Home // MMEDIA 2016, The Eighth International Conferences on Advances in Multimedia // View article

Supervised Approach for Indication of Contrast Enhancement in Application of Image Segmentation

Authors:
Gabriel F. C. Campos
Rodrigo A. Igawa
José L. Seixas
Alex M. G. Almeida
Rodrigo C. Guido
Sylvio Barbon

Keywords: Contrast; Image Segmentation; Machine Learning

Abstract:
Segmentation methods need a satisfactory input image with a good contrast between Region of Interest and background to provide a high accuracy result. Thus, the application of contrast enhancement before the segmentation is a usual practice. This paper presents a supervised approach to determine if an input image is satisfactory for a specific segmentation approach by using Feature Extraction, Feature Selection and Machine Learning. Experimental results showed the proposed approach ability to indicate the need of contrast enhancement in different segmentation problems with 94 percent accuracy.

Pages: 12 to 18

Copyright: Copyright (c) IARIA, 2016

Publication date: February 21, 2016

Published in: conference

ISSN: 2308-4448

ISBN: 978-1-61208-452-7

Location: Lisbon, Portugal

Dates: from February 21, 2016 to February 25, 2016