Neural Computation, Vol 11, 267-296, Copyright © 1999 by The MIT Press

LETTERS

JPEG Quality Transcoding Using Neural Networks Trained With a Perceptual Error Measure

John Lazzaro and John Wawrzynek

A JPEG Quality Transcoder (JQT) converts a JPEG image file that was encoded with low image quality to a larger JPEG image file with reduced visual artifacts, without access to the original uncompressed image. In this article, we describe technology for JQT design that takes a pattern recognition approach to the problem, using a database of images to train statistical models of the artifacts introduced through JPEG compression. In the training procedure for these models, we use a model of human visual perception as an error measure. Our current prototype system removes 32.2% of the artifacts introduced by moderate compression, as measured on an independent test database of linearly coded images using a perceptual error metric. This improvement results in an average PSNR reduction of 0.634 dB.

This article has been cited by other articles:

				R S B Newsom, A Clover, M T J Costen, J Sadler, J Newton, A J Luff, and C R Canning Effect of digital image compression on screening for diabetic retinopathy Br. J. Ophthalmol., July 1, 2001; 85(7): 799 - 802. [Abstract] [Full Text] [PDF]

				G. C. Cawley On a Fast, Compact Approximation of the Exponential Function Neural Comput., September 1, 2000; 12(9): 2009 - 2012. [Abstract] [Full Text]