Supervoxel classification forests for estimating pairwise image correspondences

详细信息    查看全文

• 作者：Fahdi Kanavati^a ; ^{fk412@imperial.ac.uk}Author Vitae ; Tong Tong^a ; Kazunari Misawa^b ; Michitaka Fujiwara^c ; Kensaku Mori^d ; Daniel Rueckert^a ; Ben Glocker^a
• 关键词：Random forests ; Unsupervised learning ; Image correspondences ; Supervoxels
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：63
• 期：Complete
• 页码：561-569
• 全文大小：1226 K
• 卷排序：63

文摘

A method for using random forests to estimate image correspondences is proposed. The method does not rely on the availability of manual label annotations. Labels for training are obtained via the use of supervoxels. The efficient method is effective at providing an estimate of image correspondences.