Internet Archive Scholar

Shape-based Image Retrieval Using Support Vector Classification

Wai-Tak Wong, Sheng-Hsun Hsu
2005 IAPR International Workshop on Machine Vision Applications  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (281.5 kB)
https://web.archive.org/web/20170808225123/http://b2.cvl.iis.u-tokyo.ac.jp/mva/proceedings/CommemorativeDVD/2005/papers/2005064.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

We have developed a novel method for shape-based image retrieval based on the Support Vec tor Mac hine tec hnique ( SVM) and the similarity measures. The high ac c urac y c lassific ation rate of SVM, 100% for 183 images in 8 c ategories from the public domain, shows that SVM is one of the best tools for c lassific ation problems. A sensitivity test is performed to show that SVM is quite robust against different parameter values. After the c ategory of the input image is identified, our
more » ... ty measures are used to retrieve the similar shapes from the image database. Our method c an satisfy nec essary requirements of c ognitively similarity measures from visual perc eption, suc h as rotation, sc aling and shearing invarianc e.
dblp:conf/mva/WongH05 fatcat:hrnj3yko2bevbgaxgsgfmegdye
Citation

Wai-Tak Wong, Sheng-Hsun Hsu. "Shape-based Image Retrieval Using Support Vector Classification." IAPR International Workshop on Machine Vision Applications (2005) 64-67