Digit Recognition is an essential element of the process of scanning and converting documents into electronic format. In this work, a new Multiple-Cell Size (MCS) approach is being proposed for utilizing Histogram of Oriented Gradient (HOG) features and a Support Vector Machine (SVM) based classifier for efficient classification of Handwritten Digits. The HOG based technique is sensitive to the cell size selection used in the relevant feature extraction computations. Hence a new MCS approach has been used to perform HOG analysis and compute the HOG features. The system has been tested on the Benchmark MNIST Digit Database of handwritten digits and a classification accuracy of 99.36% has been achieved using an Independent Test set strategy. A Cross-Validation analysis of the classification system has also been performed using the 10-Fold Cross-Validation strategy and a 10-Fold classification accuracy of 99.26% has been obtained. The classification performance of the proposed system is superior to existing techniques using complex procedures since it has achieved at par or better results using simple operations in both the Feature Space and in the Classifier Space. The plots of the system’s Confusion Matrix and the Receiver Operating Characteristics (ROC) show evidence of the superior performance of the proposed new MCS HOG and SVM based digit classification system.
References
[1]
Schantz, H.F. (1982) The History of OCR. Recognition Technologies Users Association, VT.
[2]
Zhou, Z.H. and Feng, J. (2017) Deep Forest: Towards an Alternative to Deep Neural Networks. arXiv preprint arXiv:1702.08835. https://arxiv.org/pdf/1702.08835.pdf
[3]
Nielsen, M.A. (2015) Neural Networks and Deep Learning.
http://neuralnetworksanddeeplearning.com/
[4]
Bengio, Y.I., Goodfellow, J. and Courville, A. (2016) Deep Learning. MIT Press, Cambridge, MA. http://www.deeplearningbook.org
[5]
Farulla, G.A., Murru, N. and Rossini, R. (2016) A Fuzzy Approach for Segmentation of Touching Characters. arXiv:1612.04862v1. https://arxiv.org/abs/1612.04862
[6]
Chen, G., Li, Y. and Srihari, S.N. (2016) Word Recognition with Deep Conditional Random Fields. Proceedings of the IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, 25-28 September 2016, 1928-1932.
https://doi.org/10.1109/icip.2016.7532694
[7]
Liu, Z., Li, Y., Ren, F. and Yu, H. (2016) A Binary Convolutional Encoder-Decoder Network for Real-Time Natural Scene Text Processing. arXiv:1612.03630v1.
https://arxiv.org/abs/1612.03630v1
[8]
Jaderberg, M., Simonyan, K., Vedaldi, A. and Zisserman, A. (2014) Reading Text in the Wild with Convolutional Neural Networks. arXiv preprint arXiv:1412.1842.
[9]
Yin, X.C., Yin, X., Huang, K. and Hao, H.W. (2014) Robust Text Detection in Natural Scene Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 970-983. https://doi.org/10.1109/TPAMI.2013.182
[10]
LeCun, Y., Cortes, C. and Burges, C.J. (1998) The MNIST Database of Handwritten Digits. http://yann.lecun.com/exdb/mnist/
[11]
Tabacof, P., Tavares, J. and Valle, E. (2016) Adversarial Images for Variational Autoencoders. https://arxiv.org/pdf/1612.00155v1.pdf
[12]
LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P.(1998) Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86, 2278-2324.
https://doi.org/10.1109/5.726791
[13]
Decoste, D. and Scholkopf, B. (2002) Training Invariant Support Vector Machines. Machine Learning, 46, 161-190. https://doi.org/10.1023/A:1012454411458
[14]
Simard, P.Y., Steinkraus, D. and Platt, J.C. (2003) Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis. Proceedings of the 7th International Conference on Document Analysis and Recognition, 3, 958-963.
https://doi.org/10.1109/icdar.2003.1227801
[15]
Keysers, D., Deselaers, T., Gollan, C. and Ney, H. (2007) Deformation Models for Image Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29, 1422-1435. https://doi.org/10.1109/TPAMI.2007.1153
[16]
Meier, U., Ciresan, D.C., Gambardella, L.M. and Schmidhuber, J. (2011) Better Digit Recognition with a Committee of Simple Neural Nets. IEEE International Conference on Document Analysis and Recognition, Beijing, 18-21 September 2011, 1250-1254.
[17]
Ciresan, D., Meier, U. and Schmidhuber, J. (2012) Multi-Column Deep Neural Networks for Image Classification. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, 16-21 June 2012, 3642-3649. https://doi.org/10.1109/cvpr.2012.6248110
[18]
Ciresan, D.C., Meier, U., Gambardella, L.M. and Schmidhuber, J. (2011) Convolutional Neural Network Committees for Handwritten Character Classification. IEEE International Conference on Document Analysis and Recognition, Beijing, 18-21 September 2011, 1135-1139.
[19]
Dalal, N. and Triggs, B (2005) Histograms of Oriented Gradients for Human Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), 1, 886-893.
[20]
Freeman, W.T. and Roth, M. (1995) Orientation Histograms for Hand Gesture Recognition. International Workshop on Automatic Face and Gesture Recognition, 12, 296-301.
[21]
Machine Learning with MATLAB, MathsWorks.
www.mathworks.com/solutions/machine-learning.html
[22]
Cortes, C. and Vapnik, V. (1995) Support-Vector Networks. Machine Learning, 20, 273-297. https://doi.org/10.1007/BF00994018
[23]
Dietterich, T.G. and Bakiri, G. (1995) Solving Multiclass Learning Problems via Error-Correcting Output Codes. Journal of Artificial Intelligence Research, 2, 263-286.
