Super-resolution inpainting

Timothy K. Shih, Rong Chi Chang

研究成果: 雜誌貢獻期刊論文同行評審

5 引文 斯高帕斯(Scopus)


Image or video resources are often received in poor condition, mostly with noise or defects making the resources hard to read. We propose an effective algorithm based on digital image inpainting. The mechanism can be used in restoring images or video frames with very high noise or defect ratio (e.g., 90%). The algorithm is based on the concept of image subdivision and estimation of color variations. Noises inside blocks of different sizes are inpainted with different levels of surrounding information. The results showed that an almost unrecognizable image can be recovered with visually good result. The algorithm can be further extended for processing motion picture with high percentage of noise.

頁(從 - 到)487-491
期刊Journal of Zhejiang University: Science
6 A
出版狀態已出版 - 6月 2005


深入研究「Super-resolution inpainting」主題。共同形成了獨特的指紋。