Adult Image Detection Using Bayesian Decision Rule Weighted by SVM Probability

Authors:
Byeongcheol Choi;Byungho Chung;Jaecheol Ryou
Affiliations:
-;-;-
Venue:
ICCIT '09 Proceedings of the 2009 Fourth International Conference on Computer Sciences and Convergence Information Technology
Year:
2009

Citing 0
Cited 3

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

Neurocomputing
A survey on visual adult image recognition

Multimedia Tools and Applications
Neuron-like algorithms of adaptive segmentation and semantic description of images in the "adult image" recognition problem

Optical Memory and Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The SVM (support vector machine) and the SCM (skin color model) are used in detection of adult contents on images. The SVM consists of multi-class learning model and is very effective method for face detection, but complex. On the contrary, the SCM is very simple for detecting adult images using skin ratio derived from statistical characteristics of RGB color information, but less effective in close-up facial images. Hence, we propose a hybrid scheme that combines the SVM for the 1st filtering scheme using learning model (with classes of adult, benign and close-up facial images) with the SCM for the 2nd filtering scheme using skin ratio and adaptive MAP (maximum a posterior) hypothesis test based on Bayes’ theorem that improves the probability of true positive detection rate of adult images.