Near-infrared and visible-light periocular recognition with Gabor features using frequency-adaptive automatic eye detection
- Author(s): Fernando Alonso-Fernandez 1 and Josef Bigun 1
-
-
View affiliations
-
Affiliations:
1:
School of Information Science, Computer and Electrical Engineering, Halmstad University, Box 823, Halmstad SE 301-18, Sweden
-
Affiliations:
1:
School of Information Science, Computer and Electrical Engineering, Halmstad University, Box 823, Halmstad SE 301-18, Sweden
- Source:
Volume 4, Issue 2,
June 2015,
p.
74 – 89
DOI: 10.1049/iet-bmt.2014.0038 , Print ISSN 2047-4938, Online ISSN 2047-4946
Periocular recognition has gained attention recently due to demands of increased robustness of face or iris in less controlled scenarios. We present a new system for eye detection based on complex symmetry filters, which has the advantage of not needing training. Also, separability of the filters allows faster detection via one-dimensional convolutions. This system is used as input to a periocular algorithm based on retinotopic sampling grids and Gabor spectrum decomposition. The evaluation framework is composed of six databases acquired both with near-infrared and visible sensors. The experimental setup is complemented with four iris matchers, used for fusion experiments. The eye detection system presented shows very high accuracy with near-infrared data, and a reasonable good accuracy with one visible database. Regarding the periocular system, it exhibits great robustness to small errors in locating the eye centre, as well as to scale changes of the input image. The density of the sampling grid can also be reduced without sacrificing accuracy. Lastly, despite the poorer performance of the iris matchers with visible data, fusion with the periocular system can provide an improvement of more than 20%. The six databases used have been manually annotated, with the annotation made publicly available.
Inspec keywords: filtering theory; eye; image matching; image sampling; feature extraction; iris recognition; image fusion; infrared imaging; gaze tracking; visual databases
Other keywords: VW range; visible range; sampling grid density reduction; Gabor features; visible databases; one-dimensional convolutions; frequency-adaptive automatic eye detection; scale changes robustness; retinotopic sampling grids; complex symmetry fllters; fusion experiments; iris matchers; Gabor analysis; near-infrared sensors; NIR sensors; detection fllter separability; eye centre; visible data; input image; error robustness; NIR data; visible-light periocular recognition; facial region; near-infrared periocular recognition
Subjects: Spatial and pictorial databases; Image recognition; Filtering methods in signal processing; Computer vision and image processing techniques
References
-
-
1)
-
44. Padole, C.N., Proenca, H.: ‘Periocular recognition: analysis of performance degradation factors’. 2012 Fifth IAPR Int. Conf. on Biometrics (ICB), March 2012, pp. 439–445.
-
-
2)
-
4. Smeraldi, F., Bigün, J.: ‘Retinal vision applied to facial features detection and face authentication’, Pattern Recognit. Lett., 2002, 23, (4), pp. 463–475 (doi: 10.1016/S0167-8655(01)00178-7).
-
-
3)
-
56. Clausi, D., Jernigan, M.: ‘Towards a novel approach for texture segmentation of SAE sea ice imagery’. 26th Int. Symp. on Remote Sensing of Environment and 18th Annual Symp. of the Canadian Remote Sensing Society, Vancouver, BC, Canada, 1996, p. 257261.
-
-
4)
- R. Wildes . Iris recognition: an emerging biometric technology. Proc. IEEE , 1348 - 1363
-
5)
-
64. Gilperez, A., Alonso-Fernandez, F., Pecharroman, S., Fierrez, J., Ortega-Garcia, J.: ‘Off-line signature verification using contour features’. Proc. Int. Conf. on Frontiers in Handwriting Recognition, ICFHR, 2008.
-
-
6)
-
42. Juefei-Xu, F., Luu, K., Savvides, M., Bui, T., Suen, C.: ‘Investigating age invariant face recognition based on periocular biometrics’. Proc. Int. Joint Conf. on Biometrics, IJCB, 2011.
