{"title":"一种基于多尺度空间的高级形状上下文描述符","authors":"Wang Wen-fei, Wen Gong-jian, G. Feng","doi":"10.1109/ICICIP.2014.7010316","DOIUrl":null,"url":null,"abstract":"Traditional approaches of shape context (SC) descriptor are invariant to object contour noise and shape local slightly deformation, meanwhile, the neighbor radius parameter of shape context model need to be effectively selected without enough apriority knowledge. Additionally, object recognition performance and computational efficiency should be improved in a step future. Therefore, this paper provides an advanced shape context descriptor based on multi-scale spaces. Beyond this method, the shape context descriptor is only extracted from robust contour curvature extremal value point, which is effective to bate the influence of contour noise and local slightly deformation, the neighbor radius parameter is also automatically selected. Comparing with traditional shape matching algorithms, the robustness and the efficiency of this paper approach is tested to be improved distinctly, and the recognition performance is more reliable at the same time.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An advanced shape context descriptor based on multi-scale spaces\",\"authors\":\"Wang Wen-fei, Wen Gong-jian, G. Feng\",\"doi\":\"10.1109/ICICIP.2014.7010316\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Traditional approaches of shape context (SC) descriptor are invariant to object contour noise and shape local slightly deformation, meanwhile, the neighbor radius parameter of shape context model need to be effectively selected without enough apriority knowledge. Additionally, object recognition performance and computational efficiency should be improved in a step future. Therefore, this paper provides an advanced shape context descriptor based on multi-scale spaces. Beyond this method, the shape context descriptor is only extracted from robust contour curvature extremal value point, which is effective to bate the influence of contour noise and local slightly deformation, the neighbor radius parameter is also automatically selected. Comparing with traditional shape matching algorithms, the robustness and the efficiency of this paper approach is tested to be improved distinctly, and the recognition performance is more reliable at the same time.\",\"PeriodicalId\":408041,\"journal\":{\"name\":\"Fifth International Conference on Intelligent Control and Information Processing\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fifth International Conference on Intelligent Control and Information Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICICIP.2014.7010316\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fifth International Conference on Intelligent Control and Information Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICICIP.2014.7010316","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
An advanced shape context descriptor based on multi-scale spaces
Traditional approaches of shape context (SC) descriptor are invariant to object contour noise and shape local slightly deformation, meanwhile, the neighbor radius parameter of shape context model need to be effectively selected without enough apriority knowledge. Additionally, object recognition performance and computational efficiency should be improved in a step future. Therefore, this paper provides an advanced shape context descriptor based on multi-scale spaces. Beyond this method, the shape context descriptor is only extracted from robust contour curvature extremal value point, which is effective to bate the influence of contour noise and local slightly deformation, the neighbor radius parameter is also automatically selected. Comparing with traditional shape matching algorithms, the robustness and the efficiency of this paper approach is tested to be improved distinctly, and the recognition performance is more reliable at the same time.