access icon free Improved average of synthetic exact filters for precise eye localisation under realistic conditions

© The Institution of Engineering and Technology
Received 14/12/2011, Accepted 09/01/2013, Revised 11/12/2012, Published

Precise eye localisation is a crucial step for many applications, including face recognition, gaze tracking and blink detection. In this study, the authors propose several improvements to the original average of synthetic exact filters (ASEF) formulation, demonstrating that its accuracy can be enhanced if adequate illumination correction, spatial priors and cross-filter responses are exploited for eye localisation. The so-called improved ASEF (iASEF) was tested on the well-known BioID database and other more challenging datasets comprising real world face imagery: labelled faces in the wild (LFW) and the very recent labelled face parts in the wild. The iASEF provides the state-of-the-art results, ranking first on BioID database and second on a 2000-image LFW subset. In addition, the authors propose a novel, much more challenging benchmark for eye localisation using the whole LFW and a standard protocol initially designed for face verification. Improvements over original ASEF were also confirmed on this difficult test, although with a significant drop in performance. They point out the necessity of adopting these realistic validation scenarios, in order to evaluate the actual state-of-the-art and fairly compare eye localisation methods in unconstrained settings, where localisation accuracy is still far from perfect.

Inspec keywords: face recognition; filtering theory; iris recognition

Other keywords: labelled faces in the wild; cross-filter response; bioID database; face recognition; illumination correction; protocol; improved synthetic exact filter formulation; improved ASEF; spatial priors; face imagery; blink detection; face verification; gaze tracking; precise eye localisation

Subjects: Computer vision and image processing techniques; Image recognition; Filtering methods in signal processing

