DocumentCode :
3421166
Title :
Hallucination of super-resolved face images
Author :
Nasrollahi, Kamal ; Moeslund, Thomas B.
Author_Institution :
Comput. Vision & Media Technol. Lab., Aalborg Univ., Aalborg, Denmark
fYear :
2010
fDate :
24-28 Oct. 2010
Firstpage :
641
Lastpage :
644
Abstract :
Reconstruction-based super-resolution algorithms are widely employed for enhancing the quality of low-resolution face images. However, these algorithms are very sensitive to the registration errors of their input images. The registration errors aggravate when working with face images coming from video sequences. The longer the video the bigger is the registration error (due to the motion of the subject). Furthermore, the improvement factor of these algorithms is limited by factors smaller than two. The proposed system in this paper deals with these two problems. In order to restrict the registration errors of the system a fuzzy-based face quality assessment is employed. To cope with the second problem, a hierarchy of different types of super-resolution algorithms is used to reach an improvement factor of four. The proposed system has been tested using real video sequences of different longs and the experimental results are promising.
Keywords :
face recognition; fuzzy set theory; image reconstruction; image registration; image resolution; image sequences; video signal processing; fuzzy-based face quality assessment; low-resolution face image quality; reconstruction-based super-resolution algorithm; registration error; super-resolved face image hallucination; video sequence; Classification algorithms; Databases; Face; Image reconstruction; Image resolution; Strontium; Video sequences; face hallucination; face-log; super-resolution;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing (ICSP), 2010 IEEE 10th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-5897-4
Type :
conf
DOI :
10.1109/ICOSP.2010.5656834
Filename :
5656834
Link To Document :
بازگشت