Two dimensional convolutional neural network CNN approach for detection of Bangla sign language
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.
| Päätekijät: | , , , , |
|---|---|
| Muut tekijät: | |
| Aineistotyyppi: | Opinnäyte |
| Kieli: | English |
| Julkaistu: |
Brac University
2023
|
| Aiheet: | |
| Linkit: | http://hdl.handle.net/10361/21850 |
| id |
10361-21850 |
|---|---|
| record_format |
dspace |
| spelling |
10361-218502024-05-19T06:52:07Z Two dimensional convolutional neural network CNN approach for detection of Bangla sign language Nag, Pollock Khan, Tamim Mahmud Biplob, Shaikh Mehedi Hasan Barmon, Rachayita Rahman, MD. Minhaj Karim, Dewan Ziaul Rahman, Rafeed Department of Computer Science and Engineering, Brac University KNN CNN Bangla sign language InceptionV3 VGG16 Resnet50 Neural network (Computer sciences) Human-computer interaction Sign language This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (page 39). Sign language is known as the primary communication medium for deaf and mute people. But the lack of available resources and a steep learning curve deter the average person from learning it making communication with the mute and deaf difficult. This problem creates an opportune place for the application of machine learning which has given rise to our emerging field. A large number of papers with high accuracy have already been published for English, French, and other languages. But the number of papers on its application for Bangla Sign language is few. Most of the researchers use SVM, ANN or KNN as classifiers. We chose CNN because it is excellent at high accuracy image classification. In this paper we use a large dataset consisting of 30 classes with 500 images each totalling to about 15000 images of bangla sign alphabets. Previous works were done only on 10 classes. We began work on those 10 bangla alphabets and later increased the number of classes to 30. We tested the accuracy’s of pre trained CNN models such as DenseNet201,VGG16, InceptionV3, Resnet50, MobileNetV2, InceptionResnet, EfficientnetB2 along with our custom CNN model and were able to achieve 97.97%, 96%, 96.22%, 56.44%, 90%, 94%, 4%,98.3 % train accuracy and 86.43%, 88%, 88.33%, 54.50%, 60%, 53%, 4.2%,87% validation accuracy respectively. Our custom CNN model has consistently given better training and validation accuracy than any pre-trained model with lesser layers which in turn require less computations making for a lighter and faster model while maintaining high accuracy. Pollock Nag Tamim Mahmud Khan Shaikh Mehedi Hasan Biplob Rachayita Barmon MD. Minhaj Rahman B.Sc. in Computer Science and Engineering 2023-10-16T08:42:02Z 2023-10-16T08:42:02Z ©2022 2022-09-28 Thesis ID: 18101114 ID: 16101116 ID: 18201087 ID: 18201016 ID: 18301072 http://hdl.handle.net/10361/21850 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. 50 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
KNN CNN Bangla sign language InceptionV3 VGG16 Resnet50 Neural network (Computer sciences) Human-computer interaction Sign language |
| spellingShingle |
KNN CNN Bangla sign language InceptionV3 VGG16 Resnet50 Neural network (Computer sciences) Human-computer interaction Sign language Nag, Pollock Khan, Tamim Mahmud Biplob, Shaikh Mehedi Hasan Barmon, Rachayita Rahman, MD. Minhaj Two dimensional convolutional neural network CNN approach for detection of Bangla sign language |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. |
| author2 |
Karim, Dewan Ziaul |
| author_facet |
Karim, Dewan Ziaul Nag, Pollock Khan, Tamim Mahmud Biplob, Shaikh Mehedi Hasan Barmon, Rachayita Rahman, MD. Minhaj |
| format |
Thesis |
| author |
Nag, Pollock Khan, Tamim Mahmud Biplob, Shaikh Mehedi Hasan Barmon, Rachayita Rahman, MD. Minhaj |
| author_sort |
Nag, Pollock |
| title |
Two dimensional convolutional neural network CNN approach for detection of Bangla sign language |
| title_short |
Two dimensional convolutional neural network CNN approach for detection of Bangla sign language |
| title_full |
Two dimensional convolutional neural network CNN approach for detection of Bangla sign language |
| title_fullStr |
Two dimensional convolutional neural network CNN approach for detection of Bangla sign language |
| title_full_unstemmed |
Two dimensional convolutional neural network CNN approach for detection of Bangla sign language |
| title_sort |
two dimensional convolutional neural network cnn approach for detection of bangla sign language |
| publisher |
Brac University |
| publishDate |
2023 |
| url |
http://hdl.handle.net/10361/21850 |
| work_keys_str_mv |
AT nagpollock twodimensionalconvolutionalneuralnetworkcnnapproachfordetectionofbanglasignlanguage AT khantamimmahmud twodimensionalconvolutionalneuralnetworkcnnapproachfordetectionofbanglasignlanguage AT biplobshaikhmehedihasan twodimensionalconvolutionalneuralnetworkcnnapproachfordetectionofbanglasignlanguage AT barmonrachayita twodimensionalconvolutionalneuralnetworkcnnapproachfordetectionofbanglasignlanguage AT rahmanmdminhaj twodimensionalconvolutionalneuralnetworkcnnapproachfordetectionofbanglasignlanguage |
| _version_ |
1814308167789576192 |