Object Classification Using Encoded Edge Based Structural Information

  • Aditya R. Kanitkar
  • Brijendra K. Bharti
  • Umesh N. Hivarkar
Part of the Communications in Computer and Information Science book series (CCIS, volume 193)


Gaining the understanding of objects present in the surrounding environment is necessary to perform many fundamental tasks. Human vision systems utilize the contour information of objects to perform identification of objects and use prior learnings for their classification. However, computer vision systems still face many limitations in object analysis and classification. The crux of the problem in computer vision systems is identifying and grouping edges which correspond to the object contour and rejecting those which correspond to finer details.

The approach proposed in this work aims to eliminate this edge selection and analysis and instead generate run length codes which correspond to different contour patterns. These codes would then be useful to classify various objects identified. The approach has been successfully applied for day time vehicle detection.


Object Classification Discrete Haar Wavelet Transform Contour Pattern Detection Run length Codes 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Basu, M.: Gaussian-based edge-detection methods: A Survey. IEEE SMC-C (32), 252–260 (2002)Google Scholar
  2. 2.
    Matthews, N.D., An, P.E., Charnley, D., Harris, C.J.: Vehicle detection and recognition in greyscale imagery. Control Eng. Practice 4(4), 473–479 (1996)CrossRefGoogle Scholar
  3. 3.
    Goerick, C., Detlev, N., Werner, M.: Artificial neural networks in real-time car detection and tracking application. Pattern Recognition Letters 17, 335–343 (1996)CrossRefGoogle Scholar
  4. 4.
    Sun, Z., Bebis, G., Miller, R.: On-road vehicle detection using Gabor filters and support vector machines. Digital Signal Processing, 1019–1022 (2002)Google Scholar
  5. 5.
    Papageorgiou, C., Poggio, T.: A trainable system for object detection. International Journal of Computer Vision 4(4), 15–33 (2000)CrossRefzbMATHGoogle Scholar
  6. 6.
    Sun, Z., Bebis, G., Miller, R.: Quantized wavelet features and support vector machines for on-road vehicle detection. In: 7th International Conference on Control, Automation, Robotics and Vision, vol. 3, pp. 1641–1646 (2002)Google Scholar
  7. 7.
    Sun, Z., Bebis, G., Miller, R.: On-road vehicle detection using optical sensors: a review. In: IEEE International Conference on Intelligent Transportation Systems, pp. 585–590. IEEE Press, Washington, DC (2004)Google Scholar
  8. 8.
    Sun, Z., Bebis, G., Miller, R.: Monocular precrash vehicle detection: features and classifiers. IEEE Transactions on Image Processing (2006)Google Scholar
  9. 9.
    Wen, X., Yuan, H., Yang, C., Song, C., Duan, B., Zhao, H.: Improved Haar Wavelet Feature Extraction Approaches for Vehicle Detection. In: Proceedings of the 2007 IEEE Intelligent Transportation Systems Conference, Seattle, WA, USA, September 30-October 3 (2007)Google Scholar
  10. 10.
    Canny, J.F.: A computational approach to edge detection. IEEE PAMI 8(6), 679–698 (1986)CrossRefGoogle Scholar
  11. 11.
    Mallat, S.: A Wavelet Tour of Signal ProcessingGoogle Scholar
  12. 12.
    Grigorescu, C., Petkov, N., Westenberg, M.A.: Contour detection based on non-classical receptive field inhibition. IEEE Trans. on Image Processing, 729–739 (2003)Google Scholar
  13. 13.
    Papari, G., Campisi, P., Petkov, N., Neri, A.: A multiscale approach to contour detection by texture suppression. In: SPIE Image Proc.: Alg. and Syst., San Jose, CA, vol. 6064A (2006)Google Scholar
  14. 14.
    Canu, S., Grandvalet, Y., Guigue, V., Rakotomamonjy, A.: SVM and Kernel Methods Matlab Toolbox. In: Perception Systèmes et Information. INSA de Rouen, Rouen (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Aditya R. Kanitkar
    • 1
  • Brijendra K. Bharti
    • 1
  • Umesh N. Hivarkar
    • 1

Personalised recommendations