The priority of the filled patch play a key role in the exemplar-based image inpainting, and it should be determined firstly to optimize the process of image inpainting. A modified image inpainting algorithm is propos...The priority of the filled patch play a key role in the exemplar-based image inpainting, and it should be determined firstly to optimize the process of image inpainting. A modified image inpainting algorithm is proposed by weighted-priority based on the Criminisi algorithm. The improved algorithm demonstrates better relationship between the data term and the confidence term for the optimization of the priority than the classical Criminisi algorithm. By comparing the effect of the inpainted images with different structure, conclusion can be drawn that the optimal priority should be chosen properly for different images with different structures.展开更多
基于纹理合成的图像修复技术用于修复大面积破损区域,目前此类算法都存在时间复杂度高的缺点。针对纹理算法的匹配技术进行改进,提出了一种基于图像平均灰度值的快速图像匹配算法。该算法在匹配之前预先计算纹理块的平均灰度值以及分割...基于纹理合成的图像修复技术用于修复大面积破损区域,目前此类算法都存在时间复杂度高的缺点。针对纹理算法的匹配技术进行改进,提出了一种基于图像平均灰度值的快速图像匹配算法。该算法在匹配之前预先计算纹理块的平均灰度值以及分割后的纹理块的局部平均灰度值,以取代计算复杂的匹配项SSD(sum of squaredd ifferences);匹配过程只需对平均灰度值进行快速比较,结合阈值控制筛选掉大部分候选纹理块。实验结果表明,该算法在不损害图像修复质量的同时,将纹理修复的效率提高到实时水平。同时在纹理合成和纹理修复中具有普遍的适用性。展开更多
基金Supported by the National Natural Science Foundation of China (No. 60972106)Postdoctoral Science Foundation (No. 20090450750)the Science Foundation of Tianjin(No. 11JCYBJC00900)
文摘The priority of the filled patch play a key role in the exemplar-based image inpainting, and it should be determined firstly to optimize the process of image inpainting. A modified image inpainting algorithm is proposed by weighted-priority based on the Criminisi algorithm. The improved algorithm demonstrates better relationship between the data term and the confidence term for the optimization of the priority than the classical Criminisi algorithm. By comparing the effect of the inpainted images with different structure, conclusion can be drawn that the optimal priority should be chosen properly for different images with different structures.
文摘基于纹理合成的图像修复技术用于修复大面积破损区域,目前此类算法都存在时间复杂度高的缺点。针对纹理算法的匹配技术进行改进,提出了一种基于图像平均灰度值的快速图像匹配算法。该算法在匹配之前预先计算纹理块的平均灰度值以及分割后的纹理块的局部平均灰度值,以取代计算复杂的匹配项SSD(sum of squaredd ifferences);匹配过程只需对平均灰度值进行快速比较,结合阈值控制筛选掉大部分候选纹理块。实验结果表明,该算法在不损害图像修复质量的同时,将纹理修复的效率提高到实时水平。同时在纹理合成和纹理修复中具有普遍的适用性。
