感知归类在目标识别中的应用研究  

Application Research on Perceptual Grouping in Object Recognition

作　　者：魏丽[1] 吴中福[1] 李云[1] 古毅[1] 

机构地区：[1]重庆大学计算机学院,重庆400044

出　　处：《计算机科学》2006年第5期238-240,共3页Computer Science

基　　金：重庆大学研究生创新基金"基于内容的图像检索引擎"项目的资助;编号200504Y1A0070113

摘　　要：感知归类是指人们在不拥有任何图像内容知识的前提下,从底层原始图像特征中提取有效的图像联系的一种视觉能力。本文着重介绍了感知归类方法在目标识别中的应用,通过使用感知归类中的接近、相似、连续等概念,逐步将底层的图像特征组合为高层的图像联系,直至获得有意义的语义表征。Perceptual grouping refers to the human visual ability to extract significant image relations from lower-level primitive image features without any knowledge of the image content. In this paper,we introduce the application of perceptual grouping in object recognition. The grouping process hierarchically groups these relations continuously until a meaningful semantic representation is achieved that may be used by a higher-level reasoning process. The grouping principles embodied such concepts as grouping by proximity, similarity, continuation.

关 键 词：感知归类 目标识别 特征提取 原始图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]