한국전자통신학회논문지 (The Journal of the Korea institute of electronic communication sciences)

한국전자통신학회 (Korea Institute of Electronic Communication Science)
권호 표지
DOI QR코드

DOI QR Code

딥러닝 합성곱 신경망을 이용한 효율적인 홍채인식

Efficient Iris Recognition using Deep-Learning Convolution Neural Network

  • 최광미 (조선대학교 sw중심대학사업단) ;
  • 정유정 (조선대학교 sw중심대학사업단)
  • 투고 : 2020.04.09
  • 심사 : 2020.06.15
  • 발행 : 2020.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문은 홍채영상의 이동불변의 특징값 을추출에 탁월한 고차 국소 자동 상관함수를 적용하여 25개의 특징 값을 입력 값으로 적용한 일반적인 HOLP 신경망에 특징 값 25개의 평균값을 추가한 개선된 HOLP 신경망을 구현하여 인식률을 확인하여 보았다. 종류가 상이한 딥러닝 구조들과 비교하였을 때 음성과 영상분야에서 탁월한 성능을 보이는 Back-Propagation 신경망과 특징 추출기와 분류기를 통합한 합성 곱 신경망을 활용하여 홍채인식의 인식률을 비교하여 보았다.

This paper presents an improved HOLP neural network that adds 25 average values to a typical HOLP neural network using 25 feature vector values as input values by applying high-order local autocorrelation function, which is excellent for extracting immutable feature values of iris images. Compared with deep learning structures with different types, we compared the recognition rate of iris recognition using Back-Propagation neural network, which shows excellent performance in voice and image field, and synthetic product neural network that integrates feature extractor and classifier.

키워드

참고문헌

  1. B. Jo, S. Woo, and S. Lee, "An Iris Detection Algorithm for Disease Prediction based Iridology," J. of the Korea Institute of information and Communication Engineering, vol. 21, no. 1, 2017, pp. 107-114. https://doi.org/10.6109/jkiice.2017.21.1.107
  2. Iris recognition - http://blog.naver.com/yutar/90009281389/
  3. S. Tada, First time to learn artificial intelligence. Seoul: Hanbit Media, 2017.
  4. S. Kwon, "Detection and classification of arrhythmia beat using convolution neural network," Master's Thesis, Department of Engineering at Yonsei University, 2019.
  5. Y. Lee, "A Comparison and Analysis of Deep Learning Framework," J. of The Korea Institute of Electronic Communication Sciences, vol. 12, no. 01, 2017, pp. 115-122. https://doi.org/10.13067/JKIECS.2017.12.1.115
  6. S. Lim, "Iris recognition by wavelet trans form and LVQ," Master's Thesis, Korea University Graduate School of Computer Science, 2001.
  7. K. Kwang, "Online iris recognition system based on HLAC feature extraction for multimedia high-speed transmission," The doctor's degree, Chosun University Graduate School, 2002.
  8. J. Lee, "Human iris verification using similarity between feature," Master's Thesis, Hongik University Graduate School, 2001.
  9. M. Kim, "A Study on User Recognition System based on Ensemble Convolutional Neural Networks using Synthetic Electrocardiogram Generation," The doctor's degree, Chosun University Graduate School, 2019.
  10. E. Kim, "study on the effective preprocessing of human iris verification," Master's Thesis, Hongik University Graduate School, 2001.
  11. Python Deep Learning CNN Convolutional Layer - https://blog.naver.com/ssdyka/221364894122/
  12. J. Kong and M, Jang, "Association Analysis of Convolution Layer, Kernel and Accuracy in CNN," J. of The Korea Institute of Electronic Communication Sciences, vol. 14, no. 06, 2019, pp. 1153-1160. https://doi.org/10.13067/JKIECS.2019.14.6.1153
  13. J. Lee, "CNN-based Automatic Modulation Classification Using Feature Image," Master's Thesis, Soongsil University Graduate School, 2019.
  14. H. Kim, "Estimation of atrial fibrillation based on convolutional neural network," Master's Thesis, Yonsei University Graduate School, 2018.
  15. Machine Learning Learning Related Skills - https://aroundck.tistory.com/5343/
  16. K. Choi and C. Jung, "Har Wavelet-based edge image extraction and face recognition using BP neural network," J. of the Korean Society for Information Processing and Science Conference, vol. 10, no. 01, 2003, pp. 0635-0638.