Multi-task learning model for detecting and filtering internet violent images for children

  • Kim Hoang Trung Le

Abstract

The Internet has emerged as an essential daily information
access, but exposing children to inappropriate content can impair their
early development. Existing content filtering methods exhibit limitations in accurately and efficiently detecting diverse inappropriate internet
content. In this paper, we propose a multi-task learning model for detecting and filtering violent images to provide safer online experiences.
The multi-task model is developed from the pre-trained lightweight base
model such as MobileNetv2 to enable proper integration within web
browser extensions. Pure training to detect violent images could raise
false alarms in the classification results when the landscape or object images don’t contain any human, hence we develop two joint learning tasks
such as detecting humans and detecting violent images simultaneously.
Our experiments demonstrate that the proposed multi-task approach
with binary rule achieves 98.5% accuracy, outperforming the single-task
model for detecting violent images by a margin. Thereafter, the multitask model is also integrated into the web extension to detect and filter
out violent images to prevent children from harmful content

Author Biography

Kim Hoang Trung Le

Le Kim Hoang Trung1, Nguyen Van Thanh Vinh1, Phan Le Viet Hung1, and
Nguyen Huu Nhat Minh1
The University of Danang, Vietnam - Korea University of Information and
Communication Technology
trunglkh.21it@vku.udn.vn, vinhnvt.21it@vku.udn.vn,
hungplv.21ad@vku.udn.vn, nhnmminh@vku.udn.vn

Published
2024-05-26