DOI QR코드

DOI QR Code

An Enhanced Method for Detecting Iris from Smartphone Images in Real-Time

스마트폰 영상에서의 개선된 실시간 눈동자 검출 방법

  • 김성훈 (가천대학교 전자계산학과) ;
  • 한기태 (가천대학교 IT대학 컴퓨터미디어융합학과)
  • Received : 2013.07.16
  • Accepted : 2013.08.03
  • Published : 2013.09.30

Abstract

In this paper, we propose a novel method for enhancing the detection speed and rate by reducing the computation in Hough Circle Transform on real-time iris detection of smartphone camera image. First of all, we find a face and eyes from input image to detect iris and normalize the iris region into fixed size to prevent variation of size for iris region according to distance from camera lens. Moreover, we carry out histogram equalization to get regular image in bright and dark illumination from smartphone and calculate minimal iris range that contains iris with the distance between corner of the left eye and corner of the right eye on the image. Subsequently, we can minimize the computation of iris detection by applying Hough Circle Transform on the range including the iris only. The experiment is carried out in two case with bright and dark illumination. Our proposed method represents that detection speed is 40% faster and detection rate is 14% better than existing methods.

본 논문은 스마트폰 영상의 실시간 눈동자 검출에서 허프 원 변환 연산의 연산량 축소를 통한 속도 및 검출율 개선 방법을 제안한다. 눈동자를 검출하기 위해서는 입력 영상에서 얼굴과 눈을 검출하고, 눈 영역의 크기에 따라 눈동자의 크기가 변하는 것을 방지하기 위해 일정크기로 눈 영역을 정규화하며, 다양한 조명환경에서 눈동자가 검출이 가능하도록 히스토그램 평활화를 실시하고, 눈의 양쪽 끝점간의 거리를 구하여 영상에서의 실제 눈동자의 크기를 포함할 수 있는 최소한의 눈동자 크기 범위를 계산하여 허프 원 변환에 적용함으로써 연산량을 최소화 하였다. 제안한 방법을 밝은 조명과 어두운 조명에서 실험한 결과 기존 방법들과 비교하여 눈동자 검출 속도는 40% 이상, 검출율은 14% 이상 향상된 것을 보였다.

Keywords

References

  1. HwangSoo Jeon, ETRI, Industry Environment Research Team, Senior Research Engineer, "Intelligent Vehicle Safety System Development Trend" National IT Industry Promotion Agency, 2012. 8.
  2. Korea Electronics Technology Institute, "Vehicle Safety System Industry Trend" 2010. 12.
  3. Bernhard Froba and Andreas Ernst, "Face Detection with the Modified Census Transform", IEEE International Conference on Automatic Face and Gesture Recognition, pp.91-96, 2004.
  4. Paul Viola and Michael Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features", in Computer Vision and Pattern Recognition, pp.511-518, 2001.
  5. Jianguo Li, Tao Wang and Yimin Zhang, "Face Detection using SURF Cascade", IEEE International Conference on Computer Vision Workshops, pp.2183-2190, 2011.
  6. Retno Supriyanti and Budi Setiawan, "Detecting Pupil and Iris under Uncontrolled Illumination using Fixed-Hough Circle Transform", International Journal of Signal Processing, Image Processing and Pattern Recognition, Vol.5, No.4, pp.175-188, 2012.
  7. Klaus Toennies, "Feasibility of Hough-Transform-Based Iris Localisation for Real-Time-Application", IEEE, Pattern Recognition, pp.1053-1056, 2002.
  8. Zinn Walter and Solomon Herbert, "Eye Care, Eye Glasses and Contact Lenses" City: Lifetime Books, 1965.
  9. John Daugman, "How iris recognition works", Proceedings of 2002 International Conference on Image Processing, Vol.1, pp.21-30, 2002.
  10. Yoav Freund and Robert E. Schapire, "Experiments with a New Boosting Algorithm", In Proc. 13th Int. Conf. On Machine Learning, pp.148-156, 1996.
  11. Carolyn Kimme, Dana Ballard and Jack Sklansky, "Finding Circles by an Array of Accumulators", Communication of the ACM, Vol.18, No.2, pp.120-122, 1975. https://doi.org/10.1145/360666.360677

Cited by

  1. A New Confidence Measure for Eye Detection Using Pixel Selection vol.4, pp.7, 2015, https://doi.org/10.3745/KTSDE.2015.4.7.291