The Study of Handwriting Recognition Algorithms Based on Neural Networks
AUTHORS
Barak Finkelstein,Athabasca University , Canada
Kaplan Kuncan,Athabasca University , Canada
ABSTRACT
Handwriting Identifies basic graph-like problems and has a high real-world value in areas such as cloud accounting, finance, and postal administration. Due to the unrestricted problem of handwritten numbers when writing, it is relatively difficult to achieve rapid and effective recognition. With the emergence of deep learning-related algorithms and the rapid development of computer hardware technology, image classification methods based on Convolutional Neural Network (CNN) have gradually become a research hotspot. Because the convolutional network has a strong letter numbering ability and network generalization ability, the recognition rate can often exceed the traditional graph classing method. Therefore, the study of hand-written word recognition should be implemented using CNN through the network. Handwriting Word Recognition is the key technique for self-identification. Therefore, summarizing and analyzing the existing handwritten digit recognition algorithms, two handwritten digit recognition algorithms based on Convolutional Neural Network (CNN) are proposed. To improve the recognition performance of the CNN model, this article proposes a handwriting recognition algorithm based on the change to CNN. To extract the image feature information more fully, this paper proposes a handwriting recognition algorithm based on feature fusion and SVM. First, using the modified CNN model and the Gabor filter that introduces curvature systems, extract the CNN and Gabor characteristics of the character image; Second, the characteristics of its progress are fused to obtain more effective new features; Finally, the fusion feature is entered into the SVM classifier into the line number of words to recognize. The results of the experiment show that the algorithm can effectively improve the recognition effect of handwritten words
KEYWORDS
Handwritten digit recognition, Convolution neural network, Character segmentation, Gabor filter, SVM classifier
REFERENCES
[1] Hao M. L., Tian Q. C., and Bai X., “The study of feature extraction of handwritten digits based on ruler algorithm,” Applied Mechanics and Materials, pp.1202-1207, (2014)
[2] Yu N. G. and Jiao P. N., “Handwritten digits recognition approach research based on distance and Kernel PCA,” // Proceedings of the 5th International Conference on Advanced Computational Intelligence. Nanjing: IEEE, pp.689-693, (2012)
[3] Ma C. Y. and Zhang H., “Effective handwritten digit recognition based on multi-feature extraction and deep analysis,” // Proceedings of the 12th International Conference on Fuzzy Systems and Knowledge Discovery, Zhangjiajie: IEEE, pp.297-301, (2015)
[4] Wu X. H. and Zhou J. J., “Fuzzy discriminant analysis with kernel methods,” Pattern Recognition, vol.39, no.11, pp.2236-2239, (2006)
[5] Robinson M. D., Manry M. T., Malalur S. S., et al., “Properties of a batch training algorithm for feedforward networks,” Neural Processing Letters, vol.45, no.3, pp.841-854, (2017)
[6] Yu B. S., Wang S. L., Yang T., et al., “BP neural network constitutive model based on optimization with genetic algorithm for SMA,” Acta Metallurgica Sinica, vol.53, no.2, pp.248-256, (2017)
[7] Sanni K., Garreau G., Molin J. L., et al., “FPGA implementation of a deep belief network architecture for character recognition using stochastic computation,” // Information Sciences and Systems. Baltimore:IEEE, pp.1-5, (2015)
[8] Alani A., “Arabic handwritten digit recognition based on restricted Boltzmann machine and convolutional neural networks,” Information, vol.8, no.4, pp.142-150, (2017)
[9] Darmatasia A., Fanany M., “Handwriting recognition on form document using convolutional neural network and support vector machines,” International Conference on Information and Communication Technology, Malaysia: IEEE, pp.345-353, (2017)
[10] D. Mishkin and J. Matas, “All you need is a good in it,” arXiv:1511.06422, (2016)
[11] Doersch C., Gupta A., and Efros A., “Unsupervised visual representation learning by context prediction,” IEEE International Conference on Computer Vision, (2015)
[12] Wang X. and Gupta A., “Unsupervised learning of visual representations using videos,” IEEE International Conference on Computer Vision, (2015)
[13] P. Agrawal, J. Carreira, and J. Malik, “Learning to see by moving,” IEEE International Conference on Computer Vision, (2015)
[14] Sun M., Song Z., Jiang X., et al., “Learning pooling for convolutional neural network,” Neurocomputing, vol.49, no.10, pp.224-235, (2016)
[15] Ma C. Y. and Zhang H., “Effective handwritten digit recognition based on multi-feature extraction and deep analysis,” Proceedings of the 12th International Conference on Fuzzy Systems and Knowledge Discovery, Zhangjiajie: IEEE, pp.297-301, (2015)
[16] Zufar Kayumov, Dmitrii Tumakov, and Sergey Mosin, “Hierarchical convolutional neural network for handwritten digits recognition,” Procedia Computer Science, vol.171, pp.1927-1934, (2020) DOI: 10.1016/j.procs.2020.04.206(CrossRef)(Google Scholar)