Investigation of a Kolmogorov Complexity Based Similarity Metric for Content Based Image Retrieval
Abstract
This paper introduces an image retrieval approach using normalized information distance based similarity metric to determine the difference between the images. The similarity metric is based on Kolmogorov complexity and measures the amount of shared information between images. Although the Kolmogorov complexity is uncomputable, we are following Vitanyi's approach for approximating it
Collections
- OSU Theses [15752]