تشخیص ارقام دست‌نویس انگلیسی با استفاده از شبکه عصبی کانولوشن

بهرامیان, مهسا; عظیم زاده ایرانی, آرش; پورقلی, رضا; علیاری بروجنی, احمد

doi:10.22052/scj.2024.243236.1021

تشخیص ارقام دست‌نویس انگلیسی با استفاده از شبکه عصبی کانولوشن

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده ریاضی و علوم کامپیوتر، دانشگاه دامغان، دامغان، ایران.

10.22052/scj.2024.243236.1021

چکیده

انسان‌ها می‌توانند با استفاده از چشم‌ها و مغز خودشان جهان اطراف خود را ببینند و حس کنند. بینایی رایانه بر روی توانایی کامپیوترها برای دیدن و پردازش تصاویر به همان روشی که انسان‌ها استفاده می‌کنند، کار می‌کند. هدف از کار ما ایجاد مدلی است که بتواند ارقام دست‌نویس انگلیسی را از تصویر اصلی با دقت زیاد شناسایی کند. هدف ما این است که با استفاده از مفاهیم شبکه عصبی کانولوشن (Convolutional Neural Network) و مجموعه داده MNIST، این کار را انجام دهیم. در این کار، هدف ما یادگیری و بکارگیری عملی مفاهیم شبکه‌های عصبی کانولوشن است. اگرچه هدف ما ایجاد مدلی است که بتواند ارقام دست‌‌نویس را تشخیص دهد، اما می‌توانیم آن را برای حروف و دست خط یک شخص دیگر نیز گسترش دهیم. در این کار توانستیم در آزمایش‌های خود به بهبود قابل قبولی نسبت به کارهای انجام شده قبلی برسیم که به دست آوردن دقت 99.30% نشان‌دهنده موفقیت روش پیشنهادی برای تشخیص ارقام دست‌نویس مجموعه داده MNIST می‌باشد.

کلیدواژه‌ها

موضوعات

پردازش تصویر

عنوان مقاله [English]

Recognition of Handwritten Digit using Convolutional Neural Network (CNN)

نویسندگان [English]

Mahsa Bahramian
Arash Azimzadeh Irani
Reza Pourgholi
Ahmad Aliyari Boroujeni

Faculty of Mathematics and Computer Science, Damghan University, Damghan, Iran.

چکیده [English]

Humans perceive and understand the surrounding world through their eyes and analysis with brains. Computer vision endeavors to equip computers with the ability to see images and and process it akin to human vision. Our objective is to develop a model capable of accurately identifying handwritten digits from their images. This will be achieved through the utilization of Convolutional Neural Network principles and its implementation on the MNIST dataset. The primary aim is to grasp and implement Convolutional Neural Network concepts effectively. While the focus is on creating a model for digit recognition, the potential expansion to letters and individual handwriting is considered. The outcomes of our experiments exhibit a notable enhancement compared to prior works, with an accuracy of 99.30%, signifying the success of the proposed method in recognizing handwritten digits.

کلیدواژه‌ها [English]

