TY - GEN
T1 - An End-to-End Face Compression and Recognition Framework Based on Entropy Coding Model
AU - Lei, Bo
AU - Liang, Feng
AU - Fu, Haisheng
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/4/24
Y1 - 2021/4/24
N2 - 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.
AB - 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.
KW - deep learning
KW - entropy coding
KW - face recognition
KW - image compression
UR - https://www.scopus.com/pages/publications/85107657716
U2 - 10.1109/ICCCBDA51879.2021.9442596
DO - 10.1109/ICCCBDA51879.2021.9442596
M3 - 会议稿件
AN - SCOPUS:85107657716
T3 - 2021 IEEE 6th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2021
SP - 450
EP - 454
BT - 2021 IEEE 6th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th IEEE International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2021
Y2 - 24 April 2021 through 26 April 2021
ER -