{"title":"An Improved Curvature Coding For Planar Shape Representation","authors":"Ke-Hua Guo, Jing-yu Yang","doi":"10.1109/CCPR.2008.30","DOIUrl":null,"url":null,"abstract":"Traditional planar shape representations cannot efficiently solve some problems such as recognition under occlusion, reconstruction and partial matching. In this paper, an improved shape representation by the extraction of contour curvature is presented based on the invariance of curvature. Then the invariance and discrete approximation solution are demonstrated. Finally the reconstruction method to the contour and a new matching approach based on improved KMP (D. E. Knuth, V. R. Pratt and J. H. Morris) algorithm are proposed. Experiments illustrate the good performance of our approach to classification, occluded objects recognition and partial matching problems.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 Chinese Conference on Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCPR.2008.30","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Traditional planar shape representations cannot efficiently solve some problems such as recognition under occlusion, reconstruction and partial matching. In this paper, an improved shape representation by the extraction of contour curvature is presented based on the invariance of curvature. Then the invariance and discrete approximation solution are demonstrated. Finally the reconstruction method to the contour and a new matching approach based on improved KMP (D. E. Knuth, V. R. Pratt and J. H. Morris) algorithm are proposed. Experiments illustrate the good performance of our approach to classification, occluded objects recognition and partial matching problems.
传统的平面形状表示不能有效地解决遮挡、重构和部分匹配下的识别问题。本文在曲率不变性的基础上,提出了一种通过提取轮廓曲率来改进形状表示的方法。然后证明了该方法的不变性和离散逼近解。最后,提出了一种基于改进KMP (D. E. Knuth, V. R. Pratt和J. H. Morris)算法的轮廓重建方法和一种新的匹配方法。实验证明了该方法在分类、遮挡物识别和部分匹配问题上的良好性能。