Learning based Facial Image Compression with semantic fidelity metric

NEUROCOMPUTING

卷:338

Article

Chen, Zhibo¹  He, Tianyu¹ 

[1] Univ Sci & Technol China, CAS Key Lab Technol Geospatial Informat Proc & Ap, Hefei, Anhui, Peoples R China

关键词: End-to-end;    Semantic metric;    Facial image compression;    Adversarial training;   

DOI  :  10.1016/j.neucom.2019.01.086

来源: Elsevier

【 摘 要 】

Surveillance and security scenarios usually require high efficient facial image compression scheme for face recognition and identification. While either traditional general image codecs or special facial image compression schemes only heuristically refine codec separately according to face verification accuracy metric. We propose a Learning based Facial Image Compression (LFIC) framework with a novel Regionally Adaptive Pooling (RAP) module whose parameters can be automatically optimized according to gradient feedback from an integrated hybrid semantic fidelity metric, including a successfully exploration to apply Generative Adversarial Network (GAN) as metric directly in image compression scheme. The experimental results verify the framework's efficiency by demonstrating performance improvement of 71.41%, 48.28% and 52.67% Bit Rate Saving separately over JPEG20 0 0, WebP and neural network-based codecs under the same face verification accuracy distortion metric. We also evaluate LFIC's superior performance gain compared with latest specific facial image codecs. Visual experiments also show some interesting insight on how LFIC can automatically capture the information in critical areas based on semantic distortion metrics for optimized compression, which is quite different from the heuristic way of optimization in traditional image compression algorithms. (C) 2019 Elsevier B.V. All rights reserved.

【 授权许可】

Free