Title :
Structure and texture image inpainting
Author :
Hesabi, Somayeh ; Jamzad, Mansour ; Mahdavi-Amiri, Nezam
Author_Institution :
Comput. Sci. Dept., Sharif Univ. of Technol., Tehran, Iran
Abstract :
Inpainting refers to the task of filling in the missing or damaged regions of an image in an undetectable manner. We have an image to be reconstructed in a user-defined region. We use a fast decomposition method to obtain two components of the image, namely structure and texture. Reconstruction of each component is performed separately. The missing information in the structure component is reconstructed using a structure inpainting algorithm, while the texture component is repaired by a texture synthesis technique. To obtain the inpainted image, the two reconstructed components are composed together. Taking advantage of both the structure inpainting methods and texture synthesis techniques, we designed an effective image reconstruction method. Comparative reconstructed test images show the merits of our proposed approach in providing high quality inpainted images.
Keywords :
image reconstruction; image texture; fast decomposition method; image reconstruction; image structure; structure inpainting algorithm; texture image inpainting; texture synthesis technique; user defined region; Image color analysis; Image decomposition; Image reconstruction; Image restoration; Maintenance engineering; Mathematical model; Pixel; Image inpainting; image decomposition; structure; texture;
Conference_Titel :
Signal and Image Processing (ICSIP), 2010 International Conference on
Conference_Location :
Chennai
Print_ISBN :
978-1-4244-8595-6
DOI :
10.1109/ICSIP.2010.5697453