Texture discrimination by local generalized symmetry

Y. Bonneh, D. Reisfeld, Y. Yeshurun

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations


Texture consists of local variance of grey level or edge intensity values. We have recently presented a Generalized Symmetry operator, that captures local spatial relations of image patterns. We show that activity differences in the continuous intensity map produced by the local generalized symmetry operator can be efficiently used to detect texture boundaries. Using almost all available quantitative results of human performance in artificial texture discrimination, we show that our algorithm favorably compares with other computational approaches (correlation coefficient > 0.09 between our model's performance and available human performance). Stressing the necessity of benchmarks for Computer Vision algorithms, we construct an exhaustive set of textures that could be used as experimental stimuli for both humans and machines, and demonstrate the performance of the algorithm on some of these artificial textures as well as on natural images.

Original languageEnglish
Title of host publication1993 IEEE 4th International Conference on Computer Vision
PublisherPubl by IEEE
Number of pages5
ISBN (Print)0818638729
StatePublished - 1993
Externally publishedYes
Event1993 IEEE 4th International Conference on Computer Vision - Berlin, Ger
Duration: 11 May 199314 May 1993

Publication series

Name1993 IEEE 4th International Conference on Computer Vision


Conference1993 IEEE 4th International Conference on Computer Vision
CityBerlin, Ger


Dive into the research topics of 'Texture discrimination by local generalized symmetry'. Together they form a unique fingerprint.

Cite this