Image Texture Classification Based on LS-SVM

摘要：

　　LS-SVM (Least Squares Support Vector Machine) is simple and has a good ability of non-linear regression.As inputs of LS-SVM,DC-Energy-Ratio and Deviation of image samples are extracted first.Output of LS-SVM is the current texture classification.The results show that LS-SVM classifies images accurately by training the proposed two features.

关键词： LS-SVM texture DC-Energy-Ratio Deviation

作者: Yanling Zhao Xiaoshi Zheng Guangqi Liu Na Li

作者单位: Shandong Provincial Key Laboratory of Computer Network,Shandong Computer Science Center,Shandong Jinan,China

会议类型: 国际会议

会议名称: 2012 International Applied Mechanics,Mechatronics Automation Symposium(2012应用力学,机电一体化自动化国际研讨会)(IAMMAS2012)

会议地点: 沈阳

会议语种:英文

页码: 869-872

在线出版日期: 2012-09-07（万方平台首次上网日期，不代表论文的发表时间）