SlideShare a Scribd company logo
1 of 35
Presented By
GROUP NO:04
NAME EXAM NO
KUMARVIVEK B8233072
AMOL MAHURKAR B8233078
MANOJ AUTADE B8233082
GUIDED BY
PROF. S.B.TAKALE
Intelligent e-Book
-making lives simpler
8/29/20131 Department of E&TC, Sinhgad College of Engineering
Objective
 Primary: Electronic – notebook
To design a device for jotting important data in various fonts
 Secondary: e-Handwriting practice book
To help children getting acquired to new languages such as
English
8/29/20132 Department of E&TC, Sinhgad College of Engineering
Contents
 Origin of Idea
 PresentTechnologies
 Basic Block Diagram
 Structure of Neuron andANN
 Character Scanning
 Character Uniqueness
 Training of network
 Testing of network
8/29/20133 Department of E&TC, Sinhgad College of Engineering
Origin of Idea
 Leave the bulky laptop at home
 Enjoy a digital life
 Free from paper piles
 Increase efficiency
 Document management
 Professional device for the meeting
 Cost Effective
8/29/20134 Department of E&TC, Sinhgad College of Engineering
Present Technologies
 Character recognition usingANN based on OCR(Optical
Character Recognition)
 A compact, fast, and flexible implementation ofANNs is possible
with dedicated mixed-modeVLSI chips , which implements a two-
character recognizer using parallelogramVLSI architecture
 Recognize the cursive writing by extracting information about
knots using SPLINE function
 Integrated (offline + online) character recognition to improve the
recognition rate.
Figure: Nvidia Tegra 2
8/29/20135 Department of E&TC, Sinhgad College of Engineering
Uniqueness of system
• Whole system in single microcontroller
• User specific
• Flexible
• Cost effective
• Compactness
• Work without PC interface
8/29/20136 Department of E&TC, Sinhgad College of Engineering
Block Diagram
8/29/20137 Department of E&TC, Sinhgad College of Engineering
Construction: Touch Screen
8/29/20138 Department of E&TC, Sinhgad College of Engineering
Neural Network Basics: Neuron
 Part of Biological nervous
system
 Electrically Excitable.
 Contains synapses
Figure: Biological Neuron
8/29/201310 Department of E&TC, Sinhgad College of Engineering
Artificial Neural Network
8/29/201311 Department of E&TC, Sinhgad College of Engineering
Structure of ANN
8/29/201312 Department of E&TC, Sinhgad College of Engineering
Work done on Character Recognition
Uniqueness Methods
1. Letter Density
2. Horizontal Scanning
3. Vertical and horizontal scanning.
8/29/2013Department of E&TC, Sinhgad College of Engineering14
Character Scanning
Step1: Invoking RealTerm using MATLAB
Step2:Capturing co-ordinates and storing in .txt file
8/29/201315 Department of E&TC, Sinhgad College of Engineering
Character Scanning
Step 3: Importing saved .txt file into MATLAB
Step 4: Differentiating between co-ordinates
Step 5: Plotting captured co-ordinates of character
8/29/201316 Department of E&TC, Sinhgad College of Engineering
Character Uniqueness: Letter Density
Step 1: Dividing character into four quadrants
Step 2: Calculating Ratio variables from density of respective quadrants
8/29/201317 Department of E&TC, Sinhgad College of Engineering
Character Uniqueness: Letter Density Results
8/29/201318 Department of E&TC, Sinhgad College of Engineering
Character Uniqueness: Horizontal Scanning
Step 1: Creating 2-D image of scanned character
Step 2: Horizontal scanning
8/29/201319 Department of E&TC, Sinhgad College of Engineering
Character Uniqueness: Horizontal Scanning Results
Step 3: Filtering unwanted data to horizontal density patches
Letter E LetterT
8/29/201320 Department of E&TC, Sinhgad College of Engineering
Character Uniqueness: Horizontal & Vertical Scanning
8/29/2013Department of E&TC, Sinhgad College of Engineering21
 Following five parameters are obtained by horizontal
scanning
 Following five parameters obtained by vertical scanning
42 7 32 7 36
50 21 27 14 12
Scanning Character
8/29/2013Department of E&TC, Sinhgad College of Engineering22
FeatureVector (FV) = [20 22 35 23 21 27 24 23 25 28]
Training and validation
8/29/2013Department of E&TC, Sinhgad College of Engineering23
 Input: 10 values obtained from horizontal and vertical
scanning.
 Hidden neurons: Decided such that it is minimum and
achieve desired performance.
 Output: Identity matrix of 26x26, each row for single
alphabet.
 Batch training:Altering the sequence of characters ten
batches are formed.
 Performance goal = 0.00000001.
 Maximum epochs = 5000.
Training and validation
8/29/2013Department of E&TC, Sinhgad College of Engineering24
Result
8/29/2013Department of E&TC, Sinhgad College of Engineering25
Design flow
8/29/2013Department of E&TC, Sinhgad College of Engineering26
1) Training of network
2) Testing
i. Software
ii. Hardware
8/29/2013Department of E&TC, Sinhgad College of Engineering27
X
Extract the
features from each
uppercase English
alphabet
Create the batch
containing mixed
characters
Decide targets for
each character
Set the
performance goal
Decide the
maximum number
of hidden neurons
, P
Initialize the
number of hidden
neurons , N=5
Train the network
Performance
achieved
N<P
N=N+1
STOP
Save the NET
Z
YESNO
NO
YES
8/29/2013Department of E&TC, Sinhgad College of Engineering28
MATLAB Coder: Savior
8/29/2013Department of E&TC, Sinhgad College of Engineering29
Applications
• Education (teachers, students)
• Healthcare (doctors, nurses)
• Insurance (sales representative)
• Legal (lawyers)
• Government ( staff)
• Businessmen (for daily meeting)
• Journalists
• Architects
• Receptionists
8/29/201330 Department of E&TC, Sinhgad College of Engineering
Bill of material
8/29/2013Department of E&TC, Sinhgad College of Engineering31
Component Cost (in Rs.)
ResistiveTouch Screen 300
Graphic Liquid Crystal Display 550
LPC2138 stack board 1100
Battery + Charger 400
PCB 200
Others 50
Total 2600
* All prices are indicative. In actual can vary by small amount
Hardware Setup
8/29/2013Department of E&TC, Sinhgad College of Engineering32
Hardware Setup
8/29/2013Department of E&TC, Sinhgad College of Engineering33
Hardware Setup
8/29/2013Department of E&TC, Sinhgad College of Engineering34
Hardware Setup
8/29/2013Department of E&TC, Sinhgad College of Engineering35
References
 S N Sivanandam, S Sumathi, S N Deepa,“Introduction to Neural Networks
using MATLAB 6.0” ,Tata McGrawHill, 2nd Editon
 Angkoon Phinyomark,“A CAD approach based onArtificial Neural Network”,
Journal of IET,Volume 92, July 18
 L. D. Jackel,“A Neural Network Approach to Handprint Character
Recognition”
 Sameh E. Rehan,“VLSI Implementation of a ModularANN Chip for Character
Recognition”
 KarinaTOSCANO, “Cursive Character Recognition System”
 [HiroshiTanaka,“Hybrid Pen-Input Character Recognition System Based on
 Integration of Online-Offline Recognition”
 http://www.learnartificialneuralnetworks.com/backpropagation.html
 http://www.learnartificialneuralnetworks.com/#Intro
 http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html
#Human andArtificial Neurones - investigating the similarities
8/29/201336 Department of E&TC, Sinhgad College of Engineering
Thank you
8/29/2013Department of E&TC, Sinhgad College of Engineering37

