A Comparative study on Bengali handwritten character recognition and prediction using CNN
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.
| Hlavní autoři: | , , |
|---|---|
| Další autoři: | |
| Médium: | Diplomová práce |
| Jazyk: | English |
| Vydáno: |
Brac University
2021
|
| Témata: | |
| On-line přístup: | http://hdl.handle.net/10361/15375 |
| id |
10361-15375 |
|---|---|
| record_format |
dspace |
| spelling |
10361-153752023-01-24T09:11:20Z A Comparative study on Bengali handwritten character recognition and prediction using CNN Abrar, Muntaqa Kadir, Md Nazial Faruk, Tabassum Islam, Md. Saiful Department of Computer Science and Engineering, Brac University SqueezeNet AlexNet; SqueezeNet Convolutional Neural Network Image processing Bengali characters Handwritten character recognition Image Processing This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021. Cataloged from PDF version of thesis. The transcription Bengali text to digital text is neither very efficient nor accurate. This proves to be a problem because most official work in Bangladesh is traditionally done in Bengali, on pen and paper hardcopy documents, which are difficult to transition to digital format. In our thesis, we attempted to solve this problem by improving the process of recognizing and extracting handwritten Bengali text to digital text. To aid us in our research, we have also collected an extensive data set consisting of approximately 25000 samples of around 90 Bengali characters each, including conjunct characters, to help us establish our findings. The main models we have implemented in our paper are- VGG-19, ResNet50, AlexNet, SqueezeNet. The highest training accuracy was 87% and was achieved from AlexNet, and least was 54% from VGG-19. The reliability of our model was validated by F1 score. Muntaqa Abrar Md Nazial Kadir Tabassum Faruk B. Computer Science 2021-10-18T09:06:13Z 2021-10-18T09:06:13Z 2021 2021-01 Thesis ID 17101288 ID 17101100 ID 17101493 http://hdl.handle.net/10361/15375 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 31 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
SqueezeNet AlexNet; SqueezeNet Convolutional Neural Network Image processing Bengali characters Handwritten character recognition Image Processing |
| spellingShingle |
SqueezeNet AlexNet; SqueezeNet Convolutional Neural Network Image processing Bengali characters Handwritten character recognition Image Processing Abrar, Muntaqa Kadir, Md Nazial Faruk, Tabassum A Comparative study on Bengali handwritten character recognition and prediction using CNN |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021. |
| author2 |
Islam, Md. Saiful |
| author_facet |
Islam, Md. Saiful Abrar, Muntaqa Kadir, Md Nazial Faruk, Tabassum |
| format |
Thesis |
| author |
Abrar, Muntaqa Kadir, Md Nazial Faruk, Tabassum |
| author_sort |
Abrar, Muntaqa |
| title |
A Comparative study on Bengali handwritten character recognition and prediction using CNN |
| title_short |
A Comparative study on Bengali handwritten character recognition and prediction using CNN |
| title_full |
A Comparative study on Bengali handwritten character recognition and prediction using CNN |
| title_fullStr |
A Comparative study on Bengali handwritten character recognition and prediction using CNN |
| title_full_unstemmed |
A Comparative study on Bengali handwritten character recognition and prediction using CNN |
| title_sort |
comparative study on bengali handwritten character recognition and prediction using cnn |
| publisher |
Brac University |
| publishDate |
2021 |
| url |
http://hdl.handle.net/10361/15375 |
| work_keys_str_mv |
AT abrarmuntaqa acomparativestudyonbengalihandwrittencharacterrecognitionandpredictionusingcnn AT kadirmdnazial acomparativestudyonbengalihandwrittencharacterrecognitionandpredictionusingcnn AT faruktabassum acomparativestudyonbengalihandwrittencharacterrecognitionandpredictionusingcnn AT abrarmuntaqa comparativestudyonbengalihandwrittencharacterrecognitionandpredictionusingcnn AT kadirmdnazial comparativestudyonbengalihandwrittencharacterrecognitionandpredictionusingcnn AT faruktabassum comparativestudyonbengalihandwrittencharacterrecognitionandpredictionusingcnn |
| _version_ |
1814308618825105408 |