The Information & Mutual Information Ratio for Counting Image Features and Their Matches

arXiv2005.06739MaRDI QIDQ6340664

Author name not available (Why is that?)

Publication date: 14 May 2020

Abstract: Feature extraction and description is an important topic of computer vision, as it is the starting point of a number of tasks such as image reconstruction, stitching, registration, and recognition among many others. In this paper, two new image features are proposed: the Information Ratio (IR) and the Mutual Information Ratio (MIR). The IR is a feature of a single image, while the MIR describes features common across two or more images.We begin by introducing the IR and the MIR and motivate these features in an information theoretical context as the ratio of the self-information of an intensity level over the information contained over the pixels of the same intensity. Notably, the relationship of the IR and MIR with the image entropy and mutual information, classic information measures, are discussed. Finally, the effectiveness of these features is tested through feature extraction over INRIA Copydays datasets and feature matching over the Oxfords Affine Covariant Regions. These numerical evaluations validate the relevance of the IR and MIR in practical computer vision tasks

Has companion code repository: https://github.com/AliKhajegiliM/IR-and-MIR

This page was built for publication: The Information & Mutual Information Ratio for Counting Image Features and Their Matches

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6340664)