Optimal PSNR estimated spectrum adaptive postfilter for DCT coded images

Author

Linares, Irving

Author_Institution

Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA

Volume

4

fYear

1995

fDate

9-12 May 1995

Firstpage

2387

Abstract

Our previous work aimed at reducing the blocking distortion of DCT coded images is further improved by introducing the optimal PSNR estimated spectrum adaptive postfilter (ESAP) algorithm. ESAP searches for a one dimensional log-sigmoid weighting function which, when applied to the separable, interpolated local block estimated spectrum of the coded image, minimizes the mean square error (MMSE) with respect to the original image using a 2-D steepest descent search. Convergence is obtained in a few iterations for integer parameters. A unique maximum PSNR is guaranteed given the asymptotic exponential overshoot behavior of the surface generated by ESAP. We obtained PSNR improvement of 1.5 dB over nonpostfiltered JPEG images as well as subjective improvement. ESAP is based on a DFT analysis of the DCT basis functions and uses spatially adaptive separable FIR postfilters

Keywords

FIR filters; adaptive filters; convergence of numerical methods; discrete cosine transforms; filtering theory; image coding; image enhancement; interpolation; iterative methods; spatial filters; 2-D steepest descent search; DCT coded images; DFT analysis; JPEG images; MMSE; asymptotic exponential overshoot behavior; basis functions; convergence; iteration; mean square error minimisation; one dimensional log-sigmoid weighting function; optimal PSNR estimated spectrum adaptive postfilter; spatially adaptive separable FIR postfilters; Bit rate; Convergence; Decoding; Discrete cosine transforms; Finite impulse response filter; Frequency; Image enhancement; Mean square error methods; NASA; PSNR;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.479973

Filename

479973