Pattern Analysis and Applications

, Volume 13, Issue 3, pp 333–348 | Cite as

A system for 3D texture-based probabilistic object recognition and its applications

Theoretical Advances

Abstract

This article presents a system for texture-based probabilistic classification and localisation of three-dimensional objects in two-dimensional digital images and discusses selected applications. In contrast to shape-based approaches, our texture-based method does not rely on object features extracted using image segmentation techniques. Rather, the objects are described by local feature vectors computed directly from image pixel values using the wavelet transform. Both gray level and colour images can be processed. In the training phase, object features are statistically modelled as normal density functions. In the recognition phase, the system classifies and localises objects in scenes with real heterogeneous backgrounds. Feature vectors are calculated and a maximisation algorithm compares the learned density functions with the extracted feature vectors and yields the classes and poses of objects found in the scene. Experiments carried out on a real dataset of over 40,000 images demonstrate the robustness of the system in terms of classification and localisation accuracy. Finally, two important real application scenarios are discussed, namely recognising museum exhibits from visitors’ own photographs and classification of metallography images.

Keywords

Object recognition Statistical modelling Wavelet analysis Image processing 

References

  1. 1.
    Amit Y, Geman D, Fan X (2004) A coarse-to-fine strategy for multi-class shape detection. IEEE Trans Pattern Anal Mach Intell 26(12):1606–1621CrossRefGoogle Scholar
  2. 2.
    Aroyo L, Wang Y, Brussee R, Gorgels P, Rutledge L, Stash N (2007) Personalized museum experience: the Rijksmuseum use case. In: Proceedings of museums and the Web. San Francisco, USAGoogle Scholar
  3. 3.
    Bentoutou Y, Taleb N, Chikr El Mezouar M, Taleb M, Jetto L (2002) An invariant approach for image registration in digital subtraction angiography. Pattern Recognit 35(12):2853–2865MATHCrossRefGoogle Scholar
  4. 4.
    Chen H, Shimshoni I, Meer P (2004) Model based object recognition by robust information fusion. In: 17th international conference on pattern recognition. Cambridge, UKGoogle Scholar
  5. 5.
    Cho S-J, Kim JH (2004) Bayesian network modeling of strokes and their relationships for on-line handwriting recognition. Pattern Recognit 37(2):253–264MATHCrossRefGoogle Scholar
  6. 6.
    Fründ J, Gausemeier J, Matysczok C, Radkowski R (2004) Using augmented reality technology to support the automobile development. In: Shen W, Lin Z, Barthès J-PA, Li T (eds) 8th international conference on computer supported cooperative work in design. Springer, Xiamen, pp 289–298Google Scholar
  7. 7.
    Gausemeier J, Grafe M, Matysczok C, Radkowski R, Krebs J, Oelschlaeger H (2005) Eine mobile augmented reality versuchsplattform zur untersuchung und evaluation von fahrzeugergonomien. In: Schulze T, Horton G, Preim B, Schlechtweg S (eds) Simulation und Visualisierung. SCS Publishing House e.V., Magdeburg, pp 185–194Google Scholar
  8. 8.
    Goodall S, Lewis PH, Matrinez K, Sinclair PAS, Giorgini F, Addis MJ, Boniface MJ, Lahanier C, Stevenson J (2004) Sculpteur: multimedia retrieval for museums. In: Third international conference on image and video retrieval (CIVR 2004). Dublin, Ireland, pp 638–646Google Scholar
  9. 9.
    Gross R, Matthews I, Baker S (2004) Appearance-based face recognition and light-fields. IEEE Trans Pattern Anal Mach Intell 26(4):449–465CrossRefGoogle Scholar
  10. 10.
    Grzegorzek M, Niemann H (2005) Statistical object recognition including color modeling. In: Kamel M, Campilho A (eds) 2nd international conference on image analysis and recognition. Lecture Notes in Computer Science, vol 3656. Toronto, Canada, Springer, Berlin, pp 481–489Google Scholar
  11. 11.
    Grzegorzek M, Reinhold M, Niemann H (2005) Feature extraction with wavelet transformation for statistical object recognition. In: Kurzynski M, Puchala E, Wozniak M, Zolnierek A (eds) 4th international conference on computer recognition systems. Rydzyna, Poland, Springer, Berlin, pp 161–168Google Scholar
  12. 12.
    Heigl B (2004) Plenoptic scene modeling from uncalibrated image sequences. Ibidem-Verlag, StuttgartGoogle Scholar
  13. 13.
    Heutte L, Nosary A, Paquet T (2004) A multiple agent architecture for handwritten text recognition. Pattern Recognit 37(4):665–674CrossRefGoogle Scholar
  14. 14.
    Hornegger J (1996) Statistische Modellierung, Klassifikation und Lokalisation von Objekten. Shaker Verlag, AachenGoogle Scholar
  15. 15.
    Jin Y, Geman S (2006) Context and hierarchy in a probabilistic image model. In : IEEE conference on computer vision and pattern recognition. New York, USA, pp 2145–2152Google Scholar
  16. 16.
