DocumentCode
2994905
Title
Detection of Mirror-Symmetric Image Patches
Author
Patraucean, Viorica ; von Gioi, Rafael Grompone ; Ovsjanikov, Maks
Author_Institution
Mil. Tech. Acad. of Bucharest, Bucharest, Romania
fYear
2013
fDate
23-28 June 2013
Firstpage
211
Lastpage
216
Abstract
We propose a novel approach for detecting partial reflectional symmetry in images. Our method consists of two principal stages: candidate selection and validation. In the first step, candidates for mirror-symmetric patches are identified using an existing heuristic procedure based on Hough voting. The candidates are then validated using a principled statistical procedure inspired from the a contrario theory, which minimizes the number of false positives. Our algorithm uses integral image properties to enhance the execution time.
Keywords
Hough transforms; image matching; statistical analysis; symmetry; Hough voting; a contrario theory; candidate identification; candidate selection; candidate validation; execution time enhancement; false positives; heuristic procedure; integral image properties; mirror-symmetric image patch detection; partial reflectional symmetry detection; principled statistical procedure; Detectors; Hypercubes; Nickel; Noise; Pipelines; Probabilistic logic; Transforms; a contrario; integral images; mirror symmetry;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition Workshops (CVPRW), 2013 IEEE Conference on
Conference_Location
Portland, OR
Type
conf
DOI
10.1109/CVPRW.2013.38
Filename
6595877
Link To Document