Title :
An adaptive quantization algorithm for MPEG-2 video coding
Author :
Luo, Lijun ; Zou, Cairong ; He, Zhenya ; Shirakawa, Isao
Author_Institution :
Dept. of Radio Eng., Southeast Univ., Nanjing, China
Abstract :
An adaptive quantization algorithm for MPEG-2 video coding using a neural network is presented in this paper. The proposed algorithm uses a backpropagation neural network to divide the macroblock activity into one of four categories: flat, edge, texture, fine-texture, and thus the macroblock can be quantized adaptively according to the human vision system (HVS) sensitivity. Experimental results show that this method can reduce block artifacts of flat area and distortion at edge effectively. Meanwhile, the picture subjective quality and objective quality of each frame are improved
Keywords :
adaptive codes; backpropagation; image sequences; image texture; neural nets; quantisation (signal); video coding; visual perception; HVS sensitivity; MPEG-2 video coding; adaptive quantization algorithm; backpropagation neural network; block artifacts; edge category; fine-texture category; flat area category; human vision system sensitivity; macroblock activity; objective quality; subjective quality; texture category; HDTV; Helium; Humans; Image coding; Machine vision; Neural networks; Quantization; TV; Video coding; Video sequences;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.678116
