Postprocessing algorithm in block-based coded images using wavelet transform and adaptive MLP

Kee-Koo Kwon1, Byung-Ju Kim1, Suk-Hwan Lee1, Jong-Won Lee1, Seong-Geun Kwon1, Kuhn-Il Lee1
1School of Electrical Engineering and Computer Science, Kyungpook National University, Daegu, South Korea

Tóm tắt

A novel postprocessing algorithm for reducing the blocking artifacts in block-based coded images is proposed using an adaptive neural network filter (NNF) in the wavelet transform domain. We use two characteristics, knowing the positions of the blocking artifacts in each band and discriminating between the horizontal and the vertical blocking artifacts using the wavelet transformed signals. At first, after performing a 3-level wavelet transform of the decompressed image, a different one-dimensional (1D) or 2D NNF is used to reduce the blocking artifacts according to the characteristic of each level. Experimental results show that the proposed algorithm produces better results than those of conventional algorithms, both subjectively and objectively.

Từ khóa

#Wavelet transforms #Filters #Data structures #Boolean functions #Image coding #Wavelet domain #Neural networks #Transform coding #Computer networks #Computer science

Tài liệu tham khảo

qui, 2000, MLP for adaptive postprocessing block-coded images, IEEE Trans Circuits Syst Video Technol, 10, 1450, 10.1109/76.889048 kim, 1999, A deblocking filter with two separate modes in block-based video coding, IEEE Trans Circuits Syst Video Technol, 9, 156, 10.1109/76.744282 haykin, 1999, Neural Networks A Comprehensive Foundation 10.1109/83.661000 10.1109/76.856457 hsung, 1998, A deblocking technique for block-transform compressed image using wavelet transform modulus maxima, IEEE Trans Image Processing, 7, 1488, 10.1109/83.718489 10.1109/76.564123 10.1109/83.392332 10.1109/83.136597 10.1109/34.142909