基于新SURF＿DAISY算法和反向验证随机kd树的图像配准

Image Registration Method Based on New SURF＿DAISY Algorithm and Reverse Verification Random kd Tree

在SURF图像配准的基础上,用新型DAISY特征描述符替换了原SURF特征描述算子,用推荐的反向验证随机kd树实现特征匹配,进而提出了一种基于新SURF_DAISY算法和反向验证随机kd树的图像配准方法。结果表明,图像配准方法在运算时间和匹配正确率上相比于SURF图像配准方法均有所提高。

On the basis of SURF image registration,the original SURF feature description operator is replaced by the new DAISY feature descriptor,and the feature matching is realized by the reverse verification of the random kd tree Then a new image registration method based on the new SURFDAISY algorithm and the reverse verification of the random kd tree is proposed.The results show that the image registration method has improved the computation time and the matching accuracy rate compared with the SURF image registration method.