Article Sidebar

XML
Date Published: 30/05/2023
Online Published: 30/05/2023
Abstract Views: 324
Views XML: 137
DOI: https://doi.org/10.54607/hcmue.js.20.5.3621(2023)
Issue
Vol. 20 No. 5 (2023)
Section
Articles
How to Cite
Đinh , T. M., Nguyễn , V. T., Nguyễn , T. H., & Trần , T. V. A. (2023). METHOD OF HANDWRITTEN DIGIT RECOGNITION BASED ON DEEP NEURAL NETWORK. HCMUE Journal of Science, 20(5), 818. https://doi.org/10.54607/hcmue.js.20.5.3621(2023)

METHOD OF HANDWRITTEN DIGIT RECOGNITION BASED ON DEEP NEURAL NETWORK

Thị Mận Đinh , Văn Thịnh Nguyễn , Thế Hữu Nguyễn , Thị Vân Anh Trần

Main Article Content

Abstract

 

 

 

In this paper, a method of handwritten digit recognition is proposed based on a deep neural network (DNN). Firstly, the image dataset is extracted with HOG (Histogram of Oriented Gradient) feature combined with SIFT (Scale-invariant feature transform) feature. Then, a DNN network model is built and trained to recognize the image. Finally, the input image is automatically recognized based on the trained model. To demonstrate the effectiveness of the proposed method, the experiment was built and evaluated on the MNIST image dataset. The experimental results showed the feasibility and effectiveness of the method while making it easier to expand to other handwritten recognition.

Keywords

digit image, handwritten digit recognition, DNN, SIFT, HOG

Article Details

References

Balas, M. B. K., Valentina, .E, & Kumar, R. (2021). Handbook of Deep Learning in Biomedical Engineering Techniques and Applications. Elsevier.
Brownlee, J. (2019). Deep Learning for Computer Vision - Image Classification, Object Detection and Face Recognition in Python. Reserved.
Dan, J. S. (2020). Multi-column Deep Neural Networks for Image Classification.
Dong, J. (2021). The example of graph cut algorithm. Retrieved from https://www.researchgate.net/figure/The-example-of-graph-cut-algorithm-13_fig2_228856802
Kulandai, J. (2017). Facial recognition using histogram of gradients and support vector machines. In 2017 International Conference on Computer, Communication and Signal Processing (ICCCSP). IEEE
Lowe, D. G. (2004). Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 60(2), 91-110.
Niranjani, N. (2021). The Real Time Face Detection and Recognition System. Retrieved from https://www.researchgate.net/publication/321669397_The_Real_Time_Face_Detection_and_Recognition_System
Pham, P. Q., & Vuong, Q. P. (2019). Nhan dang chu so viet tay dung mang neuron nhan tao [Recognition of handwritten digits using artificial neural network]. Journal of Science and Technology, University of Sciences, Hue University, 14, 119-129.
Rother, V. K. C, & Blake, A. (2004). GrabCut: Interactive foreground extraction using iterated graph cuts. Springer.
Reza, E. (2014). Efficient Handwritten Digit Recognition based on Histogram of Oriented Gradients and SVM. International Journal of Computer Applications, 9(104), 0975-8887.
Suresh, R. U. A, & Vimal, S. (2020). Deep Neural Networks for Multimodal Imaging and Biomedical Applications. United States IGI Global.
Szikora, P. Ph. D. (2021). Self-driving cars - The human side. Retrieved from https://www.researchgate.net/publication/324095773_Self-driving_cars_-_The_human_side
The Sprawls Resources. (2021). Optimization of Medical Imaging Procedures. Retrieved from: http://www.sprawls.org/resources/DIGITAL