With the rapid development of the economy, digital transformation has become a future trend. Character recognition (CR) technology, as a key technology to realize digitalization, has always been a hot research topic that people pay attention to. CR can be widely used in the fields of transportation, finance, industry, economy and artificial intelligence. In-depth study of CR technology is of great practical significance for promoting the development of science and technology and economy. In this context, this paper studies the printed CR method based on CNN. Combining wavelet theory and CNN, this paper studies the extraction and recognition methods and implementation ways of printed characters in detail. The algorithm applied in this paper is recognized on the DSP (DM642) chip, the recognition accuracy is over 99.93%, and the recognition time is controlled within 5ms, which meets the actual requirements. Comprehensive analysis verifies the feasibility and superiority of the recognition algorithm applied in this paper.

Yuan Wang. Print Character Recognition Method Based on Convolutional Neural Network. International Journal of Neural Network (2022), Vol. 3, Issue 3: 17-27. https://doi.org/10.38007/NN.2022.030303.

[1] Chandio A A, Asikuzzaman M, Pickering M R. Cursive CR in Natural Scene Images using a Multilevel CNN Fusion. IEEE Access, 2020, PP(99):1-1.

[2] Nayak V. Automatic number plate recognition. International Journal of Advanced Trends in Computer Science and Engineering, 2020, 9(3):3783-3787. https://doi.org/10.30534/ijatcse/2020/195932020

[3] Mohd M, Qamar F, Al-Sheikh I, et al. Quranic Optical Text Recognition Using Deep Learning Models. IEEE Access, 2021, PP(99):1-1. https://doi.org/10.1109/ACCESS.2021.3064019

[4] Alkhateeb J H, Turani A A, Abuhamdah A, et al. An Effective Deep Learning Approach for Improving Off-Line Arabic Handwritten CR. International Journal of Computer Systems & Software Engineering, 2021, 6(2):104-112.

[5] Phan T H, Tran D C, Hassan M F. Vietnamese CR based on CNN model with reduced character classes. Bulletin of Electrical Engineering and Informatics, 2021, 10(2):962-969. https://doi.org/10.11591/eei.v10i2.2810

[6] Jokic P, Emery S, Benini L. Improving Memory Utilization in CNN Accelerators. IEEE embedded systems letters, 2020, PP(99):1-1.

[7] Shimoda M, Sada Y, Kuramochi R, et al. SENTEI: Filter-Wise Pruning with Distillation towards Efficient Sparse CNN Accelerators. IEICE Transactions on Information and Systems, 2020, E103.D(12):2463-2470. https://doi.org/10.1587/transinf.2020PAP0013

[8] Zanghieri M, Benatti S, Burrello A, et al. Robust Real-Time Embedded EMG Recognition Framework Using Temporal Convolutional Networks on a Multicore IoT Processor. IEEE Transactions on Biomedical Circuits and Systems, 2020, 14(2):244-256. https://doi.org/10.1109/TBCAS.2019.2959160

[9] Konovalenko I A, Kokhan V V, Nikolaev D P. Optimal affine image normalization approach for optical CR. Computer Optics, 2021, 45(1):90-100. https://doi.org/10.18287/2412-6179-CO-759

[10] Mahesha C. Telugu Optical CR Using Cloud Computing and Python. International Journal of Computer Science Engineering and Information Technology Research, 2021, 11(1):95-106. https://doi.org/10.24247/ijcseitrjun20219

[11] Phan T H, Tran D C, Hassan M F. Vietnamese CR based on CNN model with reduced character classes. Bulletin of Electrical Engineering and Informatics, 2021, 10(2):962-969. https://doi.org/10.11591/eei.v10i2.2810

[12] Hubert, Phoenix P, Sudaryono R, et al. Classifying Promotion Images Using Optical CR and Nave Bayes Classifier. Procedia Computer Science, 2021, 179(1):498-506. https://doi.org/10.1016/j.procs.2021.01.033

[13] Sadouk L. Handwritten Phoenician CR and its Use to Improve Recognition of Handwritten Alphabets with Lack of Annotated Data. International Journal of Advanced Trends in Computer Science and Engineering, 2020, 9(1):171-181. https://doi.org/10.30534/ijatcse/2020/26912020

[14] Khobragade R N, Koli N A, Lanjewar V T. Comparison of Feature Extraction methods for the study of Cursive Handwritten Marathi Compound CR. Journal of engineering sciences, 2020, 11(6):1070-1079.

[15] Reddy N, Ur E, Mohammed S W. A Novel Geometrical Scale and Rotation Independent Feature Extraction Technique for Multi-lingual CR. International Journal of Advanced Computer Science and Applications, 2020, 11(11):231-239. https://doi.org/10.14569/IJACSA.2020.0111130

[16] Husen M N. Automated Car Plate Detection and CR with Parking Fee Management Using Point Feature Matching. Journal of Advanced Research in Dynamical and Control Systems, 2020, 12(SP8):214-220. https://doi.org/10.5373/JARDCS/V12SP8/20202518

[17] Beltran-Hernandez J, Ruiz-Pinales J, Lopez-Rodriguez P , et al. Multi-Stroke handwriting CR based on sEMG using convolutional-recurrent neural networks.. Mathematical biosciences and engineering: MBE, 2020, 17(5):5432-5448. https://doi.org/10.3934/mbe.2020293

[18] Venugopal A, Madanan M, Venugopal A. Devanagari Cr Using Feature Set Selection Algorithm. International Journal of Psychosocial Rehabilitation, 2020, 24(8):15710-15715.