Detecting violent scenes in movies using Gated Recurrent Units and Discrete Wavelet Transform

Authors

  • Elly Matul Imah Universitas Negeri Surabaya
  • Ivan Kurnia Laksono Universitas Negeri Surabaya
  • Karisma Karisma Universitas Negeri Surabaya
  • Atik Wintarti Universitas Negeri Surabaya

DOI:

https://doi.org/10.26594/register.v8i2.2541

Keywords:

deep learning, gate recurrent unit, violence detection, video processing, wavelet

Abstract

The easiness of accessing video on various platforms can negatively impact if not done wisely, especially for children. Parental supervision is needed so that movies platforms avoid inappropriate displays such as violence. Violent scenes in movies can trigger children to commit acts of violence, which is not desired. Unfortunately, it is not easy to supervise them fully. This study proposed a method for automatic detection of violent scenes in movies. Automatic violence detection assists the parents and censorship institutions in detecting violence easily. This study uses Gated Recurrent Units (GRU) algorithm and wavelet as feature extraction to detect violent scenes. This paper shows comparative studies on the variation of the mother wavelet. The experimental results show that GRU is robust and deliver the best performance accuracy of 0.96 while combining with mother wavelet Symlet and Coiflets8. The combination of GRU with wavelet Coiflets8 shows better results than the predecessor.

Author Biographies

Elly Matul Imah, Universitas Negeri Surabaya

Department of Mathematics

Ivan Kurnia Laksono, Universitas Negeri Surabaya

Unit of Artificial Intelligence and Scientific Publication

Karisma Karisma, Universitas Negeri Surabaya

Unit of Artificial Intelligence and Scientific Publication

Atik Wintarti, Universitas Negeri Surabaya

Department of Mathematics

References

[1] WHO, "Global status report on preventing violence against children 2020," World Health Organization, 2020.

[2] M. Lawson, M. H. Piel and M. Simon, "Child Maltreatment during the COVID-19 Pandemic: Consequences of Parental Job Loss on Psychological and Physical Abuse Towards Children," Child Abuse & Neglect, vol. 110, 2020.

[3] H. H. Fore, "Violence against children in the time of COVID-19: What we have learned, what remains unknown and the opportunities that lie ahead," Child Abuse & Neglect, vol. 116, 2021.

[4] C. Øverlien, "The COVID-19 Pandemic and Its Impact on Children in Domestic Violence Refuges," Child Abuse Review, vol. 29, no. 4, pp. 379-386, 2020.

[5] R. S. McGinnis, E. W. McGinnis, J. Hruschak, N. L. LopezDuran, K. Fitzgerald, K. L. Rosenblum and M. Muzik, "Rapid detection of internalizing diagnosis in young children enabled by wearable sensors and machine learning," PLoS ONE, vol. 14, no. 1, p. e0210267, 2019.

[6] R. Durham and P. Wilkinson, "Joker: how ‘entertaining’ films may affect public attitudes towards mental illness – psychiatry in movies," The British Journal of Psychiatry, vol. 216, no. 6, 2020.

[7] T. Han, J. Zhang, Z. Zhang, G. Sun, L. Ye, H. Ferdinando, E. Alasaarela, T. Seppänen, X. Yu and S. Yang, "Emotion recognition and school violence detection from children speech," Journal on Wireless Communications and Networking, vol. 235, no. 2018, 2018.

[8] H. Yao and X. Hu, "A survey of video violence detection," Cyber-Physical Systems, 2021.

[9] I. P. Febin, K. Jayasree and P. T. Joy, "Violence detection in videos for an intelligent surveillance system using MoBSIFT and movement filtering algorithm," Pattern Analysis and Applications, vol. 23, p. 611–623, 2020.

[10] W. Song, D. Zhang, X. Zhao, J. Yu, R. Zheng and A. Wang, "A Novel Violent Video Detection Scheme Based on Modified 3D Convolutional Neural Networks," IEEE Access, vol. 7, pp. 39172-39179, 2019.

[11] A. Jain and D. K. V. A. J. a. D. K. Vishwakarma, "Deep NeuralNet For Violence Detection Using Motion Features From Dynamic Images," in 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India, 2020.

[12] A.-M. R. Abdali and R. F. Al-Tuma, "Robust Real-Time Violence Detection in Video Using CNN And LSTM," in 2019 2nd Scientific Conference of Computer Sciences (SCCS), Baghdad, Iraq, 2019.

[13] J. Mahmoodi and A. Salajeghe, "A classification method based on optical flow for violence detection," Expert Systems with Applications, vol. 127, pp. 121-127, 2019.

[14] K. Jani, M. Chaudhuri, H. Patel and M. Shah, "Machine learning in films: an approach towards automation in film censoring," J. of Data, Inf. and Manag, vol. 2, p. 55–64, 2020.

[15] D. J. Samuel, E. Fenil, G. Manogaran, G. Vivekananda, T. Thanjaivadivel, S. Jeeva and A. Ahilan, "Real time violence detection framework for football stadium comprising of big data analysis and deep learning through bidirectional LSTM," Computer Networks, vol. 151, pp. 191-200, 2019.

[16] K. Karisma, E. M. Imah and A. Wintarti, "Violence Classification Using Support Vector Machine and Deep Transfer Learning Feature Extraction," in 2021 International Seminar on Intelligent Technology and Its Applications (ISITIA), Surabaya, Indonesia, 2021.

