Journal of Convergence for Information Technology (융합정보논문지)

Convergence Society for SMB (중소기업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Multimodal approach for blocking obscene and violent contents

멀티미디어 유해 콘텐츠 차단을 위한 다중 기법

  • Baek, Jin-heon (Department of Computer Science and Engineering, Korea University) ;
  • Lee, Da-kyeong (Department of Statistics, Inha University) ;
  • Hong, Chae-yeon (Department of Computer Science, Dongduk Women's University) ;
  • Ahn, Byeong-tae (Department of Liberal & Arts, Anyang University)
  • 백진헌 (고려대학교 컴퓨터학과) ;
  • 이다경 (인하대학교 통계학과) ;
  • 홍채연 (동덕여자대학교 컴퓨터학과) ;
  • 안병태 (안양대학교 교양대학)
  • Received : 2017.11.16
  • Accepted : 2017.12.20
  • Published : 2017.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Due to the development of IT technology, harmful multimedia contents are spreading out. In addition, obscene and violent contents have a negative impact on children. Therefore, in this paper, we propose a multimodal approach for blocking obscene and violent video contents. Within this approach, there are two modules each detects obsceneness and violence. In the obsceneness module, there is a model that detects obsceneness based on adult and racy score. In the violence module, there are two models for detecting violence: one is the blood detection model using RGB region and the other is motion extraction model for observation that violent actions have larger magnitude and direction change. Through result of these three models, this approach judges whether or not the content is harmful. This can contribute to the blocking obscene and violent contents that are distributed indiscriminately.

IT 기술의 발달로 유해 멀티미디어가 무분별하게 유포되고 있다. 또한 선정적, 폭력적 유해 콘텐츠는 청소년에게 약 영향을 끼친다. 따라서 본 논문에서는 선정성, 폭력성이 드러나는 영상 콘텐츠 차단을 위한 다중 기법을 제안한다. 다중 기법 내에는 선정성, 폭력성을 검출하는 두 가지 모듈이 있다. 선정성 검출 모듈 내에는 성인 점수와 외설점수를 기반으로 선정성을 검출하는 모델이 있다. 폭력성 검출을 위한 모듈 내에는 RGB 영역을 이용한 피 검출 모델과 폭력적인 움직임은 방향과 크기 변화가 크다는 것에 착안한 움직임 추출 모델 두 가지가 있다. 이와 같은 총 세가지 모델의 검출 결과에 따라 해당 콘텐츠의 유해 여부를 판단한다. 본 논문의 유해 콘텐츠 차단 다중 기법은 무분별하게 유포되는 선정적, 폭력적 유해 콘텐츠를 차단한다.

Keywords

References

  1. J. Y. Chang. (2017). Generalized Hough Transform using Internal Gradient Informaton. Journal of Convergence for Information Technology, 7(3), 73-81. DOI : 10.22156/CS4SMB.2017.7.3.073
  2. M. K. Kwon & H. S. Yang. (2017). A scene search method based on principal character identification using convolutional neural network. Journal of Convergence for Information Technology, 7(2), 31-36. DOI: 10.22156/CS4SMB.2017.7.2.031
  3. Korea Press Foundation. (2013). Survey of media audience. Seoul : Korea Press Foundation.
  4. T. Senst, V. Eiselein, A. Kuhn & T. Sikora. (2017) Crowd violence detection using global motioncompensated lagrangian features and scale-sensitive video-level representation. IEEE Transactions on Information Forensics and Security, 12(12), 2945-2956. DOI: 10.1109/TIFS.2017.2725820
  5. W. Hu, O. Wu, Z. Chen, Z. Fu & S. Maybank. (2007). Recognition of Pornographic Web Pages by Classifying Texts and Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(6), 1019-1034. DOI : 10.1109/TPAMI.2007.1133
  6. S. Lee, W. Shim & S. Kim. (2009). Hierarchical System for Objectionable Video Detection. IEEE Transactions on Consumer Electronic, 55(2), 667-684. DOI : 10.1109/TCE.2009.5174439
  7. C. Y. Kim, O. J. Kwon & S. Choi. (2011). A Practical System for Detecting Obscene Videos. IEEE Transactions on Consumer Electronics, 57(2), 646-650. DOI : 10.1109/TCE.2011.5955203
  8. M. Pereza, S. Avilab, D. Moreiraa, D. Moraesa, V. Testonic, E. Valleb, S. Goldensteina, A. Rocha. (2017). Video pornography detection through deep learning techniques and motion information. Neurocomputing, 230(4), 279-293. DOI : 10.1016/j.neucom.2016.12.017
  9. Y. Gao, H. Liu, X. Sun, C. Wang & Y. Liu. (2016). Violence detection using Oriented Violent Flows. Image and Vision Computing, 49(5), 37-41. DOI : 10.1049/el.2017.0970
  10. H. Fradi, B. Luvison & Q. C. Pham. (2017). Crowd Behavior Analysis Using Local Mid-Level Visual Descriptors. IEEE Transactions on Circuits and Systems for Video Technology, 27(3), 589-602. DOI : 10.1109/TCSVT.2016.2615443
  11. K. Kim, U. Kim & S. Kwak. (2017). Read-time violence video detection based on movement change characteristics. Journal of Broadcast Engineering, 22(2), 234-239. DOI : 10.5909/JBE.2017.22.2.234
  12. A. S. Keceli & A. Kaya. (2017). Violent activity detection with transfer learning method. Electronics Letters, 53(15), 1047-1048. DOI : 10.1049/el.2017.0970
  13. C. Clarin, J. Dionisio, M. Echavez & P. C. Naval. (2005). Dove: detection of movie violence using motion intensity analysis on skin and blood. Philippine Computing Science Congress, 6, 150-156.
  14. D. Marmanis, M. Datcu, T. Esch & U. Stilla. (2016). Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks. IEEE Geoscience and Remote Sensing Letters, 13(1), 105-109. DOI : 10.1109/LGRS.2015.2499239
  15. K. He, X. Zhang, S. Ren & J. Sun. (2015). Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9), 1904-1916. DOI : 10.1109/TPAMI.2015.2389824