Skin Cancer Recognition by Computer Vision

Abstract

Automatic detection of several features characteristic of basal cell epitheliomas is described. The features selected for this feasibility study are semitranslucency, telangiectasia, ulcer, crust, and tumor border. Image processing methods used in this study include frequency analysis of the Fourier transform of the image, the Sun-Wee texture analysis algorithm, and several other image analysis techniques suitable for skin photographs. This image analysis software is designed for use with AI/DERM, an expert system that models diagnosis of skin tumors by dermatologists.

Department(s)

Electrical and Computer Engineering

Second Department

Chemistry

Sponsor(s)

National Science Foundation (U.S.)

Keywords and Phrases

Artificial Intelligence--Expert Systems; Computer Programming--Algorithms; Image Processing--Medical Applications; Computer Vision; Expert System AI/DERM; Skin Cancer Recognition; Skin Tumors; Sun-Wee Texture Analysis Algorithm; Biomedical Engineering; Artificial Intelligence; Computer Analysis; Fourier Transformation; Human; Image Processing; Methodology; Photography; Priority Journal; Skin Cancer; Carcinoma, Basal Cell; Diagnosis, Differential; Expert Systems; Feasibility Studies; Fourier Analysis; Image Interpretation, Computer-Assisted; Minicomputers; Pattern Recognition; Skin Neoplasms; Skin Ulcer; Support, U.S. Gov't, Non-P.H.S.; Telangiectasis; Basal Cell Carcinoma (Epithelioma); Fourier Transform Processing; Texture Analysis

International Standard Serial Number (ISSN)

0895-6111; 1879-0771

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 1989 Elsevier, All rights reserved.

Publication Date

01 Jan 1989

PubMed ID

2924283

Link to Full Text

Share

 
COinS