Title :
Enhancement for face video from omni-directional video camera
Author :
Wu, Junwen ; Trivedi, Mohan M.
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., San Diego, La Jolla, CA, USA
Abstract :
In this paper we propose a novel algorithm to enhance the face video from omni-directional video camera. A two-stage strategy is used. First stage is the noise elimination, realized by iterative MAP update. Naive Bayesian criterion is used to model the posterior. The predominant salt and pepper noise introduced by the omni-to-perspective transformation can be removed effectively, while the image details are well preserved. The high frequency component compensation (HFCC) super-resolution algorithm is applied thereafter to remove the blocky effect. Experimental results show that the video quality has a marked improvement.
Keywords :
Bayes methods; image denoising; image enhancement; image resolution; iterative methods; maximum likelihood estimation; video signal processing; face video enhancement; high frequency component compensation super-resolution algorithm; iterative MAP; naive Bayesian criterion; noise elimination; omni-directional video camera; omni-to-perspective transformation; pepper noise; predominant salt; two-stage strategy; video quality; Bayesian methods; Cameras; Face detection; Image enhancement; Image resolution; Image segmentation; Iterative algorithms; Robot vision systems; Statistics; Streaming media;
Conference_Titel :
Signals, Systems and Computers, 2004. Conference Record of the Thirty-Eighth Asilomar Conference on
Print_ISBN :
0-7803-8622-1
DOI :
10.1109/ACSSC.2004.1399418
