基于Storm的大容量实时人脸检索系统
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Large-Scale Real-Time Face Retrieval System Based on Storm
  • 作者:王晨曦 ; 范春晓 ; 吴岳辛
  • 英文作者:WANG Chen-Xi;FAN Chun-Xiao;WU Yue-Xin;School of Electronic Engineering,Beijing University of Posts and Telecommunications;
  • 关键词:人脸检索 ; 大容量 ; Storm ; 实时
  • 英文关键词:face retrieval;;large-scale;;Storm;;real-time
  • 中文刊名:XTYY
  • 英文刊名:Computer Systems & Applications
  • 机构:北京邮电大学电子工程学院;
  • 出版日期:2019-03-15
  • 出版单位:计算机系统应用
  • 年:2019
  • 期:v.28
  • 语种:中文;
  • 页:XTYY201903013
  • 页数:6
  • CN:03
  • ISSN:11-2854/TP
  • 分类号:95-100
摘要
针对公共安全领域能够获取的人脸图像数据急速增长,传统的人工方式辨别人物身份工作量大、实时性差、准确度低,本文设计了一种大容量实时人脸检索系统.该系统通过Storm分布式平台实现人脸抓拍图像的实时存储与检索,通过HBase分布式存储系统实现大容量非结构化人脸数据的存储与维护.多组实验结果表明,该系统具有良好的加速比,在大容量人脸图像数据检索场景下具有良好的可扩展性和实时性.
        The face image data that can be obtained in the field of public security has grown rapidly.The traditional manual method to identify people has large workload,poor real-time performance,and low accuracy.This study designs a large-scale real-time face retrieval system.The system implements the real-time storage and retrieval of captured face images through the distributed platform Storm,and implements the storage and maintenance of large-scale unstructured face data through the distributed storage system HBase.The results of multiple experiments show that the system has a good speedup,good scalability,and real-time performance in the application scenarios of large-scale face image data retrieval.
引文
1王倩,谭永杰,秦杰,等.基于Hadoop分布式平台的海量图像检索.南京理工大学学报,2017, 41(4):442-447.
    2陈雯柏,黄至铖,刘琼.一种基于P稳定局部敏感哈希算法的相似人脸检索系统设计.智能系统学报,2017, 12(3):392-396.
    3顾志松,沈春锋,姚文韬,等.高清人像抓拍检索系统的设计与实现.控制工程,2015, 22(S1):68-71.
    4陈新荃,陈晓东,蒋林华.基于Spark平台的人脸图像检索系统.计算机工程,2018,44(2):251-256.
    5 Cheng WC, Qian J, Zhao ZC, et al. Large scale cross-media data retrieval based on hadoop. Proceedings of the 2015 11th International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness. Taipei, China.2015. 133-138.
    6朱珊,艾丽华.基于Hadoop的大规模图像存储与检索.计算机与现代化,2017,(6):61-66, 83.
    7 Premchaiswadi W, Tungkatsathan A, Intarasema S, et al.Improving performance of content-based image retrieval schemes using Hadoop MapReduce. Proceedings of 2013International Conference on High Performance Computing&Simulation. Helsinki, Finland. 2013. 615-620.
    8 Uttarwar D,Agarwal A, Kadiwar R, et al. Distributed content based image search engine using hadoop framework.Proceedings of 2017 International Conference on Communication and Signal Processing. Chennai, India. 2017.1706-1710.
    9 Sabarad AK, Kankudti MH, Meena SM, et al. Color and texture feature extraction using apache hadoop framework.Proceedings of 2015 International Conference on ComputingCommunication Control and Automation. Pune, India. 2015.585-588.
    10 Tungkasthan A, Premchaiswadi W. A parallel processing framework using MapReduce for content-based image retrieval. Proceedings of 2013 Eleventh International Conference on ICT and Knowledge Engineering. Bangkok.2013. 1-6.
    11 Hedjazi MA, Kourbane I, Gene Y, et al. A comparison of Hadoop, Spark and Storm for the task of large scale image classification. 2018 26th Signal Processing and Communications Applications Conference. Izmir, Turkey.2018. 1-4.[doi:10.1109/SIU.2018.8404688]
    12 Apache Software Foundation. Apache HBase. https://hbase.apache.org/.[2018-08-20]
    13 Visual Information Processing and Learning(VIPL)group.SeetaFace. https://github.com/seetaface/SeetaFaceEngine.[2018-08-20]
    14 Apache Software Foundation. Apache storm. http://storm.apache.org/.[2018-08-20]
    15 Huang GB, Ramesh M, Berg T, et al. Labeled faces in the wild:A database for studying face recognition in unconstrained environments. Workshop on Faces in RealLife Images:Detection, Alignment, and Recognition. Marseille,France,2008. Inria-00321923.
    16朱为盛,王鹏.基于Hadoop云计算平台的大规模图像检索方案.计算机应用,2014, 34(3):695-699.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700