    Kerr J, Compton P (2003) Toward generic model-based object recognition by knowledge acquisition and machine learning. In: Proceedings of the eighteenth international joint conference on artificial intelligence. Acapulco, Mexico, pp 9–15Google Scholar
  17. 17.
    Kumar A (2003) Neural network based detection of local textile defects. Pattern Recognit 36(7):1631–1644CrossRefGoogle Scholar
  18. 18.
    Latecki LJ, Lakaemper R, Wolter D (2005) Optimal partial shape similarity. Image Vis Comput J 23:227–236CrossRefGoogle Scholar
  19. 19.
    Leibe B, Schiele B (2003) Analyzing contour and appearance based methods for object categorization. In: IEEE conference on computer vision and pattern recognition. Madison, USAGoogle Scholar
  20. 20.
    Li CH, Yuen PC (2002) Tongue image matching using color content. Pattern Recognit 35(2):407–419MATHCrossRefGoogle Scholar
  21. 21.
    Liu TY, Tan TH, Chu YL (2006) The ubiquitous museum learning environment: concept, design, implementation, and a case study. In: Sixth international conference on advanced learning technologies. Kerkrade, The Netherlands, pp 989–991Google Scholar
  22. 22.
    Lowe DG (1999) Object recognition from local scale-invariant fearures. In: Seventh international conference on computer vision (ICCV). Corfu, Greece, pp 1150–1157Google Scholar
  23. 23.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  24. 24.
    Mahamud S, Hebert M (2003) The optimal distance measure for object detection. In: IEEE conference on computer vision and pattern recognition. Madison, USAGoogle Scholar
  25. 25.
    Mallat S (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674–693MATHCrossRefGoogle Scholar
  26. 26.
    Murase H, Nayar SK (1995) Visual learning and recognition of 3-D objects from appearance. Int J Comput Vis 14(1):5–24CrossRefGoogle Scholar
  27. 27.
    Nene S, Nayar S, Murase H (1996) Columbia object image library (coil-100). Technical Report CUCS-006-96, Department for Computer Science, Columbia UniversityGoogle Scholar
  28. 28.
    Nene S, Nayar S, Murase H (1996) Columbia object image library (coil-20). Technical Report CUCS-005-96, Department for Computer Science, Columbia UniversityGoogle Scholar
  29. 29.
    Ngan HYT, Pang GKH, Yung SP, Ng MK (2005) Wavelet based methods on patterned fabric defect detection. Pattern Recognit 38(4):559–576CrossRefGoogle Scholar
  30. 30.
    Park CH, Park H (2005) Fingerprint classification using fast fourier transform and nonlinear discriminant analysis. Pattern Recognit 38(4):495–503MATHCrossRefGoogle Scholar
  31. 31.
    Pontil M, Verri A (1998) Support vector machines for 3D object recognition. IEEE Trans Pattern Anal Mach Intell 20(6):637–646CrossRefGoogle Scholar
  32. 32.
    Pösl J (1999) Erscheinungsbasierte, statistische Objekterkennung. Shaker Verlag, AachenGoogle Scholar
  33. 33.
    Praks P, Grzegorzek M, Moravec R, Valek L, Izquierdo E (2007) Wavelet and eigen-space feature extraction for classification of metallography images. In: Jaakkola H, Kiyoki Y, Tokuda T (eds) European–Japanese conference on information modeling and knowledge bases. Juvenes Print-TTY, Tampere, Pori, Finland, pp 193–202Google Scholar
  34. 34.
    Reinhold M (2004) Robuste, probabilistische, erscheinungsbasierte Objekterkennung. Logos Verlag, BerlinGoogle Scholar
  35. 35.
    Rue H, Held L (2005) Gaussian Markov random fields: theory and applications. Chapman & Hall, LondonMATHCrossRefGoogle Scholar
  36. 36.
    Schiele B, Crowley JL (2000) Recognition without correspondence using multidimensional receptive field histograms. Int J Comput Vis 36(1):31–50CrossRefGoogle Scholar
  37. 37.
    Schneiderman H, Kanade T (2004) Object detection using the statistics of parts. Int J Comput Vis 56(3):151–177CrossRefGoogle Scholar
  38. 38.
    Terzopoulos D, Yuencheng L, Vasilescu M (2004) Model-based and image-based methods for facial image synthesis, analysis and recognition. In: Automatic face and gesture recognition 2004. Seoul, Korea, pp 3–8Google Scholar
  39. 39.
    Torralba A, Murphy KP, Freeman WT (2007) Sharing visual features for multiclass and multiview object detection. IEEE Trans Pattern Anal Mach Intell 29(5):854–869CrossRefGoogle Scholar
  40. 40.
    Webb AR (2002) Statistical pattern recognition. Wiley, ChichesterMATHCrossRefGoogle Scholar
  41. 41.
    You B, Hwangbo M, Lee S, Oh S, Kwon Y, Lim S (2003) Development of a home service robot issac. In: Intelligent robots and systems 2003, Las Vegas, USA, pp 2630–2635Google Scholar
  42. 42.
    Zhang Q, Yan H (2004) Fingerprint classification based on extraction and analysis of singularities and pseudo ridges. Pattern Recognit 37(11):2233–2243CrossRefGoogle Scholar
  43. 43.
    Zobel M, Denzler J, Heigl B, Nöth E, Paulus D, Schmidt J, Stemmer G (2003) Mobsy: integration of vision and dialogue in service robots. Mach Vis Appl 14(1):26–34CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2009

Authors and Affiliations

  1. 1.Information Systems and Semantic Web Research GroupUniversity of Koblenz-LandauKoblenzGermany

Personalised recommendations