Chun-Rong Huang

Efficient hierarchical method for background subtraction

Detecting moving objects by using an adaptive background model is a critical component for many vision-based applications. Most background models were maintained in pixel-based forms, while some approaches began to study block-based representations which are more robust to non-stationary backgrounds. In this paper, we propose a method that combines pixel-based and block-based approaches into a single framework. We show that efficient hierarchical backgrounds can be built by considering that these two approaches are complementary to each other. In addition, a novel descriptor is proposed for block-based background modeling in the coarse level of the hierarchy. Quantitative evaluations show that the proposed hierarchical method can provide better results than existing single-level approaches.

Contrast context histogram-An efficient discriminating local descriptor for object recognition and image matching

In this paper, we propose a new invariant local descriptor, called the contrast context histogram (CCH), for image matching and object recognition. By representing the contrast distributions of a local region, it serves as a distinctive local descriptor of the region. Our experiments demonstrate that contrast-based local descriptors can represent local regions with more compact histogram bins. Because of its high matching accuracy and efficient computation, the CCH has the potential to be used in a number of real-time applications.

Fighting Phishing with Discriminative Keypoint Features

Phishing is a form of online identity theft associated with both social engineering and technical subterfuge and is a major threat to information security and personal privacy. Here, the authors present an effective image-based antiphishing scheme based on discriminative keypoint features in Web pages. Their invariant content descriptor, the Contrast Context Histogram (CCH), computes the similarity degree between suspicious and authentic pages. The results show that the proposed scheme achieves high accuracy and low error rates.

Shot Change Detection via Local Keypoint Matching

Shot change detection is an essential step in video content analysis. However, automatic shot change detection often suffers from high false detection rates due to camera or object movements. To solve this problem, we propose an approach based on local keypoint matching of video frames. This approach aims to detect both abrupt and gradual transitions between shots without modeling different kinds of transitions. Our experiment results show that the proposed algorithm is effective for most kinds of shot changes.

Video Saliency Map Detection by Dominant Camera Motion Removal

We present a trajectory-based approach to detect salient regions in videos by dominant camera motion removal. Our approach is designed in a general way so that it can be applied to videos taken by either stationary or moving cameras without any prior information. Moreover, multiple salient regions of different temporal lengths can also be detected. To this end, we extract a set of spatially and temporally coherent trajectories of keypoints in a video. Then, velocity and acceleration entropies are proposed to represent the trajectories. In this way, long-term object motions are exploited to filter out short-term noises, and object motions of various temporal lengths can be represented in the same way. On the other hand, we are inspired by the observation that the trajectories in backgrounds, i.e., the nonsalient trajectories, are usually consistent with the dominant camera motion no matter whether the camera is stationary or not. We make use of this property to develop a unified approach to saliency generation for both stationary and moving cameras. Specifically, one-class SVM is employed to remove the consistent trajectories in motion. It follows that the salient regions could be highlighted by applying a diffusion process to the remaining trajectories. In addition, we create a set of manually annotated ground truth on the collected videos. The annotated videos are then used for performance evaluation and comparison. The promising results on various types of videos demonstrate the effectiveness and great applicability of our approach.

Maximum a Posteriori Probability Estimation for Online Surveillance Video Synopsis

To reduce human efforts in browsing long surveillance videos, synopsis videos are proposed. Traditional synopsis video generation applying optimization on video tubes is very time consuming and infeasible for real-time online generation. This dilemma significantly reduces the feasibility of synopsis video generation in practical situations. To solve this problem, the synopsis video generation problem is formulated as a maximum a posteriori probability (MAP) estimation problem in this paper, where the positions and appearing frames of video objects are chronologically rearranged in real time without the need to know their complete trajectories. Moreover, a synopsis table is employed with MAP estimation to decide the temporal locations of the incoming foreground objects in the synopsis video without needing an optimization procedure. As a result, the computational complexity of the proposed video synopsis generation method can be significantly reduced. Furthermore, as it does not require prescreening the entire video, this approach can be applied on online streaming videos.

Contrast Context Histogram - A Discriminating Local Descriptor for Image Matching

This paper presents a new invariant local descriptor, contrast context histogram, for image matching. It represents the contrast distributions of a local region, and serves as a local distinctive descriptor of this region. Object recognition can be considered as matching salient corners with similar contrast context histograms on two or more images in our work. Our experimental results show that the developed descriptor is accurate and efficient for matching

Gender classification from unaligned facial images using support subspaces

Rough face alignments result in suboptimal performance of face identification. In this study, we present an approach for identifying the gender based on facial images without proper face alignments. Instead of just using only the detected face patch for identification, a set of patches is randomly cropped around the face detection region. Each patch set is represented by a linear subspace and compared with other linear subspaces by measuring their canonical correlations. A similarity matrix comprised of the canonical correlations is then incorporated into an indefinite-kernel Support Vector Machine (SVM) formulation. The number of support vectors, which we call support subspaces, can be decided automatically, hence, we can avoid the dimension selection problem observed in our previous work. Our experimental results demonstrate that the proposed approach outperforms state-of-the-art methods.

Identifying Gender from Unaligned Facial Images by Set Classification

Rough face alignments lead to suboptimal performance of face identification systems. In this study, we present a novel approach for identifying genders from facial images without proper face alignments. Instead of using only one input for test, we generate an image set by randomly cropping out a set of image patches from a neighborhood of the face detection region. Each image set is represented as a subspace and compared with other image sets by measuring the canonical correlation between two associated subspaces. By finding an optimal discriminative transformation for all training subspaces, the proposed approach with unaligned facial images is shown to outperform the state-of-the-art methods with face alignment.

Tangible photorealistic virtual museum

Diverse museum artifacts, such as ceramics, porcelain, and ritual bronzes, can convey a sense of a peoples history and culture, time, or place. Following specific criteria about the protection, maintenance, and preservation of these artifacts ensures their proper care and restoration. Often, this means visitors must view the artifacts statically in a glass showcase, precluding any kind of physical interaction. Moreover, because of limited exhibition space, many equally precious, beautiful, and important objects in the museums possession are unfortunately out of sight in storerooms. To make these objects more accessible, we developed a tangible photorealistic virtual museum system that lets people interact naturally and have an immersive experience with museum exhibits. Our system displays the museums exhibits using augmented panorama (AP), a technique that enhances a panorama with object-centered image sets (OCISs), or object movies. The AP gives viewers the impression that theyre touring and observing the museums exhibits. The vision-based tangible interface lets viewers focus on a particular object in the exhibit using a handheld 3D physical control cube (PCC). The PCC lets the viewer control the AP and examine an artifact for a more detailed appreciation. With intuitive hand movements, viewers can enlarge the object and rotate it in any direction. Furthermore, the virtual AP space doesnt have the limitations of real museum space. The system lets visitors enjoy any and all of the museums artifacts stored in the system, even if they arent physically on exhibit in the museum.