Comparative Study on Face Detection by GPU, CPU and OpenCV

被引:1
作者
Patidar, Sanjay [1 ]
Singh, Upendra [1 ]
Patidar, Ashish [1 ]
Munsoori, Riyaz Ali [1 ]
Patidar, Jyoti [1 ]
机构
[1] Delhi Technol Univ, Dept Comp Engn, Delhi 110042, India
来源
SECOND INTERNATIONAL CONFERENCE ON COMPUTER NETWORKS AND COMMUNICATION TECHNOLOGIES, ICCNCT 2019 | 2020年 / 44卷
关键词
Face detection; CUDA; GPU; Integral image; Open CV; Cloud;
D O I
10.1007/978-3-030-37051-0_77
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Optimization of processes and functions on Software side or on Hardware side are constantly remaining under the research consideration. Optimization can decrease the average time taken by a functional element to complete a particular task. Space-Time Complexity of various algorithms has been determined. These algorithms are widely used in the real-time systems. One of the algorithms is Face detection Algorithm. This project focuses on finding the easiest way of implementing the algorithm so that it can work in real time. In this comparative study, the Viola Jones Algorithm for Face Detection is implemented in 4 forms - CPU, Multi-threaded CPU, OpenCV and GPU using CUDA may be on cloud. The Algorithm is tested over Face Detection Dataset by FDDB and the results are framed on a graph to get the comparison among the methods used. This research project also discusses the limitations, future scope and implementation of the algorithm in real-time video streaming in the most efficient way.
引用
收藏
页码:686 / 696
页数:11
相关论文
共 9 条
  • [1] [Anonymous], 2014, INT J COMPUT SCI INF
  • [2] Kizuna H, 2018, INT S COMP NETW WORK
  • [3] Kizuna H., 2017, 2017 5 INT S COMP NE
  • [4] Lienhart R, 2002, IEEE IMAGE PROC, P900
  • [5] Pan Z., 2017, ADV INF TECHN EL AUT
  • [6] Sony, FELICA CONT OFF SEC
  • [7] Rapid object detection using a boosted cascade of simple features
    Viola, P
    Jones, M
    [J]. 2001 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2001, : 511 - 518
  • [8] Robust real-time face detection
    Viola, P
    Jones, MJ
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 57 (02) : 137 - 154
  • [9] Wang Y., 2012, J HUNAN U, V6, P128