Face occlusion detection based on multi-task convolution neural network

Yizhang Xia, Bailing Zhang, Frans Coenen

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

32 Citations (Scopus)

Abstract

With the rise of crimes associated with ATM, security reinforcement by surveillance techniques has been in high agenda for both academia and industries. Though cameras are generally installed in ATMs to capture the facial images of users, the function is only limited to recording for follow-up criminal investigations, which could become useless when a criminal's face is occluded. Therefore, face occlusion detection has become very important to prevent crimes connected with ATMs. Traditional approaches to solve the problem typically consist of a succession of steps such as localization, segmentation, feature extraction and recognition. This paper proposes robust and effective facial occlusion detection based on convolutional neural networks (ConvNets) with multi-task learning. Covering of different facial parts, namely, left eye, right eye, nose and mouth, can be predicted by the multi-task CNN. In comparison with previous approaches, CNN is optimal from the system point of view as the design is based on end-to-end principle and the model operates directly on the image pixels. We created a large scale face occlusion database, consisting of over fifty thousand images, with annotated facial parts. Experimental results revealed that the proposed method is extremely effective.

Original languageEnglish
Title of host publication2015 12th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2015
EditorsZhuo Tang, Jiayi Du, Shu Yin, Renfa Li, Ligang He
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages375-379
Number of pages5
ISBN (Electronic)9781467376822
DOIs
Publication statusPublished - 13 Jan 2016
Event12th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2015 - Zhangjiajie, China
Duration: 15 Aug 201517 Aug 2015

Publication series

Name2015 12th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2015

Conference

Conference12th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2015
Country/TerritoryChina
CityZhangjiajie
Period15/08/1517/08/15

Keywords

  • ATM
  • component
  • convolusional neurol network
  • deep learning
  • face occlusion detection
  • multi-task learning

Fingerprint

Dive into the research topics of 'Face occlusion detection based on multi-task convolution neural network'. Together they form a unique fingerprint.

Cite this