A fuzzy logic system for content-based bit-rate allocation

When video coders communicate at very-low bit-rate, it is often difficult for them to preserve an acceptable global quality of the images. A selection of the key regions according to the semantic relevance may therefore be useful for improving the quality, as it would permit an adaptive bit allocation, which is important for good subjective quality at (very-)low bit-rate: the essential features could be extracted and coded with a good quality, while the remaining portions of the image would be coarsely transmitted. This paper describes tools to perform classification of regions according to the subjective priority, and a generic algorithm to optimally share out the bit-rate. Among others, an important contribution of this paper is the use of Fuzzy Logic in order to model human subjective knowledge about the attribution of priorities to picture regions. An original bit-rate allocation method is also proposed as a solution to the optimization problem posed by the rate-distortion theory. The paper concludes presenting some preliminary results. (C) 1997 Elsevier Science B.V.