Texture analysis for classification of cervix lesions.

Abstract

This paper presents a generalized statistical texture analysis technique for characterizing and recognizing typical, diagnostically most important, vascular patterns relating to cervical lesions from colposcopic images. The contributions of the research include: 1) the introduction of a generalized texture analysis technique based on the combination of the conventional statistical and structural textural analysis approaches by using a statistical description of geometric primitives; 2) the introduction of a set of textural measures that capture the specific characteristics of cervical textures as perceived by human. Experimental study with real images demonstrated the feasibility and promising of the proposed approach in discriminating between cervical texture patterns indicative of different stages of cervical lesions.