Title :
Image segmentation using histogram specification
Author_Institution :
Electr. & Comput. Eng. Dept., Univ. of Manitoba, MB
Abstract :
Development of an accurate image segmentation algorithm can be the most demanding part of a computer vision system. There is not a panacean method that can work with several different types of images and a segmentation approach is usually designed for solving a specific problem. In this work, histogram specification is proposed in order to help the segmentation step in what was found to be a robust way regardless of the segmentation approach used. Semiautomatic algorithms for histogram specification are discussed. Examples using different segmentation techniques are shown.
Keywords :
computer vision; image segmentation; statistical analysis; computer vision system; histogram specification; image segmentation; semiautomatic algorithm; Calibration; Computer vision; Filtering; Frequency; Histograms; Image segmentation; Magnetic resonance imaging; Matched filters; Robustness; Shape; Image segmentation; histogram filtering; histogram matching; histogram specification;
Conference_Titel :
Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-1765-0
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2008.4711823