An End-to-End Face Compression and Recognition Framework Based on Entropy Coding Model

  • Bo Lei
  • , Feng Liang
  • , Haisheng Fu

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

2 Scopus citations

Abstract

Recent years, more and more image/video data were produced, which brings great challenge to data storage and transmission. For face recognition and video surveillance scenario, images/videios need to be compressed and transmitted to intelligent back end for analysis. While general image codecs only extract the feature towards pixel or perceptual similarity, ignoring the Rate-Accuracy performance. In this paper, we proposed an learned end-to-end face compression framework based on entropy coding model, jointly optimize face recognition and image compression performance. Compared with traditional codings, such as JPEG and JPEG2000, better Rate-Accuracy and Rate-Distrotion performance can be achieved by the proposed scheme in LFW(Labeled Faces in the Wild) dataset, especially at low bit rate.

Original languageEnglish
Title of host publication2021 IEEE 6th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages450-454
Number of pages5
ISBN (Electronic)9780738105338
DOIs
StatePublished - 24 Apr 2021
Event6th IEEE International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2021 - Chengdu, China
Duration: 24 Apr 202126 Apr 2021

Publication series

Name2021 IEEE 6th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2021

Conference

Conference6th IEEE International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2021
Country/TerritoryChina
CityChengdu
Period24/04/2126/04/21

Keywords

  • deep learning
  • entropy coding
  • face recognition
  • image compression

Fingerprint

Dive into the research topics of 'An End-to-End Face Compression and Recognition Framework Based on Entropy Coding Model'. Together they form a unique fingerprint.

Cite this