Research on Method of Items Recognition Based on SURF Algorithm
Items detection and recognition have become one of hotspots in the field of computer vision research.Based on image features method has the advantage of low amount of information,fast running speed,high precision,and SIFT algorithm is one of them.But traditional SIFI algorithm have large amount of calculation data and spend long time to compute in terms of items recognition.Therefore,this paper come up with a method of items recognition based on SURF.This article elaborates the basic principle of SURF algorithm that firstly use SURF algorithm to extract feature points of item image,secondly adopt Euclidean distance method to find corresponding interest points of image,and finally get the image after items recognition combination with mapping relation of item image using RANSAC(Random Sample Consesus).Experimental results show that the system of item recognition based on SURF algorithm have better effect on matching recognition,higher instantaneity,better robustness.
items recognition SURF interest point feature extraction feature matching
Wenyu Chen Wenzhi Xie Yanli Zhao Zhongbo Hao
School of Computer Science&Engineering, University of Electronic Science & Technology of China, Chen School of Software,University of Electronic Science & Technology of China,Chengdu, China
国际会议
台湾
英文
4630-4634
2011-12-11(万方平台首次上网日期,不代表论文的发表时间)