References

    1. 1)
      • 18. Scheirer, W., Rocha, A., Heflin, B., Boult, T.: ‘Difficult detection: a comparison of two different approaches to eye detection for unconstrained environments’. BTAS09, 2009, pp. 1–8.
    2. 2)
      • 5. Belhumeur, P., Jacobs, D., Kriegman, D., Kumar, N.: ‘Localizing parts of faces using a consensus of exemplars’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2011, June 2011, pp. 545–552.
    3. 3)
      • 9. Wolf, L., Hassner, T., Taigman, Y.: ‘Similarity scores based on background samples’. ACCV, 2009, pp. 88–97.
    4. 4)
      • 8. Rodriguez, Y., Cardinaux, F., Bengio, S., Marithoz, J.: ‘Measuring the performance of face localization systems’, Image Vis. Comput., 2006, 24, (8), pp. 882–893.
    5. 5)
      • 40. Campadelli, P., Lanzarotti, R., Lipori, G.: ‘Precise eye and mouth localization’, Int. J. Pattern Recognit. Artif. Intell., 2009, 23, (3), pp. 359–377.
    6. 6)
      • 7. Wang, P., Green, M., Ji, Q., Waymanm, J.: ‘Automatic eye detection and its validation’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005, pp. 164–171.
    7. 7)
      • 41. Valenti, R., Gevers, T.: ‘Accurate eye center location and tracking using isophote curvature’. IEEE Conf. Computer Vision and Pattern Recognition, 2008, CVPR 2008, June 2008, pp. 1–8.
    8. 8)
      • 3. Kumar, N., Belhumeur, P.N., Nayar, S.K.: ‘FaceTracer: a search engine for large collections of images with faces’. ECCV, October 2008, pp. 340–353.
    9. 9)
      • 44. Jobson, D., Rahman, Z., Woodell, G.: ‘A multiscale retinex for bridging the gap between color images and the human observations of scenes’, IEEE Trans. Image Process., 1997, 6, (7), pp. 965–976.
    10. 10)
      • 11. Kroon, B., Maas, S., Boughorbel, S., Hanjalic, A.: ‘Eye localization in low and standard definition content with application to face matching’. CVIU, 2009, vol. 113, pp. 921–933.
    11. 11)
      • 45. Chen, W., Er, M., Wu, S.: ‘Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithmic domain’, IEEE Trans. Syst. Man Cybern., B, 2006, 36, pp. 458–466.
    12. 12)
      • 47. Tan, X., Triggs, B.: ‘Enhanced local texture feature sets for face recognition under difficult lighting conditions’, IEEE Trans. Image Process., 2010, 19, pp. 1635–1650.
    13. 13)
      • 29. Castrillón, M., Dóniz, O., Hernández, D., Lorenzo, J.: ‘A comparison of face and facial feature detectors based on the Viola–Jones general object detection framework’, Mach. Vis. Appl., 2011, 22, pp. 481–494.
    14. 14)
      • 28. Wiskott, L., Kruger, J.M., von der Malsburg, C.: ‘Face recognition by elastic bunch graph matching’, IEEE Trans. Pattern Anal. Mach. Intell., 1997, 19, (7), pp. 775–779.
    15. 15)
      • 25. Štruc, V., Pavešić, N.: ‘Gabor-based kernel partial-least-squares discrimination features for face recognition’, Informatica (Vilnius), 2009, 20, (1), pp. 115–138.
    16. 16)
      • 21. Štruc, V., Gros, J., Pavešić, N.: ‘Principal directions of synthetic exact filters for robust real-time eye localization’, in Vielhauer, C., Dittmann, J., Drygajlo, A., Juul, N., Fairhurst, M., (Ed.): ‘Biometrics and ID management’, (Springer, Berlin – Heidelberg, 2011), (LNCS, 6583), pp. 180–192.
    17. 17)
      • 20. Yang, F., Huang, J., Yang, P., Metaxas, D.: ‘Eye localization through multiscale sparse dictionaries’. IEEE Int. Conf. Automatic Face Gesture Recognition and Workshops (FG 2011), 2011, March 2011, pp. 514–518.
    18. 18)
      • 37. Asteriadis, S., Nikolaidis, N., Hajdu, A., Pitas, I.: A model eye detection algorithm utilizing edge related geometrical information. 14th European Signal Processing Conference, EUSIPCO, 2006.
    19. 19)
      • 39. Niu, Z., Shan, S., Yan, S., Chen, X., Gao, W.: ‘2d cascaded Adaboost for eye localization’. 18th Int. Conf. Pattern Recognition, 2006, ICPR 2006, 2006, vol. 2, pp. 1216–1219.
    20. 20)
      • 10. Bolme, D., Draper, B., Beveridge, J.: ‘Average of synthetic exact filters’. CVPR, June 2009, pp. 2105–2112.
    21. 21)
      • 33. Monzo, D., Albiol, A., Sastre, J., Albiol, A.: ‘Precise eye localization using hog descriptors’, Mach. Vis. Appl., 2011, 22, pp. 471–480.
    22. 22)
      • 43. Jobson, D., Rahman, Z., Woodell, G.: ‘Properties and performance of a center/surround retinex’, IEEE Trans. Image Process., 1997, 6, (3), pp. 451–462.
    23. 23)
      • 1. Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: ‘Labeled faces in the wild: a database for studying face recognition in unconstrained environments’. Technical Report 07-49, University of Massachusetts, Amherst, October2007.
    24. 24)
      • 48. Wang, B., Li, W., Yang, W., Liao, Q.: ‘Illumination normalization based on Weber's law with application to face recognition’, IEEE Signal Process. Lett., 2011, 18, (8), pp. 462–465.
