Title :
Face inpainting by feature guidance
Author :
Tang, Nick C. ; Zhuang, Yueting ; Wang, Yushun ; Shih, Timothy K. ; Tsai, Joseph C.
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Tamkang Univ., Tamsui, Taiwan
Abstract :
Face image partially occluded or damaged can be repaired automatically. We proposed a new inpainting algorithm, based on patch guidance deduced from an existing face database, to recover the damaged portions. This newly proposed concept of guided inpainting method produces seamless faces which are hardly seen drawbacks. Examples of our results can be retrieved from http://member.mine.tku.edu.tw/www/ISCAS09/.
Keywords :
face recognition; feature extraction; image restoration; damaged image; face database; face inpainting; feature guidance; image occlusion; image restoration; Artificial intelligence; Computer science; Educational institutions; Face; Humans; Image databases; Image reconstruction; Mouth; Nose; Skin;
Conference_Titel :
Circuits and Systems, 2009. ISCAS 2009. IEEE International Symposium on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-3827-3
Electronic_ISBN :
978-1-4244-3828-0
DOI :
10.1109/ISCAS.2009.5118337
