Recognizing Handwritten Characters with Local Descriptors and Bags of Visual Words

  • Olarik Surinta
  • Mahir F. Karaaba
  • Tusar K. Mishra
  • Lambert R. B. Schomaker
  • Marco A. Wiering
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 517)


In this paper we propose the use of several feature extraction methods, which have been shown before to perform well for object recognition, for recognizing handwritten characters. These methods are the histogram of oriented gradients (HOG), a bag of visual words using pixel intensity information (BOW), and a bag of visual words using extracted HOG features (HOG-BOW). These feature extraction algorithms are compared to other well-known techniques: principal component analysis, the discrete cosine transform, and the direct use of pixel intensities. The extracted features are given to three different types of support vector machines for classification, namely a linear SVM, an SVM with the RBF kernel, and a linear SVM using L2-regularization. We have evaluated the six different feature descriptors and three SVM classifiers on three different handwritten character datasets: Bangla, Odia and MNIST. The results show that the HOG-BOW, BOW and HOG method significantly outperform the other methods. The HOG-BOW method performs best with the L2-regularized SVM and obtains very high recognition accuracies on all three datasets.


Handwritten character recognition Feature extraction Bag of visual words Histogram of oriented gradients Support vector machines 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abdullah, A., Veltkamp, R., Wiering, M.: Ensembles of novel visual keywords descriptors for image categorization. In: 2010 11th International Conference on Control Automation Robotics Vision (ICARCV), pp. 1206–1211, December 2010Google Scholar
  2. 2.
    Arróspide, J., Salgado, L., Camplani, M.: Image-based on-road vehicle detection using cost-effective histograms of oriented gradients. Visual Communication and Image Representation 24(7), 1182–1190 (2013)CrossRefGoogle Scholar
  3. 3.
    Bhowmik, T.K., Ghanty, P., Roy, A., Parui, S.: SVM-based hierarchical architectures for handwritten Bangla character recognition. Document Analysis and Recognition (IJDAR) 12(2), 97–108 (2009)CrossRefGoogle Scholar
  4. 4.
    Cireşan, D.C., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3642–3649, June 2012Google Scholar
  5. 5.
    Coates, A., Carpenter, B., Case, C., Satheesh, S., Suresh, B., Wang, T., Wu, D., Ng, A.: Text detection and character recognition in scene images with unsupervised feature learning. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 440–445, September 2011Google Scholar
  6. 6.
    Coates, A., Lee, H., Ng, A.Y.: An analysis of single-layer networks in unsupervised feature learning. In: 2011 International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 215–223, April 2011Google Scholar
  7. 7.
    Csurka, G., Dance, C.R., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: 2004 8th European Conference on Computer Vision (ECCV), pp. 1–22 (2004)Google Scholar
  8. 8.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 The IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 886–893, vol. 1, June 2005Google Scholar
  9. 9.
    Deepu, V., Madhvanath, S., Ramakrishnan, A.: Principal component analysis for online handwritten character recognition. In: 2004 The 17th International Conference on Pattern Recognition (ICPR), vol. 2, pp. 327–330, August 2004Google Scholar
  10. 10.
    Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., Lin, C.-J.: LIBLINEAR: A library for large linear classification. Machine Learning Research 9, 1871–1874 (2008)MATHGoogle Scholar
  11. 11.
    Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)MathSciNetCrossRefMATHGoogle Scholar
  12. 12.
    Hinton, G.E., Zemel, R.S.: Autoencoders, minimum description length and Helmholtz free energy. In: Cowan, J., Tesauro, G., Alspector, J. (eds.) Advances in Neural Information Processing Systems, vol. 6, pp. 3–10. Morgan-Kaufmann (1994)Google Scholar
  13. 13.
    Hossain, M., Amin, M., Yan, H.: Rapid feature extraction for bangla handwritten digit recognition. In: 2011 International Conference on Machine Learning and Cybernetics (ICMLC), vol. 4, pp. 1832–1837, July 2011Google Scholar
  14. 14.
    Karaaba, M.F., Schomaker, L., Wiering, M.: Machine learning for multi-view eye-pair detection. Engineering Applications of Artificial Intelligence 33, 69–79 (2014)CrossRefGoogle Scholar
  15. 15.
    Lawgali, A., Bouridane, A., Angelova, M., Ghassemlooy, Z.: Handwritten Arabic character recognition: Which feature extraction method? Advanced Science and Technology 34, 1–8 (2011)Google Scholar
  16. 16.
    LeCun, Y., Cortes, C.: The MNIST database of handwritten digits (1998)Google Scholar
  17. 17.
    Meier, U., Ciresan, D., Gambardella, L., Schmidhuber, J.: Better digit recognition with a committee of simple neural nets. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 1250–1254, September 2011Google Scholar
  18. 18.
    Mishra, T., Majhi, B., Panda, S.: A comparative analysis of image transformations for handwritten odia numeral recognition. In: 2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 790–793, August 2013Google Scholar
  19. 19.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man and Cybernetics 9(1), 62–66 (1979)CrossRefGoogle Scholar
  20. 20.
    Schmidhuber, J.: Deep learning in neural networks: An overview. Neural Networks 61, 85–117 (2015)CrossRefGoogle Scholar
  21. 21.
    Surinta, O., Schomaker, L., Wiering, M.: A comparison of feature and pixel-based methods for recognizing handwritten bangla digits. In: 2013 International Conference on Document Analysis and Recognition (ICDAR), pp. 165–169, August 2013Google Scholar
  22. 22.
    Takahashi, K., Takahashi, S., Cui, Y., Hashimoto, M.: Remarks on computational facial expression recognition from HOG features using quaternion multi-layer neural network. In: Mladenov, V., Jayne, C., Iliadis, L. (eds.) EANN 2014. CCIS, vol. 459, pp. 15–24. Springer, Heidelberg (2014) Google Scholar
  23. 23.
    Vapnik, V.N.: Statistical Learning Theory. Wiley, September 1998Google Scholar
  24. 24.
    Ye, P., Kumar, J., Kang, L., Doermann, D.: Unsupervised feature learning framework for no-reference image quality assessment. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1098–1105, June 2012Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Olarik Surinta
    • 1
  • Mahir F. Karaaba
    • 1
  • Tusar K. Mishra
    • 2
  • Lambert R. B. Schomaker
    • 1
  • Marco A. Wiering
    • 1
  1. 1.Institute of Artificial Intelligence and Cognitive Engineering (ALICE)University of GroningenGroningenThe Netherlands
  2. 2.Department of Computer Science and EngineeringNational Institute of TechnologyRourkelaIndia

Personalised recommendations