Abstract: An image mosaic algorithm based on curvature scale space was proposed.The Curvature Scale Space（CSS） is employed to detect the feature points.And the matching point pairs are obtained by comparing the Euclidean distance of the Zernike moments，which are computed around a circular neighborhood centered at the feature point.Then the transform parameters are computed through the correct mapping model.Finally，the weighed average method is used to achieve image mosaic.Experimental results demonstrate that the proposed algorithm can effectively stitch two images which are different by rotation，translation and noises.

Key words: image mosaic, CSS, feature points, Zernike moments

摘要： 提出了一种基于曲率尺度空间的图像拼接算法。该算法利用曲率尺度空间（CSS）角点检测法提取特征点，通过比较各特征点圆形邻域Zernike矩的欧式距离得到匹配点对，然后利用正确的映射模型计算出变换参数，最后采用加权平均法得到图像的拼接结果。实验表明，该算法在图像间存在旋转、平移及噪声干扰的情况下，仍能得到很好的拼接结果。

关键词: 图像拼接, 曲率尺度空间, 特征点, Zernike矩