Fast and Effective Bag-of-Visual-Word Model to Pornographic Images Recognition Using the FREAK Descriptor

S.Hadi Yaghoubyan, Mohd Aizaini Maarof, Anazida Zainal, Mohd Fo’ad Rohani, Mahdi Maktabdar Oghaz

Abstract


Abstract

Recently, the Bag of Visual Word (BoVW) has gained enormous popularity between researchers to object recognition. Pornographic image recognition with respect to computational complexity, appropriate accuracy, and memory consumption is a major challenge in the applications with time constraints such as the internet pornography filtering. Most of the existing researches based on the Bow, using the very popular SIFT and SURF algorithms to description and match detected keypoints in the image. The main problem of these methods is high computational complexity due to constructing the high dimensional feature vectors. This research proposed a BoVW based model by adopting very fast and simple binary descriptor FREAK to speed-up pornographic recognition process. Meanwhile, the keypoints are detected in the ROI of images which improves the recognition speed due to eliminating many noise keypoints placed in the image background. Finally, in order to find the most representational visual-vocabulary, different vocabularies are generated from size 150 to 500 for BoVW. Compared with the similar works, the experimental results show that the proposed model has gained remarkable improvement in the terms of computational complexity.


Keywords


Bag of Visual-Words (BoVW), Pornographic image recognition, Fast descriptor, ROI selection

Full Text:

Abstract PDF

References


Alahi, A., R. Ortiz, and P. Vandergheynst. 2012. “FREAK: Fast Retina Keypoint.†2012 IEEE Conference on Computer Vision and Pattern Recognition: 510–17.

Bay, Herbert, Tinne Tuytelaars, and Luc Van Gool. 2006. “Surf: Speeded up Robust Features.†Springer berlin Heidelberg, Computer Vision–ECCV 2006: 404–17.

Casati, JPB, DR Moraes, and ELL Rodrigues. 2013. “SFA: A Human Skin Image Database Based on FERET and AR Facial Images.†iris.sel.eesc.usp.br.

Chang, CC, and CJ Lin. 2011. “LIBSVM: A Library for Support Vector Machines.†ACM Transactions on Intelligent Systems and Technology (TIST): 1–39.

Deselaers, Thomas, Lexi Pimenidis, and Hermann Ney. 2008. “Bag-of-Visual-Words Models for Adult Image Classification and Filtering.†2008 19th International Conference on Pattern Recognition: 1–4.

Fleck, MM, DA Forsyth, and Chris Bregler. 1996. “Finding Naked People.†Computer Vision—ECCV’96. .

Forsyth, D A, and M.M. Fleck. 1996. “Identifying Nude Pictures.†(1): 103–8.

Gauglitz, Steffen, Tobias Höllerer, and Matthew Turk. 2011. “Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking.†International Journal of Computer Vision 94(3): 335–60.

Herwindiati, Dyah E, Sani M Isa, and Rahmat Sagara. 2010. “THE NEW NOTION DISTANCE OF CONTENT BASED IMAGE RETRIEVAL ( CBIR ).†16(1): 51–67.

Jiang, Yu-Gang, Chong-Wah Ngo, and Jun Yang. 2007. “Towards Optimal Bag-of-Features for Object Categorization and Semantic Video Retrieval.†Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR ’07: 494–501.

Kherfi, ML, D Ziou, and A Bernardi. 2004. “Image Retrieval from the World Wide Web: Issues, Techniques, and Systems.†ACM Computing Surveys (CSUR) 36(1): 35–67.

Lienhart, Rainer. 2009. “FILTERING ADULT IMAGE CONTENT WITH TOPIC MODELS Rainer Lienhart Lehrstuhl F ¨ Ur Multimedia Computing Universit ¨ at Augsburg Augsburg , Germany Rudolf Hauke Advanced US Technology Group , Inc . IEEE International: 1472–75.

Liu, Yizhi, and Hongtao Xie. 2009. “Constructing SURF Visual-Words for Pornographic Images Detection.†IEEE Conference, Computers and Information Technology, 2009. ICCIT ’09. 12th International Conference on (Iccit): 404–7.

Lopes, Ana P B et al. 2009. “A BAG-OF-FEATURES APPROACH BASED ON HUE-SIFT DESCRIPTOR FOR NUDE DETECTION.†(Eusipco): 1552–56.

Lopes, APB, and SEF de Avila. 2009. “Nude Detection in Video Using Bag-of-Visual-Features.†IEEE Conference, Computer Graphics and Image Processing (SIBGRAPI), 2009 XXII Brazilian Symposium on: 224–31.

Lowe, David G. 2004. “Distinctive Image Features from Scale-Invariant Keypoints.†International Journal of Computer Vision 60(2): 91–110.

Lv, Lintao et al. 2011. “Pornographic Images Detection Using High-Level Semantic Features.†2011 Seventh International Conference on Natural Computation: 1015–18.

Maktabdar Oghaz, Mahdi et al. 2015. “A Hybrid Color Space for Skin Detection Using Genetic Algorithm Heuristic Search and Principal Component Analysis Technique.†Plos One 10(8): e0134828.

O’Hara, S, and BA Draper. 2011. “Introduction to the Bag of Features Paradigm for Image Classification and Retrieval.†arXiv preprint arXiv:1101.3354 (July): 1–25.

Steel, C. 2012. “The Mask-SIFT Cascading Classifier for Pornography Detection.†Internet Security (WorldCIS), 2012 World Congress on: 139–42.

Wang, James Ze, Jia Li, Gio Wiederhold, and Oscar Firschein. 1998. “System for Screening Objectionable Images.†(April 1998): 1–12.

Wang, Meng, Richang Hong, Xiao-Tong Yuan, et al. 2012. “Movie2Comics: Towards a Lively Video Content Presentation.†IEEE Transactions on Multimedia 14(3): 858–70.

Wang, Meng, Richang Hong, Guangda Li, and ZJ Zha. 2012. “Event Driven Web Video Summarization by Tag Localization and Key-Shot Identification.†… , IEEE Transactions on 14(4): 975–85.

Wang, YS, LY Ning, and W Gao. 2008. “Detecting Pornographic Images with Visual Words.†Transactions of Beijing Institute of Technology 28(5): 410–13.

Yizhi, Liu, Lin Shouxun, Tang Sheng, and Zhang Yongdong. 2010. “Adult Image Detection Combining BoVW Based on Region of Interest and Color Moments.†IFIP Advances in Information and Communication Technology 340: 316–25.

Zhang, Jing et al. 2013. “An Approach of Bag-of-Words Based on Visual Attention Model for Pornographic Images Recognition in Compressed Domain.†Neurocomputing 110: 145–52.

Zheng, Huicheng, Mohamed Daoudi, and Bruno Jedynak. 2004. “Blocking Adult Images Based on Statistical Skin Detection.†4(2): 1–14.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.