The Information & Mutual Information Ratio for Counting Image Features and Their Matches
| Autor: | Ali Khajegili Mirabadi, Stefano Rini |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Pixel Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Information Theory (cs.IT) Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Mutual information Image stitching Feature (computer vision) Histogram Entropy (information theory) Artificial intelligence Affine transformation business |
| Zdroj: | IWCIT |
| DOI: | 10.48550/arxiv.2005.06739 |
| Popis: | 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 8-th Iran Workshop on Communication and Information Theory, 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|