Abstract
Convolutional neural networks (CNNs) are best suited for image data. The most important layer in CNNs is the convolution layer. In this paper, cellular automata neural network or CA-NN is proposed for handwritten pattern recognition that replaces the convolution layer in CNN with the cellular automata (CA) layer. The idea is to make CNNs more biological where an image pattern would grow or decay instead of convolving. To grow or decay an image, CA is used as they are designed precisely for this purpose. In doing so, what would be the response of CA-NN to smaller data sets since CNNs require very large data to train. The model is tested and compared with 3 different well-known CNN architectures using 6 relatively small-sized handwritten data sets. The experimental results are very promising and raise very interesting future directions.
Similar content being viewed by others
References
Abdelazeem S, El-Sherif E (2008) Arabic handwritten digit recognition, Int J Doc Anal Recognit (IJDAR) 11(3):127–141. http://datacenter.aucegypt.edu/shazeem/
Ahamed P, Kundu S, Khan T, Bhateja V, Sarkar R, Mollah AF (2020) Handwritten arabic numerals recognition using convolutional neural network. J Ambient Intell Human Comput
Ahranjany SS, Razzazi F, Ghassemian MH (2010) A very high accuracy handwritten character recognition system for farsi/arabic digits using convolutional neural networks. In: 2010 IEEE fifth international conference on bio-inspired computing: theories and applications (BIC-TA), IEEE, pp 1585–1592
Alom MZ, Sidike P, Taha TM, Asari VK (2017) Handwritten bangla digit recognition using deep learning. arXiv preprint http://arxiv.org/abs/1705.02680
Altwaijry N, Al-Turaiki I (2020) Arabic handwriting recognition system using convolutional neural network. Neural Comput Appl, pp 1–13
Bell DI (1994) High life–an interesting variant of life. Available from David Bell’s
Bhattacharya U, Chaudhuri BB (2009) Handwritten numeral databases of indian scripts and multistage recognition of mixed numerals. IEEE Trans Pattern Anal Mach Intell 31(3):444–457
Bhattacharya U, Chaudhuri B (2005) Databases for research on recognition of handwritten characters of indian scripts. In: Eighth international conference on document analysis and recognition (ICDAR’05), pp 789–793
Boufenar C, Kerboua A, Batouche M (2018) Investigation on deep learning for off-line handwritten Arabic character recognition. Cognit Syst Res 50:180–195
Cireşan D, Meier U, Multi-column deep neural networks for offline handwritten chinese character classification. In: (2015) International joint conference on neural networks (IJCNN). IEEE 2015:1–6
Conway J (1970) The game of life. Sci Am 223(4):4
Fornés A, Lladós J, Sánchez G (2007) Old handwritten musical symbol classification by a dynamic time warping based method. In: International workshop on graphics recognition, Springer, pp 51–60
Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, Vol. 1, MIT press Cambridge, Cambridge
Hazra A, Choudhary P, Inunganbi S, Adhikari M (2020) Bangla-meitei mayek scripts handwritten character recognition using convolutional neural network. Appl Intell, pp 1–21
Khodabandelou G, Routhier E, Mozziconacci J (2020) Genome annotation across species using deep convolutional neural networks. Peer J Comput Sci 6:e278
LeCun Y, Cortes C, Burges CJ (1998) The mnist database of handwritten digits
Mehrotra K, Jetley S, Deshmukh A, Belhe S (2013) Unconstrained handwritten devanagari character recognition using convolutional neural networks. In: Proceedings of the 4th international workshop on multilingual OCR, ACM, p 15
Parseh M, Rahmanimanesh M, Keshavarzi P (2020) Persian handwritten digit recognition using combination of convolutional neural network and support vector machine methods. Int Arab J Inf Technol 17(4):572–578
Tsai C (2016) Recognizing handwritten Japanese characters using deep convolutional neural networks. university of Stanford in Stanford, California
Wali A, Saeed M (2018) Biologically inspired cellular automata learning and prediction model for handwritten pattern recognition. Biol Insp Cognit Arch 24:77–86
Wali A, Saeed M (2019) m-calp: Yet another way of generating handwritten data through evolution for pattern recognition. Biosystems 175:24–29
Wolfram S (2002) A new kind of science, Wolfram media
Yang W, Jin L, Tao D, Xie Z, Feng Z (2016) Dropsample: A new training method to enhance deep convolutional neural networks for large-scale unconstrained handwritten chinese character recognition. Pattern Recogn 58:190–203
Yuan A, Bai G, Jiao L, Liu Y (2012) Offline handwritten english character recognition based on convolutional neural network. In: (2012) 10th IAPR international workshop on document analysis systems. IEEE. pp 125–129
Zeng T, Li R, Mukkamala R, Ye J, Ji S (2015) Deep convolutional neural networks for annotating gene expression patterns in the mouse brain. BMC Bioinf 16(1):147
Zhou J, Peng H (2007) Automatic recognition and annotation of gene expression patterns of fly embryos. Bioinformatics 23(5):589–596
Acknowledgement
This statement is to certify that I am the only author. The Author also confirm that this research has not been published previously and that it is not under consideration for publication elsewhere. The Author shall bear full responsibility for the submission. There is no conflict of interest.
Funding
No funding was received for conducting this study.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The author declare that he has no competing financial interests or personal relationships that could influence the work reported in this paper. The author has no conflicts of interest to declare that are relevant to the content of this article.
Human and animal participants
This research did not involve any human participants and/or animals.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wali, A. CA-NN: a cellular automata neural network for handwritten pattern recognition. Nat Comput (2022). https://doi.org/10.1007/s11047-022-09937-8
Accepted:
Published:
DOI: https://doi.org/10.1007/s11047-022-09937-8