Progressive Image Inpainting Based on Wavelet Transform(Image Coding, <Special Section>Information Theory and Its Applications)
スポンサーリンク
概要
- 論文の詳細を見る
Currently, the automatic image inpainting methods emphasize the inpainting techniques either globally or locally. They didn't consider the merits of global and local techniques to compensate each other. On the contrary, the artists fixed an image in global view firstly, and then focus on the local features of it, when they repaired it. This paper proposes a progressive processing of image inpainting method based on multi-resolution analysis. In damaged and defective area, we imitate the artistic techniques to approach the effectiveness of image inpainting in human vision. First, we use the multi-resolution characteristics of wavelet transform, from the lowest spatial-frequency layer to the higher one, to analyze the image from global-area to local-area progressively. Then, we utilize the variance of the energy of wavelet coefficients within each image block, to decide the priority of inpainting blocks. Finally, we extract the multi-resolution features of each block. We take account of the correlation among horizontal, vertical and diagonal directions, to determine the inpainting strategy for filling image pixels and approximate a high-quality image inpainting to human vision. In our experiments, the performance of the proposed method is superior to the existing methods.
- 2005-10-01
著者
-
HSIEH Ching-Tang
Department of Electrical Engineering Tamkang University
-
HSU Chih-Hsu
Department of Electrical Engineering Tamkang University
-
Hsu Chih-hsu
Department Of Information Engineering Dahan Institute Of Technology
-
Hsieh Ching‐tang
Tamkang Univ. Twn
-
Chen Yen‐liang
Tamkang Univ. Twn
-
Chen Yen-liang
Department Of Electrical Engineering Tamkang University
関連論文
- Continuous Speech Segmentation Based on a Self-Learning Neuro-Fuzzy System (Special Section on Digital Signal Processing)
- A Novel Bandelet-Based Image Inpainting
- Progressive Image Inpainting Based on Wavelet Transform(Image Coding, Information Theory and Its Applications)
- Robust Speaker Identification System Based on Multilayer Eigen-Codebook Vector Quantization(Speech Dynamics by Ear, Eye, Mouth and Machine)
- Generalized Fuzzy Kohonen Clustering Networks (Special Section on Information Theory and Its Applications)
- Self-Assembled $c$-Plane GaN Nanopillars on $\gamma$-LiAlO2 Substrate Grown by Plasma-Assisted Molecular-Beam Epitaxy