Bangla Hand Written Digit Recognition presentation slide .pptx

KhondokerAbuNaim
Bangladesh Army University of
Science and Technology,Saidpur
 Course Title: Artifacial Intelligence and
Fuzzy Systems
 Course Code: CSE 4132
 Level-4;Term-1
 Course Adviser:Hasan Muhammad
Kafi
 Abu Rayhan Mouno (180201118)
 Khondoker Abu Naim (200101103)
2
Project Title: Bangla handwritten digit
recognition using deep learning.
 Peresented by,
 Introduction
 Bangla Handwritten Characters
Proposed Methodology
 Dataset Discription
 Preprocessing
 Methodology
 Implemented Model Architecture
 Training The Network
 Results Analysis
 Limitation
 Future Recomendation
 Conlusion
3
Contents
4
Introduction
Handwritten digit recognition is a
classical problem in computer vision,
with 10 unique Bangla digits to classify.
The models evaluated are:
 EfficientNetB0
 MobileNet.
These models' performances are
contrasted under various training
regimes. We are using baseline,
transfer learning, and fine-tuning.
)
Bangla Handwritten Digits
Handwritten digits have unique characteristics such as
strokes, styles, and structure
Different people’s digits are unique to each person
Bangla handwritten digits have a morphologically complex nature
PROPOSED METHODOLOGY
6
Data Collection &
Preprocessing
Dataset Generation
Training
Classification using
CNN
Optimization
Testing
Dataset Discription
7
 We have used our own dataset- 10 different Bangla
handwritten digits.
 2500 images for the Training and 500 images for the Testing
Datasets
 10 folders for the both Training and Testing Datasets,
denoting 10 digits' classes
 Each folders contain an equal number of sample images
Dataset Description
8
০ ১ ২ ৩ ৪ ৫ ৬ ৭ ৮ ৯
200 220 250 250 203 267 223 231 224 245
Class
Train Set
Validatio
n
Set
69 71 75 73 70 75 73 60 65
The Dataset(Cont.)
9
The training dataset was further split
into two groups:
 Training Dataset (90% of the
original training dataset)
 Testing Dataset (10% of the
original training dataset) -
Ensuring no bias was enforced
in Testing
0
500
1000
1500
2000
2500
3000
Training Dataset Testing Dataset
Dataset
Fig1.Dataset chart
The Dataset(Cont.)
10
Fig2.Sample of images from dataset Fig3.sample of images from result
Methodology: Preprocessing
11
• Image were converted into
grayscale images
• All images were resized into a
124x124 dimension to target size
10 Kilobytes
Fig4. 124x124 resized images of digit “9”
Methodology:Environment
12
Resources Required to Accomplish the Task:
• Python
• Kaggle
Installation of all necessary tools and libraries, such as
TensorFlow, Keras, and NumPy, in both settings.
Methodology:Model Architecture
13
Figure5. An illustration of the structure of our model training
• We are using pre-trained deep learning models including
EfficientNetB0 and MobileNet.
• We compared this models under different training regimes including
baseline, fine-tuning and transfer learning.
Input
124x124x1 124x124x64 124x124x64 14x14x128 7x7x256 7x7x256 7x7x256
TRAINING THE NETWORK
14
• Weights were initialized with Xavier initialization method
• The network was trained all over using Adam optimizer
with initial standard parameters
• The model was trained using batches of size 32
• We used LR Scheduler for reducing the learning rate
when validation loss was not improving
• Total iteration to train the model: 16
Result and analysis: overview of performance
15
Model Baseline Transfer
learning
Fine-tuning
EffNetB0 31% 95% 99.4%
MobileNet 9% 92% 94%
31
9
99.4
94
95 92
0
20
40
60
80
100
120
EffNetB0 MobileNet
Result Analysis
Baseline Fine-tuning Transfer learning
16
Limitations
• Sample size: This dataset's sample size was limited, which might have
had an impact on the statistical power and generalizability of the results.
• Data quality: Data quality was determined by accuracy and
comprehensiveness of participant replies.
• Generalizability: Due to the sample being restricted to a particular
participant group, it is possible that the results of this study cannot be
applied to other populations or circumstances.
17
Future recommendations
• Examine other pre-trained models:Explore different Neural Network
models Work with various datasets to create a more robust and effective
automated system.
• Improve dataset quality
• Improve dataset quality
• Dataset Quality:Increase the amount of high-quality data was
collected, especially for underrepresented classes, to improve the
precision of machine learning models.
• Try different optimizer algorithoms:Try out several
optimization techniques, such RMSprop or SGD to boost the
effectiveness of the digit recognition system.
• Extend to real-time applications:Extend current implementation
to real-time applications for practical use.
Conclusion
• Created models for recognizing digit
using a variety of deep learning
architectures and training methods.
• As far as our knowledge, the achieved
result is the state-of-the art accuracy in
Bangla digit recognition.
• Could result in advancement in the
pursuit of digitization.
18
“
”
Thank You
19
1 von 19

Recomendados

Guiding through a typical Machine Learning Pipeline von
Guiding through a typical Machine Learning PipelineGuiding through a typical Machine Learning Pipeline
Guiding through a typical Machine Learning PipelineMichael Gerke
450 views9 Folien
Activity Monitoring Using Wearable Sensors and Smart Phone von
Activity Monitoring Using Wearable Sensors and Smart PhoneActivity Monitoring Using Wearable Sensors and Smart Phone
Activity Monitoring Using Wearable Sensors and Smart PhoneDrAhmedZoha
340 views18 Folien
End-to-end deep auto-encoder for segmenting a moving object with limited tra... von
End-to-end deep auto-encoder for segmenting a moving object  with limited tra...End-to-end deep auto-encoder for segmenting a moving object  with limited tra...
End-to-end deep auto-encoder for segmenting a moving object with limited tra...IJECEIAES
11 views13 Folien
Mnist soln von
Mnist solnMnist soln
Mnist solnDanishFaisal4
85 views12 Folien
Bangla Handwritten Digit Recognition Report.pdf von
Bangla Handwritten Digit Recognition  Report.pdfBangla Handwritten Digit Recognition  Report.pdf
Bangla Handwritten Digit Recognition Report.pdfKhondokerAbuNaim
18 views9 Folien
Presentation of master thesis von
Presentation of master thesisPresentation of master thesis
Presentation of master thesisSeoung-Ho Choi
210 views31 Folien

Más contenido relacionado

Similar a Bangla Hand Written Digit Recognition presentation slide .pptx

A SIMPLE PROCESS TO SPEED UP MACHINE LEARNING METHODS: APPLICATION TO HIDDEN ... von
A SIMPLE PROCESS TO SPEED UP MACHINE LEARNING METHODS: APPLICATION TO HIDDEN ...A SIMPLE PROCESS TO SPEED UP MACHINE LEARNING METHODS: APPLICATION TO HIDDEN ...
A SIMPLE PROCESS TO SPEED UP MACHINE LEARNING METHODS: APPLICATION TO HIDDEN ...cscpconf
64 views11 Folien
Comparative analysis of various data stream mining procedures and various dim... von
Comparative analysis of various data stream mining procedures and various dim...Comparative analysis of various data stream mining procedures and various dim...
Comparative analysis of various data stream mining procedures and various dim...Alexander Decker
485 views6 Folien
IRJET- Deep Learning Model to Predict Hardware Performance von
IRJET- Deep Learning Model to Predict Hardware PerformanceIRJET- Deep Learning Model to Predict Hardware Performance
IRJET- Deep Learning Model to Predict Hardware PerformanceIRJET Journal
11 views4 Folien
IRJET- Analysis of PV Fed Vector Controlled Induction Motor Drive von
IRJET- Analysis of PV Fed Vector Controlled Induction Motor DriveIRJET- Analysis of PV Fed Vector Controlled Induction Motor Drive
IRJET- Analysis of PV Fed Vector Controlled Induction Motor DriveIRJET Journal
21 views4 Folien
FlorenceAI: Reinventing Data Science at Humana von
FlorenceAI: Reinventing Data Science at HumanaFlorenceAI: Reinventing Data Science at Humana
FlorenceAI: Reinventing Data Science at HumanaDatabricks
464 views28 Folien
Optimal Model Complexity (1).pptx von
Optimal Model Complexity (1).pptxOptimal Model Complexity (1).pptx
Optimal Model Complexity (1).pptxMurindanyiSudi1
12 views12 Folien

Similar a Bangla Hand Written Digit Recognition presentation slide .pptx(20)

A SIMPLE PROCESS TO SPEED UP MACHINE LEARNING METHODS: APPLICATION TO HIDDEN ... von cscpconf
A SIMPLE PROCESS TO SPEED UP MACHINE LEARNING METHODS: APPLICATION TO HIDDEN ...A SIMPLE PROCESS TO SPEED UP MACHINE LEARNING METHODS: APPLICATION TO HIDDEN ...
A SIMPLE PROCESS TO SPEED UP MACHINE LEARNING METHODS: APPLICATION TO HIDDEN ...
cscpconf64 views
Comparative analysis of various data stream mining procedures and various dim... von Alexander Decker
Comparative analysis of various data stream mining procedures and various dim...Comparative analysis of various data stream mining procedures and various dim...
Comparative analysis of various data stream mining procedures and various dim...
Alexander Decker485 views
IRJET- Deep Learning Model to Predict Hardware Performance von IRJET Journal
IRJET- Deep Learning Model to Predict Hardware PerformanceIRJET- Deep Learning Model to Predict Hardware Performance
IRJET- Deep Learning Model to Predict Hardware Performance
IRJET Journal11 views
IRJET- Analysis of PV Fed Vector Controlled Induction Motor Drive von IRJET Journal
IRJET- Analysis of PV Fed Vector Controlled Induction Motor DriveIRJET- Analysis of PV Fed Vector Controlled Induction Motor Drive
IRJET- Analysis of PV Fed Vector Controlled Induction Motor Drive
IRJET Journal21 views
FlorenceAI: Reinventing Data Science at Humana von Databricks
FlorenceAI: Reinventing Data Science at HumanaFlorenceAI: Reinventing Data Science at Humana
FlorenceAI: Reinventing Data Science at Humana
Databricks464 views
ANALYSIS OF INSTANCE SEGMENTATION APPROACH FOR LANE DETECTION von RajatRoy60
ANALYSIS OF INSTANCE SEGMENTATION APPROACH FOR LANE DETECTIONANALYSIS OF INSTANCE SEGMENTATION APPROACH FOR LANE DETECTION
ANALYSIS OF INSTANCE SEGMENTATION APPROACH FOR LANE DETECTION
RajatRoy603 views
Identifying and classifying unknown Network Disruption von jagan477830
Identifying and classifying unknown Network DisruptionIdentifying and classifying unknown Network Disruption
Identifying and classifying unknown Network Disruption
jagan4778303 views
Task Adaptive Neural Network Search with Meta-Contrastive Learning von MLAI2
Task Adaptive Neural Network Search with Meta-Contrastive LearningTask Adaptive Neural Network Search with Meta-Contrastive Learning
Task Adaptive Neural Network Search with Meta-Contrastive Learning
MLAI2135 views
Towards Distributed, Semi-Automatic Content-Based Visual Information Retrieva... von Christian Kehl
Towards Distributed, Semi-Automatic Content-Based Visual Information Retrieva...Towards Distributed, Semi-Automatic Content-Based Visual Information Retrieva...
Towards Distributed, Semi-Automatic Content-Based Visual Information Retrieva...
Christian Kehl281 views
Artificial Intelligence based Pattern Recognition von Dr. Amarjeet Singh
Artificial Intelligence based Pattern RecognitionArtificial Intelligence based Pattern Recognition
Artificial Intelligence based Pattern Recognition
An Effective Storage Management for University Library using Weighted K-Neare... von C Sai Kiran
An Effective Storage Management for University Library using Weighted K-Neare...An Effective Storage Management for University Library using Weighted K-Neare...
An Effective Storage Management for University Library using Weighted K-Neare...
C Sai Kiran3 views
Multi Layer Federated Learning.pptx von TimePass43152
Multi Layer Federated Learning.pptxMulti Layer Federated Learning.pptx
Multi Layer Federated Learning.pptx
TimePass4315213 views
Intelligent Career Guidance System.pptx von Anonymous366406
Intelligent Career Guidance System.pptxIntelligent Career Guidance System.pptx
Intelligent Career Guidance System.pptx
Anonymous366406222 views
StackNet Meta-Modelling framework von Sri Ambati
StackNet Meta-Modelling frameworkStackNet Meta-Modelling framework
StackNet Meta-Modelling framework
Sri Ambati760 views
MachineLearning Seminar PPT.pptx von AmanDixit74
MachineLearning Seminar PPT.pptxMachineLearning Seminar PPT.pptx
MachineLearning Seminar PPT.pptx
AmanDixit7412 views

Más de KhondokerAbuNaim

Assignment of RSA Algorithm in Cryptography..pdf von
Assignment of RSA Algorithm in Cryptography..pdfAssignment of RSA Algorithm in Cryptography..pdf
Assignment of RSA Algorithm in Cryptography..pdfKhondokerAbuNaim
112 views5 Folien
Assignment-1-NF.docx von
Assignment-1-NF.docxAssignment-1-NF.docx
Assignment-1-NF.docxKhondokerAbuNaim
6 views6 Folien
Bangla_handwritten_dig1] final proposal .pdf von
Bangla_handwritten_dig1] final proposal .pdfBangla_handwritten_dig1] final proposal .pdf
Bangla_handwritten_dig1] final proposal .pdfKhondokerAbuNaim
9 views5 Folien
Project t Proposal Bangla alphabet handwritten recognition using deep learnin... von
Project t Proposal Bangla alphabet handwritten recognition using deep learnin...Project t Proposal Bangla alphabet handwritten recognition using deep learnin...
Project t Proposal Bangla alphabet handwritten recognition using deep learnin...KhondokerAbuNaim
112 views5 Folien
Quiz-Gam_1-converted.pptx von
Quiz-Gam_1-converted.pptxQuiz-Gam_1-converted.pptx
Quiz-Gam_1-converted.pptxKhondokerAbuNaim
407 views15 Folien
BAUST Lab report cover page .docx von
BAUST Lab report cover page .docxBAUST Lab report cover page .docx
BAUST Lab report cover page .docxKhondokerAbuNaim
1.1K views1 Folie

Más de KhondokerAbuNaim(9)

Assignment of RSA Algorithm in Cryptography..pdf von KhondokerAbuNaim
Assignment of RSA Algorithm in Cryptography..pdfAssignment of RSA Algorithm in Cryptography..pdf
Assignment of RSA Algorithm in Cryptography..pdf
KhondokerAbuNaim112 views
Bangla_handwritten_dig1] final proposal .pdf von KhondokerAbuNaim
Bangla_handwritten_dig1] final proposal .pdfBangla_handwritten_dig1] final proposal .pdf
Bangla_handwritten_dig1] final proposal .pdf
Project t Proposal Bangla alphabet handwritten recognition using deep learnin... von KhondokerAbuNaim
Project t Proposal Bangla alphabet handwritten recognition using deep learnin...Project t Proposal Bangla alphabet handwritten recognition using deep learnin...
Project t Proposal Bangla alphabet handwritten recognition using deep learnin...
KhondokerAbuNaim112 views
Online Voting System Project Proposal ( Presentation Slide).pptx von KhondokerAbuNaim
Online Voting System Project Proposal ( Presentation Slide).pptxOnline Voting System Project Proposal ( Presentation Slide).pptx
Online Voting System Project Proposal ( Presentation Slide).pptx
KhondokerAbuNaim576 views
Online Voting System project proposal report.doc von KhondokerAbuNaim
Online Voting System project proposal report.docOnline Voting System project proposal report.doc
Online Voting System project proposal report.doc
KhondokerAbuNaim3.7K views

Último

UNIDAD 3 6º C.MEDIO.pptx von
UNIDAD 3 6º C.MEDIO.pptxUNIDAD 3 6º C.MEDIO.pptx
UNIDAD 3 6º C.MEDIO.pptxMarcosRodriguezUcedo
124 views32 Folien
CWP_23995_2013_17_11_2023_FINAL_ORDER.pdf von
CWP_23995_2013_17_11_2023_FINAL_ORDER.pdfCWP_23995_2013_17_11_2023_FINAL_ORDER.pdf
CWP_23995_2013_17_11_2023_FINAL_ORDER.pdfSukhwinderSingh895865
536 views6 Folien
MIXING OF PHARMACEUTICALS.pptx von
MIXING OF PHARMACEUTICALS.pptxMIXING OF PHARMACEUTICALS.pptx
MIXING OF PHARMACEUTICALS.pptxAnupkumar Sharma
82 views35 Folien
Recap of our Class von
Recap of our ClassRecap of our Class
Recap of our ClassCorinne Weisgerber
81 views15 Folien
REPRESENTATION - GAUNTLET.pptx von
REPRESENTATION - GAUNTLET.pptxREPRESENTATION - GAUNTLET.pptx
REPRESENTATION - GAUNTLET.pptxiammrhaywood
107 views26 Folien
unidad 3.pdf von
unidad 3.pdfunidad 3.pdf
unidad 3.pdfMarcosRodriguezUcedo
106 views38 Folien

Último(20)

REPRESENTATION - GAUNTLET.pptx von iammrhaywood
REPRESENTATION - GAUNTLET.pptxREPRESENTATION - GAUNTLET.pptx
REPRESENTATION - GAUNTLET.pptx
iammrhaywood107 views
Dance KS5 Breakdown von WestHatch
Dance KS5 BreakdownDance KS5 Breakdown
Dance KS5 Breakdown
WestHatch86 views
Ch. 7 Political Participation and Elections.pptx von Rommel Regala
Ch. 7 Political Participation and Elections.pptxCh. 7 Political Participation and Elections.pptx
Ch. 7 Political Participation and Elections.pptx
Rommel Regala105 views
CUNY IT Picciano.pptx von apicciano
CUNY IT Picciano.pptxCUNY IT Picciano.pptx
CUNY IT Picciano.pptx
apicciano54 views
Classification of crude drugs.pptx von GayatriPatra14
Classification of crude drugs.pptxClassification of crude drugs.pptx
Classification of crude drugs.pptx
GayatriPatra1492 views
When Sex Gets Complicated: Porn, Affairs, & Cybersex von Marlene Maheu
When Sex Gets Complicated: Porn, Affairs, & CybersexWhen Sex Gets Complicated: Porn, Affairs, & Cybersex
When Sex Gets Complicated: Porn, Affairs, & Cybersex
Marlene Maheu73 views
Create a Structure in VBNet.pptx von Breach_P
Create a Structure in VBNet.pptxCreate a Structure in VBNet.pptx
Create a Structure in VBNet.pptx
Breach_P75 views

