Pattern Analysis and Applications

, Volume 7, Issue 2, pp 117–127 | Cite as

A probabilistic hit-and-miss transform for face localization

  • B. Raducanu
  • M. GrañaEmail author
  • F. X. Albizuri
  • A. d’Anjou
Theoretical Advances


Face localization is needed for any face processing procedure whose applications range from biometric identification to content-based image retrieval. It consists in giving the image coordinates of the face. In this paper we propose a probabilistic pattern matching procedure for face localization in greyscale images similar to the morphological hit-and-miss-transform (HMT), which we call probabilistic HMT (PHMT). This procedure is defined on the morphological multiscale fingerprints (MMF), which are image features extracted from the morphological erosion/dilation scale spaces. The face location is estimated as the maximum likelihood image window matching both erosive and dilative MMF models of the object. The MMF models are computed at a discrete set of scales. The MMF models may be built up from a small set of training face images and do not involve numerically sophisticated training algorithms. Training does not use non-face sample images. Therefore resampling is not needed for the construction of the MMF models. The experimental results on the NIST Mugshot Identification Database endorse our claims about the accuracy and robustness of the proposed procedure.


Computer vision Face localization Hit-and-miss transform Mathematical morphology Morphological scale spaces 



The work has been partially supported by grant TIC2000-0739-C04-02 of the Ministerio de Ciencia y Tecnologia. B. Raducanu benefited from a predoctoral grant from the University of the Basque Country (UPV/EHU).


