Title :
Grating cell operator features for oriented texture segmentation
Author :
Kruizinga, P. ; Petkov, N.
Author_Institution :
Math. Inst., Groningen Univ., Netherlands
Abstract :
The performance of two well-known texture operators (based on Gabor-energy and the cooccurrence matrix) is compared with the performance of a new, biologically motivated texture operator, the grating cell operator, previously proposed by the authors (1995, 1997). The comparison is made using a new quantitative method, based on the Fisher criterion (1923). The results show the clear superiority of the new operator in oriented texture problems
Keywords :
image segmentation; image texture; Fisher criterion; Gabor-energy; cooccurrence matrix; grating cell operator features; oriented texture segmentation; Animal structures; Bars; Ear; Feature extraction; Gratings; High performance computing; Mathematics; Maximum likelihood detection; Neurons; Visual system;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.711860