On multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system

The main objective on this study proposed anti-pornography system works on four machine learning methods in two different stages namely skin detector stage and pornography classifier stage. A multi-agent learning is used twice. In the first stage, we propose a multi-agent learning method that combin...

Full description

Bibliographic Details
Main Authors: Zaidan, Aws Alaa, Ahmad, Nurul Nadia, Abdul Karim, Hezerul, Larbani, Moussa, Zaidan, Bilal Bahaa, Sali, Aduwati
Format: Article
Published: Elsevier 2014
Online Access:http://psasir.upm.edu.my/id/eprint/34731/
_version_ 1848847855756771328
author Zaidan, Aws Alaa
Ahmad, Nurul Nadia
Abdul Karim, Hezerul
Larbani, Moussa
Zaidan, Bilal Bahaa
Sali, Aduwati
author_facet Zaidan, Aws Alaa
Ahmad, Nurul Nadia
Abdul Karim, Hezerul
Larbani, Moussa
Zaidan, Bilal Bahaa
Sali, Aduwati
author_sort Zaidan, Aws Alaa
building UPM Institutional Repository
collection Online Access
description The main objective on this study proposed anti-pornography system works on four machine learning methods in two different stages namely skin detector stage and pornography classifier stage. A multi-agent learning is used twice. In the first stage, we propose 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 extract skin regions from the image accurately with taking into consideration the problems of the light-changing conditions, skin-like colour and reflection from glass and water. In the second stage, the features from the skin are extracted to classify the images into either pornographic or non-pornographic. Inaccurate classification occurs when different image sizes are used in the existing anti-pornography systems. Thus, this paper proposes a multi-agent learning that combines the Bayesian method with a grouping histogram technique again to extract the features from the skin detection based on YCbCr colour space and the back propagation neural network method using shape features extracted again from skin detection. The classification of the pornographic images becomes more robust to the variation in images sizes. The findings from this study have shown that the proposed multi-agent learning system for skin detection has produced a significant rate of true positives (TP) (i.e., 98.44%). In addition, it has achieved a significant low average rate for the false positives (FP) (i.e., only 0.14%) while the proposed multi-agent learning for pornography classifier has produced significant rates of TP (i.e., 96%). Moreover, it has achieved a significant low average rate of FP (i.e., only 2.67%). The experimental results show that multi-agent learning in the skin detector and pornography classifier are more efficient than other approaches.
first_indexed 2025-11-15T09:25:14Z
format Article
id upm-34731
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T09:25:14Z
publishDate 2014
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling upm-347312015-12-21T12:46:35Z http://psasir.upm.edu.my/id/eprint/34731/ On multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system Zaidan, Aws Alaa Ahmad, Nurul Nadia Abdul Karim, Hezerul Larbani, Moussa Zaidan, Bilal Bahaa Sali, Aduwati The main objective on this study proposed anti-pornography system works on four machine learning methods in two different stages namely skin detector stage and pornography classifier stage. A multi-agent learning is used twice. In the first stage, we propose 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 extract skin regions from the image accurately with taking into consideration the problems of the light-changing conditions, skin-like colour and reflection from glass and water. In the second stage, the features from the skin are extracted to classify the images into either pornographic or non-pornographic. Inaccurate classification occurs when different image sizes are used in the existing anti-pornography systems. Thus, this paper proposes a multi-agent learning that combines the Bayesian method with a grouping histogram technique again to extract the features from the skin detection based on YCbCr colour space and the back propagation neural network method using shape features extracted again from skin detection. The classification of the pornographic images becomes more robust to the variation in images sizes. The findings from this study have shown that the proposed multi-agent learning system for skin detection has produced a significant rate of true positives (TP) (i.e., 98.44%). In addition, it has achieved a significant low average rate for the false positives (FP) (i.e., only 0.14%) while the proposed multi-agent learning for pornography classifier has produced significant rates of TP (i.e., 96%). Moreover, it has achieved a significant low average rate of FP (i.e., only 2.67%). The experimental results show that multi-agent learning in the skin detector and pornography classifier are more efficient than other approaches. Elsevier 2014-05-05 Article PeerReviewed Zaidan, Aws Alaa and Ahmad, Nurul Nadia and Abdul Karim, Hezerul and Larbani, Moussa and Zaidan, Bilal Bahaa and Sali, Aduwati (2014) On multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system. Neurocomputing, 131. pp. 397-418. ISSN 0925-2312; ESSN: 1872-8286 http://www.sciencedirect.com/science/article/pii/S0925231213009326 10.1016/j.neucom.2013.10.003
spellingShingle Zaidan, Aws Alaa
Ahmad, Nurul Nadia
Abdul Karim, Hezerul
Larbani, Moussa
Zaidan, Bilal Bahaa
Sali, Aduwati
On multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system
title On multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system
title_full On multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system
title_fullStr On multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system
title_full_unstemmed On multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system
title_short On multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system
title_sort on multi-agent learning neural and bayesian methods in skin detector and pornography classifier: an automated anti-pornography system
url http://psasir.upm.edu.my/id/eprint/34731/
http://psasir.upm.edu.my/id/eprint/34731/
http://psasir.upm.edu.my/id/eprint/34731/