Title :
Texture element extraction via cepstral filtering of projections
Author :
Rangayyan, Rangaraj M. ; Martins, Antonio C G
Author_Institution :
Dept. of Electr. & Comput. Eng., Calgary Univ., Alta., Canada
Abstract :
This paper presents a method for the extraction of the texton from an image with ordered or quasi-periodic texture, without the assumption of homogeneity of the element. The method includes application of homomorphic or cepstral filtering in the Radon or projection domain. Good approximations to the texton were obtained even when variations are presented in the textured image
Keywords :
Radon transforms; cepstral analysis; feature extraction; filtering theory; image texture; Radon domain; cepstral filtering; element homogeneity; homomorphic filtering; ordered texture; projection domain; quasi-periodic texture; texton extraction; texture element extraction; textured image; Application software; Cepstral analysis; Computer graphics; Filtering; Image generation; Image texture; Image texture analysis; Layout; Shape measurement; Surface texture;
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
DOI :
10.1109/ICIP.1997.632062