Title :
Matching of SAR images and optical images based on edge feature extracted via SVM
Author :
Hui Cheng ; Sheng Zheng ; Yu, Qiwe ; Tian, Jinwen ; Liu, Jian
Author_Institution :
Key Lab. of Educ. Minist. for Image Process & Intelligence Control, Huazhong Univ. of Sci. & Technol., Wuhan, China
fDate :
31 Aug.-4 Sept. 2004
Abstract :
A novel algorithm for matching synthetic aperture radar (SAR) image to optical image based on edge feature using Hausdorff distance combined with genetic algorithm is proposed in this paper. A new method is presented to extract edge feature from low signal to noise ratio SAR image via support vector machine (SVM). Based on, the least squares support vector machine (LS-SVM), a set of the new gradient operators and the corresponding second derivative operators are obtained. Modified Hausdorff distance is adopted as a similarity measure and genetic algorithm is used as searching strategy. Experimental results demonstrate that the algorithm is feasible, fast and can achieve high matching accuracy.
Keywords :
edge detection; feature extraction; genetic algorithms; gradient methods; image matching; optical images; radar imaging; support vector machines; synthetic aperture radar; Hausdorff distance; LS-SVM; SAR image; edge feature extraction; genetic algorithm; gradient operators; image matching; least squares support vector machine; optical image; synthetic aperture radar; Adaptive optics; Feature extraction; Genetic algorithms; Image edge detection; Laser radar; Least squares methods; Optical noise; Optical sensors; Support vector machine classification; Support vector machines;
Conference_Titel :
Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on
Print_ISBN :
0-7803-8406-7
DOI :
10.1109/ICOSP.2004.1441472