image processing
IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART C: APPLICATIONS AND REVIEWS, VOL. 37, NO. 5, SEPTEMBER 2007
971
Real-Time Iris Detection on
Coronal-Axis-Rotated Faces
Claudio A. Perez, Senior Member, IEEE, Vanel A. Lazcano, and Pablo A. Est´ vez, Senior Member, IEEE e Abstract—Real-time face and iris detection on video sequences is important in diverse applications such as, study of the eye function, drowsiness detection, virtual keyboard interfaces, face recognition, and multimedia retrieval. In this paper, a real-time robust method is developed to detect irises on faces with coronal axis rotation within the normal range of −40◦ to 40◦ . The method allows head movements with no restrictions to the background. The method is based on anthropometric templates applied to detect the face and eyes. The templates use key features of the face such as the elliptical shape, and location of the eyebrows, nose, and lips. For iris detection, a template following the iris–sclera boundary shape is used. The method was compared to Maio–Maltoni’s and Rowley’s methods for face detection on five video sequences (TEST 1). The method was also assessed in an additional set of five video sequences for iris detection (TEST 2). Results of correct face detection in
TEST 1 were above 99% in three of the five video sequences. The fourth video sequence reached 97.6% and the third 90.6%. In
TEST 2, the iris detection was above 96% in all five video sequences with two above 99.7% and two at 100%. Face size estimation is also above 99.9%. The average processing time of our method was 0.02 s per frame. Thus, the proposed method can process frames at a rate near to 50 frames/s, and therefore, is applicable in real time in a standard personal computer (PC 1.8 GHz).
Index Terms—Anthropometric templates, face rotation, iris tracking, real-time face detection, real-time iris detection.
I. INTRODUCTION
AZE estimation represents an important area of research
971
Real-Time Iris Detection on
Coronal-Axis-Rotated Faces
Claudio A. Perez, Senior Member, IEEE, Vanel A. Lazcano, and Pablo A. Est´ vez, Senior Member, IEEE e Abstract—Real-time face and iris detection on video sequences is important in diverse applications such as, study of the eye function, drowsiness detection, virtual keyboard interfaces, face recognition, and multimedia retrieval. In this paper, a real-time robust method is developed to detect irises on faces with coronal axis rotation within the normal range of −40◦ to 40◦ . The method allows head movements with no restrictions to the background. The method is based on anthropometric templates applied to detect the face and eyes. The templates use key features of the face such as the elliptical shape, and location of the eyebrows, nose, and lips. For iris detection, a template following the iris–sclera boundary shape is used. The method was compared to Maio–Maltoni’s and Rowley’s methods for face detection on five video sequences (TEST 1). The method was also assessed in an additional set of five video sequences for iris detection (TEST 2). Results of correct face detection in
TEST 1 were above 99% in three of the five video sequences. The fourth video sequence reached 97.6% and the third 90.6%. In
TEST 2, the iris detection was above 96% in all five video sequences with two above 99.7% and two at 100%. Face size estimation is also above 99.9%. The average processing time of our method was 0.02 s per frame. Thus, the proposed method can process frames at a rate near to 50 frames/s, and therefore, is applicable in real time in a standard personal computer (PC 1.8 GHz).
Index Terms—Anthropometric templates, face rotation, iris tracking, real-time face detection, real-time iris detection.
I. INTRODUCTION
AZE estimation represents an important area of research
References: pp. 277–287, Aug. 2003. vol. 15, no. 11, pp. 1148–1161, 1993. Video Technol., vol. 14, no. 1, pp. 21–30, Jan. 2004. [4] J. Dowall, I. Pavlidis, and G. Bebis, “Face detection in the near-IR spectrum,” Image Vis. Comput., vol. 21, pp. 565–578, Jul. 2001. Res. Lab., Tech. Rep., TR2003-96 Jul. 2003. pp. 577–587, Aug. 2000. CVC Tech. Rep. 24, 1998, [Online]. Available: http://rv11.ecn.purdue. tracking algorithm based on digital image processing,” in Proc. 2001 IEEE Int pp. 1178–1183. Syst., Man, Cybern. A, vol. 35, no. 6, pp. 955–964, Nov. 2005. IV(RB5), Providence, RI, Oct. 2003, vol. 5264, pp. 42–53. iris detection on faces with coronal axis rotation,” in Proc. 2004 IEEE Int no. 10–13, pp. 6389–6394. [29] H. Rowley, S. Ahuja, and T. Kanade, “Rotation invariant neural networkbased face detection,” in Proc. 1998 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR), Santa Barbara, CA, Jun. 1998, pp. 38– 44. 1401, Jun. 2002. Syst., Man, Cybern. B, vol. 32, no. 3, pp. 332–350, Jun. 2002. 58, Jan. 2002. Image Understanding, vol. 98, pp. 124–154, 2005.