DOI QR코드

DOI QR Code

Design and Implementation of Visitor Access Control System using Deep learning Face Recognition

딥러닝 얼굴인식 기술을 활용한 방문자 출입관리 시스템 설계와 구현

  • Heo, Seok-Yeol (Dept. of IT Engineering & Application, Pusan National University) ;
  • Kim, Kang Min (Dept. of IT Engineering & Application, Pusan National University) ;
  • Lee, Wan-Jik (Dept. of IT Engineering & Application, Pusan National University)
  • 허석렬 (부산대학교 IT응용공학과) ;
  • 김강민 (부산대학교 IT응용공학과) ;
  • 이완직 (부산대학교 IT응용공학과)
  • Received : 2021.01.19
  • Accepted : 2021.02.20
  • Published : 2021.02.28

Abstract

As the trend of steadily increasing the number of single or double household, there is a growing demand to see who is the outsider visiting the home during the free time. Various models of face recognition technology have been proposed through many studies, and Harr Cascade of OpenCV and Hog of Dlib are representative open source models. Among the two modes, Dlib's Hog has strengths in front of the indoor and at a limited distance, which is the focus of this study. In this paper, a face recognition visitor access system based on Dlib was designed and implemented. The whole system consists of a front module, a server module, and a mobile module, and in detail, it includes face registration, face recognition, real-time visitor verification and remote control, and video storage functions. The Precision, Specificity, and Accuracy according to the change of the distance threshold value were calculated using the error matrix with the photos published on the Internet, and compared with the results of previous studies. As a result of the experiment, it was confirmed that the implemented system was operating normally, and the result was confirmed to be similar to that reported by Dlib.

1,2인 가구가 꾸준하게 늘어나고 있는 추세에 비어 있는 시간대에 집을 방문하는 외부인이 누구인지 확인하고 싶은 요구가 증가하고 있다. 얼굴인식 기술은 많은 연구를 통해 여러 가지 모델이 제안되었는데 OpenCV의 Harr Cascade와 Dlib의 Hog가 대표적인 오픈소스 모델이다. 두 모델은 사용 환경에 따른 장단점을 가지고 있는데, 본 연구에서 초점을 둔 실내 현관 앞과 제한된 거리에서는 Dlib의 Hog가 강점을 가진다. 본 논문에서는 딥러닝 오픈 소스인 Dlib에 기반을 둔 얼굴인식 방문자 출입관리 시스템을 설계하고 구현하였다. 전체 시스템은 프론트 모듈과 서버모듈, 모바일모듈로 구성되며 세부적으로는 얼굴등록, 얼굴인식, 실시간 방문자 확인 및 원격제어, 동영상 저장 기능을 포함한다. 인터넷에서 공개된 사진을 이용하여 거리임계 값의 변화에 따른 정밀도, 특이도, 정확도를 구하고 선행연구 결과와 비교하였다. 실험 결과 구현된 시스템이 정상적으로 동작하는 것을 확인 하였으며 Dlib에서 보고한 것과 비슷한 결과를 보이는 것을 확인 하였다.

Keywords

References

  1. Kang, Ji-Hyon.(2019). Fear of Crime among One-person Households. Korean Crime Victimization Survey, 15(4), 22-54. DOI: 10.25023/kapsa.15.4.2019.02.23
  2. Kim, Jong Yun.(2019). G. D. Hong & H. K. Kim. (2016). A Study on the Effect of Different Types of Housing on the Burglary and the Preventive Effect of Crime Prevention. The Journal of Police Science, 19(4), 111-131. DOI:10.22816/polsci.2019.19.4.005.
  3. Hwang Ji-Tae. (2004). A Study on Target Selection of Burglars, Robbers and Thieves. Korean Institute of Criminology, 17-247. UCI(KEPA): I410-ECN-0101-2012-364-003835478
  4. Kang Yong gil and Cho Jun Taek. (2010). The research for Burglary Prevention Measures through Criminal Behavior Analysis. The Journal of Police Science, 10(1), 185-212. UCI(KEPA): I410-ECN-0101-2017-360-001374598
  5. OpenCV Libary. (2020). https://github.com/opencvopencv.
  6. Dlib C++ Library. (2020). OpenCV Libary. (2020). http://dlib.net/.
  7. Vikas Gupta. (2018). Face Detection-OpenCV, Dlib and Deep Learning(C++/Python). https://learnopencv.com/face-detection-opencv-dlib-and-deep-learning-c-python/.
  8. Martin Krasser. (2018). Deep face recognition with Keras, Dlib and OpenCV. http://krasserm.github.io/2018/02/07/deep-face-recognition/.
  9. Alvin Prayuda. (2018). Performance Showdown of Publicly Available Face Detection Model. https://medium.com/nodeflux/performance-showdown-of-publicly-available-face-detection-model-7c725747094a
  10. Sang-Young Park, Hwa-Young Kang, Kang-Hee Lee. (2019). Design and Implementation of an OpenCV-based Digital Doorlock. Proceedings of the Korean Society of Computer Information Conference 27(2), 321-324.
  11. Se-Yeol Rhyou, Hye-Jin Kim and Kyung-Ae Cha. (2019). Development of Access Management System based on Face Recognition using ResNet. Journal of Korea Multimedia Society, 22(8), 823-831. DOI:10.9717/kmms.2019.22.8.823
  12. Bu-Yeol Park, Eun-Jeong Jin, Boon-Giin Lee, Su-Min Lee. (2018). Establishment of electronic attendance using PCA recognition. Journal of the Institute of Convergence Signal Processing, 19(4), 174-179.
  13. Kisu OK, Dongwoo Kwon, Hyeonwoo Kim, Donghyeok An, Hongtaek Ju. (2017). Development of a Visitor Recognition System Using Open APIs for Face Recogmition. KIPS Transactions on Computer and Communication Systems. 6(4), 169-178. https://doi.org/10.3745/KTCCS.2017.6.4.169
  14. Jin-Suk Bang. (2020). Face recognition attendance management system through Raspberry Pi. KIICE 2020. 24(1), 373-375. UCI(KEPA) : I410-ECN-0101-2020-004-000906492.
  15. Icons8 Blog. (2020). Generated Photos:100,000 Free AI Generated Faces for Your Designs. https://icons8.com/articles/ai-generated-faces/.