Optimal illumination directions for faces and rough surfaces for single and multiple light imaging using class-specific prior knowledge
- Submitting institution
-
Kingston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-06-1340
- Type
- D - Journal article
- DOI
-
10.1016/j.cviu.2014.01.012
- Title of journal
- Computer Vision And Image Understanding
- Article number
- -
- First page
- 16
- Volume
- 125
- Issue
- -
- ISSN
- 1077-3142
- Open access status
- Out of scope for open access requirements
- Month of publication
- -
- 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
-
-
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work proposes a novel approach to detect the optimal illumination for object reconstruction assuming shape commonality, such as in the case of human faces. This method estimates the best illumination directions achieving higher reconstruction quality using photometric-stereo equivalent to movie standards. It is used in the film and game industries where actors need their faces to be digitised. Moreover, industrial applications where faulty products need to be detected also use these technologies, e.g., photometric stereo is used to detect cracks on products or defects on food and vegetables.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -