Title :
An inpainting method for face images
Author :
Yin, Lixin ; Song, Xiumin ; Jiang, Haibo
Author_Institution :
Sch. of Inf. Sci. & Eng., Shandong Univ., Jinan, China
Abstract :
The digital inpainting process is a process of filling the unknown region of an image and its aim is to inpaint the damaged image and make the observer not aware of that this image has been damaged off and has been inpainted. In this paper, Criminisi algorithm has been studied and improved. In the improved method the gradient term is taken into account together with confidence term and data term in calculating the priority. Thus more information of known pixels is considered in the improved algorithm. Then an inpainting method for face images is proposed based on the improved algorithm. It does not need to spend too much time analyzing the facial features, and can achieve reasonable results.
Keywords :
image restoration; Criminisi algorithm; digital inpainting process; face images; facial features; image restoration; inpainting method; Algorithm design and analysis; Face; Facial features; Image color analysis; Image edge detection; Mirrors; Skin; Criminisi; Face Images; HSV; Inpainting;
Conference_Titel :
Communication Technology (ICCT), 2011 IEEE 13th International Conference on
Conference_Location :
Jinan
Print_ISBN :
978-1-61284-306-3
DOI :
10.1109/ICCT.2011.6157904
