Abstract
The recognition of handwritten digits is an application which has been used as a benchmark for comparing shape recognition methods. We train COSFIRE filters to be selective for different parts of handwritten digits. In analogy with the neurophysiological concept of population coding we use the responses of multiple COSFIRE filters as a shape descriptor of a handwritten digit. We demonstrate the effectiveness of the proposed approach on two data sets of handwritten digits: Western Arabic (MNIST) and Farsi for which we achieve high recognition rates of 99.52% and 99.33%, respectively. COSFIRE filters are conceptually simple, easy to implement and they are versatile trainable feature detectors. The shape descriptor that we propose is highly effective to the automatic recognition of handwritten digits.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Azzopardi, G., Petkov, N.: Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(2), 490–503 (2013)
Basu, S., Das, N., Sarkar, R., Kundu, M., Nasipuri, M., Basu, D.K.: Recognition of Numeric Postal Codes from Multi-script Postal Address Blocks. In: Chaudhury, S., Mitra, S., Murthy, C.A., Sastry, P.S., Pal, S.K. (eds.) PReMI 2009. LNCS, vol. 5909, pp. 381–386. Springer, Heidelberg (2009)
Belkasim, S.O., Shridhar, M., Ahmadi, M.: Shape recognition using Zernike moment invariants. In: Chen, R.R. (ed.) Conference Record. Twenty-Third Asilomar Conference on Signals, Systems ands Computers (IEEE Cat. No.89-CH2836-5), vol. 1, pp. 167–171. IEEE, Naval Postgraduate Sch., San Jose State Univ. Conference Record. Twenty-Third Asilomar Conference on Signals, Systems ands Computers (IEEE Cat. No.89-CH2836-5), Pacific Grove, CA, USA, October 30–November 1 (1989)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(4), 509–522 (2002)
Borji, A., Hamidi, M., Mahmoudi, F.: Robust handwritten character recognition with features inspired by visual ventral stream. Neural Processing Letters 28(2), 97–111 (2008)
Bunte, K., Biehl, M., Jonkman, M.F., Petkov, N.: Learning effective color features for content based image retrieval in dermatology. Pattern Recognition 44(9), 1892–1902 (2011)
Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Convolutional Neural Network Committees for Handwritten Character Classification. In: 11th International Conference on Document Analysis and Recognition, Bei**g, China, pp. 1135–1139 (2011)
Freitas, C.O.A., Oliveira, L.S., Aires, S.B.K., Bortolozzi, F.: Metaclasses and zoning mechanism applied to handwriting recognition. Journal of Universal Computer Science 14(2), 211–223 (2008)
Gader, P., Forester, B., Ganzberger, M., Gillies, A., Mitchell, B., Whalen, M., Yocum, T.: Recognition of handwritten using template and model-matching. Pattern Recognition 24(5), 421–431 (1991)
Hamidi, M., Borji, A.: Invariance analysis of modified C2 features: case study-handwritten digit recognition. Machine Vision and Applications 21(6), 969–979 (2010)
Hammer, B., Villmann, T.: Generalized relevance learning vector quantization. Neural Networks 15(8-9), 1059–1068 (2002)
Kauppinen, H., Seppanen, T., Pietikainen, M.: An experimental comparison of autoregressive and fourier-based descriptors in 2D shape classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(2), 201–207 (1995)
Khosravi, H., Kabir, E.: Introducing a very large dataset of handwritten Farsi digits and a study on their varieties. Pattern Recognition Letters 28(10), 1133–1141 (2007)
Klement, S., Martinetz, T.: The support feature machine for classifying with the least number of features. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part II. LNCS, vol. 6353, pp. 88–93. Springer, Heidelberg (2010)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)
Liu, C.L., Nakashima, K., Sako, H., Fujisawa, H.: Handwritten digit recognition: benchmarking of state-of-the-art techniques. Pattern Recognition 36(10), 2271–2285 (2003)
Oberhoff, D., Kolesnik, M.: Unsupervised shape learning in a neuromorphic hierarchy. Pattern Recognition and Image Analysis, 314–322 (2008)
Pasupathy, A., Connor, C.E.: Population coding of shape in area v4. Nature Neuroscience 5, 1332–1338 (2002)
Petkov, N.: Biologically motivated computationally intensive approaches to image pattern-recognition. Future Generation Computer Systems 11, 451–465 (1995)
Soltanzadeh, H., Rahmati, M.: Recognition of Persian handwritten digits using image profiles of multiple orientations. Pattern Recognition Letters 25(14), 1569–1576 (2004)
Wang, D., **e, W.: Invariant image recognition by a neural networks and modified moment invariants. In: Proceedings of the SPIE - The International Society for Optical Engineering, SPIE; China Opt. & Optoelectron, Manuf. Assoc.; Chinese Opt. Soc. Electronic Imaging and Multimedia Systems, Bei**g, China, November 4-5, pp. 217–223 (1996)
Wang, X.W., Ding, X.Q., Liu, C.S.: Gabor filters-based feature extraction for character recognition. Pattern Recognition 38(3), 369–379 (2005)
Chuang, Z., Zhiqing, L., Bo, X., Jun, G.: The segmentation algorithm for handwritten numeral strings in bank-check recognition. Frontiers of Electrical and Electronic Engineering in China, 39–44 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Azzopardi, G., Petkov, N. (2013). A Shape Descriptor Based on Trainable COSFIRE Filters for the Recognition of Handwritten Digits. In: Wilson, R., Hancock, E., Bors, A., Smith, W. (eds) Computer Analysis of Images and Patterns. CAIP 2013. Lecture Notes in Computer Science, vol 8048. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40246-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-40246-3_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40245-6
Online ISBN: 978-3-642-40246-3
eBook Packages: Computer ScienceComputer Science (R0)