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

Ali Khajegili Mirabadi, Stefano Rini

研究成果: Conference contribution同行評審

1 引文 斯高帕斯(Scopus)

摘要

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.

原文English
主出版物標題IWCIT 2020 - Iran Workshop on Communication and Information Theory
發行者Institute of Electrical and Electronics Engineers Inc.
頁數6
ISBN(電子)9781728182575
DOIs
出版狀態Published - 26 五月 2020
事件2020 Iran Workshop on Communication and Information Theory, IWCIT 2020 - Tehran, Iran, Islamic Republic of
持續時間: 26 五月 202028 五月 2020

出版系列

名字IWCIT 2020 - Iran Workshop on Communication and Information Theory

Conference

Conference2020 Iran Workshop on Communication and Information Theory, IWCIT 2020
國家Iran, Islamic Republic of
城市Tehran
期間26/05/2028/05/20

指紋 深入研究「The Information Mutual Information Ratio for Counting Image Features and Their Matches」主題。共同形成了獨特的指紋。

引用此