    25. 25)
      • 22. Gallagher, A., Chen, T.: ‘Understanding images of groups of people’. CVPR2009.
    26. 26)
      • 27. Phillips, P., Moon, H., Rizvi, S., Rauss, P.: ‘The Feret evaluation methodology for face-recognition algorithms’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, pp. 1090–1104.
    27. 27)
      • 13. Li, P., Warrell, J., Aghajanian, J., Prince, S.: ‘Context-based additive logistic model for facial key point localization’. BMVA2010, pp. 28.1–28.11.
    28. 28)
      • 4. Grgic, M., Delac, K., Grgic, S.: ‘Scface – surveillance cameras face database’, Multimed. Tools Appl., 2011, 51, pp. 863–879.
    29. 29)
      • 14. Valenti, R., Yucel, Z., Gevers, T.: ‘Robustifying eye center localization by head pose cues’. CVPR 2009, June 2009, pp. 612–618.
    30. 30)
      • 19. Asteriadis, S., Nikolaidis, N., Pitas, I.: ‘Facial feature detection using distance vector fields’, Pattern Recognit., 2009, 42, pp. 1388–1398.
    31. 31)
      • 31. Felzenszwalb, P.F., Huttenlocher, D.P.: ‘Pictorial structures for object recognition’, Int. J. Comput. Vis., 2006, 61, pp. 55–79.
    32. 32)
      • 16. Tan, X., Song, F., Zhou, Z.-H., Chen, S.: ‘Enhanced pictorial structures for precise eye localization under uncontrolled conditions’. CVPR, June 2009, pp. 1621–1628.
    33. 33)
      • 35. Hamouz, M., Kittler, J., Kamarainen, J., Paalanen, P., Kalviainen, H., Matas, J.: ‘Feature-based affine-invariant localization of faces’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, pp. 1490–1495.
    34. 34)
      • 42. Viola, P., Jones, M.J.: ‘Robust real-time face detection’, Int. J. Comput. Vis., 2004, 57, pp. 137–154.
    35. 35)
      • 50. Saragih, J.M., Lucey, S., Cohn, J.: ‘Face alignment through subspace constrained meanshifts’. Int. Conf. Computer Vision (ICCV), September 2009.
    36. 36)
      • 30. Aghajanian, J., Prince, S.J.D., Street, G.: ‘Face pose estimation in uncontrolled environments’. BMCV09, 2009, pp. 1–11.
    37. 37)
      • 38. Bai, L., Shen, L., Wang, Y.: ‘A novel eye location algorithm based on radial symmetry transform’. Int. Conf. Pattern Recognition, 2006, vol. 3, pp. 511–514.
    38. 38)
      • 36. Cristinacce, D., Cootes, T., Scott, I.: ‘A multi-stage approach to facial feature detection’. BMVC, 2004, pp. 231–240.
    39. 39)
      • 17. Everingham, M., Zisserman, A.: ‘Regression and classification approaches to eye localization in face images’. FG 2006, April 2006, pp. 441–446.
    40. 40)
      • 49. Bolme, D., Lui, Y.M., Draper, B., Beveridge, J.: ‘Simple real-time human detection using a single correlation filter’. 12th IEEE Int. Workshop Performance Evaluation of Tracking and Surveillance (PETS-Winter), 2009, December 2009, pp. 1–8.
    41. 41)
      • 34. Hamouz, M., Kittler, J., Kamarainen, J.-K., Paalanen, P., Kalviainen, H.: ‘Affine-invariant face detection and localization using gmm-based feature detector and enhanced appearance model’. Sixth IEEE Int. Conf. Automatic Face and Gesture Recognition, 2004, May 2004, pp. 67–72.
    42. 42)
      • 32. Campadelli, P., Lanzarotti, R., Lipori, G.: ‘Precise eye localization through a general-to-specific model definition’. BMVC06, 2006, pp. I:187.
    43. 43)
      • 26. Degtyarev, N.: ‘Manual eye coordinates for labeled faces in the wild (lfw)’, http://lda.tsu.tula.ru/FD/lfw_eyes.zip.
    44. 44)
      • 2. Kumar, N., Berg, A.C., Belhumeur, P.N., Nayar, S.K.: ‘Attribute and simile classifiers for face verification’. IEEE ICCV, October 2009.
    45. 45)
      • 46. Vu, N.-S., Caplier, A.: ‘Illumination-robust face recognition using retina modeling’. ICIP, November 2009, pp. 3289–3292.
    46. 46)
      • 6. Shan, S., Chang, Y., Gao, W.: ‘Curse of mis-alignment in face recognition: problem and a novel mis-alignment learning solution’. Proc. IEEE Conf. Automatic Face and Gesture Recognition, 2004, pp. 314–320.
    47. 47)
      • 12. Song, M., Tao, D., Sun, Z., Li, X.: ‘Visual-context boosting for eye detection’. Syst. Man Cybern., B2010, 40, pp. 1460–1467.
    48. 48)
      • 24. Štruc V., Pavešić N.: “Photometric normalization technique for illumination invariance”, Advances in Face Image Analysis: Techniques and Technologies. IGI Global, 2011.
    49. 49)
      • 15. Qian, Z., Xu, D.: ‘Automatic eye detection using intensity filtering and k-means clustering’, Pattern Recognit. Lett., 2010, 31, (12), pp. 1633–1640.
    50. 50)
      • 23. Jesorsky, O., Kirchberg, K.J., Frischholz, R.: ‘Robust face detection using the Hausdorff distance’. AVBPA, AVBPA'01, Springer-Verlag, London, UK, 2001, pp. 90–95.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2011.0006
Loading

Related content

content/journals/10.1049/iet-bmt.2011.0006
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading