Journal of Industrial Convergence (산업융합연구)

DAEHAN Society of Industrial Management (대한산업경영학회)
권호 표지
DOI QR코드

DOI QR Code

A Survey on Deep Learning based Face Recognition for User Authentication

사용자 인증을 위한 딥러닝 기반 얼굴인식 기술 동향

  • Mun, Hyung-Jin (Dept. of Information & Communication Engineering, Sungkyul University) ;
  • Kim, Gea-Hee (Dept. of Computer Science & Engineering, Gyeongnam National University of Science and Technology)
  • 문형진 (성결대학교 정보통신공학과) ;
  • 김계희 (경남과학기술대학교 컴퓨터 메카트로닉스 공학과)
  • Received : 2019.08.21
  • Accepted : 2019.09.20
  • Published : 2019.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Object recognition distinguish objects which are different from each other. But Face recognition distinguishes Identity of Faces with Similar Patterns. Feature extraction algorithm such as LBP, HOG, Gabor is being replaced with Deep Learning. As the technology that identify individual face with machine learning using Deep Learning Technology is developing, The Face Recognition Technology is being used in various field. In particular, the technology can provide individual and detailed service by being used in various offline environments requiring user identification, such as Smart Mirror. Face Recognition Technology can be developed as the technology that authenticate user easily by device like Smart Mirror and provide service authenticated user. In this paper, we present investigation about Face Recognition among various techniques for user authentication and analysis of Python source case of Face recognition and possibility of various service using Face Recognition Technology.

차이가 나는 물체를 구별하는 물체인식과 달리, 얼굴인식은 유사한 패턴을 가진 얼굴의 Identity를 구별한다. 이에 따라 LBP, HOG, Gabor과 같은 특징 추출 알고리즘이 딥러닝 기반으로 대체되고 있다. 딥 러닝 기술을 활용하여 머신러닝으로 얼굴을 식별할 수 있는 기술이 발전하면서 다양한 분야에서 얼굴인식 기술이 활용되고 있다. 특히, 금융 거래 외에도 사용자 식별이 필요한 다양한 오프라인 환경에서 활용되어 세밀하고 개인에 적합한 서비스가 제공될 수 있다. 얼굴 인식 기술은 스마트 미러와 같은 장치를 통해 손쉽게 사용자 인증을 하고, 식별이 된 사용자에게 서비스를 제공할 수 있는 기술로 발전할 수 있다. 본 논문에서는 사용자 인증의 다양한 기법 중에서 얼굴인식 기술에 대한 조사 및 파이썬으로 작성된 얼굴인식 사례 소스 분석과 얼굴인식 기술을 활용한 다양한 서비스의 가능성을 제시하고자 한다.

Keywords

References

  1. H. J. Mun. (2019). A Study on the User Identification and Authentication in the Smart Mirror in Private. Journal of Convergence for Information Technology, 9(7), 100-105. DOI : 10.22156/CS4SMB.2019.9.7.100
  2. H. J. Mun. (2018). Biometric Information and OTP based on Authentication Mechanism using Blockchain. Journal of Convergence for Information Technology, 8(3), 85-90. DOI : 10.22156/CS4SMB.2018.8.3.085
  3. H. J. Moon, S. H. Kim (2013). Face Recognition : A Survey. Korea Information Processing Society Review, 20(3), 14-23.
  4. T. Horiuchi, T. Hada (2013). A complementary study for the evaluation of face recognition technology. 2013 47th International Carnahan Conference on Security Technology (ICCST), pp. 1-5.
  5. S. Xie, S. Shan, X. Chen & J. Chen (2010). Fusing Local Patterns of Gabor Magnitude and Phase for Face Recognition. IEEE Transactions on Image Processing, 19(5), 1349-1361. https://doi.org/10.1109/TIP.2010.2041397
  6. Y. C. Hwang, H. J. Mun, J. W. Lee. (2015). Face Recognition System Technologies for Authentication System - A Survey. Journal of Convergence for Information Technology, 5(3), 9-13. https://doi.org/10.22156/CS4SMB.2015.5.3.009
  7. J. Shin, Z. Liu, C. M. Kim & H. J. Mun. (2018). Writer identification using intra-stroke and inter-stroke information for security enhancements in P2P systems. Peer-to-Peer Networking and Applications, 11(6), 1166-1175. DOI : 10.1007/s12083-017-0606-0
  8. H. S. Choi, Y. H. Cho. (2019). Analysis of Security Problems of Deep Learning Technology. Journal of the Korea Convergence Society, 10(5), 9-16. DOI : 10.15207/JKCS.2019.10.5.009
  9. ETRI. (2016). Trends on Distributed Frameworks for Deep Learning, Electronics and Telecommunications Trends, 31(3), 131-141. https://ettrends.etri.re.kr/ettrends/159/0905002137/0905002137.html
  10. Naver. https://developers.naver.com/products/clova/face/
  11. Kakao. https://vision-api.kakao.com/
  12. Microsoft. https://azure.microsoft.com/ko-kr/services/cognitive-services/face/
  13. H. I. Kim, J. Y. Moon & J. Y. Park. (2018). Research Trends for Deep Learning-Based High-Performance Face Recognition Technology, Electronics and Telecommunications Trends, 33(4), 43-53. DOI : 10.22648/ETRI.2018.J.330405
  14. S. H. Lee. (2018). A Method for Determining Face Recognition Suitability of Face Image. JKAIS,19(11), 295-302.
  15. Github. https://github.com/kairess/simple_face_recognition