-
-
7)
- J. Daugman . How iris recognition works. IEEE Trans. Circuits Syst. Video Technol. , 1 , 21 - 30
-
8)
-
39. Miller, P.E., Rawls, A.W., Pundlik, S.J., Woodard, D.L.: ‘Personal identification using periocular skin texture’. Proc. ACM Symp. on Applied Computing (SAC), Sierre, Switzerland, March 2010, pp. 1496–1500.
-
-
9)
-
5. Li, S.Z., Jain, A.K. (Eds.): ‘Handbook of face recognition’ (Springer Verlag, New York, USA, 2004).
-
-
10)
- T. Chan , L. Vese . Active contours without edges. IEEE Trans. Image Process. , 2 , 266 - 277
-
11)
-
48. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, CVPR, 2005.
-
-
12)
-
20. Rathgeb, C., Uhl, A.: ‘Secure iris recognition based on local intensity variations’, in Campilho, A., Kamel, M. (Eds.): ‘Image analysis and recognition’ (Springer, Berlin, Heidelberg, 2010), vol. 6112 of Lecture Notes in Computer Science, pp. 266–275.
-
-
13)
-
59. Bigun, J.: ‘Pattern recognition in images by symmetry and coordinate transformation’, Comput. Vis. Image Underst., 1997, 68, (3), pp. 290–307 (doi: 10.1006/cviu.1997.0556).
-
-
14)
- D.G. Lowe . Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis , 2 , 91 - 110
-
15)
- S. Shah , A. Ross . Iris segmentation using geodesic active contours. IEEE Trans. Inf. Forensics Secur. , 4 , 824 - 836
-
16)
-
61. Nilsson, K., Bigun, J.: ‘Localization of corresponding points in fingerprints by complex filtering’, Pattern Recognit. Lett., 2003, 24, pp. 2135–2144 (doi: 10.1016/S0167-8655(03)00083-7).
-
-
17)
-
27. Proenca, H., Filipe, S., Santos, R., Oliveira, J., Alexandre, L.A.: ‘The UBIRIS.v2: a database of visible wavelength iris images captured on-the-move and at-a-distance’, IEEE Trans. Pattern Anal. Mach. Intell. , 2010, 32, (8), pp. 1529–1535 (doi: 10.1109/TPAMI.2009.66).
-
-
18)
-
57. NICE II: ‘Noisy Iris Challenge Evaluation, Part II’. Available at http://www.nice2.di.ubi.pt/, 2010.
-
-
19)
-
3. Hollingsworth, K., Darnell, S.S., Miller, P.E., Woodard, D.L., Bowyer, K.W., Flynn, P.J.: ‘Human and machine performance on periocular biometrics under near-infrared light and visible light’, IEEE Trans. Inf. Forensics Sec., 2012, 7, (2), pp. 588–601 (doi: 10.1109/TIFS.2011.2173932).
-
-
20)
-
6. Burge, M.J., Bowyer, K.W. (Eds.): ‘Handbook of iris recognition’ (Springer, London, 2013).
-
-
21)
-
1. Santos, G., Proenca, H.: ‘Periocular biometrics: an emerging technology for unconstrained scenarios’. Proc. IEEE Workshop on Computational Intelligence in Biometrics and Identity Management (CIBIM), April 2013, pp. 14–21.
-
-
22)
-
37. Uhl, A., Wild, P.: ‘Combining face with face-part detectors under Gaussian assumption’. Proc. Ninth Int. Conf. on Image Analysis and Recognition, ICIAR, 2012, (LNCS, 7325), p. 89.
-
-
23)
-
8. Woodard, D.L., Pundlik, S.J., Lyle, J.R., Miller, P.E.: ‘Periocular region appearance cues for biometric identification’. Proc. IEEE Computer Vision and Pattern Recognition Biometrics Workshop, 2010.
-
-
24)
-
68. Bigun, E.S., Bigun, J., Duc, B., Fischer, S.: ‘Expert conciliation for multi modal person authentication systems by Bayesian statistics’. Proc. Int. Conf.on Audio- and Video-Based Biometric Person Authentication, AVBPA, 1997 (LNCS, 1206), pp. 291–300.
-
-
25)
-
69. Fierrez-Aguilar, J., Chen, Y., Ortega-Garcia, J., Jain, A.K.: ‘Incorporating image quality in multi-algorithm fingerprint verification’. Proc. Int. Conf. on Biometrics, ICB, 2006 (LNCS, 3832), pp. 213–220.
-
-
26)
-
14. Bigun, J., Fronthaler, H., Kollreider, K.: ‘Assuring liveness in biometric identity authentication by real-time face tracking’. Proc. Int. Conf. on Computational Intelligence for Homeland Security and Personal Safety, CIHSPS, 2004.
-
-
27)
- T. Ojala , M. Pietikǎinen , T. Mǎenpǎǎ . Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. , 7 , 971 - 987
-
28)
- S.G. Mallat . A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. , 7 , 674 - 693
-
29)
-
11. Alonso-Fernandez, F., Bigun, J.: ‘Periocular recognition using retinotopic sampling and Gabor decomposition’. Proc. Int. Workshop What's in a Face? WIAF, in conjunction with the European Conf. on Computer Vision, ECCV, 2012 (LNCS, 7584), pp. 309–318.
-
-
30)
-
67. Zuo, J., Schmid, N.A.: ‘An automatic algorithm for evaluating the precision of iris segmentation’. Proc. IEEE Conf. on Biometrics: Theory, Applications and Systems, BTAS, Washington DC (USA), 2008.
-
-
31)
-
60. Bigun, J., Granlund, G.H., Wiklund, J.: ‘Multidimensional orientation estimation with applications to texture analysis and optical flow’, IEEE Trans. Pattern Anal. Mach. Intell., 1991, 13, (8), pp. 775–790 (doi: 10.1109/34.85668).
-
-
32)
-
62. Fronthaler, H., Kollreider, K., Bigun, J., et al: ‘Fingerprint image quality estimation and its application to multi-algorithm verification’, IEEE Trans. Inf. Forensics Sec., 2008, 3, (2), pp. 331–338 (doi: 10.1109/TIFS.2008.920725).
-
-
33)
-
40. Adams, J., Woodard, D.L., Dozier, G., Miller, P., Bryant, K., Glenn, G.: ‘Genetic-based type ii feature extraction for periocular biometric recognition: less is more’. 2010 20th Int. Conf. on Pattern Recognition (ICPR), August 2010, pp. 205–208.
-
-
34)
-
19. Masek, L.: ‘Recognition of human iris patterns for biometric identification’. MS thesis, School of Computer Science and Software Engineering, University of Western Australia, 2003.
-
-
35)
-
6. OToole, A., Flynn, P., Bowyer, K., et al: ‘FRVT 2006 and ICE 2006 large-scale experimental results’, IEEE Trans. PAMI, 2010, 32, (5), pp. 831–846 (doi: 10.1109/TPAMI.2009.59).
-
-
36)
-
54. Hurley, D.J., Nixon, M.S., Carter, J.N.: ‘A new force field transform for ear and face recognition’. 2000 Int. Conf. on Image Processing, 2000. Proc., 2000, vol. 1, pp. 25–28.
-
-
37)
-
46. Mikaelyan, A., Alonso-Fernandez, F., Bigun, J.: ‘Periocular recognition by detection of local symmetry patterns’. Proc. Workshop on Insight on Eye Biometrics, IEB, in conjunction with the Int. Conf. on Signal Image Technology and Internet Based Systems, SITIS, Marrakech, Morocco, 2014.
-
-
38)
-
26. Sequeira, A.F., Monteiro, J.A.C., Rebelo, A., Oliveira, H.P.: ‘MobBio: a multimodal database captured with a portable handheld device’. Proc. Int. Conf. on Computer Vision Theory and Applications, VISAPP, 2014, vol. 3, pp. 133–139.
