Blurring Inappropriate Behavior Image for Digital Images and Videos Using Deep Learning Techniques
Article Sidebar
Main Article Content
Abstract
This research has developed a deep learning system for blurring images of inappropriate behavior. Blurring inappropriate images can be challenging for employees, as these pictures and clips are often widely published. Therefore, this paper presents a system that consists of three steps: training deep learning, detecting inappropriate behavior, and blurring the detected regions. The first step involves training the deep learning system using the Mask R-CNN model. In the second step, inappropriate behavior is detected using Mask R-CNN. Finally, in the last step, the detected regions are blurred using a Gaussian filter. The results of the evaluation showed that the system's performance in blurring images was assessed using metrics such as Accuracy, Precision, Recall, and F1 score, calculated from the Confusion Matrix. The metrics for the blurred images were found to be 0.72, 0.8, 0.86, and 0.83, respectively. For videos, the metrics were 0.88, 0.93, 0.92, and 0.93, respectively.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The content and information in articles published in the Journal of Advanced Development in Engineering and Science are the opinions and responsibility of the article's author. The journal editors do not need to agree or share any responsibility.
Articles, information, content, etc. that are published in the Journal of Advanced Development in Engineering and Science are copyrighted by the Journal of Advanced Development in Engineering and Science. If any person or organization wishes to publish all or any part of it or to do anything. Only prior written permission from the Journal of Advanced Development in Engineering and Science is required.
References
Bengio, Y. & Lecun, Y. (1998). Convolutional Networks for Images, Speech, and Time-Series. In Arbib, M. A. (Ed.). The Handbook of Brain Theory and Neural Networks (p. 255–258). Massachusetts: The MIT Press.
Girshick, R. (2015). Fast R-CNN. In 2015 IEEE International Conference on Computer Vision (p. 1440-1448). 11 – 18 December, 2015, Araucano Park, Chile.
Girshick, R., et al. (2014). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition (p. 580–587). 23 – 28 June, 2014, Columbus, Ohio, USA.
He, K. (2017). Mask R-CNN. In 2017 IEEE International Conference on Computer Vision (p. 2980–2988). 22 – 29 October, 2017, Venice, Italy.
Redmon, J. (2016). You Only Look Once: Unified, Real-Time Object Detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (p. 779 - 788). 26 June – 1 July, 2016, Las Vegas, NV, USA.
Wongta, P. (2017). Vision-Based Bus Route Number Reader, (Master thesis, Chulalongkorn University). (in Thai)
Sanuksan, J. & Surinta, O. (2019). Deep Convolutional Neural Networks for Plant Recognition in Natural Environment, Journal of Science and Technology Mahasarakham University, 38(2), 113–124. (in Thai)
Manokij, F. (2019). Thailand’s Precipitation Forecasting Using Deep Learning Approach, (Master thesis, Chulalongkorn University). (in Thai)
Yongying, N. (2019). A Deep Learning Approach on Road Detection from Unmanned Aerial Vehicle-Based Images in Rural Road Monitoring, (Master thesis, Naresuan University). (in Thai)
Rattanachot, P. (2019). Automated Plant Disease Detection using Drones and Deep Learning, (Master Thesis, Dhurakij Pundit University). (in Thai)
Posawang, P., et al. (2021). The Road Surface Anomalies Detection using Deep Convolutional Neural Networks with Transfer Learning Technique. Information Technology Journal, 17(1), 31-42. (in Thai)
Metkarunchit, T. & Charoenpojvajana, K. (2020). Detection of COVID-19 using Deep Learning with CT Scan Images. TNI Journal of Engineering and Technology, 8(2), 8-17. (in Thai)
Tipakorn, K. & Tanasai, S. (2021). Rice Image Segmentation using Deep Learning. In The 11th National and the 5th International PIM Conference (p.510 – 523). 16 July, 2021, Nonthaburi, Thailand. (in Thai)
Worasit, T., et al. (2022). Rice Bacterial Blight And Blast Diseases Recognition using Deep Learning Techniques. Khon Kaen Agriculture Journal, 50(1), 216-228. (in Thai)
Parinee, A., et al. (2022). Laser Pointer Control for Deep Learning Human Detection. Journal of Science and Technology Mahasaraknam University, 41(3), 151-163. (in Thai)
Saisangchan, U. (2022). Analysis of Lime Leaf Disease using Deep Learning. Journal of Applied Informatics and Technology, 4(1), 71-86. (in Thai)