Effectiveness of artificial neural networks in recognising handwriting characters
Marek Miłosz
m.milosz@pollub.plInstitute of Computer Science, Lublin University of Technology, Nadbystrzycka 36B, 20-618 Lublin, Poland (Poland)
Janusz Gazda
Institute of Computer Science, Lublin University of Technology, Nadbystrzycka 36B, 20-618 Lublin, Poland (Poland)
Abstract
Artificial neural networks are one of the tools of modern text recognising systems from images, including handwritten ones. The article presents the results of a computational experiment aimed at analyzing the quality of recognition of handwritten digits by two artificial neural networks (ANNs) with different architecture and parameters. The correctness indicator was used as the basic criterion for the quality of character recognition. In addition, the number of neurons and their layers and the ANNs learning time were analyzed. The Python language and the TensorFlow library were used to create the ANNs, and software for their learning and testing. Both ANNs were learned and tested using the same big sets of images of handwritten characters.
Keywords:
character recognition; handwriting; artificial neural networksReferences
[2] S. Anagnoste, Robotic Automation Process - The next major revolution in terms of back office operations improvement, Proceedings of The International Conference on Business Excellence, vol 11(1) (2017), 676-686.
[3] W. Kacalak, M. Majewski, A New Method for Handwriting Recognition Using Artificial Neural Networks. Intelligent Engineering Systems Through Artificial Neural Networks, 16 (2006), 459-465.
[4] J. Smołka, M. Skublewska-Paszkowska, E. Łukasik, Algorithm for selecting optimal clustering parameters used for oversegmentation reduction. PRZEGLAD ELEKTROTECHNICZNY, 9, ( 2016), 250-256.
[5] Z. Gomółka, B. Twaróg, E. Żesławska, Rozpoznawanie pisma odręcznego za pomocą sztucznych sieci neuronowych, Technical News, (2013), 98-102.
[6] J. Gazda, Zastosowanie sztucznych sieci neuronowych do rozpoznawania tekstu. Praca dyplomowa pod kierunkiem M.Miłosza, Lublin, (2018), 42.
[7] What is the TensorFlow machine intelligence platform? https://opensource.com/article/17/11/intro-tensorflow [11.01.2018]
[8] HaoBiao, Dae-Seong Kang, The Research of Face Expression Recognition based on CNN using Tensorflow. Journal of Advanced Information Technology and Convergence, 7, (2017), 55-63.
[9] A. Ignatov, Real-time human activity recognition from accelerometer data using Convolutional Neural Networks. Applied Soft Computing, 62, (2018), 915-922.
[10] F. Ertam, G. Aydin, Data classification with deep learning using Tensorflow. 2017 International Conference on Computer Science and Engineering (UBMK), (2017), 755-758.
[11] N. Gavai, Y. Jakhade, S. Tribhuvan, R. Bhattad, MobileNets for flower classification using TensorFlow. 2017 International Conference on Big Data, IoT and Data Science (BID) Big Data, IoT and Data Science, (2017), 154-158.
[12] J. Evermann, J. R. Rehse, P. Fettke, XES tensorflow - Process prediction using the tensorflow deep-learning framework. Proceedings of the 29th International Conference on Advanced Information Systems Engineering, 1848, (2017), 41-48.
[13] The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/ [11.01.2018]
Authors
Marek Miłoszm.milosz@pollub.pl
Institute of Computer Science, Lublin University of Technology, Nadbystrzycka 36B, 20-618 Lublin, Poland Poland
Authors
Janusz GazdaInstitute of Computer Science, Lublin University of Technology, Nadbystrzycka 36B, 20-618 Lublin, Poland Poland
Statistics
Abstract views: 307PDF downloads: 223
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
