Fast pornographic image recognition using compact holistic features and multi-layer neural network

The paper presents an alternative fast pornographic image recognition using compact holistic features and multi-layer neural network (MNN). The compact holistic features of pornographic images, which are invariant features against pose and scale, is extracted by shape and frequency analysis on pornographic images under skin region of interests (ROIs). The main objective of this work is to design pornographic recognition scheme which not only can improve performances of existing methods (i.e., methods based on skin probability, scale invariant feature transform, eigenporn, and Multilayer-Perceptron and Neuro-Fuzzy (MP-NF)) but also can works fast for recognition. The experimental outcome display that our proposed system can improve 0.3% of accuracy and reduce 6.60% the false negative rate (FNR) of the best existing method (skin probability and eigenporn on YCbCr, SEP), respectively. Additionally, our proposed method also provides almost similar robust performances to the MP-NF on large size dataset. However, our proposed method needs short recognition time by about 0.021 seconds per image for both tested datasets.

[1]  Arne Leijon,et al.  Human skin color detection in RGB space with Bayesian estimation of beta mixture models , 2010, 2010 18th European Signal Processing Conference.

[2]  Keiichi Uchimura,et al.  D-12-33 Pornographic Image Recognition using Eigenporn of HSV Skin Segmented Image , 2015 .

[3]  Tapan Kumar Hazra,et al.  Optical character recognition using KNN on custom image dataset , 2017, 2017 8th Annual Industrial Automation and Electromechanical Engineering Conference (IEMECON).

[4]  Bhavna Sharma,et al.  Comparison of Neural Network Training Functions for Hematoma Classification in Brain CT Images , 2014 .

[5]  Vladimir Vezhnevets,et al.  A Survey on Pixel-Based Skin Color Detection Techniques , 2003 .

[6]  Hong Jiang,et al.  Face recognition based on DWT/DCT and SVM , 2010, 2010 International Conference on Computer Application and System Modeling (ICCASM 2010).

[7]  Zhouyu Fu,et al.  Recognition of Pornographic Web Pages by Classifying Texts and Images , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Chang-Hsing Lee,et al.  An adult image identification system employing image retrieval technique , 2007, Pattern Recognit. Lett..

[9]  Gabriel Pérez,et al.  Explicit image detection using YCbCr space color model as skin detection , 2011 .

[10]  Mohsen Ebrahimi Moghaddam,et al.  A Novel Scheme for Intelligent Recognition of Pornographic Images , 2014, ArXiv.

[11]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[12]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[13]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .

[14]  Alamsyah Alamsyah,et al.  Wavelet based approach for facial expression recognition , 2015 .

[15]  Rafael C. González,et al.  Digital image processing, 3rd Edition , 2008 .

[16]  Jirí Bíla,et al.  Fast fourier transform for feature extraction and neural network for classification of electrocardiogram signals , 2015, 2015 Fourth International Conference on Future Generation Communication Technology (FGCT).

[17]  Dingju Zhu,et al.  Objectionable Image Detection in Cloud Computing Paradigm-a Review , 2013, J. Comput. Sci..

[18]  Lung-Hao Lee,et al.  Generation of pornographic blacklist and its incremental update using an inverse chi-square based method , 2008, Inf. Process. Manag..

[19]  Gualberto Aguilar-Torres,et al.  Detection of Pornographic Digital Images , .

[20]  Rainer Lienhart,et al.  A survey on visual adult image recognition , 2012, Multimedia Tools and Applications.

[21]  Ping Li,et al.  Adult Image and Video Recognition by a Deep Multicontext Network and Fine-to-Coarse Strategy , 2017, ACM Trans. Intell. Syst. Technol..

[22]  Keiichi Uchimura,et al.  Phonographic image recognition using fusion of scale invariant descriptor , 2015, 2015 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV).

[23]  B. B. Zaidan,et al.  On the multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: An automated anti-pornography system , 2014, Neurocomputing.

[24]  Keiichi Uchimura,et al.  Pornographic image rejection using eigenporn of simplified LDA of skin ROIs images , 2015, 2015 International Conference on Quality in Research (QiR).

[25]  Meng Joo Er,et al.  PCA and LDA in DCT domain , 2005, Pattern Recognit. Lett..

[26]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[27]  I Gede Pasek Suta Wijaya,et al.  Pornographic Image Recognition Based on Skin Probability and Eigenporn of Skin ROIs Images , 2015 .

[28]  Majd Latah,et al.  Human action recognition using support vector machines and 3D convolutional neural networks , 2017 .