Getian Ye

Mutual information-based method for selecting informative feature sets

Feature selection is one of the fundamental problems in pattern recognition and data mining. A popular and effective approach to feature selection is based on information theory, namely the mutual information of features and class variable. In this paper we compare eight different mutual information-based feature selection methods. Based on the analysis of the comparison results, we propose a new mutual information-based feature selection method. By taking into account both the class-dependent and class-independent correlation among features, the proposed method selects a less redundant and more informative set of features. The advantage of the proposed method over other methods is demonstrated by the results of experiments on UCI datasets (Asuncion and Newman, 2010 [1]) and object recognition.

Arobust approach to super-resolution sprite generation

In this paper, we propose a robust approach to super-resolution static sprite generation from multiple low-resolution images. Considering both short-term and long-term motion influences, a hybrid global motion estimation technique is first presented for sprite generation. An iterative super-resolution reconstruction algorithm is then proposed for the super-resolution sprite construction. This algorithm is robust to outliers and results in a sprite image with high visual quality. In addition, the generated super-resolution sprite can provide better reconstructed images than a conventional low-resolution sprite. Experimental results demonstrate the effectiveness of the proposed methods.

Finding shareable informative patterns and optimal coding matrix for multiclass boosting

A multiclass classification problem can be reduced to a collection of binary problems using an error-correcting coding matrix that specifies the binary partitions of the classes. The final classifier is an ensemble of base classifiers learned on binary problems and its performance is affected by two major factors: the qualities of the base classifiers and the coding matrix. Previous studies either focus on one of these factors or consider two factors separately. In this paper, we propose a new multiclass boosting algorithm called AdaBoost.SIP that considers both two factors simultaneously. In this algorithm, informative patterns, which are shareable by different classes rather than only discriminative on specific single class, are generated at first. Then the binary partition preferred by each pattern is found by performing stage-wise functional gradient descent on a margin-based cost function. Finally, base classifiers and coding matrix are optimized simultaneously by maximizing the negative gradient of such cost function. The proposed algorithm is applied to scene and event recognition and experimental results show its effectiveness in multiclass classification.

Region-based image categorization with reduced feature set

In this paper we propose a new algorithm for region-based image categorization that is formulated as a multiple instance learning (MIL) problem. The proposed algorithm transforms the MIL problem into a traditional supervised learning problem, and solves it using a standard supervised learning method. The features used in the proposed algorithm are the hyperclique patterns which are ldquocondensedrdquo into a small set of discriminative features. Each hyperclique pattern consists of multiple strongly-correlated instances (i.e., features). As a result, hyperclique patterns are able to capture the information that are not shared by individual features. The advantages of the proposed algorithm over existing algorithms are threefold: (i) unlike some existing algorithms which use learning methods that are specifically designed for MIL or for certain datasets, the proposed algorithm uses a general-purpose standard supervised learning method, (ii) it uses a significantly small set of features which are empirically more discriminative than the PCA features (i.e. principal components), and (iii) it is simple and efficient and achieves a comparable performance to most state-of-the-art algorithms. The efficiency and good performance of the proposed algorithm make it a practical solution to general MIL problems. In this paper, we apply the proposed algorithm to both drug activity prediction and image categorization, and promising results are obtained.

Feature clustering for vehicle detection and tracking in road traffic surveillance

In this paper, we formulate the feature clustering problem for vehicle detection and tracking as a general MAP problem and solve it using MCMC. The proposed approach exhibits two advantages over existing methods: general Bayesian model can handle arbitrary objective functions and MCMC guarantees global optimal solution. Our algorithm is validated on real-world traffic video sequences, and is shown to outperform the state-of-the-art approach.

Incremental EM for Probabilistic Latent Semantic Analysis on Human Action Recognition

Human action recognition is a significant task in automatic understanding systems for video surveillance. Probabilistic Latent Semantic Analysis (PLSA) model has been used to learn and recognize human actions in videos. Specifically, PLSA employs the expectation maximization (EM) algorithm for parameter estimation during the training. The EM algorithm is an iterative estimation scheme that is guaranteed to find a local maximum of the likelihood function. However its convergence usually takes a large number of iterations. For action recognition with large amount of training data, this would result in long training time. This paper presents an incremental version of EM to speed up the training of PLSA without sacrificing performance accuracy. The proposed algorithm is tested on two challenging human action datasets. Experimental results demonstrate that the proposed algorithm converges with fewer number of full passes compared with the batch EM algorithm. And the trained PLSA models achieve comparable or better recognition accuracies than those using batch EM training.

A practical approach to multiple super-resolution sprite generation

The MPEG-4 video coding standard introduces a novel concept of sprite or mosaic that is a large image composed of pixels belonging to a video object visible throughout a video segment. The sprite captures spatio-temporal information in a very compact way and makes it possible for efficient object-based video compression. In this paper, we propose a practical approach to generating multiple super-resolution sprites for sprite coding. In order to construct super-resolution sprites and reduce coding cost, we firstly partition a video sequence into multiple independent sprites and group the images covering a similar scene into the same sprite. We then propose efficient and practical algorithms for cumulative global motion estimation and super-resolution sprite construction. Experiments with real video sequences show that the proposed approach outperforms the previous single sprite and multiple sprite techniques.

A transform-domain approach to super-resolution mosaicing of compressed images

The combination of image mosaicing and super-resolution imaging, i.e. super-resolution mosaicing, is a powerful means of representing all the information of multiple overlapping images to obtain a high resolution broad view of a scene. In most current image acquisition systems, images are routinely compressed prior to transmission and storage. In this paper, we present a robust super-resolution mosaicing algorithm which can be applied to compressed images. The algorithm operates on the quantized transform coefficients available in the compressed bitstream so that super-resolution reconstruction can be implemented directly in the transform domain. In order to improve the performance of super-resolution mosaicing, an adaptive approach to determining a regularization parameter is proposed. It is shown that this algorithm is robust against outliers and provides reconstructed super-resolution images with improved quality.

Efficient multi-image registration with illumination and lens distortion correction

In this paper, we propose some extensions of an efficient gradient-based image registration method called the inverse compositional algorithm. Specifically, these extensions include cumulative multi-image registration and incorporations of illumination change and lens distortion correction. By combining these extensions, we propose efficient cumulative multi-image registration methods with illumination and lens distortion correction. It is shown that high efficiency can still be achieved for multiple images using the proposed methods. Some experimental results show the efficacy of the proposed methods.

Simultaneous tracking and registration in a multisensor surveillance system

In this paper, we present a multisensor surveillance system that consists of an optical sensor and an infrared sensor. In this system, a background subtraction method based on zero-order statistics is utilized for the moving object segmentation. Additionally, we propose a generic approach to simultaneous object tracking and multisensor image registration. An efficient face detection system is shown as an application that will have enhanced performance from the registration and fusion of the information from the two sensors. Experimental results show the efficacy of the proposed system.