[17] K. Deepak, L. Vignesh and S. Chandrakala, "Autocorrelation of gradients based violence detection in surveillance videos," ICT Express, vol. 6, no. 3, pp. 155-159, 2020.

[18] P. Wang, P. Wang and E. Fan, "Violence detection and face recognition based on deep learning," Pattern Recognition Letters, vol. 142, pp. 20-24, 2021.

[19] A. Sen and K. Deb, "Categorization of actions in soccer videos using a combination of transfer learning and Gated Recurrent Unit," ICT Express, 2021.

[20] F. Harrou, Y. Sun, A. S. Hering, M. Madakyaru and A. Dairi, "Chapter 7 - Unsupervised recurrent deep learning scheme for process monitoring," in Statistical Process Monitoring Using Advanced Data-Driven and Deep Learning Approaches, Elsevier, 2021, pp. 225-253.

[21] E. Ditsanthia, L. Pipanmaekaporn and S. Kamonsantiroj, "Video Representation Learning for CCTV-Based Violence Detection," in 2018 3rd Technology Innovation Management and Engineering Science International Conference (TIMES-iCON), Bangkok, Thailand, 2018.

[22] A. Nurhopipah and A. Harjoko, "Motion Detection and Face Recognition For CCTV Surveillance System," IJCCS (Indonesian Journal of Computing and Cybernetics Systems), vol. 12, no. 2, pp. 107-118, 2018.

[23] E. M. Imah, W. Jatmiko and T. Basaruddin, "Adaptive Multilayer Generalized Learning Vector Quantization (AMGLVQ) as new algorithm with integrating feature extraction and classification for Arrhythmia heartbeats classification," in 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Seoul, Korea, 2012.

[24] A. H. Masruroh, E. M. Imah and E. Rahmawati, "Classification of Emotional State Based on EEG Signal using AMGLVQ," Procedia Computer Science, vol. 157, pp. 552-559, 2019.

[25] W. Zhang and S. Xiang, "Face anti-spoofing detection based on DWT-LBP-DCT features," Signal Processing: Image Communication, vol. 89, 2020.

[26] J. Wang and Z. Du, "A method of processing color image watermarking based on the Haar wavelet," Journal of Visual Communication and Image Representation, vol. 64, 2019.

[27] R. Chatterjee and R. Halder, "Discrete Wavelet Transform for CNN-BiLSTM-Based Violence Detection," in Advances in Systems, Control and Automations: Select Proceedings of ETAEERE 2020, Singapore, 2021.

[28] F. Deeba, S. Kun, F. A. Dharejo and Y. Zhou, "Wavelet-Based Enhanced Medical Image Super Resolution," IEEE Access, vol. 8, pp. 37035-37044, 2020.

[29] R. Chatterjee and R. Halder, "Discrete Wavelet Transform for CNN-BiLSTM-Based Violence Detection," in Advances in Systems, Control and Automations: Select Proceedings of ETAEERE 2020, Singapore, 2021.

[30] J. Imran, B. Raman and A. S. Rajput, "Robust, efficient and privacy-preserving violent activity recognition in videos," in SAC '20: Proceedings of the 35th Annual ACM Symposium on Applied Computing, Brno Czech Republic, 2020.

[31] I. S. Gracia, O. D. Suarez, G. B. Garcia and T.-K. Kim, "Fast Fight Detection," PLoS ONE, vol. 10, no. 4, 2015.

[32] J. Panyavaraporn and P. Horkaew, "DWT/DCT-based Invisible Digital Watermarking Scheme for Video Stream," in 2018 10th International Conference on Knowledge and Smart Technology (KST), Chiang Mai, Thailand, 2018.

[33] D. Zhang, "Wavelet Transform," in Fundamentals of Image Data Mining, Cham, Springer, 2019, pp. 35-44.

[34] D. Popov, A. Gapochkin and A. Nekrasov, "An Algorithm of Daubechies Wavelet Transform in the Final Field When Processing Speech Signals," Electronics, vol. 7, no. 7, p. 120, 2018.

[35] D. Zhang, "Windowed Fourier Transform," in Fundamentals of Image Data Mining, Cham, Springer, 2019, pp. 25-34.

[36] S. A. Sumon, R. Goni, N. B. Hashem, T. Shahria and R. M. Rahman, "Violence Detection by Pretrained Modules with Di®erentDeep Learning Approaches," Vietnam Journal of Computer Science, vol. 7, no. 1, p. 19–40, 2020.

[37] C.-H. Demarty, C. Penet, M. Soleymani and G. Gravier, "VSD, a public dataset for the detection of violent scenes in movies: design, annotation, analysis and evaluation," Multimedia Tools and Applications, vol. 74, p. 7379–7404, 2015.

[38] V. Varuikhin and A. Levina, "Continuous Wavelet Transform Applications In Steganography," Procedia Computer Science, vol. 186, pp. 580-587, 2021.

[39] L. Kabbai, M. Abdellaoui and A. Douik, "Image classification by combining local and global features," The Visual Computer, vol. 35, p. 679–693, 2019.

Downloads

Published

2022-04-06

How to Cite

[1]
E. M. Imah, I. K. Laksono, K. Karisma, and A. Wintarti, “Detecting violent scenes in movies using Gated Recurrent Units and Discrete Wavelet Transform”, Register: Jurnal Ilmiah Teknologi Sistem Informasi, vol. 8, no. 2, pp. 94–103, Apr. 2022.

Issue

Section

Article