期刊名称：Indian Journal of Computer Science and Engineering
印刷版ISSN：2231-3850
电子版ISSN：0976-5166
出版年度：2012
卷号：3
期号：3
页码：487-491
出版社：Engg Journals Publications
摘要：Inpainting is the technique of filling in holes in an image to preserve its overall continuity. Applications of this technique include the restoration of old photographs and damaged film; removal of superimposed text like dates, subtitles, or publicity; and the removal of entire objects from the image like microphones or wires in special effects. In this paper, we analyze different digital inpainting algorithms for still images. The simultaneous propagation of texture and structure information achieved. The texture image repaired by the exemplar �based method; for the structure image, the Laplacian operator is used to enhance the structure information. The Laplacian image is inpainted by the exemplar-based algorithm and the Poisson equation based reconstruction is applied thereafter. In 8 pixel neighborhood method, central pixel value is identified by investigating surrounded 8 neighborhood pixel properties like color variation, repetition, intensity and direction. Finally, in 2e based inpainting technique, original image analyzed at encoder side so that some blocks removed during encoding. At decoder side, the image is restored by 2e-based inpainting and texture synthesis. Finally, we compare the computational cost of all the algorithms.
