Image similarity using sparse representation and compression distance
- Submitting institution
-
The University of Warwick
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 5988
- Type
- D - Journal article
- DOI
-
10.1109/TMM.2014.2306175
- Title of journal
- IEEE Transactions on Multimedia
- Article number
- -
- First page
- 980
- Volume
- 16
- Issue
- 4
- ISSN
- 1520-9210
- Open access status
- Out of scope for open access requirements
- Month of publication
- June
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
A - Applied Computing
- Citation count
- 32
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Published in the top journal in multimedia and supported by a strategic grant from Canada's NSERC, this well-cited paper is the first to connect three seemingly disparate concepts: Kolmogorov complexity, sparse representation and image similarity. It established the idea of sparsity-based compressibility and conditional sparsity to measure image similarity via compression algorithms. This work has found a number of new applications in image retrieval, quality estimation, and medical image classification; and has impacted the works of several groups across the world (Winkler, NUS; Acton, University of Virgina; Wang, Waterloo; Guo, National Taiwan University; Zhang, University of Alberta).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -