基于图像势能理论的目标轮廓特征提取方法  

Research on Target Contour Feature Extraction Based on Image Potential Energy Theory

作　　者：陈雪松[1] 徐学军[1] 朱洪波[1] 

机构地区：[1]华中科技大学数字工程与仿真中心,武汉430074

出　　处：《计算机科学》2011年第6期270-274,共5页Computer Science

基　　金：国家部委基金资助

摘　　要：在进行模式识别和目标分类系统中,一种好的特征提取方法可以提高系统性能。采集图像势能并用于图像特征的提取与保存是二值图像处理的一个新方法和新理论。势能方法把每一个像素点所具有的势能按序收集、顺序存放,较好地保留了图像的特征,以便存储和分类。图像轮廓是一个对象区别于其他对象的最主要特征之一,运用势能理论计算出目标轮廓的势能,可以较好地表现出图像的特征,其计算速度快,运算量小,占用存储空间小,可用于目标识别和目标分类等领域。A good feature extraction method helps to improve the efficiency of pattern recognition system and classification system.Computing of potential energy of an image can be used to extract and save image features,which is a new theory to collect and store the potential energy of each pixel in order.In this way,the feature of the image is better retained contributing to storage and classification.Contour is the main distinction between different objects.With potential energy theory,the potential energy computed can better show the image feature with the high advantage of speed,easy computing and less storage space.The theory can be applied to target recognition and target classification and so on.

关 键 词：图像处理 轮廓 势能 特征提取 目标识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]