Аннотация.

В статье представлен обзор методов классификации изображений для решения задач фильтрации содержимого сети Интернет и приведены результаты экспериментов по классификации изображений при помощи сверточных нейронных сетей и метода мешка визуальных слов. Для экспериментов сформирована искусственно усложненная выборка, составленная из слабоотличимых изображений. Подтверждены высокие показатели качества классификации изображений при помощи сверточных нейронных сетей по сравнению с классическими методами, особенно в усложненных условиях эксперимента. Сделаны выводы о перспективности описанных методов и подходов, а также об их применимости для решения задач фильтрации контента.

Ключевые слова:

сверточные нейронные сети, искусственные нейронные сети, мешок визуальных слов, классификация изображений, фильтрация контента, динамическая контентная фильтрация.

Стр. 3-12.

V.P. Fralenko, R.E. Suvorov, R.I. Ovcharenko, I.A. Tikhomirov

"Automatic Image Classification for Content Filtering"

The paper presents a survey of methods for image classification in the context of Web content filtering, as well as results of new experiments using convolutional neural networks and SVM with bag-of-visual-words. Within the experiments, a special difficult dataset was collected that consisting of two hardly distinguishable classes. The quality achieved using convolutional neural network is higher than that of traditional methods in the complicated conditions. Thus, the classifier based on convolutional neural networks proved to be very useful for purposes of Web content filtering.

Keywords: convolutional neural networks, artificial neural networks, bag of visual words, image classification, content filtering, dynamic content filtering. 

 Полная версия статьи в формате pdf.

REFERENCES 

1. Smirnov I.V., Sochenkov I.V., Suvorov R.Ye., Tikhomirov I.A. Filtratsiya kontenta v internete: sovremennyy uroven i perspektivy // Iskusstvennyy intellekt i prinyatie resheniy. – M.: ISA RAN, №2, 2013, s.54-62.
2. Suvorov R., Sochenkov I., Tikhomirov I. Method for Pornography Filtering in the WEB Based on Automatic Classification and Natural Language Processing // in Proceedings of 15th International Conference, SPECOM 2013. Ed. Miloš Železný, Ivan Habernal, Andrey Ronzhin. Pilsen, Czech Republic, 2013, pp 233-240. ISBN 978-3-319-01930-7.
3. Suvorov R., Sochenkov I., Tikhomirov I. Training Datasets Collection and Evaluation of Feature Selection Methods for Web Content Filtering // Artificial Intelligence: Methodology, Systems, and Applications. – Springer International Publishing, 2014, pp.129-138.
4. Hammami M., Chahir Y., Chen L. Webguard: A web filtering engine combining textual, structural, and visual content-based analysis // Knowledge and Data Engineering, IEEE Transactions on. – 2006. – T. 18. – №. 2. – P. 272-284.
5. Drimbarean A.F. et al. Image processing techniques to detect and filter objectionable images based on skin tone and shape recognition // Consumer Electronics, 2001. ICCE. International Conference on. – IEEE, 2001. –P. 278-279.
6. Liu B. et al. Pornographic images detection based on CBIR and skin analysis // International Conference on Semantics, Knowledge and Grid (SKG), vol. 0. – 2008. – P. 487-488.
7. Shih J.L., Lee C.H., Yang C.S. An adult image identification system employing image retrieval technique // Pattern Recognition Letters. – 2007. – T. 28. – №. 16. – P. 2367-2374.
8. Abadpour A., Kasaei S. Pixel-based skin detection for pornography filtering // Iranian Journal of Electrical & Electronic Engineering. – 2005. – T. 1. – №. 3. – P. 21-41.
9. Basilio J. A. M. et al. Explicit content image detection // Signal & Image Processing: International Journal (SIPIJ). – 2010. – T. 1. – №. 2. – P. 47-58.
10. Lee J.S. et al. Naked image detection based on adaptive and extensible skin color model // Pattern recognition. – 2007. – T. 40. – №. 8. – P. 2261-2270.
11. Kia S.M. et al. A Novel Scheme for Intelligent Recognition of Pornographic Images // arXiv preprint arXiv:1402.5792. – 2014.
12. Deselaers T., Pimenidis L., Ney H. Bag-of-visual-words models for adult image classification and filtering //Pattern Recognition, 2008. ICPR 2008. 19th International Conference on. – IEEE, 2008. – P. 1-4.
13. Sayed U., Sadek S., Michaelis B. Two phases neural  network-based system for pornographic image classification // Proceedings of the IEEE International Conference on Sciences of Electronic, Technologies of Information and Telecommunications. – 2009. – P. 1-6.
14. Libing Wu, Yalin Ke, Yanxiang He, Dan Wu, Nan Liu. An efficient Method to Automatic Adult Image Identification // International Journal of Digital Content Technology and its Applications. – 2012. – T 6. – № 22. – P. 459-466.
15. Fu Y., Wang W. Fast and Effectively Identify Pornographic Images // Computational Intelligence and Security (CIS), 2011 Seventh International Conference on. – IEEE, 2011. – P. 1122-1126.
16. Zheng H., Liu H., Daoudi M. Blocking objectionable images: adult images and harmful symbols // Multimedia and Expo, 2004. ICME'04. 2004 IEEE International Conference on. – IEEE, 2004. – T. 2. – P. 1223-1226.
17. Zeng W. et al. Image guarder: An intelligent detector for adult images //Asian Conference on Computer Vision. – 2004. – P. 1080-1084.
18. Ulges A., Stahl A. Automatic detection of child pornography using color visual words // Multimedia and Expo (ICME), 2011 IEEE International Conference on. – IEEE, 2011. – P. 1-6.
19. Lienhart R., Hauke R. Filtering adult image content with  topic models // Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on. – IEEE, 2009. – P. 1472-1475.
20. Polpinij J. et al. A web pornography patrol system by content-based analysis: In particular text and image //Systems, Man and Cybernetics, 2008. SMC 2008. IEEE International Conference on. – IEEE, 2008. – P. 500-505.
21. Talalaev A.A., Tishchenko I.P., Fralenko V.P., Khachumov V.M. Analiz effektivnosti primeneniya iskusstvennykh neyronnykh setey dlya resheniya zadach raspoznavaniya, szhatiya i prognozirovaniya // Iskusstvennyy intellekt i prinyatie resheniy, №2, 2008, s.24-33.
22. LeCun Y., Bengio Y. Convolutional Networks for Images, Speech, and Time-Series, in Arbib, M. A. (Eds), The Handbook of Brain Theory and Neural Networks, MIT Press, 1995
23. Hubel D.H., Wiesel T.N. Receptive fields, binocular  interaction and functional architecture in the cat's visual cortex. Journal of Physiology 160:106–154, 1962
24. Lowe D.G. Distinctive image features from scale-invariantkeypoints // International journal of computer vision. – 2004. – T. 60. – №. 2. – P. 91-110.
25. Bay H., Tuytelaars T., Van Gool L. Surf: Speeded up robust features //Computer vision–ECCV 2006. – Springer Berlin Heidelberg, 2006. – P. 404-417.
26. Fralenko V.P., Talalaev A.A. Obnaruzhenie nezhelatelnogo graficheskogo kontenta v seti Internet s pomoshchyu svertochnoy neyronnoy seti glubokogo obucheniya // Svidetelstvo o gosudarstvennoy registratsii programmy dlya EVM №2015611772, data prioriteta: 09.12.2014, data registratsii: 06.02.2015