Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Pornographic image region detection based on visual attention model in compressed domain

© The Institution of Engineering and Technology
Received 12/07/2012, Accepted 04/12/2012, Revised 07/11/2012, Published

According to biological attention mechanism, a region of interest (ROI) detection based on visual attention model is closer to human visual system. Taken into account the characteristics of pornographic image during regions detection, a pornographic image region detection method based on visual attention model in compressed domain is proposed in this study, which includes the following four steps: (i) the skin colour regions of pornographic images are detected in compressed domain; (ii) visual saliency map in compressed domain is computed to construct visual attention model; (iii) threshold segmentation method is used for visual saliency map, and then the torso information is retained as pornographic regions; and (iv) four features of colour, texture, intensity and skin are extracted to represent pornographic region. The experimental results show that the proposed method can perform well on the speed/accuracy of pornographic regions detection and representation.

Inspec keywords: object detection; image segmentation; image representation; image colour analysis; image coding; image texture

Other keywords: image texture; biological attention mechanism; torso information; skin colour regions; visual attention model; pornographic regions representation; region of interest detection; ROI detection; pornographic image region detection; compressed domain; human visual system; threshold segmentation method; visual saliency map; image intensity

Subjects: Image and video coding; Computer vision and image processing techniques

References

    1. 1)
      • 20. Chang, H.S., Kang, K.: ‘A compressed domain scheme for classifying block edge patterns’, IEEE Trans. Image Process., 2005, 14, (2), pp. 145–151 (doi: 10.1109/TIP.2004.840706).
    2. 2)
      • 12. Itti, L., Koch, C.: ‘A saliency-based search mechanism for overt and covert shifts of visual attention’, Vis. Res., 2000, 40, (6), pp. 1489–1506 (doi: 10.1016/S0042-6989(99)00163-7).
    3. 3)
      • 3. Wang, Y.S., Huang, Q.M., Gao, W.: ‘Pornographic image detection based on multilevel representation’, Int. J. Pattern Recognit. Artif. Intell., 2009, 23, (8), pp. 1633–1655 (doi: 10.1142/S0218001409007739).
    4. 4)
      • 10. Huang, H.M., Liu, G.P.: ‘A region of interest extraction for color image based on bottom-up saliency map’. Int. Congress on Image and Signal Processing, Yantai, China, October 2010, pp. 43–46.
    5. 5)
      • 15. Sui, L., Zhang, J., Zhuo, L., Yang, Y.C.: ‘Visual attention model based regions of interest detection in compressed domain’, Chin. J. Electron., 2012, 21, (4), pp. 697–700.
    6. 6)
      • 5. Chen, S.Q., Shen, Y.J., Liu, C.L., et al: ‘Pornographic pictures detection based on SIFT algorithm’. Int. Symp. Information Engineering and Electronic Commerce, Huangshi, China, July 2011, pp. 1–4.
    7. 7)
      • 1. Lee, P.Y., Hui, S.C., Fong, A.C.M.: ‘An intelligent categorization engine for bilingual web content filtering’, IEEE Trans. Multimed., 2005, 7, (6), pp. 1183–1190 (doi: 10.1109/TMM.2005.858414).
    8. 8)
      • 19. Viola, P., Jones, M.J.: ‘Rapid object detection using a boosted cascade of simple features’, Computer Vision and Pattern Recognition, Cambridge, USA, December 2001, 1, pp. 511–518.
    9. 9)
      • 7. Sui, L., Zhang, J., Zhuo, L., Yang, Y.C.: ‘Research on pornographic images recognition method based on visual words in a compressed domain’, IET Image Process., 2012, 6, (1), pp. 87–93 (doi: 10.1049/iet-ipr.2011.0005).
    10. 10)
      • 17. Zhao, S.W., Zhuo, L., Shen, L.S.: ‘A data-mining based skin detection method in JPEG compressed domain’. Int. Conf. Fuzzy Systems and Knowledge Discovery, Tianjin, China, August 2009, pp. 297–301.
    11. 11)
      • 14. Sui, L., Zhang, J., Zhuo, L., Yang, Y.C.: ‘Regions of interest extraction based on visual saliency in compressed domain’. IEEE Int. Symp. Multimedia, Dana Point, CA, USA, December 2011, pp. 434–439.
    12. 12)
      • 6. Sui, L., Zhang, J., Zhuo, L., Yang, Y.C.: ‘Creating visual vocabulary based on SIFT descriptor in compressed domain’. Int. Conf. Wireless Communications and Signal Processing, Nanjing, China, November 2011, pp. 1–5.
    13. 13)
      • 22. Brauer, J., Hübner, W., Arens, M.: ‘Generative 2D and 3D human pose estimation with vote distributions’, ISVC, 2012, 1, pp. 470–481.
    14. 14)
      • 9. Stentiford, F.: ‘An attention based similarity measure with application to content-based information retrieval’. Proc. Storage and Retrieval for Media Databases Conf., Santa Clara, CA, January 2003, vol. 5021, pp. 1–12.
    15. 15)
      • 4. Lopes, A.B.P., Avila, S.E.F., de Peixoto, A.N.A.: ‘A bag-of-features approach based on HUE-SIFT descriptor for nude detection’. Proc. 17th European Signal Processing Conf., Glasgow, Scotland, 2009, pp. 1552–1556.
    16. 16)
      • 16. Zhao, G., Wang, S.H., Wang, T., Chen, J.: ‘HSV color space and face detection based objectionable image detecting’. Int. Conf. Future Generation Communication and Networking Symp., Washington, USA, March 2008, pp. 107–110.
    17. 17)
      • 13. Zhang, J., Shen, L.S., Gao, J.J.: ‘Region of interest detection based on visual attention model and evolutionary programming’, J. Electron. Inf. Technol., 2009, 31, (7), pp. 1646–1652.
    18. 18)
      • 21. Gaidon, A., Harchaoui, Z., Schmid, C.: ‘Recognizing activities with cluster-trees of tracklets’. British Machine Vision Conf., Surrey, September 2012, pp. 1–13.
    19. 19)
      • 11. Chi, M.C., Yeh, C.H.: ‘Robust region-of-interest determination based on user attention model through visual rhythm analysis’, IEEE Trans. Circuits Syst. Video Technol., 2009, 19, (7), pp. 1025–1038 (doi: 10.1109/TCSVT.2009.2022822).
    20. 20)
      • 8. Mira, J., Delgado, A.E., Lopez, M.T., et al: ‘A conceptual frame with two neural mechanisms to model selective visual attention processes’, Neurocomputing, 2008, 71, (4–6), pp. 704–720 (doi: 10.1016/j.neucom.2007.10.005).
    21. 21)
      • 2. Wang, Y.S., Ning, L.Y., Gao, W.: ‘Detecting pornographic images with visual words’, Trans. Beijing Inst. Technol., 2008, 28, (5), pp. 410–413.
    22. 22)
      • 18. Zhuo, L., Zhang, J., Zhao, Y.D., Zhao, S.W.: ‘Compressed domain based pornographic image recognition using multi-cost sensitive decision trees’, Signal Process., 2012, 7, http://www.dx.doi.org/10.1016/j.sigpro.2012.07.003.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2012.0381
Loading

Related content

content/journals/10.1049/iet-ipr.2012.0381
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address