Robust exemplar based image and video inpainting for object removal and region filling
Robust exemplar based image and video inpainting for object removal and region filling
复制标题
基于鲁棒样本的图像和视频修复，用于对象移除和区域填充
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Ashvini Pinjarkar
中科院分区：
文献类型：
--
作者：
D. J. Tuptewar;Ashvini Pinjarkar
修复艺术是修复旧的、损坏的图像。基于示例的修复是使用基于补丁的方法。该方法使用补丁来填充图像的目标区域。该方法同时采用纹理合成和结构传播。但经过一定的迭代后，该方法出现了置信项的下降效应。基于鲁棒样本的方法通过引入鲁棒优先权函数避免了丢弃效应。在基于样本的鲁棒性修复算法的基础上，提出了一种基于区域分割的视频修复方法。在我们的算法中，我们使用鲁棒的优先权函数来避免丢弃效应，并使用区域分割来确定自适应的块大小和缩小的搜索区域。实验结果表明了该方法的有效性。
Inpainting an art the restores old, damage image. Exemplar based inpainting is that use the patch based approach. This method uses patches to fill the target region of the image. This method uses simultaneous the texture synthesis and structural propagation. But after some iteration the dropping effect of confidence term is occur in this method. The robust exemplar based method avoid dropping effect by using robust priority function. We proposed a video inpainting method on the basis of the robust exemplar based inpainting algorithm using region segmentation. In our we use robust priority function to avoid dropping effect and region segmentation to determine the adaptive patch size and reduced search region. The experimental results show the effectiveness of our method.