Using multiple video-information representations in automatic image-analysis systems

摘要

This paper analyzes the necessity of using many information representations simultaneously in image-processing and-analysis systems. The difference between Kolmogorov-complexity and algorithmic-probability criteria when solving induction problems and making decisions is investigated. It is shown that making the optimum decisions (for example, in recognition or prediction problems) requires the use of many representations of information, in terms of which alternative descriptions of the images are constructed. A representational algorithmic-probability criterion is derived for determining the optimum set of representations from a given selection of images.