More Related Content

Similar to Intelligent ebook

Internship report on AI , ML & IIOT and project responses
Internship report on AI , ML & IIOT and project responsesInternship report on AI , ML & IIOT and project responses
Internship report on AI , ML & IIOT and project responsesRakesh Arigela
 
3D PRINTING PRACTICE LAB .pdf
3D PRINTING PRACTICE LAB .pdf3D PRINTING PRACTICE LAB .pdf
3D PRINTING PRACTICE LAB .pdfMOKSHIT TECH
 
Company detailed profile
Company detailed profileCompany detailed profile
Company detailed profileGopi Be
 
Computer_department_NAAC.pptx
Computer_department_NAAC.pptxComputer_department_NAAC.pptx
Computer_department_NAAC.pptxDipak463154
 
Murugan c publications and participations
Murugan c publications and participationsMurugan c publications and participations
Murugan c publications and participationsmuruganachievements
 
Cs8581 networks lab manual 2017
Cs8581 networks lab manual   2017Cs8581 networks lab manual   2017
Cs8581 networks lab manual 2017Kayathri Devi D
 
Real time multimedia-signal_proccesing_using_matlab
Real time multimedia-signal_proccesing_using_matlabReal time multimedia-signal_proccesing_using_matlab
Real time multimedia-signal_proccesing_using_matlabangshumanjob
 
Resume upto august 2016
Resume upto august 2016Resume upto august 2016
Resume upto august 2016Chandan Raj
 
