Parallel Region-Based Deep Residual Networks for Face Hallucination

被引:8
|
作者
Lu, Tao [1 ]
Hao, Xiaohui [1 ]
Zhang, Yanduo [1 ]
Liu, Kai [2 ]
Xiong, Zixiang [3 ]
机构
[1] Wuhan Inst Technol, Sch Comp Sci & Engn, Hubei Key Lab Intelligent Robot, Wuhan 430073, Hubei, Peoples R China
[2] Beihang Univ, Sch Elect & Informat Engn, Beijing 100191, Peoples R China
[3] Texas A&M Univ, Dept Elect & Comp Syst Engn, College Stn, TX 77843 USA
基金
国家重点研发计划;
关键词
Face hallucination; face structural prior; region-based; parallel strategy; residual network; SUPERRESOLUTION;
D O I
10.1109/ACCESS.2019.2923023
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Face hallucination is a super-resolution algorithm specially designed to improve the resolution and quality of low-resolution (LR) input face images. Although a deep neural network offers an end-to-end mapping from LR to high-resolution (HR) images, most of the deep learning-based face hallucinations neglect the structure prior for face images. To utilize the highly structured facial prior, a parallel region-based deep residual network (PRDRN) was developed to predict the missing detailed information for accurate image reconstruction. Initially, the image is divided into multiple regions with the symmetry of face structures. Then, the sub-networks corresponding to multiple regions are trained in parallel. Finally, all reconstructed regions are combined to form the HR image. The experimental results on FEI, CASIA-Webface and CMU-MIT public face databases show that the proposed network outperforms other state-of-the-art approaches.
引用
收藏
页码:81266 / 81278
页数:13
相关论文
共 50 条
  • [1] FACE HALLUCINATION USING REGION-BASED DEEP CONVOLUTIONAL NETWORKS
    Lu, Tao
    Wang, Hao
    Xiong, Zixiang
    Jiang, Junjun
    Zhang, Yanduo
    Zhou, Huabing
    Wang, Zhongyuan
    [J]. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 1657 - 1661
  • [2] Region-based reconstruction for face hallucination
    Park, Jeong-Seon
    Lee, Junseak
    Lee, Seong-Whan
    [J]. ADVANCES IN MULTIMEDIA MODELING, PT 1, 2007, 4351 : 44 - 53
  • [3] Region-based Eigentransformation for Face Image Hallucination
    Hu, Yu
    Shen, Tingzhi
    Lam, Kin Man
    [J]. ISCAS: 2009 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-5, 2009, : 1421 - +
  • [4] Face Hallucination Based on Independent Residual Features
    Yan, Hua
    Sun, Jiande
    Du, Lina
    [J]. 2010 IEEE 10TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS (ICSP2010), VOLS I-III, 2010, : 1074 - +
  • [5] Region-based face detection
    Ayinde, O
    Yang, YH
    [J]. PATTERN RECOGNITION, 2002, 35 (10) : 2095 - 2107
  • [6] Graphic Logo Detection with Deep Region-based Convolutional Networks
    Li, Yuanyuan
    Shi, Qiuyue
    Deng, Jiangfan
    Su, Fei
    [J]. 2017 IEEE VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP), 2017,
  • [7] Semantic-Driven Face Hallucination Based on Residual Network
    Yu, Xiaoyuan
    Zhang, Langwen
    Xie, Wei
    [J]. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2021, 3 (02): : 214 - 228
  • [8] Region-Based Global Reasoning Networks
    Wang, Chuanming
    Fu, Huiyuan
    Ling, Charles X.
    Du, Peilun
    Ma, Huadong
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 12136 - 12143
  • [9] Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification
    Cao, Xiaoyu
    Gong, Neil Zhenqiang
    [J]. 33RD ANNUAL COMPUTER SECURITY APPLICATIONS CONFERENCE (ACSAC 2017), 2017, : 278 - 287
  • [10] Deep Neural Networks With Region-Based Pooling Structures for Mammographic Image Classification
    Shu, Xin
    Zhang, Lei
    Wang, Zizhou
    Lv, Qing
    Yi, Zhang
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2020, 39 (06) : 2246 - 2255