样本块双向匹配图像修补算法

Exemplar bidirectional matching algorithm for image inpainting

为了解决基于样本图像修补算法的误匹配、结构断续等问题,提出了一种基于样本块的双向匹配图像修补算法。从待修补块中已知和未知两部分信息的邻域出发研究修补问题,引入匹配块中与待修补块中未知区域对应信息的一致性判定准则,提出待修补块优先级和最佳匹配块是由与待修补块中已知信息的相似性和与待修补块中未知信息邻域的一致性共同决定,更大限度地利用了图像的已知信息。该算法有效地解决了Criminisi算法的误匹配及结构断续问题以及Kawai算法的模糊问题,实验结果表明该算法是有效、可行的。

In order to solve npainting, an exemplar the issue mismatc bidirectional matc and structure disconnecting in exemplar based image algorithm for image inpainting is proposed. The neighborhoods of known and unknown regions in the repairing patch are investigated. The consistency criterion of the unknown region corresponding information in the matching patch and in the repairing patch is adopted. The priority of the repairing patch and the best matching patch are determined by the similarity of the known information and the consistency of the unknown information in the repairing patch. The known information of the image is sufficiently used. It can effectively solve the problems of mismatching and structure disconnecting in Criminis algorithm and the problem of blurring in Kawai algorithm. Experimental results demonstrate the effectiveness of the proposed algorithm.