Title :
Learning local pixel structure for face hallucination
Author :
Hu, Yu ; Lam, Kin Man ; Qiu, Guoping ; Shen, Tingzhi ; Tian, Hui
Author_Institution :
Dept. of Electron. Eng., Beijing Inst. of Technol., Beijing, China
Abstract :
In this paper, we present a novel learning-based face hallucination method based on the assumption that similar faces will have similar local pixel structures. We use the low- resolution (LR) input face to search a database for K example faces that are the most similar to the input and align them with the input accordingly. The local pixel structures of the target high-resolution (HR) image are learned from those warped HR example faces in a neighbor embedding manner, and a total variation (TV) constraint is employed to aid the learning of all pixels´ embedding weights. The learned local pixel structures are then used as constraints to reconstruct a HR version of the input face. Experimental results show that the method performs well in terms of both reconstruction error and visual quality.
Keywords :
face recognition; image reconstruction; image resolution; learning (artificial intelligence); visual databases; HR version; K example faces; learning based face hallucination method; local pixel structure learning; neighbor embedding manner; pixel embedding weight; reconstruction error; target high resolution image; total variation constraint; visual quality; Face; Image reconstruction; Image resolution; Pixel; Strontium; TV; Training; TV norm; face hallucination; local pixel structure; super resolution;
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-7992-4
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2010.5651052