{"title":"Combination of histogram of oriented gradients and hierarchical centroid for sketch-based image retrieval","authors":"Norah M. Asiri, Nourah AlHumaidi, Nourah AlOsaim","doi":"10.1109/CSCESM.2015.7331884","DOIUrl":null,"url":null,"abstract":"The sketch based image retrieval (SBIR) systems is still little argued and debated. Histogram of oriented gradients (HOG) has shown good performance in sketch based retrieval systems over all other methods. In this paper, we propose an enhancement of HOG by using HOG combined with hierarchical centroid of irregular shape. We also compare the result with original HOG, edge histogram and the shape properties descriptors. The system uses free-hand sketched queries as input and matches it with images from different 12 classes.","PeriodicalId":232149,"journal":{"name":"2015 Second International Conference on Computer Science, Computer Engineering, and Social Media (CSCESM)","volume":"275 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 Second International Conference on Computer Science, Computer Engineering, and Social Media (CSCESM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CSCESM.2015.7331884","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
Abstract
The sketch based image retrieval (SBIR) systems is still little argued and debated. Histogram of oriented gradients (HOG) has shown good performance in sketch based retrieval systems over all other methods. In this paper, we propose an enhancement of HOG by using HOG combined with hierarchical centroid of irregular shape. We also compare the result with original HOG, edge histogram and the shape properties descriptors. The system uses free-hand sketched queries as input and matches it with images from different 12 classes.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
