Masters Theses

Abstract

"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® 7.4.0.287 (R2007a)"--Abstract, page iii.

Advisor(s)

Moss, Randy Hays, 1953-

Committee Member(s)

Stanley, R. Joe
Shrestha, Bijaya

Department(s)

Electrical and Computer Engineering

Degree Name

M.S. in Electrical Engineering

Publisher

Missouri University of Science and Technology

Publication Date

2009

Pagination

viii, 67 pages

Note about bibliography

Includes bibliographical references (page 66).

Rights

© 2009 Ankur Dilip Dalal, All rights reserved.

Document Type

Thesis - Restricted Access

File Type

text

Language

English

Subject Headings

Melanoma -- Diagnosis
Skin -- Cancer -- Diagnosis
Image processing

Thesis Number

T 10544

Print OCLC #

903587723

Electronic OCLC #

904023228

Link to Catalog Record

Electronic 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://merlin.lib.umsystem.edu/record=b10719254~S5

Download
Off-campus S&T users

Share My Thesis If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the button above.

 
COinS