Classifying cervix tissue patterns with texture analysis

This paper presents a generalized statistical texture analysis technique fo r characterizing and recognizing typical, diagnostically most important, va scular patterns relating to cervical lesions from colposcopic images. The m ajor contributions of this research include the development of a novel gene ralized statistical texture analysis approach for accurately characterizing cervical textures and the introduction of a set of textural features that capture the specific characteristics of cervical textures as perceived by h uman. Experimental study demonstrated the feasibility and promising of the proposed approach in discriminating between cervical texture patterns indic ative of different stages of cervical lesions. (C) 2000 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.