DocumentCode :
3504798
Title :
A new texture segmentation method based on visual perception and phase feature
Author :
Puhui, Long ; Rongchun, Zhao
Author_Institution :
Inst. of Artificial Intelligence & Robotics, Xi´´an Jiaotong Univ., China
Volume :
2
fYear :
1996
fDate :
14-18 Oct 1996
Firstpage :
1015
Abstract :
A new method of texture segmentation based on the human visual perception mechanism and local phase features is proposed in this paper. We point out the importance of phase features for image segmentation. The whole segmentation algorithm is composed of three main parts which are orientational filtering, local unwrapped phase extracting and variable pyramid segmentation. There are some important improvements to each part. Some typical simulation experiments are given to show the correctness and validity of the method
Keywords :
image segmentation; image texture; two-dimensional digital filters; visual perception; 2D optimal quadrature separable orientational filter; human visual perception mechanism; local unwrapped phase extraction; orientational filtering; phase feature; texture segmentation method; variable pyramid segmentation; visual perception; Computer science; Filtering; Filters; Frequency; Humans; Image segmentation; Robots; Signal processing; Uncertainty; Visual perception;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
Type :
conf
DOI :
10.1109/ICSIGP.1996.566263
Filename :
566263
Link To Document :
بازگشت