一种新的结合区域与边缘特征的目标提取方法  

A New Target Extraction Method Combined Region Features with Edges

作　　者：单丽杰[1] 刘铁军[1] 朱丹[1] 肖颖杰[1] 

机构地区：[1]中国科学院沈阳自动化研究所,沈阳110016

出　　处：《计算机工程与应用》2004年第21期98-99,103,共3页Computer Engineering and Applications

基　　金：国家创新基金项目(编号:cx02-04-02)资助

摘　　要：该文借助知识理论,提出一种新的基于子图像块的区域分割与边缘检测相结合的目标提取方法。先对分块后的图像进行粗检,辅以知识确定目标的大概区域,然后借助改进的方向Canny边缘检测器增强并检测出较弱的目标边缘。实验结果表明该方法计算量较小、便于硬件实现,使复杂自然背景中,低对比度及不均匀光照条件下的一定形状尺寸的目标提取获得了满意的效果。A target extraction method based on subimage-block segmentation and edge detection is presented in virtue of knowledge theory.Firstly,we coarsely detect the feature image obtained from subimage blocks,the target regions are identified according to prior knowledge.Then,dim edges are enhanced by an improved directional Canny edge detector.Satisfied target edges are obtained finally.The experiments illustrate that this method is good at extracting targets with some certain shape and size from complex natural scenes under low contrast and varied illumination conditions。It is low computaitional cost and easy for hardware realization.

关 键 词：自然背景 目标提取 子图像块 CANNY边缘检测 弱边缘 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]