Title :
Robust texture feature extraction using two dimension genetic algorithms
Author :
Zheng, Hong ; Zheng, Zhaobao
Author_Institution :
Dept. of Electr. Eng., Wuhan Tech. Univ. of Surveying & Mapping, China
Abstract :
This paper describes the robust texture feature, which is invariant to rotation and scale changes. The feature is the texture energy associated with a mask generated by two dimension genetic algorithms. The detail procedure and algorithm to generate the mask is discussed in the paper. Moreover, feature extraction experiments on aerial images are done. Experimental results show that the robust feature is effective and the segmentation results are satisfied
Keywords :
feature extraction; genetic algorithms; image texture; stability; 2D genetic algorithms; aerial images; robust texture feature extraction; segmentation; texture energy; Feature extraction; Fractals; Genetic algorithms; Image edge detection; Image segmentation; Image texture analysis; Probability distribution; Robustness; Statistics; Stochastic processes;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.893402