  1. 1.
    Fukunaga K (1990) Introduction to statistical pattern recognition. Academic Press, LondonGoogle Scholar
  2. 2.
    Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, New YorkGoogle Scholar
  3. 3.
    Yang M-H, Kriegman DJ, Ahuja N (2002) Detecting faces in images: a survey. IEEE Trans Pattern Anal Mach Intell 24(1):34–58CrossRefzbMATHGoogle Scholar
  4. 4.
    Rowley HA, Baluja S, Kanade T (1998) Neural network-based face detection. IEEE Trans Pattern Anal Mach Intell 20(1):23–38CrossRefGoogle Scholar
  5. 5.
    Sung K-K, Poggio T (1998) Example-based learning for view-based human face detection. IEEE Trans Pattern Anal Mach Intell 20(1):39–51CrossRefGoogle Scholar
  6. 6.
    Lin S-H, Kung S-Y, Lin L-J (1997) Face recognition/detection by probabilistic decision-based neural network. IEEE Trans Neural Netw 8(1):114–132CrossRefzbMATHGoogle Scholar
  7. 7.
    Juell P, Marsh R (1996) A hierarchical neural network for human face detection. Pattern Recognition 29(5):781–787CrossRefGoogle Scholar
  8. 8.
    Dai Y, Nakano Y (1998) Recognition of facial images with low resolution using a hopfield memory model. Pattern Recognition 31(2):159–167CrossRefzbMATHGoogle Scholar
  9. 9.
    Féraud R, Bernier OJ, Viallet J-E, Collobert M (2001) A fast and accurate face detector based on neural networks. IEEE Trans Pattern Anal Mach Intell 23(1):42–53CrossRefGoogle Scholar
  10. 10.
    Liu C (2003) A bayesian discriminating features method for face detection. IEEE Trans Pattern Anal Mach Intell 25(6):725–740CrossRefGoogle Scholar
  11. 11.
    Viola P, Jones M (2004) Robust real-time object detection. Int J Comput Vision, in pressGoogle Scholar
  12. 12.
    Lee CH, Kim JS, Park KH (1996) Automatic human face location in a complex background using motion and color information. Pattern Recognition 29(11):1877–1889CrossRefGoogle Scholar
  13. 13.
    Yang G, Huang TS (1994) Human face detection in a complex background. Pattern Recognition 27(1):53–63CrossRefzbMATHGoogle Scholar
  14. 14.
    Yoo T-W, Oh I-S (1999) A fast algorithm for tracking human faces based on chromatic histograms. Pattern Recognition Lett 20:967–978CrossRefGoogle Scholar
  15. 15.
    McKenna SJ, Gong S, Raja Y (1998) Modelling facial colour and identity with gaussian mixtures. Pattern Recognition 31(12):1883–1992CrossRefGoogle Scholar
  16. 16.
    Wang J, Tan T (2000) A new face detection method based on shape information. Pattern Recognition Lett 21:463–471CrossRefzbMATHGoogle Scholar
  17. 17.
    Yokoo Y, Hagiwara M (1996) Human faces detection method using genetic algorithms. In: Proceedings of international conference on evolutionary computation, pp 113–118Google Scholar
  18. 18.
    Leung TK, Burl MC, Perona P (1995) Finding faces in cluttered scenes using random labeled graph matching. In: Proceedings of 5th international conference on computer vision, pp 637–644Google Scholar
  19. 19.
    Yow KC, Cipolla R (1995) Finding initial estimates of the human face location. In: Proceedings of 2nd Asian Conference on Computer Vision, vol 3, pp 514–518Google Scholar
  20. 20.
    Wiskott L (1999) The role of topographical constraints in face recognition. Pattern Recognition Lett 20(1):89–96zbMATHGoogle Scholar
  21. 21.
    Moghaddam B, Pentland A (1997) Probabilistic visual learning for object representation. IEEE Trans Pattern Anal Mach Intell 19(7):696–710CrossRefGoogle Scholar
  22. 22.
    Pentland A (1997) Machine understanding of human behavior. In: Maybury MT (ed) Intelligent multimedia information retrieval. MIT Press, Cambridge, MA, pp 175–188Google Scholar
  23. 23.
    Su MC, Chu CH (2001) A modified version of the K-means algorithm with a distance based on cluster symmetry. IEEE Trans Pattern Anal Mach Intell 23(6):674–680CrossRefGoogle Scholar
  24. 24.
    Lades M, Vorbruggen J, Buhmann J, Malburg CVD, Wurtz R (1993) Distortion invariant object recognition in the dynamic link architecture. IEEE Trans Comput 42(3):300–311CrossRefGoogle Scholar
  25. 25.
    Kotropoulos C, Tefas A, Pitas I (2000) Frontal face authentication using morphological elastic graph matching. IEEE Trans Image Process 9(4):555–560CrossRefGoogle Scholar
  26. 26.
    Tefas A, Kotropoulos C, Pitas I (2001) Using support vector machines to enhance the performance of elastic graph matching for frontal face authentication. IEEE Trans Pattern Anal Mach Intell 23(7):735–746CrossRefGoogle Scholar
  27. 27.
    Han C-C, Liao H-YM, Yu KC, Chen L-H (1998) Fast face detection via morphology-based pre-processing. In: Proceedings of the 9th international conference on image analysis and processing, pp 469–476Google Scholar
  28. 28.
    Marques F, Villaplana V, Buxes A (1999) Human face segmentation and tracking using connected operators and partition projection. In: Proceedings of international conference on computer vision, pp 1320–1324Google Scholar
  29. 29.
    Raducanu B, Graña M, Albizuri FX, d’Anjou A (2001) Face localization based on the morphological multiscale fingerprints. Pattern Recognition Lett 22(3–4):359–371Google Scholar
  30. 30.
    Tsapatsoulis N, Avrithis Y, Kollias S (2001) Facial image indexing in multimedia databases. Pattern Anal Appl 4 (2–3):93–107Google Scholar
  31. 31.
    Fan J, Yau DKY, Elmagarmid AK, Aref WG (2001) Automatic image segmentation by integrating color-edge extraction and seeded region growing. IEEE Trans Image Process 10(10):1454–1466CrossRefzbMATHGoogle Scholar
  32. 32.
    Hsu RL, Abdel-Mottaleb M, Jain AK (2002) Face detection in color images. IEEE Pattern Anal Mach Intell 24(5):696–706CrossRefGoogle Scholar
  33. 33.
    Serra J (1982) Image analysis and mathematical morphology. Academic Press, London, UKGoogle Scholar
  34. 34.
    Gonzalez R C, Woods RE (1992) Digital image processing. Addison-Wesley, New YorkGoogle Scholar
  35. 35.
    Haralick RM, Shapiro LG (1992) Computer and robot vision. Addison-Wesley, New YorkGoogle Scholar
  36. 36.
    Dougherty ER (1994) Optimal mean-absolute-error filtering of gray-scale signals by the morphological hit-and-miss transform. J Math Imaging Vision 4:255–271Google Scholar
  37. 37.
    Bloomberg DS, Vincent L (2000) Pattern matching using the blur hit-miss transform. J Electron Imaging 9(2):140–150CrossRefGoogle Scholar
  38. 38.
    Khosravi M, Schafer RW (1996) Template matching based on a grayscale hit-and-miss transform. IEEE Trans Image Process 5(6):1060–1066CrossRefGoogle Scholar
  39. 39.
    Raducanu B, Graña M (2000) Face localization based on the morphological multiscale fingerprints. In: Proceedings of the international conference on pattern recognition, ICPR2000, pp 929–932Google Scholar
  40. 40.
    Jackway PT, Deriche M (1996) Scale-space properties of the multiscale morphological dilation-erosion. IEEE Trans Pattern Anal Mach Intell 18(1):38–51CrossRefGoogle Scholar
  41. 41.
    Huttenlocher DP, Klanderman GA, Rucklidge WJ (1993) Comparing images using the hausdorff distance. IEEE Trans Pattern Anal Mach Intell 15(9):850–863CrossRefGoogle Scholar
  42. 42.
    Wiskott L, Fellous J-M, Kuiger N, Malsburg C vd (1997) Face recognition by elastic bunch graph matching. IEEE Trans Pattern Anal Mach Intell 19(7):775–779CrossRefGoogle Scholar
  43. 43.
    Wilson RC, Hancock ER (1997) Structural matching by discrete relaxation. IEEE Trans Pattern Anal Mach Intell 19(6):634–648CrossRefGoogle Scholar
  44. 44.
    Boomgaard R vd, Smeulders AWM, Schavemaker JGM (1994) Image segmentation in morphological scale-space. In: Proceedings of international symposium on mathematical morphology, pp 15–16Google Scholar
  45. 45.
    Kohonen T (1995) Self organizing maps. Springer, Berlin Heidelberg New YorkGoogle Scholar
  46. 46.
    Turk M, Pentland A (1991) Eigenfaces for recognition. J Cognitive Neurosci 3(1):71–86Google Scholar

Copyright information

© Springer-Verlag London Limited 2004

Authors and Affiliations

  • B. Raducanu
    • 1
  • M. Graña
    • 1
    Email author
  • F. X. Albizuri
    • 1
  • A. d’Anjou
    • 1
  1. 1.Department of CCIAUniversidad del Pais VascoSpain

Personalised recommendations