Project.12
Project.12Project.12
Project.12GS Kosta
 
IRJET- 3D Printer for Printing Biological Structures
IRJET- 3D Printer for Printing Biological StructuresIRJET- 3D Printer for Printing Biological Structures
IRJET- 3D Printer for Printing Biological StructuresIRJET Journal
 
Anik Roy CV
Anik Roy CVAnik Roy CV
Anik Roy CVANIK ROY
 
CV_Salim_August-2016
CV_Salim_August-2016CV_Salim_August-2016
CV_Salim_August-2016SALIM ISTYAQ
 
Design and Development of FDM 3D Printer Machine.pptx
Design and Development of FDM 3D Printer Machine.pptxDesign and Development of FDM 3D Printer Machine.pptx
Design and Development of FDM 3D Printer Machine.pptxVitthalKanade1
 
An Overview of Additive Manufacturing Technology, its Materials, Applications...
An Overview of Additive Manufacturing Technology, its Materials, Applications...An Overview of Additive Manufacturing Technology, its Materials, Applications...
An Overview of Additive Manufacturing Technology, its Materials, Applications...IRJET Journal
 
Web based e manufacturing of prototypes by using rapid prototyping technology
Web based e  manufacturing of prototypes by using rapid prototyping technologyWeb based e  manufacturing of prototypes by using rapid prototyping technology
Web based e manufacturing of prototypes by using rapid prototyping technologyIAEME Publication
 

Similar to Intelligent ebook (20)

Internship report on AI , ML & IIOT and project responses
Internship report on AI , ML & IIOT and project responsesInternship report on AI , ML & IIOT and project responses
Internship report on AI , ML & IIOT and project responses
 
3D PRINTING PRACTICE LAB .pdf
3D PRINTING PRACTICE LAB .pdf3D PRINTING PRACTICE LAB .pdf
3D PRINTING PRACTICE LAB .pdf
 
Company detailed profile
Company detailed profileCompany detailed profile
Company detailed profile
 
shridhar cv
shridhar cvshridhar cv
shridhar cv
 
Computer_department_NAAC.pptx
Computer_department_NAAC.pptxComputer_department_NAAC.pptx
Computer_department_NAAC.pptx
 
Murugan c publications and participations
Murugan c publications and participationsMurugan c publications and participations
Murugan c publications and participations
 
Cs8581 networks lab manual 2017
Cs8581 networks lab manual   2017Cs8581 networks lab manual   2017
Cs8581 networks lab manual 2017
 
ML PPT.pptx
ML PPT.pptxML PPT.pptx
ML PPT.pptx
 
Real time multimedia-signal_proccesing_using_matlab
Real time multimedia-signal_proccesing_using_matlabReal time multimedia-signal_proccesing_using_matlab
Real time multimedia-signal_proccesing_using_matlab
 
Resume upto august 2016
Resume upto august 2016Resume upto august 2016
Resume upto august 2016
 
Project.12
Project.12Project.12
Project.12
 
IT6511 Networks Laboratory
IT6511 Networks LaboratoryIT6511 Networks Laboratory
IT6511 Networks Laboratory
 
IRJET- 3D Printer for Printing Biological Structures
IRJET- 3D Printer for Printing Biological StructuresIRJET- 3D Printer for Printing Biological Structures
IRJET- 3D Printer for Printing Biological Structures
 
Anik Roy CV
Anik Roy CVAnik Roy CV
Anik Roy CV
 
CV_Salim_August-2016
CV_Salim_August-2016CV_Salim_August-2016
CV_Salim_August-2016
 
Design and Development of FDM 3D Printer Machine.pptx
Design and Development of FDM 3D Printer Machine.pptxDesign and Development of FDM 3D Printer Machine.pptx
Design and Development of FDM 3D Printer Machine.pptx
 
An Overview of Additive Manufacturing Technology, its Materials, Applications...
An Overview of Additive Manufacturing Technology, its Materials, Applications...An Overview of Additive Manufacturing Technology, its Materials, Applications...
An Overview of Additive Manufacturing Technology, its Materials, Applications...
 
