期刊名称：International Journal of Computer Science Research and Application
印刷版ISSN：2012-9564
电子版ISSN：2012-9572
出版年度：2012
卷号：2
期号：2
出版社：INREWI Publications
摘要：Object detection and segmentation are critical task for many computer vision applications; they provide classification of the pixels into either foreground or background. In this paper, a new algorithm of objects detection and segmentation is proposed. Traditional approaches to object detection only look at local pieces of the image, whether it will be within a sliding window or the regions around an interest point detector. However, such local pieces can be ambiguous, especially when the object of interest is small, or imaging conditions are otherwise unfavorable. This ambiguity can be reduced by using global features of the image
