We suggest the use of the color correlogram as a generic indexing tool to tackle various computer vision problems. Correlograms were shown to be very effective for contentbased image retrieval [4]. We adapt the correlogram to handle the problems of image subregion querying, object localization, object tracking, and cut detection. Experimental results suggest that the color correlogram is much more effective than the histogram for these applications, with insignificant additional computational, storage, or processing cost. We also provide a technique to cut down the storage requirement of correlograms so that it is the same as that of histograms, with only negligible performance penalty compared to the original correlogram. 1

In this paper, we first apply the theory of wallpaper groups to natural images and extract a novel feature to depict the symmetry property of natural images. The original proposed algorithm takes autocorrelation and correlation as a preprocessing step, which is very timeconsuming. Through further analysis, we develop a set of schemes to accelerate this algorithm. Experimental results demonstrate that in performing content-based image retrieval, the proposed symmetry feature outperforms wavelet feature, which is a widely accepted descriptor of texture, and water-filling feature. The accelerated version of the algorithm improves the processing speed by a large margin while it brings little degradation to retrieval performance. 1.

In content based retrieval, color indexing is one of the most prevalent retrieval methods. Two key problems in color indexing are (1) determination of the color space and (2) finding the best distance measure. Most of the attention from the research literature has been focussed on the color model with little or no consideration of the noise models. By focusing on the noise model, we showed how to find a distance measure which is optimal in the sense that it maximizes the similarity probability. Our results include experiments in color based retrieval and object recognition. Furthermore, we implemented and tested several promising algorithms from the research literature as benchmarks. 1. INTRODUCTION As the world enters the digital age, visual media is becoming prevalent and easily accessible. Factors such as the explosive growth of the World Wide Web, terabyte disk servers, and the digital versatile disk, reveal the growing amount of visual media which is available to society. With t...

Based on our previous work in deformable shape modelbased object detection, a new method is proposed that uses index trees for organizing shape features to support contentbased retrieval applications. In the proposed strategy, different shape feature sets can be used in index trees constructed for object detection and shape similarity comparison respectively. There is a direct correspondence between the two shape feature sets. As a result, application-specific features can be obtained efficiently for shape-based retrieval after object detection. A novel approach is proposed that allows retrieval of images based on the population distribution of deformed shapes in each image. Experiments testing these new approaches have been conducted using an image database that contains blood cell micrographs. The precision vs. recall performance measure shows that our method is superior to previous methods.

this paper we describe a system to show some limited effects on a static toy-car model and present techniques that can be used in similar setups. Our focus is on creating apparent motion for animation

We propose an improved local appearance and color modeling method, as an extension of Moghaddam & Zhou [lo], for object detection and recognition in clut-tered scenes. The approach is based on the joint distri-bution of local feature vectors at multiple salient points and factorization with Independent Component Anal-ysis (ICA). We we are able to obtain a tractable set of joint probability densities which can model high-order dependencies in local image features. In this work we replace multi-dimensional histograms with Gaussian mixture models with model-order selection based on the Minimum Description Length (MDL) cri-terion. Furthermore, a hybrid color/appearance mod-eling scheme is introduced which significantly increases performance. 1

Many video surveillance applications require detecting human reappearances in a scene monitored by a camera or over a network of cameras. This is the human reappearance detection (HRD) problem. Studying this problem is important for analyzing a surveillance scenario at semantic level. In this paper, we propose a novel online learning framework for solving HRD problem. Both generative model and discriminative model are employed in this framework and a voting scheme is presented to fuse the decisions of both models for determining whether a just entered person is one of those who have shown up, i.e. whether a reappearance happens. Both models will be updated based on mistake-driven online learning strategy. Our experimental results show that the adopted online learning framework not only improves the reappearance detection accuracy but also achieves high robustness in various surveillance scenes. 1.