基于显著结构重构与纹理合成的图像修复算法

An Image Restoration Algorithm Based on Structure and Texture Synthesis with Reconstruction of Significant Structure of Images

文章结合结构修复算法及纹理修复算法各自的优点,并考虑显著结构对图像修复的巨大影响,提出结合显著结构重构与纹理合成的图像修复算法。算法先利用形态学算子剥离待修复图像中细小结构与大块区域;然后利用快速结构修复算法对图像进行处理;再利用插值对待修复图像进行显著结构重构;最后利用基于改进优先级的加权匹配图像修复算法进行后续修复。实验结果表明,对既有显著结构同时又包含丰富纹理的待修复图像,与传统算法相比,本文的算法不但有更好的修复效果,而且耗时更少。

This paper presents an image restoration algorithm by integrating structure and texture features with reconstruction of significant structure of images. Firstly, the algorithm splits the fine structures and large areas in the damaged image using morphological operators. Secondly, the rapid structural restoration algorithm is used for image inpainting. Thirdly, significant structures in the image are reconstructed by interpolation. Finally, the large damaged areas are restored by the weighted matching image restoration algorithm based on the modified priority. For the damaged image with significant structure and texture, the experimental results show the better restoration result and less time consuming of the proposed algorithm than that of the traditional algorithms.