Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65170
Volume:
10 |
6 |
Jun 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Information Technology
Vidya Pratishthan's Kamalnayan Bajaj Institute of Engineering & Technology

Information Technology
Vidya Pratishthan's Kamalnayan Bajaj Institute of Engineering & Technology

Information Technology
Vidya Pratishthan's Kamalnayan Bajaj Institute of Engineering & Technology
Children are now much more exposed to animated content with violent sequences including fights, explosions, shoot-ings, and bloodshed due to the quick development of digital entertainment platforms. Children’s emotional and psychological conduct may be adversely affected by ongoing exposure to such damaging content. As a result, automatic identification of violent scenes in cartoon videos has grown in importance as a field of study for deep learning and computer vision. Using pretrained MobileNetV2 and Long Short-Term Memory (LSTM) networks, this study suggests an effective and lightweight approach for detecting cartoon violence. While the LSTM net-work records temporal connections between successive video frames for precise violence recognition, the suggested approach uses MobileNetV2 to extract deep spatial characteristics from cartoon frames using transfer learning. Video preprocessing, keyframe extraction, feature extraction, temporal learning, and multi-class violence classification are all part of the methodology.
KEYWORDS
The MobileNetV2-LSTM Framework that has been sug-gested will be capable of identifying scenes of violence in cartoon videos. The Framework has been tested with respect to accuracy, generalization and computational efficiency. The Framework will also help to moderate content and use filters associated with/controlled by the parent. Future work may include: real time use; and more accurate identifying through use of multiple sources of media (i.e. text, audio, video).
[1] N. F. Khan, S. U. Amin, Z. Jan and C. Yan, ”Detection of Violent Scenes in Cartoon Movies Using a Deep Learning Approach,” in IEEE Access, vol. 12, pp. 154080-154091, 2024 [2] Q. Zhang, Z. Duan, D. Xiang, Y. Yu, and J. Tian, “The effects of prosocial cartoon examples on children’s donating behavior,” Psychol. Res. Behav. Manage., vol. 14, pp. 1257–1268, Aug. 2021. [3] S. Gon¸calves, R. Ferreira, E. M. Concei¸c˜ao, C. Silva, P. P. P. Machado,E. Boyland, and A. Vaz, “The impact of exposure to cartoons promoting healthy eating on children’s food preferences and choices,” J. Nutrition Edu. Behav., vol. 50, no. 5, pp. 451 457, May 2018. [4] A. Drummond, J. D. Sauer, C. J. Ferguson, P. R. Cannon, and L. C. Hall, “Violent and non violent virtual reality video games: Influences on affect, aggressive cogni tion, and aggressive behavior. Two pre registered experiments,” J. Experim. Social Psychol., vol. 95, Jul. 2021, Art. no. 104119. [5] F. Craig, F. Tenuta, A. De Giacomo, A. Trabacca, and A. Costabile, “A systematic review of problematic video gameuseinpeoplewithautism spectrum disorders,” Res. Autism Spectr. Disorders, vol. 82, Apr. 2021, Art. no. 101726. [6] F. Parvin and S. Islam, “The impact of cartoon programs on children’s physical health, intelligence, behavior and activities,” Eur. J. Physiother apy Rehabil. Stud., vol. 1, no. 1, pp. 647–648, 2020. [7] P. Zhou, Q. Ding, H. Luo, and X. Hou, “Violent interaction detection in video based on deep learning,” J. Phys., Conf. Ser., vol. 844, Jun. 2017, Art. no. 012044. [8] M. Khan, M. A. Tahir, and Z. Ahmed, “Detection of violent content in cartoon videos using multimedia content detection techniques,” in Proc. IEEE 21st Int. Multi Topic Conf. (INMIC), Nov. 2018, pp. 1–5. [9] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst., vol. 25, 2012, pp. 1097–1105. [10] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
Publication Date
6/19/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...