基于改进SURF算子的彩色图像配准算法

Color image registration algorithm based on improved SURF

为了解决传统SURF算法存在的问题,提高彩色图像配准的精度和准确率,提出一种双向邻近匹配的彩色图像配准算法。该算法对传统的SURF描述符进行改进,将图像的色彩信息叠加在只包含灰度信息的传统SURF特征描述符上,组成改进的SURF特征描述符,以增强彩色信息对配准的影响,提高配准的准确率;采用FLANN算法搜索匹配点对,并对匹配点对进行双向邻近匹配,以提高搜索效率和匹配精度;利用改进RANSAC算法剔除匹配错误的特征点对,以进一步优化匹配结果。实验结果表明,该算法能够有效地提高彩色图像配准的精度和准确率,具有较好的鲁棒性和图像变换适应性。

In order to solve the existing problems of the traditional SURF algorithm,a color image registration algorithm based on bidirectional neighbor matching is proposed to improve the precision and accuracy of the color image registration. The algorithm makes some improvements on the traditional SURF feature descriptor. The color information of the image is firstly superimposed on the traditional SURF feature descriptor which only contains gray information,then forms the improved SURF feature descriptor,in order to enhance the impact of color information on registration,and improve the registration accuracy. To improve searching efficiency and matching precision,a bidirectional FLANN matching algorithm is applied to image matching,and improved RANSAC algorithm is used to eliminate mismatched feature points,which can further optimize the matching results. The experimental results show that the proposed algorithm can effectively improve the precision and accuracy of the color image registration,and has better robustness and adaptability for image transform.