Skip to content

Detail of publication


Jiřík, M. and Ryba, T. and Železný, M. : Gabor filter and graph cut based texture analysis . Pattern Recognition and Image Analysis, 1, vol. 22, p. 215-220, Springer US, 2012.


This paper describes a method for texture based segmentation. Texture features are extracted by applying a bank of Gabor filters using twosided convolution strategy. Probability texture model is represented by Gaussian mixture that is trained with the Expectation maximization algorithm. Texture similarity, obtained this way, is used like the input of a Graph cut method. We show that the combination of texture analysis and the Graph cut method produce good results.

Detail of publication

Title: Gabor filter and graph cut based texture analysis
Author: Jiřík, M. ; Ryba, T. ; Železný, M.
Language: English
Date of publication: 1 Jan 2012
Year: 2012
Type of publication: Papers in journals
Title of journal or book: Pattern Recognition and Image Analysis
Series: 1
Číslo vydání: 22
Page: 215 - 220
DOI: 10.1134/S1054661812010208
ISSN: 1054-6618
Publisher: Springer US
/ 2015-10-13 15:44:11 /


Gabor filter, the Graph cut method


 author = {Ji\v{r}\'{i}k, M. and Ryba, T. and \v{Z}elezn\'{y}, M.},
 title = {Gabor filter and graph cut based texture analysis},
 year = {2012},
 publisher = {Springer US},
 journal = {Pattern Recognition and Image Analysis},
 volume = {22},
 pages = {215-220},
 series = {1},
 ISSN = {1054-6618},
 doi = {10.1134/S1054661812010208},
 url = {},