Blotch Detection in Pigmented Skin Lesions Using Fuzzy Co-clustering and Texture Segmentation

Abstract

The ‘Fuzzy Co-Clustering Algorithm for Images (FCCI)’ technique has been successfully applied to colour segmentation of medical images. The goal of this work is to extend this technique by the inclusion of texture features as a clustering parameter for detecting blotches in skin lesions based on colour information. The objective function is optimized using the bacterial foraging algorithm which gives image specific values to the parameters involved in the algorithm. Experiments show the efficacy of the proposed method in extracting malignant blotches from different types of pigmented skin lesion images.