-
-
39)
-
51. Laws, K.I.: ‘Rapid texture identification’. Proc. Image Processing for Missile Guidance Seminar, San Diego, CA, 1980, pp. 376–380.
-
-
40)
-
45. Hollingsworth, K., Bowyer, K.W., Flynn, P.J.: ‘Identifying useful features for recognition in near-infrared periocular images’. 2010 Fourth IEEE Int. Conf. on Biometrics: Theory Applications and Systems (BTAS), September 2010, pp. 1–8.
-
-
41)
- A.K. Jain , K. Nandakumar , A. Ross . Score normalization in multimodal biometric systems. Patt. Recogn. , 2270 - 2285
-
42)
- A. Kumar , A. Passi . Comparison and combination of iris matchers for reliable personal authentication. Pattern Recognit. , 1016 - 1026
-
43)
-
30. Viola, P., Jones, M.: ‘Rapid object detection using a boosted cascade of simple features’. Proc. Computer Vision and Pattern Recognition Conf., CVPR, 2001, vol. 1, pp. 511–518.
-
-
44)
-
38. Vijaya Kumar, B.V.K., Savvides, M., Xie, C., Venkataramani, K., Thornton, J., Mahalanobis, A.: ‘Biometric verification with correlation filters’, Appl. Opt., 2004, 43, (2), pp. 391–402 (doi: 10.1364/AO.43.000391).
-
-
45)
-
9. Woodard, D., Pundlik, S., Miller, P., Jillela, R., Ross, A.: ‘On the fusion of periocular and iris biometrics in non-ideal imagery’. Proc. IAPR Int. Conf. on Pattern Recognition, ICPR, 2010.
-
-
46)
-
19. Ahmed, N., Natarajan, T., Rao, K.R.: ‘Discrete cosine transform’, IEEE Trans. Comput., 1974, C-23, (1), pp. 90–93 (doi: 10.1109/T-C.1974.223784).
-
-
47)
- H. Bay , A. Ess , T. Tuytelaars , L.V. Gool . SURF: speeded up robust features. Comput. Vis. Image Underst. , 3 , 346 - 359
-
48)
-
18. He, Z., Tan, T., Sun, Z., Qiu, X.: ‘Toward accurate and fast iris segmentation for iris biometrics’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 31, (9), pp. 1295–1307.
-
-
49)
- K.W. Bowyer , K. Hollingsworth , P.J. Flynn . Image understanding for iris biometrics: a survey. Comput. Vis. Image Underst. , 2 , 281 - 307
-
50)
-
63. Alonso-Fernandez, F., Bigun, J.: ‘Iris boundaries segmentation using the generalized structure tensor. An study on the effects of image degradation’. Proc. IEEE Conf. on Biometrics: Theory, Applications and Systems, BTAS, Washington DC (USA), 2012.
-
-
51)
-
35. Ryan, W.J., Woodard, D.L., Duchowski, A.T., Birchfield, S.T.: ‘Adapting starburst for elliptical iris segmentation’. Second IEEE Int. Conf. on in Biometrics: Theory, Applications and Systems, 2008. BTAS 2008, September 2008, pp. 1–7.
-
-
52)
-
23. Fierrez, J., Ortega-Garcia, J., Torre-Toledano, D., Gonzalez-Rodriguez, J.: ‘BioSec baseline corpus: a multimodal biometric database’, Pattern Recognit., 2007, 40, (4), pp. 1389–1392 (doi: 10.1016/j.patcog.2006.10.014).
-
-
53)
-
21. Monro, D.M., Rakshit, S., Zhang, D.: ‘DCT-based iris recognition’, IEEE Trans. Pattern Anal. Mach. Intelli., 2007, 29, (4), pp. 586–595 (doi: 10.1109/TPAMI.2007.1002).
