by discarding information about DCT coefficients that is considered to be less important. The major drawback is visible discontinuities along block boundaries, commonly referred to as blocking artifacts. These often limit the maximum compression ratios that can be achieved. Various postprocessing techniques have been published that reduce these blocking effects, but most of them introduce unnecessary blurring, ringing, or other artifacts. In this paper, a novel postprocessing algorithm based on Markov random fields (MRFs) is proposed. It efficiently removes blocking effects while retaining the sharpness of the image and without introducing new artifacts. The degraded image is first segmented into regions, and then each region is enhanced separately to prevent blurring of dominant edges. A novel texture detector allows the segmentation of images containing both texture and monotone areas. It finds all texture regions in the image before the remaining monotone areas are segmented by an MRF segmentation algorithm that has a new edge component incorporated to detect dominant edges more reliably. The proposed enhancement stage then finds the maximum a posteriori estimate of the unknown original image, which is modeled by an MRF and is therefore Gibbs distributed. A very efficient implementation is presented. Experiments demonstrate that our proposed postprocessor gives excellent results compared to other approaches, from both a subjective and an objective viewpoint. Furthermore, it will be shown that our technique also works for wavelet encoded images, which typically contain ringing artifacts.