Fast image inpainting using similarity of subspace method

Fast image inpainting using similarity of subspace method
复制标题

使用子空间相似度方法进行快速图像修复

DOI:
10.1109/icip.2011.6116452
复制
发表时间:
2011
期刊:
Proceedings of IEEE International Conference on Image Processing 2011
影响因子:
--
通讯作者:
Takafumi Aoki
Takafumi Aoki
中科院分区:
--
文献类型:
--
作者:
Tomoki Hosoi;Koji Kobayashi;Koichi Ito;Takafumi Aoki

文献摘要

参考文献

被引文献

相似文献

图像修复是通过使用从缺失像素的相邻像素获得的像素值信息或通过学习对象类别导出的先验知识来估计图像中的缺失像素值的技术。本文提出了一种利用子空间相似性的快速准确的图像修复方法。该方法在学习步骤中从与对象类相关的多幅图像中生成子空间,并估计属于同一对象类的输入图像的缺失像素值,从而在修复步骤中最大化输入图像与子空间之间的相似性。通过一组实验,我们证明了所提出的方法具有良好的性能,无论是修复精度和计算时间相比,传统的算法。
Image inpainting is a technique for estimating missing pixel values in an image by using the pixel value information obtained from neighbor pixels of a missing pixel or the prior knowledge derived from learning the object class. In this paper, we propose a fast and accurate image inpainting method using similarity of the subspace. The proposed method generates the subspace from many images related to the object class in the learning step and estimates the missing pixel values of the input image belonging to the same object class so as to maximize the similarity between the input image and the subspace in the inpainting step. Through a set of experiments, we demonstrate that the proposed method exhibits excellent performance in terms of both inpainting accuracy and computation time compared with conventional algorithms.
DOI: 10.1109/icpr.2004.1333860
发表时间: 2004
期刊: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.
影响因子: --
作者:
Toshiyuki Amano
通讯作者: Toshiyuki Amano
在特征空间上使用 BPLP 方法进行图像插值
DOI: 10.1002/scj.10319
发表时间: 2007
期刊: Systems and Computers in Japan
影响因子: --
作者:
Toshiyuki Amano;Yukio Sato
通讯作者: Yukio Sato