文章基本信息

标题：Automatic Thresholding Techniques for Optical Images
本地全文：下载
作者：Moumena Al-Bayati ; Ali El-Zaart
期刊名称：Signal & Image Processing : An International Journal (SIPIJ)
印刷版ISSN：2229-3922
电子版ISSN：0976-710X
出版年度：2013
卷号：4
期号：3
页码：1
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Image segmentation is one of the important tasks in computer vision and image processing. Thresholding isa simple but most effective technique in segmentation. It based on classify image pixels into object andbackground depended on the relation between the gray level value of the pixels and the threshold. Otsutechnique is a robust and fast thresholding techniques for most real world images with regard to uniformityand shape measures. Otsu technique splits the object from the background by increasing the separabilityfactor between the classes. Our aim form this work is (1) making a comparison among five thresholdingtechniques (Otsu technique, valley emphasis technique, neighborhood valley emphasis technique, varianceand intensity contrast technique, and variance discrepancy technique)on different applications. (2)determining the best thresholding technique that extracted the object from the background. Ourexperimental results ensure that every thresholding technique has shown a superior level of performanceon specific type of bimodal images
关键词：Segmentation; Thresholding; Otsu Method; Valley Emphasis Method; Neighborhood Valley Emphasis;Method; Variance and Intensity Contrast Method; & Variance Discrepancy Method