Open Access Open Access  Restricted Access Subscription or Fee Access

Use of Sparse Histogram in Patch Based Generic Visual Categorization

R. Ahila Priyadharshini, S. Arivazhagan

Abstract


This paper elaborately discusses on effective method for object classification. In the intricate process of object recognition, it so happens that images have often to be classified based on objects which constitute only a very limited part of the image. By using Patches (local features) properly, the properties of certain regions of an image can be described in detail. Then the object parts can be modeled based on the image patches extracted with regard to each salient point, where the information content is high. The information collected thus are, then, properly stored in an histogram. It is proposed to use a sparse representation of the histograms, i.e., only those bins whose content is not empty are stored. The distances between the histograms of the test image and training images are computed by using an appropriate classifier and finally they are classified. The experimental evaluation of the proposed method is carried out using the Caltech database.

Keywords


Salient Points, Principal Component Analysis, Sparse Histogram, Cross-Bin Distance Measures

Full Text:

PDF

References


A. Opelt, A. Pinz, M. Fussenegger, P. Auer, „Generic Object Recognition with Boosting‟, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.28, N0. 3, pp. 416-431, March 2006.

C. Schmid and R. Mohr, „Local gray value invariants for image retrieval‟, IEEE PAMI, pp. 530-534, 1997.

T. Desealers, D. Keysers, H. Ney, „Features for Image Retrieval-A Quantitative Comparison‟, Proc. DAGM 2004, Pattern Recognition, 26th DAGM Symposium, number 3175 in Lecture Notes in Computer Science, pp.228-236, Tubingen, Germany, Sept.2004.

R. Pardes, J. Perez-Cortes, A. Juan, E. Vidal, „Local Representations and a Direct Voting Scheme for Face Recognition. Proc. Workshop on Pattern Recognition in Information Systems, pp. 71-79, Setubal, Portugal, July 2001.

Shivani Agarwal and Dan Roth, „Learning a sparse representation for object detection‟, In Proceedings of the Seventh European Conference on Computer Vision, Vol. 4, pp. 113-130, 2002.

V. Ferrari, T. Tuytelaars, L.J. van Goola, „Simultaneous Object Recognition and Segmentation by Image Exploration‟, Proc. European Conference on Computer Vision, pp. 40-54, 2004.

Y. LeCun, F.J. Huang, L. Bottou, „Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting‟, Proc. CVPR(2), pp.97-104, 2004.

Krystian Mikolajczyk and Cordelia Schmid , „Scale & Affine Interest Point Detectors‟, International Journal of Computer Vision 60(1), 63–86, 2004.

Haralick, R.M. and Shapiro, L.G, „Computer and Robot Vision‟, Addison-Wesley, Readin, Massachusetts, USA, 1992.

C. Harris and M.J. Stephens, „A Combined corner and edge detector‟, In Alvey Vision Conference, pp 147-152, 1988.

T. Desealers, D. Keysers, H. Ney, „Improving a Discriminative Training Approach to Object Recognition using Image Patches‟, Proc. DAGM 2005,Pattern Recognition,26th DAGM Symposium, number 3663 in Lecture Notes in Computer Science, pp.326-333,Vienna, Austria, Aug, 2005.

R.O. Duda, P.E. Hart, D.G. Stork, „Pattern Classification‟, John Wiley and Sons, New York, Ny, 2nd Edition, 2001.

R. Paredes, D. Keysers, T.M. Lehmann, B.B. Wein, H. Ney, E. Vidal, „Classification of Medical Images using Local Representations‟, Proc. Bildverarbeitung fur die Medizin, pp.171-174, Leipzig, Germany, 2002.

Desealers, D. Keysers, H. Ney, „Discriminative training for Object Recognition using Image Patches‟, Proc. IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2, pp.157-162, San Diego, CA, June 2005.

Thomas Deselaers, Andre Hegerath, Daniel Keysers, Hermann Ney, „Sparse Patch-Histograms for Object Classification in Cluttered Images‟, DAGM 2006.

J. Puzicha, Y. Rubner, C. Tomasi, J. Buhmann, “Empirical Evaluation of Dissimilarity Measures for Color and Texture”, Proc. International Conference on Computer Vision, Vol.2, pp.1165-1173, Corfu, Greece. Sept.1999.

D. Keysers, C. Gollan, H. Ney, „Local Context in Non-Linear Deformation Models for Handwritten Character Recognition‟, Proc. International conference on Pattern Recognition, Vol. 4, pp.511-514, Cambridge, UK, Aug 2004.

Atutorial on Principal Component Analysis „http://www. cs.otago.ac.nz/cosc453/student_tutorials/principal_components.pdf‟

Principal Component Analysis „http://support.sas.com/publishing /pubcat/chaps/55129.pdf‟


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.