Skip to main navigation Skip to search Skip to main content

Improving the face recognition system by hybrid image preprocessing

  • Harbin Institute of Technology Shenzhen
  • Hunan University

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

Abstract

In this paper we present a framework for improving face recognition system that have several stages. Some improvements of every stage are very important to the recognition results. Driven by this intuition, we proposed a novel scheme that gives the system a better performance. The scheme including dataset augment for learning, especially for big data requirement of deep learning. Enhancing the image contrast ratio and rotate the image for several angles that can improve the detection accuracy. Then, cropping the face in appropriate area for feature extraction and getting the optimal feature vector for face recognition at last.

Original languageEnglish
Title of host publication6th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, IEEE-CYBER 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages442-447
Number of pages6
ISBN (Electronic)9781509027323
DOIs
StatePublished - 22 Sep 2016
Externally publishedYes
Event6th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, IEEE-CYBER 2016 - Chengdu, China
Duration: 19 Jun 201622 Jun 2016

Publication series

Name6th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, IEEE-CYBER 2016

Conference

Conference6th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, IEEE-CYBER 2016
Country/TerritoryChina
CityChengdu
Period19/06/1622/06/16

Keywords

  • deep learning
  • face recognition
  • framwork
  • preprocessing

Fingerprint

Dive into the research topics of 'Improving the face recognition system by hybrid image preprocessing'. Together they form a unique fingerprint.

Cite this