TEXTURE CLASSIFICATION OF SARS INFECTED REGION IN RADIOGRAPHIC IMAGE (WA-P8)

Author(s) : Xiaoou Tang (The Chinese University of Hong Kong, Hong Kong) Dacheng Tao (The Chinese University of Hong Kong, Hong Kong) Gregory E. Antonio (The Chinese University of Hong Kong, Hong Kong)

Abstract : In this paper, we conduct a first study on SARS radiographic image processing. In order to distinguish SARS infected regions from normal lung regions using texture features, we propose several improvements to the traditional gray-level co-occurrence texture features [2]. We use a multi-level feature selection approach to extract texture features from a multi-resolution region based co-occurrence matrix directly for texture classification. The selected texture features can preserve most of the discriminant information in the texture image. Satisfactory results are obtained on a large set of chest radiographic images of SARS patients.

Menu