WhoAreYou (WAY): A Mobile CUDA Powered Picture ID Card Recognition System

被引:3
|
作者
Montella, Raffaele [1 ]
Petrosino, Alfredo [1 ]
Santopietro, Vincenzo [1 ]
机构
[1] Univ Naples Parthenope, Dept Sci & Technol, Naples, Italy
基金
欧盟地平线“2020”;
关键词
Cloud computing; Neural network; Deep learning; Face matching; GPGPUS;
D O I
10.1007/978-3-319-70742-6_35
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
The paper reports a novel cloud based approach for image matching between high-resolution images of faces and low resolution images of ID Cards. We design our application matching the mobile cloud computing design guidelines with the use of CUDA kernel invocation from regular mobile devices (devices that naively don't support CUDA GPGPUs) as a novel contribution. Face matching is performed by the OpenFace deep neural network, which evaluates pre-processed images in cloud, whilst pre-processing is done on mobile device. To test our system, we built an image dataset of 30 subject caputeres in 10 different poses, denoised to reduce any traces of stamps or watermark on the ID cards, mixed to the well known ORL and LFW datasets.
引用
下载
收藏
页码:375 / 382
页数:8
相关论文
共 3 条
  • [1] ID Card Identification System based on Image Recognition
    Fang, Xuwei
    Fu, Xiaowei
    Xu, Xin
    PROCEEDINGS OF THE 2017 12TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA), 2017, : 1488 - 1492
  • [2] A Recognition System for Farm Produce ID Card Image Based on Virtual Instruments
    Qian Ji
    Zhou Juan
    PROCEEDINGS OF 2008 INTERNATIONAL CONFERENCE ON INFORMATIONIZATION, AUTOMATION AND ELECTRIFICATION IN AGRICULTURE, 2008, : 25 - +
  • [3] An Improved Design and Implementation of Chinese Name card recognition system on mobile Devices
    Cui, Chi
    IIH-MSP: 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Proceedings, 2006, : 313 - 316