Quantitative Image Analysis of Chest CT Using Gray Level Local Binary Pattern Texture Feature

초록

Texture feature is one of the most popular image analysis methods for computer-aided diagnosis (CAD) system. This paper presents a texture feature extraction method based on gray level local binary pattern (GLLBP) to help the diagnosis of emphysema disease using chest CT images. The proposed method allows us to extract texture features with multiple directions. Experimental results show that GLLBP can achieve better performance than the existing texture features.