Title :
SAR image segmentation by 2-D fussy entropy
Author :
Cao Laming ; Kunhui, Zhang ; Liangzheng, Xia
Author_Institution :
Dept. of Autom. Control Eng., Southeast Univ., Jiangsu
Abstract :
In the process of SAR (synthetic aperture radar) ATR (automatic target recognition), segmentation is the core procedure. In this paper, analyzing the characteristics of SAR images, we introduced a new method for segmenting SAR images. The method is based on 2D c-partition fussy entropy and adaptive genetic algorithm. 2D fussy entropy is used as the fitness function, and adaptive genetic algorithm is used for optimizing thresholds. The results of the segmentation procedure are presented in this paper and it shows a promising output
Keywords :
entropy; genetic algorithms; geophysical signal processing; image segmentation; object detection; remote sensing by radar; synthetic aperture radar; 2D c-partition fussy entropy; 2D fussy entropy; SAR images; adaptive genetic algorithm; automatic target recognition; fitness function; image segmentation; segmentation procedure; synthetic aperture radar; Entropy; Genetic algorithms; Histograms; Image segmentation; Pixel; Radar imaging; Shape control; Speckle; Statistics; Synthetic aperture radar;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2004. IGARSS '04. Proceedings. 2004 IEEE International
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-8742-2
DOI :
10.1109/IGARSS.2004.1369950
