Generic image similarity based on Kolmogorov complexity

Image similarity measurement is a fundamental and common issue in a broad range of problems in image processing, compression, communication, recognition and retrieval. Existing image similarity measures are limited to restricted application environments. The theory of Kolmogorov complexity and the related normalized information distance (NID) measure provide an attractive theoretic framework for generic image similarity that is applicable to any scenario. While this is appealing, the difficulty lies in the implementation due to the non-computable nature of Kolmogorov complexity. In this paper, we propose a practical framework to approximate NID, where the key is to find the shortest program within a set of potential transformations that convert one image to another and vice versa. As one of the initial attempts in this new and promising research direction, our preliminary experimental work demonstrates the wider applicability of the proposed approach than existing methods.