Image matching method based on local filtering Eigen vector

The invention discloses an image matching method based on a local filtering Eigen vector. According to the method, image local information is extracted in a condition of different scales, an Eigen vector is obtained through Gauss filtering, and binary system binary system features with better comprehensive performance are extracted to conduct image matching. The method includes the steps of conducting multi-scale self-adaptive sliding window Gauss filtering on images, conducting ordering on the basis of the Gauss filtering, cutting off too bright and too dark region segments, generating filtering vectors of the images in a condition of different scales, carrying out amplitude comparison between Harris feature points and the filtering vectors, generating a binary system Eigen vector, and carrying out matching of the image feature points through the Eigen vector. 本发明公开了种基于局部滤波特征矢量的图像匹配方法。该方法在不同尺度下提取图像局部信息，利用高斯滤波得到特征矢量，并借此提取综合性能更好的二进制特征，用以进行图像匹配。该方法首先对图像进行多尺度的自适应滑窗高斯滤波，然后在此基础上进行排序，并分别剪裁掉其中过明过暗区域段，生成图像不同尺度下的滤波矢量；