Abstract
To prevent pornography from spreading on the Internet effectively, we propose a novel method of adult image detection which combines bag-of-visual-words (BoVW) based on region of interest (ROI) and color moments (CM). The goal of BoVW is to automatically mine the local patterns of adult contents, called visual words. The usual BoVW method clusters visual words from the patches in the whole image and adopts the weighting schemes of hard assignment. However, there are many background noises in the whole image and soft-weighting scheme is better than hard assignment. Therefore, we propose the method of BoVW based on ROI, which includes two perspectives. Firstly, we propose to create visual words in ROI for adult image detection. The representative power of visual words can be improved because the patches in ROI are more indicative to adult contents than those in the whole image. Secondly, soft-weighting scheme is adopted to detect adult images. Moreover, CM is selected by evaluating some commonly-used global features to be combined with BoVW based on ROI. The experiments and the comparison with the state-of-the-art methods show that our method is able to remarkably improve the performance of adult image detection.
Chapter PDF
Similar content being viewed by others
Keywords
References
Wang, Y.S., Li, Y.N., Gao, W.: Detecting pornographic images with visual words. Transactions of Beijing Institute of Technology 28, 410–413 (2008) (in Chinese)
Deselaers, T., Pimenidis, L., Ney, H.: Bag-of-visual-words models for adult image classification and filtering. In: 19th International Conference on Pattern Recognition, Tampa, USA, pp. 1–4 (2008)
Jiang, Y.G., Ngo, C.W., Yang, J.: Towards optimal bag-of-features for object categorization and semantic video retrieval. In: 6th ACM International Conference on Image and Video Retrieval, Amsterdam, Netherlands, pp. 494–501 (2007)
Yang, J., Jiang, Y.G., Hauptmann, A.G., et al.: Evaluating bag-of-visual-words representations in scene classification. In: 9th ACM SIGMM International Workshop on Multimedia Information Retrieval, Augsburg, Germany, pp. 197–206 (2007)
Fleck, M.M., Forsyth, D.A., Bregler, C.: Finding naked people. In: 4th European Conference on Computer Vision, Cambridge, UK, pp. 593–602 (1996)
Zeng, W., Gao, W., Zhang, T., et al.: Image guarder: an intelligent detector for adult. In: 6th Asian Conference of Computer Vision, Jeju Island, Korea, pp. 198–203 (2004)
Kuan, Y.H., Hsieh, C.H.: Content-based pornography image detection. In: International Conference on Imaging Science, System and Technology, Las Vegas, USA (2004)
Zheng, Q.F., Zeng, W., Gao, W., et al.: Shape-based adult images detection. In: 3th International Conference on Image and Graphics, Hong Kong, China, pp. 150–153 (2004)
Rowley, H.A., Yushi, J., Baluja, S.: Large scale image-based adult-content filtering. In: 1st International Conference on Computer Vision Theory and Applications, pp. 290–296 (2006)
Tang, S., Li, J., Zhang, Y., et al.: PornProbe: an LDA-SVM based Pornography Detection System. In: ACM International Conference on Multimedia, Beijing, China (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 IFIP International Federation for Information Processing
About this paper
Cite this paper
Yizhi, L., Shouxun, L., Sheng, T., Yongdong, Z. (2010). Adult Image Detection Combining BoVW Based on Region of Interest and Color Moments. In: Shi, Z., Vadera, S., Aamodt, A., Leake, D. (eds) Intelligent Information Processing V. IIP 2010. IFIP Advances in Information and Communication Technology, vol 340. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16327-2_38
Download citation
DOI: https://doi.org/10.1007/978-3-642-16327-2_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16326-5
Online ISBN: 978-3-642-16327-2
eBook Packages: Computer ScienceComputer Science (R0)