An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks

被引：18
|
作者：
Chen, Jun-Cheng [1 ]
Ranjan, Rajeev [1 ]
Kumar, Amit [1 ]
Chen, Ching-Hui [1 ]
Patel, Vishal M. [2 ]
Chellappa, Rama [1 ]
机构：
[1] Univ Maryland, College Pk, MD 20742 USA
[2] Rutgers State Univ, New Brunswick, NJ 08903 USA
来源：
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW) | 2015年
关键词：
D O I：
10.1109/ICCVW.2015.55
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, we present an end-to-end system for the unconstrained face verification problem based on deep convolutional neural networks (DCNN). The end-to-end system consists of three modules for face detection, alignment and verification and is evaluated using the newly released IARPA Janus Benchmark A (IJB-A) dataset and its extended version Janus Challenging set 2 (JANUS CS2) dataset. The IJB-A and CS2 datasets include real-world unconstrained faces of 500 subjects with significant pose and illumination variations which are much harder than the Labeled Faces in the Wild (LFW) and Youtube Face (YTF) datasets. Results of experimental evaluations for the proposed system on the IJB-A dataset are provided.
引用
收藏
页码：360 / 368
页数：9
相关论文
共 50 条
  • [31] A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images
    Pang, Shuchao
    Yu, Zhezhou
    Orgun, Mehmet A.
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2017, 140 : 283 - 293
  • [32] End-to-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation
    Yang, Wei
    Ouyang, Wanli
    Li, Hongsheng
    Wang, Xiaogang
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 3073 - 3082
  • [33] SampleCNN: End-to-End Deep Convolutional Neural Networks Using Very Small Filters for Music Classification
    Lee, Jongpil
    Park, Jiyoung
    Kim, Keunhyoung Luke
    Nam, Juhan
    APPLIED SCIENCES-BASEL, 2018, 8 (01):
  • [34] End-to-End Training of Deep Neural Networks in the Fourier Domain
    Fulop, Andras
    Horvath, Andras
    MATHEMATICS, 2022, 10 (12)
  • [35] An End-to-End Steel Strip Surface Defects Recognition System Based on Convolutional Neural Networks
    Yi, Li
    Li, Guangyao
    Jiang, Mingming
    STEEL RESEARCH INTERNATIONAL, 2017, 88 (02) : 176 - 187
  • [36] End-To-End Vessel Plate Number Detection and Recognition Using Deep Convolutional Neural Networks and LSTMs
    Huang, Sizhe
    Xu, Huosheng
    Xia, Xuezhi
    Zhang, Yi
    2018 11TH INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DESIGN (ISCID), VOL 1, 2018, : 195 - 199
  • [37] An end-to-end deep learning system for requirements classification using recurrent neural networks
    AlDhafer, Osamah
    Ahmad, Irfan
    Mahmood, Sajjad
    INFORMATION AND SOFTWARE TECHNOLOGY, 2022, 147
  • [38] Face verification based on deep Bayesian convolutional neural network in unconstrained environment
    Mengjie Zhao
    Bin Song
    Yue Zhang
    Hao Qin
    Signal, Image and Video Processing, 2018, 12 : 819 - 826
  • [39] Face verification based on deep Bayesian convolutional neural network in unconstrained environment
    Zhao, Mengjie
    Song, Bin
    Zhang, Yue
    Qin, Hao
    SIGNAL IMAGE AND VIDEO PROCESSING, 2018, 12 (05) : 819 - 826
  • [40] End-to-end Convolutional Neural Networks for Sound Event Detection in Urban Environments
    Zinemanas, Pablo
    Cancela, Pablo
    Rocamora, Martin
    PROCEEDINGS OF THE 24TH CONFERENCE OF OPEN INNOVATIONS ASSOCIATION (FRUCT), 2019, : 533 - 539
12345