"This thesis presents an algorithm for automatically segmenting the white areas in dermoscopy images. The algorithm includes preprocessing of images, plotting the histogram (RGB) and calculating the average and standard deviation values (RGB) of the lesion. A threshold value for each color plane is determined using these parameters and white areas are automatically segmented. Various image features such as decile percentages and globule features are extracted and given to a neural network. The proposed algorithm has produced a maximum diagnostic accuracy of 94.67% and, when the lesions which touch the image border are removed from the set, the diagnostic accuracy is 96.17% using Receiver Operating Characteristic curve analysis. The code is implemented in MATLAB® 18.104.22.1687 (R2007a)"--Abstract, page iii.
Moss, Randy Hays, 1953-
Stanley, R. Joe
Electrical and Computer Engineering
M.S. in Electrical Engineering
Missouri University of Science and Technology
viii, 67 pages
© 2009 Ankur Dilip Dalal, All rights reserved.
Thesis - Restricted Access
Library of Congress Subject Headings
Melanoma -- Diagnosis
Skin -- Cancer -- Diagnosis
Print OCLC #
Electronic OCLC #
Link to Catalog RecordElectronic access to the full-text of this document is restricted to Missouri S&T users. Otherwise, request this publication directly from Missouri S&T Library or contact your local library. http://laurel.lso.missouri.edu/record=b10719254~S5
Dalal, Ankur Dilip, "Automatic detection of white areas in dermoscopy images" (2009). Masters Theses. 7349.