Object Feature Based Coding Quality Prediction for Coding Scheme Selection

Abstract

Current developments in digital image coding tend to involve more and more complex algorithms. Overall compression performance can be improved by decomposing the image into regions and applying, for each region, the algorithm best suited to encode the region. Such schemes are referred to as dynamic coding schemes. However, this implies an algorithm selection phase. Current selection methods require the encoding and decoding of the image with all the selected algorithms to choose the best method. Some other schemes use ways of pruning the search in the algorithm space. Both approaches suffer from a heavy computational load. The computational complexity is increased even more if the parameters for a given algorithm have to be adjusted during the search.

This paper describes a way to predict the coding quality of a region of the input image for any given coding method. This prediction is then used to select the most suited coding algorithm for each region. This prediction scheme has low complexity, and also enables the adjustment of algorithm specific parameters during the search.