Image skin segmentation based on multi-agent learning Bayesian and neural network
Skin colour is considered to be a useful and discriminating spatial feature for many skin detection-related applications, but it is not sufficiently robust to address complex image environments because of light-changing conditions, skin-like colours and reflective glass or water. These factors can c...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2014
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/37931/ http://psasir.upm.edu.my/id/eprint/37931/1/Image%20skin%20segmentation%20based%20on%20multi-agent%20learning%20Bayesian%20and%20neural%20network.pdf |
| _version_ | 1848848739460972544 |
|---|---|
| author | Zaidan, A. A. Ahmad, Nurul Nadia Abdul Karim, Hezerul Larbani, Moussa Zaidan, B. B. Sali, Aduwati |
| author_facet | Zaidan, A. A. Ahmad, Nurul Nadia Abdul Karim, Hezerul Larbani, Moussa Zaidan, B. B. Sali, Aduwati |
| author_sort | Zaidan, A. A. |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Skin colour is considered to be a useful and discriminating spatial feature for many skin detection-related applications, but it is not sufficiently robust to address complex image environments because of light-changing conditions, skin-like colours and reflective glass or water. These factors can create major difficulties in face pixel-based skin detectors when the colour feature is used. Thus, this paper proposes a multi-agent learning method that combines the Bayesian method with a grouping histogram (GH) technique and the back-propagation neural network with a segment adjacent-nested (SAN) technique based on the YCbCr and RGB colour spaces, respectively, to improve skin detection performance. The findings from this study have shown that the proposed multi-agent learning for skin detector has produced significant true positive (TP) and true negative (TN) average rates (i.e. 98.44% and 99.86% respectively). In addition, it has achieved a significantly lower average rate for the false negative (FN) and false positive (FP) (i.e. only 1.56% and 0.14% respectively). The experimental results show that multi-agent learning in the skin detector is more efficient than other approaches. |
| first_indexed | 2025-11-15T09:39:17Z |
| format | Article |
| id | upm-37931 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T09:39:17Z |
| publishDate | 2014 |
| publisher | Elsevier |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-379312015-12-29T12:23:24Z http://psasir.upm.edu.my/id/eprint/37931/ Image skin segmentation based on multi-agent learning Bayesian and neural network Zaidan, A. A. Ahmad, Nurul Nadia Abdul Karim, Hezerul Larbani, Moussa Zaidan, B. B. Sali, Aduwati Skin colour is considered to be a useful and discriminating spatial feature for many skin detection-related applications, but it is not sufficiently robust to address complex image environments because of light-changing conditions, skin-like colours and reflective glass or water. These factors can create major difficulties in face pixel-based skin detectors when the colour feature is used. Thus, this paper proposes a multi-agent learning method that combines the Bayesian method with a grouping histogram (GH) technique and the back-propagation neural network with a segment adjacent-nested (SAN) technique based on the YCbCr and RGB colour spaces, respectively, to improve skin detection performance. The findings from this study have shown that the proposed multi-agent learning for skin detector has produced significant true positive (TP) and true negative (TN) average rates (i.e. 98.44% and 99.86% respectively). In addition, it has achieved a significantly lower average rate for the false negative (FN) and false positive (FP) (i.e. only 1.56% and 0.14% respectively). The experimental results show that multi-agent learning in the skin detector is more efficient than other approaches. Elsevier 2014-06 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/37931/1/Image%20skin%20segmentation%20based%20on%20multi-agent%20learning%20Bayesian%20and%20neural%20network.pdf Zaidan, A. A. and Ahmad, Nurul Nadia and Abdul Karim, Hezerul and Larbani, Moussa and Zaidan, B. B. and Sali, Aduwati (2014) Image skin segmentation based on multi-agent learning Bayesian and neural network. Engineering Applications of Artificial Intelligence, 32. pp. 136-150. ISSN 0952-1976; ESSN: 1873-6769 http://www.sciencedirect.com/science/article/pii/S0952197614000578 10.1016/j.engappai.2014.03.002 |
| spellingShingle | Zaidan, A. A. Ahmad, Nurul Nadia Abdul Karim, Hezerul Larbani, Moussa Zaidan, B. B. Sali, Aduwati Image skin segmentation based on multi-agent learning Bayesian and neural network |
| title | Image skin segmentation based on multi-agent learning Bayesian and neural network |
| title_full | Image skin segmentation based on multi-agent learning Bayesian and neural network |
| title_fullStr | Image skin segmentation based on multi-agent learning Bayesian and neural network |
| title_full_unstemmed | Image skin segmentation based on multi-agent learning Bayesian and neural network |
| title_short | Image skin segmentation based on multi-agent learning Bayesian and neural network |
| title_sort | image skin segmentation based on multi-agent learning bayesian and neural network |
| url | http://psasir.upm.edu.my/id/eprint/37931/ http://psasir.upm.edu.my/id/eprint/37931/ http://psasir.upm.edu.my/id/eprint/37931/ http://psasir.upm.edu.my/id/eprint/37931/1/Image%20skin%20segmentation%20based%20on%20multi-agent%20learning%20Bayesian%20and%20neural%20network.pdf |