Title :
A Method of Debris Image Segmentation Based on SVM
Author :
Tian, Xianzhong ; Hu, Tongsen
Author_Institution :
Inf. Eng. Coll., Zhejiang Univ. of Technol., Hangzhou
Abstract :
This paper realizes debris image segmentation using SVM. First we consider image segmentation as a pixel classification problem, and then build a SVM to solve the classification problem. Meanwhile we try to lower dimension in SVM, and select a proper kernel function and kernel parameter. At last we compare the image segmentation result using SVM with using BP network
Keywords :
backpropagation; image classification; image segmentation; support vector machines; BP network; SVM; debris image segmentation; kernel function; kernel parameter; pixel classification problem; support vector machine; Educational institutions; Entropy; Histograms; Hydrogen; Image segmentation; Iron; Kernel; Pixel; Support vector machine classification; Support vector machines;
Conference_Titel :
Computer and Computational Sciences, 2006. IMSCCS '06. First International Multi-Symposiums on
Conference_Location :
Hanzhou, Zhejiang
Print_ISBN :
0-7695-2581-4
DOI :
10.1109/IMSCCS.2006.13
