Title :
Improved SURF algorithm based on SVM classification
Author :
Chang Junlin ; Wei, Wei ; Liang Junyan
Author_Institution :
China Univ. of Minning & Technol., Xuzhou, China
Abstract :
An new SURF algorithm based on support vector machine is presented in order to solve the problem of mismatch between feature points. Put the data of the normalized Euclidean distance of feature points into support vector machine to achieve adaptive match after training SVM by data. The experiment by OpenCV library verify that the improved SURF algorithm proposed in this paper has higher accuracy than the old one. Besides, there is no significant increase in complexity.
Keywords :
image classification; image matching; statistical analysis; support vector machines; Euclidean distance; OpenCV library; SURF algorithm; SVM classification; support vector machine; Classification algorithms; Computer languages; Computer vision; Euclidean distance; Feature extraction; Image matching; Support vector machines; Image Matching; OpenCV; SURF; SVM;
Conference_Titel :
Control Conference (CCC), 2011 30th Chinese
Conference_Location :
Yantai
Print_ISBN :
978-1-4577-0677-6
Electronic_ISBN :
1934-1768
