Local probabilistic descriptors for image categorisation

Access Full Text

Local probabilistic descriptors for image categorisation

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Add to cart
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)
Add to cart

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

© The Institution of Engineering and Technology
Published

Image categorisation involves the well known difficulties with different visual appearances of a single object, but also introduces the problem of within-category variation. This within-category variation makes highly distinctive local descriptors less appropriate for categorisation. Difficulties because of the within category variation and clutter are tackled by modelling image fragments in a new manner. The authors propose a family of local image descriptors, called probabilistic patch descriptors (PPDs). PPDs encode the appearance of image fragments as well as their variability within a category. PPDs extend the usual local descriptors by also modelling the variance of the descriptors' elements, for example pixels or bins in a histogram. To compare two PPDs, and a PPD with an image, a new similarity measure called PPD matching score is introduced. For each object category, a set of representative PPDs is learnt. Images are represented as feature vectors of the best matching scores obtained for representative PPDs in images. Support vector machine classifiers are then trained on the feature vectors. PPDs are applied to image categorisation using machine learning where the features are the matching scores between images and PPDs. The authors experiment with two variants of PPDs that are based on complementary local descriptors. An interesting observation is that combining the two PPD variants improves the accuracy of categorisation. Experiments indicate that the benefits of modelling the within-category variation give results that are comparable with the state-of-the-art categorisation methods, and show good robustness with respect to noise and occlusions.

Inspec keywords: image matching; support vector machines; probability; image classification; image representation; image coding; learning (artificial intelligence)

Other keywords: local probabilistic patch descriptor; histogram; machine learning; image categorisation; image matching; support vector machine classifier; image representation; feature vector; encoding

Subjects: Image and video coding; Other topics in statistics; Computer vision and image processing techniques; Other topics in statistics; Knowledge engineering techniques

References

    1. 1)
    2. 2)
    3. 3)
      • Mikolajczyk, K., Zisserman, A., Schmid, C.: `Shape recognition with edge based features', Proc. British Machine Vision Conf., BMVC, 2003, Norwich, England, 2, p. 779–788.
    4. 4)
      • Csurka, G., Dance, G., Fan, L., Willamowski, J., Bray, C.: `Visual categorization with bags of keypoints', Proc. Workshop on Statistical Learning in Computer Vision, ECCV, 2004, Prague, Czech Republic, p. 1–22.
    5. 5)
      • Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: `Weak hypotheses and boosting for generic object detection and recognition', European Conf. Computer Vision, ECCV, 2004, Prague, Czech Republic, 2, p. 71–84.
    6. 6)
      • Perronnin, F., Dance, C.R., Csurka, G., Bressan, M.: `Adapted vocabularies for generic visual categorization', European Conf. Computer Vision, ECCV, 2006, Graz, Austria, 4, p. 464–475.
    7. 7)
      • Fritz, M., Schiele, B.: `Towards unsupervised discovery of visual categories', Proc. 28th Annual Symp. German Association for Pattern Recognition, DAGM, 2006, Berlin, Germany.
    8. 8)
      • Agarwal, S., Roth, D.: `Learning a sparse representation for object detection', European Conf. Computer Vision, ECCV, 2002, Copenhagen, Denmark, 4, p. 113–130.
    9. 9)
      • Leibe, B., Leonardis, A., Schiele, B.: `Combined object categorization and segmentation with an implicit shape model', Proc. Workshop on Statistical Learning in Computer Vision, ECCV, 2004, Prague, Czech Republic.
    10. 10)
      • Mele, K.: `Visual learning of categories by local descriptors', 2005, PhD, University of Ljubljana, Slovenia, Slovene.
    11. 11)
      • Borenstein, E., Ullman, S.: `Learning to segment', European Conf. Computer Vision, ECCV, 2004, Prague, Czech Republic, 3, p. 315–328.
    12. 12)
      • Deng, H., Zhang, W., Mortensen, E.N., Dietterich, T.G., Shapiro, L.G.: `Principal curvature-based region detector for object recognition', IEEE Conf. Computer Vision and Patern Recognition, CVPR, 2007, Minneapolis, Minnesota.
    13. 13)
      • Mikolajczyk, K., Leibe, B., Schiele, B.: `Local features for object class recognition', Proc. Int. Conf. Computer Vision, ICCV, 2005, Washington, DC, p. 1792–1799.
    14. 14)
      • Fei-Fei, L., Fergus, R., Perona, P.: `Learning generative visual models from few training examples an incremental bayesian approach tested on 101 object categories', Proc. Workshop on Generative-Model Based Vision, 2004, Washington, DC.
    15. 15)
      • Berg, A.C., Malik, J.: `Geometric blur for template matching', IEEE Conf. Computer Vision and Patern Recognition, CVPR, 2001, Kauai, Hawaii, 1, p. 607–614.
    16. 16)
      • Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: `Discovering object categories in image collections', Proc. Int. Conf. Computer Vision, ICCV, 2005, Bejing, China.
    17. 17)
      • Berg, A.C., Berg, T.L., Malik, J.: `Shape matching and object recognition using low distortion correspondences', IEEE Conf. Computer Vision and Patern Recognition, CVPR, 2005, San Diego, CA, USA, 1, p. 26–33.
    18. 18)
      • Ke, Y., Sukthankar, R.: `Pca-sift: a more distinctive representation for local image descriptors', IEEE Conf. Computer Vision and Patern Recognition, CVPR, 2004, 2, p. 506–513.
    19. 19)
    20. 20)
      • J. Platt , B. Scölkopf , C.J.C. Burges , A.J. Smola . (1999) Fast training of support vector machines using sequential minimal optimization, Advances in Kernel methods – support vector learning.
    21. 21)
    22. 22)
      • Weber, M., Welling, M., Perona, P.: `Unsupervised learning of models for recognition', European Conf. Computer Vision, ECCV, 2000, Dublin, Ireland, 1, p. 18–32.
    23. 23)
      • Weber, M.: `Unsupervised learning of models for visual object class recognition', 2000, PhD, California Institute of Technology.
    24. 24)
      • Thureson, J., Carlsson, S.: `Appearance based qualitative image description for object class recognition', European Conf. Computer Vision, ECCV, 2004, Prague, Czech Republic, 2, p. 518–529.
    25. 25)
      • Fergus, R., Perona, P., Zisserman, A.: `A visual category filter for google images', European Conf. Computer Vision, ECCV, 2004, Prague, Czech Republic, p. 242–256.
    26. 26)
    27. 27)
      • Leibe, B., Schiele, B.: `Scale-invariant object categorization using a scale adaptive mean-shift search', DAGM-Symp., 2004, Tüubingen, Germany, p. 145–153.
    28. 28)
      • I.H. Witten , E. Frank . (1999) Data mining: practical machine learning tools and techniques with Java implementations.
    29. 29)
      • Jojić, N., Frey, B., Kannan, A.: `Epitomic analysis of appearance and shape', Proc. Int. Conf. Computer Vision, ICCV, 2003, Nice, France, p. 34–42.
    30. 30)
      • Fussenegger, M., Opelt, A., Pinz, A., Auer, P.: `Object recognition using segmentation for feature detection', Int. Conf. Pattern Recognition, ICPR, 2004, Cambridge, UK, 3, p. 41–44.
    31. 31)
      • Winn, J.M., Criminisi, A., Minka, T.P.: `Object categorization by learned universal visual dictionary', Proc. Int. Conf. Computer Vision, ICCV, 2005, Bejing, China, p. 1800–1807.
    32. 32)
      • http://www.vision.caltech.edu/Image_Datasets/Caltech101/, accessed April 2008.
    33. 33)
      • Kadir, T., Zisserman, A., Brady, M.: `An affine invariant salient region detector', European Conf. Computer Vision, ECCV, 2004, Pragne, Czech Republic, 1, p. 228–241.
    34. 34)
      • Perronnin, F., Dance, C.R.: `Fisher kernels on visual vocabularies for image categorization', IEEE Conf. Computer Vision and Patern Recognition, CVPR, 2007, Minneapolis, Minnesota, p. 1–8.
    35. 35)
      • T. Kadir , M. Brady . Saliency, scale and image description. Int. J. Comput. Vis. , 83 - 105
    36. 36)
      • Nilsback, M., Caputo, B.: `Cue integration through discriminative accumulation', IEEE Conf. Computer Vision and Patern Recognition, CVPR, Washington, DC, 2, IEEE Computer Society, p. 578–585, 2004.
    37. 37)
      • Nanda, H., Davis, L.: `Probabilistic template based pedestrian detection in infrared videos', Technical Report MD-20742, 2001, Department of Computer Science, University of Maryland.
    38. 38)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi_20070001
Loading

Related content

content/journals/10.1049/iet-cvi_20070001
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading