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

Ali Khajegili Mirabadi, Stefano Rini

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

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 Oxford's Affine Covariant Regions. These numerical evaluations validate the relevance of the IR and MIR in practical computer vision tasks.

Original languageEnglish
Title of host publicationIWCIT 2020 - Iran Workshop on Communication and Information Theory
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781728182575
DOIs
StatePublished - 26 May 2020
Event2020 Iran Workshop on Communication and Information Theory, IWCIT 2020 - Tehran, Iran, Islamic Republic of
Duration: 26 May 202028 May 2020

Publication series

NameIWCIT 2020 - Iran Workshop on Communication and Information Theory

Conference

Conference2020 Iran Workshop on Communication and Information Theory, IWCIT 2020
CountryIran, Islamic Republic of
CityTehran
Period26/05/2028/05/20

Keywords

  • Computer vision
  • Entropy
  • Feature counting
  • Feature Matching
  • Mutual Information

Fingerprint Dive into the research topics of 'The Information Mutual Information Ratio for Counting Image Features and Their Matches'. Together they form a unique fingerprint.

Cite this