Low-resolution and open-set face recognition via recursive label propagation based on statistical classification

被引:0
|
作者
Xue, Shan [1 ]
Zhu, Hong [1 ]
机构
[1] Xian Univ Technol, Fac Automat & Informat Engn, Xian 710048, Shaanxi, Peoples R China
基金
美国国家科学基金会;
关键词
Face recognition; open-set; low-resolution; deep learning; ReLPBSC; REPRESENTATION; POSE;
D O I
10.1142/S0219691319400022
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In video surveillance, the captured face images are usually suffered from low-resolution (LR), besides, not all the probe images have mates in the gallery under the premise that only a single frontal high-resolution (HR) face image per subject. To address this problem, a novel face recognition framework called recursive label propagation based on statistical classification (ReLPBSC) has been proposed in this paper. Firstly, we employ VGG to extract robust discriminative feature vectors to represent each face. Then we select the corresponding LR face in the probe for each HR gallery face by similarity. Based on the picked HR-LR pairs, ReLPBSC is implemented for recognition. The main contributions of the proposed approach are as follows: (i) Inspired by substantial achievements of deep learning methods, VGG is adopted to achieve discriminative representation for LR faces to avoid the super-resolution steps; (ii) the accepted and rejected threshold parameters, which are not fixed in face recognition, can be achieved with ReLPBSC adaptively; (iii) the unreliable subjects never enrolled in the gallery can be rejected automatically with designed methods. Experimental results in 16 x 16 pixels resolution show that the proposed method can achieve 86.64% recall rate while keeping 100% precision.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] CCFace: Classification Consistency for Low-Resolution Face Recognition
    Saadabadi, Mohammad Saeed Ebrahimi
    Malakshan, Sahar Rahimi
    Kashiani, Hossein
    Nasrabadi, Nasser M.
    2023 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS, IJCB, 2023,
  • [2] Towards open-set text recognition via label-to-prototype learning
    Liu, Chang
    Yang, Chun
    Qin, Hai-Bo
    Zhu, Xiaobin
    Liu, Cheng-Lin
    Yin, Xu-Cheng
    PATTERN RECOGNITION, 2023, 134
  • [3] Open-Set Face Recognition-Based Visitor Interface System
    Ekenel, Hazim K.
    Szasz-Toth, Lorant
    Stiefelhagen, Rainer
    COMPUTER VISION SYSTEMS, PROCEEDINGS, 2009, 5815 : 43 - 52
  • [4] Efficient Low-Resolution Face Recognition via Bridge Distillation
    Ge, Shiming
    Zhao, Shengwei
    Li, Chenyu
    Zhang, Yu
    Li, Jia
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 : 6898 - 6908
  • [5] Low-Resolution Face Recognition via Sparse Representation of Patches
    Zhuang, Liansheng
    Wang, Mengliao
    Yu, Wen
    Yu, Nenghai
    Qian, Yangchun
    PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON IMAGE AND GRAPHICS (ICIG 2009), 2009, : 200 - 204
  • [6] Low-Resolution Face Recognition via Convolutional Neural Network
    Ding, Chunhui
    Bao, Tianlong
    Karmoshi, Saleem
    Zhu, Ming
    2017 IEEE 9TH INTERNATIONAL CONFERENCE ON COMMUNICATION SOFTWARE AND NETWORKS (ICCSN), 2017, : 1157 - 1161
  • [7] OPEN-SET RECOGNITION VIA AUGMENTATION-BASED SIMILARITY LEARNING
    Esmaeilpour, Sepideh
    Shu, Lei
    Liu, Bing
    CONFERENCE ON LIFELONG LEARNING AGENTS, VOL 199, 2022, 199
  • [8] Open-set Text Recognition via Part-based Similarity
    Liu, Chang
    Yang, Chun
    Yin, Xu-Cheng
    Zidonghua Xuebao/Acta Automatica Sinica, 2024, 50 (10): : 1977 - 1987
  • [9] Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation
    Ge, Shiming
    Zhao, Shengwei
    Li, Chenyu
    Li, Jia
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (04) : 2051 - 2062
  • [10] CNN Classifier based Low-resolution Face Recognition Algorithm
    Rajput, Shyam Singh
    Arya, K., V
    2020 INTERNATIONAL CONFERENCE ON EMERGING FRONTIERS IN ELECTRICAL AND ELECTRONIC TECHNOLOGIES (ICEFEET 2020), 2020,