[彭复员] Department of Telecommunication, Huazhong Science and Technology University, Wuhan 430076, China
[赵坤; 万亚平] Department of Computer Science and Technology, Nanhua University, Hengyang 421001, China
[刘立] Department of Telecommunication, Huazhong Science and Technology University, Wuhan 430076, China, Department of Computer Science and Technology, Nanhua University, Hengyang 421001, China
通讯机构:
[Liu, L.] D
Department of Telecommunication, Huazhong Science and Technology University, China
Due to the invarianc e of scale, rotation, illumination, SIFT (Scale Invariant Feature Transform) descriptor is commonly used in image matching. However, the fact that the presentation of one feature point needs 128 dimensions will reduce real -time efficiency of the algorithm. A simplified algorithm based on SIFT (SSIFT) is developed to express a feature point with only 12 dimensions based on a circular window to improve the efficiency of matching. The experimental results show that the algorithm can reduce the rate of time complexity and maintain a relatively good ...