Bangla Hand Written Digit Recognition presentation slide .pptx

  • 1. Bangladesh Army University of Science and Technology,Saidpur  Course Title: Artifacial Intelligence and Fuzzy Systems  Course Code: CSE 4132  Level-4;Term-1  Course Adviser:Hasan Muhammad Kafi
  • 2.  Abu Rayhan Mouno (180201118)  Khondoker Abu Naim (200101103) 2 Project Title: Bangla handwritten digit recognition using deep learning.  Peresented by,
  • 3.  Introduction  Bangla Handwritten Characters Proposed Methodology  Dataset Discription  Preprocessing  Methodology  Implemented Model Architecture  Training The Network  Results Analysis  Limitation  Future Recomendation  Conlusion 3 Contents
  • 4. 4 Introduction Handwritten digit recognition is a classical problem in computer vision, with 10 unique Bangla digits to classify. The models evaluated are:  EfficientNetB0  MobileNet. These models' performances are contrasted under various training regimes. We are using baseline, transfer learning, and fine-tuning.
  • 5. ) Bangla Handwritten Digits Handwritten digits have unique characteristics such as strokes, styles, and structure Different people’s digits are unique to each person Bangla handwritten digits have a morphologically complex nature
  • 6. PROPOSED METHODOLOGY 6 Data Collection & Preprocessing Dataset Generation Training Classification using CNN Optimization Testing
  • 7. Dataset Discription 7  We have used our own dataset- 10 different Bangla handwritten digits.  2500 images for the Training and 500 images for the Testing Datasets  10 folders for the both Training and Testing Datasets, denoting 10 digits' classes  Each folders contain an equal number of sample images
  • 8. Dataset Description 8 ০ ১ ২ ৩ ৪ ৫ ৬ ৭ ৮ ৯ 200 220 250 250 203 267 223 231 224 245 Class Train Set Validatio n Set 69 71 75 73 70 75 73 60 65
  • 9. The Dataset(Cont.) 9 The training dataset was further split into two groups:  Training Dataset (90% of the original training dataset)  Testing Dataset (10% of the original training dataset) - Ensuring no bias was enforced in Testing 0 500 1000 1500 2000 2500 3000 Training Dataset Testing Dataset Dataset Fig1.Dataset chart
  • 10. The Dataset(Cont.) 10 Fig2.Sample of images from dataset Fig3.sample of images from result
  • 11. Methodology: Preprocessing 11 • Image were converted into grayscale images • All images were resized into a 124x124 dimension to target size 10 Kilobytes Fig4. 124x124 resized images of digit “9”
  • 12. Methodology:Environment 12 Resources Required to Accomplish the Task: • Python • Kaggle Installation of all necessary tools and libraries, such as TensorFlow, Keras, and NumPy, in both settings.
  • 13. Methodology:Model Architecture 13 Figure5. An illustration of the structure of our model training • We are using pre-trained deep learning models including EfficientNetB0 and MobileNet. • We compared this models under different training regimes including baseline, fine-tuning and transfer learning. Input 124x124x1 124x124x64 124x124x64 14x14x128 7x7x256 7x7x256 7x7x256
  • 14. TRAINING THE NETWORK 14 • Weights were initialized with Xavier initialization method • The network was trained all over using Adam optimizer with initial standard parameters • The model was trained using batches of size 32 • We used LR Scheduler for reducing the learning rate when validation loss was not improving • Total iteration to train the model: 16
  • 15. Result and analysis: overview of performance 15 Model Baseline Transfer learning Fine-tuning EffNetB0 31% 95% 99.4% MobileNet 9% 92% 94% 31 9 99.4 94 95 92 0 20 40 60 80 100 120 EffNetB0 MobileNet Result Analysis Baseline Fine-tuning Transfer learning
  • 16. 16 Limitations • Sample size: This dataset's sample size was limited, which might have had an impact on the statistical power and generalizability of the results. • Data quality: Data quality was determined by accuracy and comprehensiveness of participant replies. • Generalizability: Due to the sample being restricted to a particular participant group, it is possible that the results of this study cannot be applied to other populations or circumstances.
  • 17. 17 Future recommendations • Examine other pre-trained models:Explore different Neural Network models Work with various datasets to create a more robust and effective automated system. • Improve dataset quality • Improve dataset quality • Dataset Quality:Increase the amount of high-quality data was collected, especially for underrepresented classes, to improve the precision of machine learning models. • Try different optimizer algorithoms:Try out several optimization techniques, such RMSprop or SGD to boost the effectiveness of the digit recognition system. • Extend to real-time applications:Extend current implementation to real-time applications for practical use.
  • 18. Conclusion • Created models for recognizing digit using a variety of deep learning architectures and training methods. • As far as our knowledge, the achieved result is the state-of-the art accuracy in Bangla digit recognition. • Could result in advancement in the pursuit of digitization. 18