Edinburgh Research Explorer

A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

Original languageEnglish
Title of host publicationColor Medical Image Analysis
EditorsM. Emre Celebi, Gerald Schaefer
PublisherSpringer Netherlands
Number of pages24
ISBN (Electronic)978-94-007-5389-1
ISBN (Print)978-94-007-5388-4
Publication statusPublished - 2013

Publication series

NameLecture Notes in Computational Vision and Biomechanics
PublisherSpringer Netherlands
ISSN (Print)2212-9391
ISSN (Electronic)2212-9413


This chapter proposes a novel hierarchical classification system based on the K-Nearest Neighbors (K-NN) model and its application to non-melanoma skin lesion classification. Color and texture features are extracted from skin lesion images. The hierarchical structure decomposes the classification task into a set of simpler problems, one at each node of the classification. Feature selection is embedded in the hierarchical framework that chooses the most relevant feature subsets at each node of the hierarchy. The accuracy of the proposed hierarchical scheme is higher than 93 % in discriminating cancer and potential at risk lesions from benign lesions, and it reaches an overall classification accuracy of 74 % over five common classes of skin lesions, including two non-melanoma cancer types. This is the most extensive known result on non-melanoma skin cancer classification using color and texture information from images acquired by a standard camera (non-dermoscopy).

ID: 5034152