Convolutional neural network
MNIST dataset
Model
ReLu
Softmax

مراجع

[1] S. Ahlawat, A. Choudhary, A. Nayyar, S. Singh, and B. Yoon, “Improved handwritten digit recognition using convolutional neural networks (CNN),” Sensors, vol. 20, no. 12, p. 3344, 2020, doi: 10.3390/s20123344.
[2] M.A. Hossain and M.M. Ali, “Recognition of handwritten digit using convolutional neural network (CNN),” Global J. Comput. Sci. Technol., vol. 19, no. 2, pp. 27-33, 2019.
[3] N. Jain, K. Rahul, I. Khamaru. A.K. Jha, and A. Ghosh, “HandWritten Digit Recognition using Convolutional Neural Network (CNN),” Int. J. Innov. Adv. Comput. Sci., vol. 6, no. 5, 2017.
[4] H.A. Alwzwazy, H.M. Albehadili, Y.S. Alwan, and N.E. Islam, “Handwritten digit recognition using convolutional neural networks,” Int. J. Innov. Res. Comput. Commun. Eng., vol. 4, no. 2, pp. 1101-1106, 2016.
[5] E. Kussul and T. Baidyk, “Improved method of handwritten digit recognition tested on MNIST database,” Image Vis. Comput., vol. 22, no. 12, pp. 971-981, 2004, doi: 10.1016/j.imavis.2004.03.008.
[6] H. Wu, “CNN-Based Recognition of Handwritten Digits in MNIST Database,” Research School of Computer Science. The Australia National University, Canberra, 2018.
[7] R. Jana and S. Bhattacharyya, “Character recognition from handwritten image using convolutional neural networks,” in Recent Trends in Signal and Image Processing: Proceedings of ISSIP 2018, 2019: Springer, pp. 23-30, doi: 10.1007/978-981-13-6783-0_3.
[8] F. Siddique, S. Sakib and M.A.B. Siddique, “Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers,” in 5th Int. Conf. Adv. Electr. Eng. (ICAEE), Dhaka, Bangladesh, 2019, pp. 541-546, doi: 10.1109/ICAEE48663.2019.8975496.
[9] M.M. Abu Ghosh and A.Y. Maghari, “A Comparative Study on Handwriting Digit Recognition Using Neural Networks,” in Int. Conf. Promising Electron. Technol. (ICPET), Deir El-Balah, Palestine, 2017, pp. 77-81, doi: 10.1109/ICPET.2017.20.
[10] D.-Y. Ge, X.-F. Yao, W.-J. Xiang, X.-J. Wen and E.-C. Liu, “Design of High Accuracy Detector for MNIST Handwritten Digit Recognition Based on Convolutional Neural Network,” in 12th Int. Conf. Intell. Comput. Technol. Autom. (ICICTA), Xiangtan, China, 2019, pp. 658-662, doi: 10.1109/ICICTA49267.2019.00145.
[11] S. Ali, Z. Shaukat, M. Azeem, Z. Sakhawat, T. Mahmood, and K. ur Rehman, “An efficient and improved scheme for handwritten digit recognition based on convolutional neural network,” SN Appl. Sci., vol. 1, no. 9, p. 1125, 2019, doi: 10.1007/s42452-019-1161-5.
[12] A.-M. Saeed, “Intelligent handwritten digit recognition using artificial neural network,” Int. J. Eng. Res. Appl., vol. 5, no. 5, pp. 46-51, 2015.
[13] M. Ramprasath, M.V. Anand, and S. Hariharan, “Image classification using convolutional neural networks,” Int. J. Pure Appl. Math., vol. 119, no. 17, pp. 1307-1319, 2018.
[14] E. Tuba, M. Tuba, and D. Simian, “Handwritten Digit Recognition by Support Vector Machine Optimized by Bat Algorithm,” in 24th Conf. Comput. Graph. Visual. Comput. Vis., 2016, pp. 369-376.
[15] S. Ahlawat and A. Choudhary, “Hybrid CNN-SVM Classifier for Handwritten Digit Recognition,” Proc. Comput. Sci., vol. 167, pp. 2554-2560, 2020, doi: 10.1016/j.procs.2020.03.309
[16] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[17] A. Biswas and M.S. Islam, “An efficient CNN model for automated digital handwritten digit classification,” J. Inf. Syst. Eng. Business Intell., vol. 7, no. 1, pp. 42-55, 2021.
[18] X.-X. Niu and C.Y. Suen, “A novel hybrid CNN-SVM classifier for recognizing handwritten digits,” Pattern Recognit., vol. 45, no. 4, pp. 1318-1325, 2012, doi: 10.1016/j.patcog.2011.09.021.
[19] C. Kaensar, “A Comparative Study on Handwriting Digit Recognition Classifier Using Neural Network, Support Vector Machine and K- Nearest Neighbor,” in 9th Int. Conf. Comput. Inf. Technol. (AISC), 2013, pp. 155-163.
[20] R. Ebrahimzadeh and M. Jampour, “Efficient handwritten digit recognition based on histogram of oriented gradients and SVM,” Int. J. Comput. Appl., vol. 104, no. 9, 2014.
[21] B. El Qacimy, M.A. Kerroum, and A. Hammouch, “Feature extraction based on DCT for handwritten digit recognition,” Int. J. Comput. Sci. Issues (IJCSI), vol. 11, no. 6, p. 27, 2014.
[22] M. Sarchahi and E. Mahdipour, “Using ensemble deep learning to improve the accuracy of CT-Scan lung image detection of COVID-19 patients,” Soft Comput. J., vol. 13, no. 1, pp. 20-39, 2024, doi: 10.22052/scj.2023.253142.1158 [In Persian].
[23] M. Eftekharian and A. Nodehi, “Breast Cancer Diagnosis and Classification Improvement based on Deep Learning and image Processing methods,” Soft Comput. J., vol. 12, no .1, pp. 22-26, 2023, doi: 10.22052/scj.2023.246416.1067.
[24] M. Mousavi, S. Hosseini, and M.R. Omidi, “Improved Deep Neural Network Algorithm for Covid-19 Detection in Internet of Things,” Soft Comput. J., vol. 12, no. 2, pp. 54-71, 2024, doi: 10.22052/scj.2023.248686.1117 [In Persian].