Optical character recognition using backpropagation neural network for handwritten digit characters
Recognizing handwritten characters, the accuracy of the optical character recognition is usually not relatively high due to every person having their unique way of writing characters. Therefore, we focus on finding a high recognition accuracy of optical character recognition by using a backpropagati...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
IEEE
2021
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/32381/ http://umpir.ump.edu.my/id/eprint/32381/1/Optical%20character%20recognition%20using%20backpropagation%20neural%20network%20for%20handwritten%20.pdf http://umpir.ump.edu.my/id/eprint/32381/2/Optical%20character%20recognition%20using%20backpropagation%20neural%20network%20for%20handwritten_FULL.pdf |
| _version_ | 1848824006750240768 |
|---|---|
| author | Yap, Mei Ing Moorthy, Kohbalan Kauthar, Mohd Daud Ernawan, Ferda |
| author_facet | Yap, Mei Ing Moorthy, Kohbalan Kauthar, Mohd Daud Ernawan, Ferda |
| author_sort | Yap, Mei Ing |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Recognizing handwritten characters, the accuracy of the optical character recognition is usually not relatively high due to every person having their unique way of writing characters. Therefore, we focus on finding a high recognition accuracy of optical character recognition by using a backpropagation neural network. The input layer of the backpropagation neural network is the pixel number of the one-character image, which is 784 input nodes that will be the input layer of the neural network. Then the output layer of the neural network will be the 10-digit characters which are 0 to 9. The dataset that used for this research has a total of 280,000 data. The output of the neural network will a computerized digit representing the recognized digit characters. The performance measurement is the recognition accuracy where the recognized data and the expected output data are compared and calculated. Additionally, the dataset was applied with salt and pepper noise to represent the corrupted data and use a median filter to repair the image. The recognition accuracy for the corrupted image and the corrected image are obtained and discussed. |
| first_indexed | 2025-11-15T03:06:10Z |
| format | Conference or Workshop Item |
| id | ump-32381 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-15T03:06:10Z |
| publishDate | 2021 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-323812022-01-12T08:15:28Z http://umpir.ump.edu.my/id/eprint/32381/ Optical character recognition using backpropagation neural network for handwritten digit characters Yap, Mei Ing Moorthy, Kohbalan Kauthar, Mohd Daud Ernawan, Ferda QA76 Computer software Recognizing handwritten characters, the accuracy of the optical character recognition is usually not relatively high due to every person having their unique way of writing characters. Therefore, we focus on finding a high recognition accuracy of optical character recognition by using a backpropagation neural network. The input layer of the backpropagation neural network is the pixel number of the one-character image, which is 784 input nodes that will be the input layer of the neural network. Then the output layer of the neural network will be the 10-digit characters which are 0 to 9. The dataset that used for this research has a total of 280,000 data. The output of the neural network will a computerized digit representing the recognized digit characters. The performance measurement is the recognition accuracy where the recognized data and the expected output data are compared and calculated. Additionally, the dataset was applied with salt and pepper noise to represent the corrupted data and use a median filter to repair the image. The recognition accuracy for the corrupted image and the corrected image are obtained and discussed. IEEE 2021-08 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/32381/1/Optical%20character%20recognition%20using%20backpropagation%20neural%20network%20for%20handwritten%20.pdf pdf en http://umpir.ump.edu.my/id/eprint/32381/2/Optical%20character%20recognition%20using%20backpropagation%20neural%20network%20for%20handwritten_FULL.pdf Yap, Mei Ing and Moorthy, Kohbalan and Kauthar, Mohd Daud and Ernawan, Ferda (2021) Optical character recognition using backpropagation neural network for handwritten digit characters. In: 2021 International Conference on Software Engineering & Computer Systems and 4th International Conference on Computational Science and Information Management (ICSECS-ICOCSIM) , 24-26 August 2021 , Pekan. 167 -171.. ISBN 9781665414074 (Published) https://doi.org/10.1109/ICSECS52883.2021.00037 |
| spellingShingle | QA76 Computer software Yap, Mei Ing Moorthy, Kohbalan Kauthar, Mohd Daud Ernawan, Ferda Optical character recognition using backpropagation neural network for handwritten digit characters |
| title | Optical character recognition using backpropagation neural network for handwritten digit characters |
| title_full | Optical character recognition using backpropagation neural network for handwritten digit characters |
| title_fullStr | Optical character recognition using backpropagation neural network for handwritten digit characters |
| title_full_unstemmed | Optical character recognition using backpropagation neural network for handwritten digit characters |
| title_short | Optical character recognition using backpropagation neural network for handwritten digit characters |
| title_sort | optical character recognition using backpropagation neural network for handwritten digit characters |
| topic | QA76 Computer software |
| url | http://umpir.ump.edu.my/id/eprint/32381/ http://umpir.ump.edu.my/id/eprint/32381/ http://umpir.ump.edu.my/id/eprint/32381/1/Optical%20character%20recognition%20using%20backpropagation%20neural%20network%20for%20handwritten%20.pdf http://umpir.ump.edu.my/id/eprint/32381/2/Optical%20character%20recognition%20using%20backpropagation%20neural%20network%20for%20handwritten_FULL.pdf |