-
-
54)
-
24. CASIA Iris Image Database. Available at http://www.biometrics.idealtest.org.
-
-
55)
-
2. Park, U., Jillela, R., Ross, A., Jain, A.K.: ‘Periocular biometrics in the visible spectrum’, IEEE Trans. Inf. Forensics Sec., 2011, 6, (1), pp. 96–106 (doi: 10.1109/TIFS.2010.2096810).
-
-
56)
-
17. Bigun, J.: ‘Vision with direction’ (Springer-Verlag, Berlin, Heidelberg, 2006).
-
-
57)
-
10. Jillela, R., Ross, A.A., Boddeti, V.N., et al: ‘Iris segmentation for challenging periocular images’, in Burge, M.J., Bowyer, K.W. (Eds.): ‘Handbook of iris recognition’ (Springer, London, 2013), pp. 281–308.
-
-
58)
- J. Bigun , T. Bigun , K. Nilsson . Recognition by symmetry derivatives and the generalized structure tensor. IEEE Trans. Pattern Anal. Mach. Intell. , 12 , 1590 - 1605
-
59)
-
16. Mikaelyan, A., Bigun, J.: ‘Frequency and ridge estimation by structure tensor’. Proc. Biometric Technologies in Forensic Science Conf., Nijmegen, The Nehterlands, 2013, pp. 58–59.
-
-
60)
-
13. Smeraldi, F., Carmona, O., Bigun, J.: ‘Saccadic search with Gabor features applied to eye detection and real-time head tracking’, Image Vis. Comput., 2000, 18, (4), pp. 323–329 (doi: 10.1016/S0262-8856(99)00080-3).
-
-
61)
-
50. Beer, T.: ‘Walsh transforms’, Am. J. Phys., 1981, 49, (5), pp. 466–472 (doi: 10.1119/1.12714).
-
-
62)
-
29. Hofbauer, H., Alonso-Fernandez, F., Wild, P., Bigun, J., Uhl, A.: ‘A ground truth for iris segmentation’. Proc. Int. Conf. on Pattern Recognition, ICPR, 2014.
-
-
63)
- J. Bigun , J.M. Du Buf . N-folded symmetries by complex moments in Gabor space and their applications to unsupervised texture segmentation. IEEE Trans. Pattern Anal. Mach. Intell. , 1 , 80 - 87
-
64)
-
7. Miller, P.E., Lyle, J.R., Pundlik, S.J., Woodard, D.L.: ‘Performance evaluation of local appearance based periocular recognition’. Proc. IEEE Int. Conf. on Biometrics: Theory, Applications, and Systems, BTAS, 2010.
-
-
65)
-
65. Rathgeb, C., Uhl, A., Wild, P.: ‘Iris biometrics – from segmentation to template security, vol. 59 of advances in information security’ (Springer, New York, NY, 2013).
-
-
66)
-
41. Juefei-Xu, F., Cha, M., Heyman, J., Venugopalan, S., Abiantun, R., Savvides, M.: ‘Robust local binary pattern feature sets for periocular biometric identification’. Proc. IEEE Conf. on Biometrics: Theory, Applications and Systems, BTAS, 2010.
-
-
67)
-
15. Alonso-Fernandez, F., Bigun, J.: ‘Eye detection by complex filtering for periocular recognition’. Proc. Second Int. Workshop on Biometrics and Forensics, IWBF, Valletta, Malta, 2014.
-
-
68)
-
43. Bharadwaj, S., Bhatt, H.S., Vatsa, M., Singh, R.: ‘Periocular biometrics: when iris recognition fails’. Proc. IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS, 2010.
-
-
69)
-
22. Ko, J.-G., Gil, Y.-H., Yoo, J.-H., Chung, K.-I.: ‘A novel and efficient feature extraction method for iris recognition’, ETRI J., 2007, 29, (3), pp. 399–401 (doi: 10.4218/etrij.07.0206.0141).
-
-
1)