BIMP : a real-time biological model of multi-scale keypoint detection in V1
- Submitting institution
-
University of St Andrews
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 267302164
- Type
- D - Journal article
- DOI
-
10.1016/j.neucom.2014.09.054
- Title of journal
- Neurocomputing
- Article number
- -
- First page
- 227
- Volume
- 150
- Issue
- Part A
- ISSN
- 0925-2312
- Open access status
- Out of scope for open access requirements
- Month of publication
- October
- 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
-
2
- Research group(s)
-
A - Artificial Intelligence
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Computational models of biological vision are often too slow for real-time use, limiting their adoption. This paper introduces an optimised model of simple and complex cells in area V1 of the visual cortex that is several orders of magnitude faster than the previous model it extends. The new model exhibits state-of-the-art performance on the keypoint detection task (first for a biological model) and works in real-time. It is also shown that the model can also be used to significantly reduce amount of data needed for classifying images.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
