Face Detection Algorithm in Classroom Scene Based on Deep Learning

EasyChair Preprint 14826

Abstract

As informatization progresses in education, the application of artificial intelligence technology in the field of education is increasing day by day. Although some breakthroughs have been made, the application in specific scenes (such as classroom scenes) faces many difficulties, such as small target detection, severe occlusion, and so on. We propose a target detection algorithm based on video data for the classroom scene, which combines the optical flow information to improve the accuracy and alleviate the impact of occlusion. We also put forward the counting method suitable for classroom scenes, which can be used as the evaluation standard of attendance rate, head-up rate, and other indicators in classroom quality evaluation.

Keyphrases: face detection, optical flow method, target detection, video analysis

@booklet{EasyChair:14826,
  author    = {Yi Zhang and Chongwen Wang},
  title     = {Face Detection Algorithm in Classroom Scene Based on Deep Learning},
  howpublished = {EasyChair Preprint 14826},
  year      = {EasyChair, 2024}}