Title :
An approach for textures classification and definition by categories
Author :
Chen, Xing ; Hong, Kun ; Wang, Hai-tao
Author_Institution :
Yunnan Provincial Key Lab. of Comput. Applic., Kunming Univ. of Sci. & Technol., Kunming, China
Abstract :
Textures is one of the keys in image pattern recognition. To realize the computer vision for textures, it is necessary that understand textures rationally. The key of understanding textures is explaining them by the human´s signs and approaches. We believe the mathematical structure of categories is similar to human´s rational intelligence. In this paper, we describe the common textures by notes and term in categories theory. It means categories are useful for textures and image recognition. The combination of categories and neural network is worth to research which will gradually reveal the unity way of human´s percept and rationality.
Keywords :
image classification; image texture; neural nets; pattern recognition; computer vision; image pattern recognition; perception; rational intelligence; texture classification; Computational modeling; Computers; Floors; Humans; Image color analysis; Pattern recognition; Pixel; Categories theory; Image pattern recognition; Textures;
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
DOI :
10.1109/CISP.2010.5646883