Hua Cao

Huazhong University of Science and Technology | hust · School of Software Engineering

The head pose on roll and yaw directions is decided by the asymmetric appearance in human faces, and the contextual information of asymmetric appearance is encoded in a head pose related neighborhood. However, CNNs used in existing head pose estimation methods often evenly performs on the features of full image. Thus it is hard to collect the conte...

A novel saliency detection method via spectral graph (SG) weighted low rank matrix recovery (LR) is presented in this paper. The location, color, and boundary priors are exploited in many LR-based saliency detection methods. However, these priors do not work well when the salient objects are far away from image center, especially when the backgroun...

This paper presents a novel saliency detection method via updating initial labels from spectral graph in a semi-supervised learning (SSL) framework. For updating labels efficiently with graph-based SSL, two principles generally should be considered. The first one is that the updated labels should not change too much from their initial assignment. T...

In existing local and global consistency framework, the cost functions related to classifying functions adopts the sum of each row of weight matrix as an important factor. Some of these classifying functions are successfully applied to saliency detection. From the point of saliency detection, this factor is inversely proportional to the color contr...

An attention region usually possesses a closed contour and a significant color contrast against its surroundings. Inspired by this observation, a novel prior so called closure prior is introduced as an important high-level saliency cue in this paper. Specifically, firstly, the connectivity analysis is used in layered bit planes to extract closed re...

This paper presents a novel perspective of performance evaluation for visual attention estimation: how the saliency models perform in mobile conditions. In particular, a broad-spectrum contrast sensitivity function is firstly proposed in this work. Based on this function, a new visual perception model is established, which will be further used to s...

TGR5 activation of enteroendocrine cells increases glucagon-like peptide 1 (GLP-1) release, which maintains glycemic homeostasis. However, TGR5 activation in the gallbladder and heart is associated with severe side effects. Therefore, intestinally-targeted TGR5 agonists were suggested as potential hypoglycemic agents with minimal side effects. Howe...

In this paper, an image dimming perceptual model is proposed as the foundation of image compensation and quality evaluation. Specifically, under this model an ideal compensation function is derived out and objective quality metrics SSIM and PSNR are adopted to evaluate the compensation performance. A practical compensation function is obtained by m...

320 Slice Dynamic Volume CT provides intracranial aneurysm patients with 4D digital subtraction angiography (DSA) imaging and the Key technology of which are the wide detection platform and ConeXact Cone-beam reconstruction algorithm. In this thesis, some familiar cone-beam scan reconstruction algorithms are analyzed and compared, especially those...

According to the nature of saliency map generation with colour contrast, a non-attention region first initialisation (NARFI) k-means clustering for saliency detection is proposed. The NAR is obtained by multiwavelet reconstruction based on the cutoff low-frequency. The initial seeds of the k-means are chosen from the NAR. This way, the NAR is clust...

Because of the high data dependency between ADL (adaptive directional lifting) operations, such as interpolation, directional prediction and update, the existing CUDA-specific (Compute Unified Device Architecture) implementation of traditional rectilinear lifting-based transform is difficult to be used for ADL-based transform. This paper proposes a...

An important processing stage in computer vision such as recognizes an object is feature extraction. Among those feature extraction algorithms, Lowe proposed the scale-invariant feature transform (SIFT) algorithm has been considered as one of the robust approaches. But due to the implementation of the convolution operation, the computing of SIFT al...

A symmetric-antisymmetric (SA) multiwavelet lifting factorization of matrix filter banks is presented as an extension of Sweldens’ traditional scalar wavelet lifting scheme. A prefilter absorbed (PA) multiwavelet lifting factorization is also presented to reduce the redundant computations in prefiltering. Then an algorithm of multiwavelet lifting i...

Because of high data dependency between ADL (adaptive directional lifting) steps, such as interpolation, directional prediction and update, the existing CUDA (Compute Unified Device Architecture) configuration method for traditional rectilinear transform is difficult to be used for ADL-based transform. This paper proposed a new configuration method...

The high compression ratio of fractal encoding is based on the increasing of the computation complexity. In order to meet the application requirements of real-time sharing and transmission, it is becoming an important research area to advance the encoding speed by developing the parallelization algorithm based on multi-core programming. In this pap...

The high compression ratio of fractal encoding is based on the increasing of the computation complexity. In order to meet the application requirements of real-time sharing and transmission, it is becoming an important research area to advance the encoding speed by developing the parallelization algorithm based on multi-core programming. In this pap...

Wireless sensor networks (WSN) have been recently be proposed for great deal of applications in industrial automation, health and environment monitoring. Increasingly there is a need to access wireless sensor networks from other IP-based networks. However, WSN has its own application-specific non-standardized protocols such as data-centric router p...

Digital watermarking is the technique which embeds an invisible signal including owner identification and copy control information into multimedia data such as image, audio and video for copyright protection. A blind robust algorithm of hiding data into H.264 video stream rapidly was proposed in this paper, copyright protection can be achieved by e...

Digital watermarking technology is an effective solution to protect copyright of multimedia data such as still images, video and audio. In this paper, a new still image watermark embedding algorithm based on fractal transformation is proposed. The watermark information is embedded into the host image through directly modifying the contrast factor w...