Showing papers by "Qixiang Ye published in 2004"

A new method to segment playfield and its applications in match analysis in sports video

Abstract: With the growing popularity of digitized sports video, automatic analysis of them need be processed to facilitate semantic summarization and retrieval. Playfield plays the fundamental role in automatically analyzing many sports programs. Many semantic clues could be inferred from the results of playfield segmentation. In this paper, a novel playfield segmentation method based on Gaussian mixture models (GMMs) is proposed. Firstly, training pixels are automatically sampled from frames. Then, by supposing that field pixels are the dominant components in most of the video frames, we build the GMMs of the field pixels and use these models to detect playfield pixels. Finally region-growing operation is employed to segment the playfield regions from the background. Experimental results show that the proposed method is robust to various sports videos even for very poor grass field conditions. Based on the results of playfield segmentation, match situation analysis is investigated, which is also desired for sports professionals and longtime fanners. The results are encouraging.

Automatic text segmentation from complex background

Abstract: In this paper, we proposed an automatic method to segment text from complex background for recognition task. First, a rule-based sampling method is proposed to get portion of the text pixels. Then, the sampled pixels are used for training Gaussian mixture models of intensity and hue components in HSI color space. Finally, the trained GMMs together with the spatial connectivity information are used for segment all of text pixels form their background. We used the word recognition rate to evaluate the segmentation result. Experiments results show that the proposed algorithm can work fully automatically and performs much better than the traditional methods.

A new text detection algorithm in images/video frames

Abstract: In this paper, we propose a new text detection algorithm for images/video frames in a coarse-to-fine framework. Firstly, in the coarse detection, multiscale wavelet energy feature is employed to locate all possible text pixels and then a density-based region growing method is developed to connect these pixels into text lines. Secondly, in the fine detection, four kinds of texture features are combined to represent a text line and a SVM classifier is employed to identify texts from the candidate ones. Experimental results on two datasets show the encouraging performance of the proposed algorithm.