Non-pornographic images containing large naked skin or skin-like areas may be detected as pornographic using ordinary pornographic image-filtering method that heavily depend on skin detection. We design a different pornographic image-filtering system based on body parts. The system extracts Haar-like features describing local grayscale distribution of the body parts, and uses these features to train and obtain a classifier for body parts using the Adaboost learning algorithm. The candidate body part areas can be obtained with the classifier. To further improve the system performance, we extract histogram of oriented gradient features,textual features based on gray level co-occurrence matrix, and color moment features of the candidates. These
features are then used to train an support vector machine (SVM) classifier. Experiments show that the system can precisely detect key body parts in images, and therefore can effectively reduce false detection rate against non-pornographic images.
[1] HU W, WU O, CHEN A, Fu Z, MAYBANK S. Recognition of pornographic web pages by classifying texts and images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(6):1019- 1034.
[2] LEE J-S, KUO Y-M, CHUNG P-C, CHEN E-L. Naked image detection based on adaptive and extensible skin color model[J]. Pattern Recognition, 2007, 40(8): 2261-2270.
[3] YIN H, HUANG X, WEI Y. SVM-based pornographic images detection[J]. Software Engineering and Knowledge Engineering, 2012, Vol.2, AISC 115:751-759.
[4] SHARMA J, PATHAK V K. Automatic pornographic detection in web pages based on images and text data using support vector machine[C]// Proceedings of the International Conference on SocProcS, 2011, AISC 131:473-483.
[5] LV L-T, ZHAO C-X, LV H, SHANG J, YANG Y-X, WANG J-F. Pornographic images detection using high-level semantic features[C]// 2011 Seventh International Conference on Natural Computation, 2011:1015-1018.
[6] FUANGKHON P, TANPRASERT T. Nipple detection for obscene pictures[C]// Proceedings of the 5th International Conference On Signal, Speech and Image Processing, Greece, August 2005:315-320.
[7] SHEN X, WEI W, QIAN Q. The filtering of internet images based on detecting erotogenic-part[C]//Third International Conference on Natural Computation, ICNC 2007, v 2:732-736.
[8] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]// Computer Vision and Pattern Recognition, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001,Vol.1: I-511- I-518.
[9] LIENHART R, MAYDT J. An extended set of Haar-like features for rapid object detection[C]//Proceedings of IEEE Conference on Image Processing,2002:900-903.
[10] HARALICK R M, SHANMUGAM K, DINSTEIN I. Textual features for image classification[J]. IEEE Transaction on System, Man, and Cybernetics, 1973, 3(6):610-621.
[11] STRICKER M A, ORENGO M. Similarity of color images[C]//Proceedings of SPIE: Storage and Retrieval for Image and Video Databases,1995, volume 2420:381-392.
[12] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005, 1(2):886-893.
[13] VIOLA P, JONES M J. Robust real-time face detection [J]. International Journal of Computer Vision, 2004, 57(2):137-154.
[14] VAPNIK V. The nature of statistical learning theory. New York: Springer-Verlag,1995.
[15] NOR N, HARUN S, KASSIM A. Radial basis function modeling of hourly streamflow hydrograph[J]. Journal of Hydrologic Engineering, 2007,12(1):113-123.
[16] YANG Z-R. A model radial basis function neural network for discriminant analysis[J]. IEEE Transactions on Neural Networks, 2006, 17(3):604-612.
[17] KOHAVI R. A study of cross-validation and bootstrap for accuracy estimation and model selection[J]. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, 1995:1137-1143.
