RGB 영상에서 딥러닝 기반 동공 중심점을 이용한 홍채 검출
Iris Localization using the Pupil Center Point based on Deep Learning in RGB Images
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문에서는 RGB 영상에서 홍채 검출 방법에 관하여 기술하였다. 기존의 홍채 검출 방법은 대부분 적외선 영상을 대상으로 하고 있어, 다양한 응용을 위해서는 RGB 영상의 홍채 검출 기술이 요구된다. 제안된홍채 검출 방법은 i) 입력 영상에서 원형 허프 변환을 사용한 홍채 후보 영역 검출, ii) 딥러닝 기반의 동공중심점 검출, iii) 동공 중심점을 이용한 홍채 영역 선택, iv) 선택된 홍채 영역 보정 과정으로 구성된다. 홍채후보 영역은 허프 공간을 생성한 후 중심점 후보의 교차 개수가 많은 순으로 검출하며, 후보 영역 중 홍채는검출된 동공의 중심점을 기준으로 선택한다. 그리고, 홍채의 모양이 왜곡되어 오차가 발생하는 것을 보완하기위해 검출된 홍채 중심을 기준으로 새로운 경계점을 찾아 보정하는 방법을 사용하였다. 또한, 실험을 통하여제안된 방법이 기존 원형 허프 변환 방법 대비 약 27.4% 향상된 정확도를 갖는 것을 확인하였다.
Abstract
In this paper, we describe the iris localization method in RGB images. Most of the iris localization methods are developed for infrared images, thus an iris localization method in RGB images is required for various applications. The proposed method consists of four stages: i) detection of the candidate irises using circular Hough transform (CHT) from an input image, ii) detection of a pupil center based on deep learning, iii) determine the iris using the pupil center, and iv) correction of the iris region. The candidate irises are detected in the order of the number of intersections of the center point candidates after generating the Hough space, and the iris in the candidates is determined based on the detected pupil center. Also, the error due to distortion of the iris shape is corrected by finding a new boundary point based on the detected iris center. In experiments, the proposed method has an improved accuracy about 27.4% compared to the CHT method.
참고문헌 (12)
- Kevin W. Bowyer, "Handbook of Iris Recognition" (2016), Springer
- 고종국, "원거리 홍채인식 기술 동향", 전자통신동향분석, 28(3), pp.67~75 (2013)
- C. N. Padole, "Periocular Recognition : Analysis of Performance Degradation Factors", IAPR International Conference on Biometrics, pp.439~445 (2012)
- Hugo Proenca, "The UBIRIS.v2: A Database of Visible Wavelength Iris Images Captured On-the-Move and At-a-Distance", IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(8), pp.1529~1535 (2010), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Z. Zhao, "An Accurate Iris Segmentation Framework under Relaxed Imaging Constraints using Total Variation Model", Proceeding of the IEEE International Conference on Computer Vision, pp.3828~3836 (2015)
- J. Daugman, "Statistical Richness of Visual Phase Information : Update on Recognizing Persons by Iris Patterns", Int'l Journal of Computer Vision, 45(1), pp.25~38 (2001)
- L. Ma, "Efficient Iris Recognition by Characterizing Key Local Variations", IEEE Transactions on Image Processing, 13(6), pp.739~750 (2004), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- M. Arsalan, "Deep Learning-based Iris Segmentation for Iris Recognition in Visible Light Environment", Symmetry, 9(11), pp.263~ (2017)[DOI]
- F.J. Vera-Olmos, "DeepEye: Deep convolutional network for pupil detection in real environments", Integrated Computer-Aided Engineering, 26(1), pp.85~95 (2018), IOS Press[DOI]
- G. J. Mohammed, "Accurate Pupil Features Extraction based on New Projection Function", Computing and Informatics, 29(4), pp.663~680 (2012)
- Liang-Chieh Chen, "DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs", IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), pp.834~848 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Noureddine Cherabit, "Circular Hough Transform for Iris localization", Science and Technology, 2(5), pp.114~121 (2012), Scientific and Academic Publishing[DOI]