摘要
采用改进的SIFT(Scale Invariant Feature Transform)算法对自然环境下获取的复杂场景图像进行特征量提取;通过添加存入最小优先级队列的限制条件,对现有的BBF(Best Bin First)匹配算法进行改进以提高算法的搜索效率;针对复杂图像误匹配较为严重的现象,设置匹配判定准则和几何约束条件,对匹配结果中可能的误匹配加以剔除。实验结果表明,新方法在匹配效率和匹配准确率的提高上效果明显。
An improved SIFT (scale invariant feature transform) algorithm is employed to extract features of images obtained under nature environment. With a constraint of logging minimum priority queue, BBF (best bin first) algorithm is modified to improve the search efficiency. In view of the fact that there are mistake matched points in complex image feature matching, matching judgment and geometrical constraint between feature points are set, some error matched feature points from modified BBF are eliminated. Experimental results show that, with the proposed method, the efficiency and accuracy of feature extraction and matching are greatly improved.
出处
《安徽工业大学学报(自然科学版)》
CAS
2012年第1期73-77,共5页
Journal of Anhui University of Technology(Natural Science)
基金
国家自然科学基金项目(50874001
51007002)
863项目(2006AA10Z247)