文章基本信息

标题：Object Detection Using Hausdorff Distance and Multiclass Discriminative Field
本地全文：下载
作者：Xiaofeng Zhang ; Hong Ding ; Rengui Cheng 等
期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2013
卷号：6
期号：1
出版社：SERSC
摘要：In this paper, we present a novel object detection scheme using only local contour fragments. A sample fragment extraction method decomposes a whole contour into several parts. Then, the candidate locations of corresponding fragments in test images are detected by a modified Hausdorff distance with punishment on clutter edge regions. The most probable locations are selected by Multiclass Discriminative Field (MDF). Finally, contours of the objects can be drawn with these locations and sample fragments. Our major contributions are simplifying the MDF by an undirected graph constructed by the candidate locations and directly selecting the fragment locations by this MDF. The results on our postmark database and the ETHZ database from internet show that the proposed scheme is practicable.
关键词：object detection; fragment extraction; Hausdorff distance; Multiclass;Discriminative Field