Share Email Print

Proceedings Paper

Method of student identification through college classroom surveillance videos using deep learning features and label propagation
Author(s): Bo Sun; Bojie Rong; Jun He
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

For education or management, it is often necessary to identify students with their identification (ID) photos through the surveillance videos of the college classrooms. This is a typical application of ID photo based single-sample per-person (SSPP-ID) face recognition. After analyzing the main challenges, we propose a framework by combining deep learning method and label propagation algorithm together. It is composed of three sequential steps: the first step aims to partition the face image into several patches and get an unbalanced-patch based feature using ConvNets; In the second step, we select a few key-frames by using the log-likelihood ratio calculated by the Joint Bayesian model; The last step uses label propagation algorithm to propagate the labels from the key frames to the whole video by simultaneously incorporating constraints in temporal and feature spaces. The performance of the proposed method is evaluated on Movie Trailer Face Dataset and practical college class surveillance videos. Experiments with these challenging datasets validate the utility of the proposed method.

Paper Details

Date Published: 24 October 2017
PDF: 10 pages
Proc. SPIE 10462, AOPC 2017: Optical Sensing and Imaging Technology and Applications, 104622L (24 October 2017); doi: 10.1117/12.2284886
Show Author Affiliations
Bo Sun, Beijing Normal Univ. (China)
Bojie Rong, Beijing Normal Univ. (China)
Jun He, Beijing Normal Univ. (China)

Published in SPIE Proceedings Vol. 10462:
AOPC 2017: Optical Sensing and Imaging Technology and Applications
Yadong Jiang; Haimei Gong; Weibiao Chen; Jin Li, Editor(s)

© SPIE. Terms of Use
Back to Top