A Shape Descriptor Based on Trainable COSFIRE Filters for the Recognition of Handwritten Digits

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.

[1]  Thomas Villmann,et al.  Generalized relevance learning vector quantization , 2002, Neural Networks.

[2]  Thomas Martinetz,et al.  The Support Feature Machine for Classifying with the Least Number of Features , 2010, ICANN.

[3]  Luiz Eduardo Soares de Oliveira,et al.  Metaclasses and Zoning Mechanism Applied to Handwriting Recognition , 2008, J. Univers. Comput. Sci..

[4]  Nikolay Petkov,et al.  Biologically motivated computationally intensive approaches to image pattern recognition , 1995, Future Gener. Comput. Syst..

[5]  Ehsanollah Kabir,et al.  Introducing a very large dataset of handwritten Farsi digits and a study on their varieties , 2007, Pattern Recognit. Lett..

[6]  Mohammad Rahmati,et al.  Recognition of Persian handwritten digits using image profiles of multiple orientations , 2004, Pattern Recognit. Lett..

[7]  Matti Pietikäinen,et al.  An Experimental Comparison of Autoregressive and Fourier-Based Descriptors in 2D Shape Classification , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Cheng-Lin Liu,et al.  Handwritten digit recognition: benchmarking of state-of-the-art techniques , 2003, Pattern Recognit..

[9]  Changsong Liu,et al.  Gabor filters-based feature extraction for character recognition , 2005, Pattern Recognit..

[10]  Lazaros S. Iliadis,et al.  Artificial Neural Networks - ICANN 2010 - 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part I , 2010, International Conference on Artificial Neural Networks.

[11]  Ali Borji,et al.  Invariance analysis of modified C2 features: case study—handwritten digit recognition , 2009, Machine Vision and Applications.

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  George Azzopardi,et al.  Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Majid Ahmadi,et al.  Shape redognition using zernike moment invariants , 1989, Twenty-Third Asilomar Conference on Signals, Systems and Computers, 1989..

[15]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[16]  C. Connor,et al.  Population coding of shape in area V4 , 2002, Nature Neuroscience.

[17]  Marcel F. Jonkman,et al.  Learning effective color features for content based image retrieval in dermatology , 2011, Pattern Recognit..

[18]  Luca Maria Gambardella,et al.  Convolutional Neural Network Committees for Handwritten Character Classification , 2011, 2011 International Conference on Document Analysis and Recognition.

[19]  Fariborz Mahmoudi,et al.  Robust Handwritten Character Recognition with Features Inspired by Visual Ventral Stream , 2008, Neural Processing Letters.

[20]  M. Kolesnik,et al.  Unsupervised shape learning in a neuromorphic hierarchy , 2008, Pattern Recognition and Image Analysis.

[21]  Zhang Chuang,et al.  The segmentation algorithm for handwritten numeral strings in bank-check recognition , 2007 .

[22]  Paul D. Gader,et al.  Recognition of handwritten digits using template and model matching , 1991, Pattern Recognit..

[23]  Subhadip Basu,et al.  Recognition of Numeric Postal Codes from Multi-script Postal Address Blocks , 2009, PReMI.

[24]  Dayong Wang,et al.  Invariant image recognition by neural networks and modified moment invariants , 1996, Other Conferences.