Web based e manufacturing of prototypes by using rapid prototyping technology
Web based e  manufacturing of prototypes by using rapid prototyping technologyWeb based e  manufacturing of prototypes by using rapid prototyping technology
Web based e manufacturing of prototypes by using rapid prototyping technology
 
vikash kumar
vikash kumarvikash kumar
vikash kumar
 
Meena.CV
Meena.CVMeena.CV
Meena.CV
 

Recently uploaded

Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityWSO2
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfOrbitshub
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 
The Zero-ETL Approach: Enhancing Data Agility and Insight
The Zero-ETL Approach: Enhancing Data Agility and InsightThe Zero-ETL Approach: Enhancing Data Agility and Insight
The Zero-ETL Approach: Enhancing Data Agility and InsightSafe Software
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Victor Rentea
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Zilliz
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Bhuvaneswari Subramani
 
Modernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using BallerinaModernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using BallerinaWSO2
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusZilliz
 
Quantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation ComputingQuantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation ComputingWSO2
 
ChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps ProductivityChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps ProductivityVictorSzoltysek
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxRemote DBA Services
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Stronger Together: Developing an Organizational Strategy for Accessible Desig...
Stronger Together: Developing an Organizational Strategy for Accessible Desig...Stronger Together: Developing an Organizational Strategy for Accessible Desig...
Stronger Together: Developing an Organizational Strategy for Accessible Desig...caitlingebhard1
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
 
Introduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMIntroduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMKumar Satyam
 
Design and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data ScienceDesign and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data SciencePaolo Missier
 

Recently uploaded (20)

Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
The Zero-ETL Approach: Enhancing Data Agility and Insight
The Zero-ETL Approach: Enhancing Data Agility and InsightThe Zero-ETL Approach: Enhancing Data Agility and Insight
The Zero-ETL Approach: Enhancing Data Agility and Insight
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Modernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using BallerinaModernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using Ballerina
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
Quantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation ComputingQuantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation Computing
 
ChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps ProductivityChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps Productivity
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering Developers
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Stronger Together: Developing an Organizational Strategy for Accessible Desig...
Stronger Together: Developing an Organizational Strategy for Accessible Desig...Stronger Together: Developing an Organizational Strategy for Accessible Desig...
Stronger Together: Developing an Organizational Strategy for Accessible Desig...
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Introduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMIntroduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDM
 
Design and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data ScienceDesign and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data Science
 

Intelligent ebook

  • 1. Presented By GROUP NO:04 NAME EXAM NO KUMARVIVEK B8233072 AMOL MAHURKAR B8233078 MANOJ AUTADE B8233082 GUIDED BY PROF. S.B.TAKALE Intelligent e-Book -making lives simpler 8/29/20131 Department of E&TC, Sinhgad College of Engineering
  • 2. Objective  Primary: Electronic – notebook To design a device for jotting important data in various fonts  Secondary: e-Handwriting practice book To help children getting acquired to new languages such as English 8/29/20132 Department of E&TC, Sinhgad College of Engineering
  • 3. Contents  Origin of Idea  PresentTechnologies  Basic Block Diagram  Structure of Neuron andANN  Character Scanning  Character Uniqueness  Training of network  Testing of network 8/29/20133 Department of E&TC, Sinhgad College of Engineering
  • 4. Origin of Idea  Leave the bulky laptop at home  Enjoy a digital life  Free from paper piles  Increase efficiency  Document management  Professional device for the meeting  Cost Effective 8/29/20134 Department of E&TC, Sinhgad College of Engineering
  • 5. Present Technologies  Character recognition usingANN based on OCR(Optical Character Recognition)  A compact, fast, and flexible implementation ofANNs is possible with dedicated mixed-modeVLSI chips , which implements a two- character recognizer using parallelogramVLSI architecture  Recognize the cursive writing by extracting information about knots using SPLINE function  Integrated (offline + online) character recognition to improve the recognition rate. Figure: Nvidia Tegra 2 8/29/20135 Department of E&TC, Sinhgad College of Engineering
  • 6. Uniqueness of system • Whole system in single microcontroller • User specific • Flexible • Cost effective • Compactness • Work without PC interface 8/29/20136 Department of E&TC, Sinhgad College of Engineering
  • 7. Block Diagram 8/29/20137 Department of E&TC, Sinhgad College of Engineering
  • 8. Construction: Touch Screen 8/29/20138 Department of E&TC, Sinhgad College of Engineering
  • 9. Neural Network Basics: Neuron  Part of Biological nervous system  Electrically Excitable.  Contains synapses Figure: Biological Neuron 8/29/201310 Department of E&TC, Sinhgad College of Engineering
  • 10. Artificial Neural Network 8/29/201311 Department of E&TC, Sinhgad College of Engineering
  • 11. Structure of ANN 8/29/201312 Department of E&TC, Sinhgad College of Engineering
  • 12. Work done on Character Recognition Uniqueness Methods 1. Letter Density 2. Horizontal Scanning 3. Vertical and horizontal scanning. 8/29/2013Department of E&TC, Sinhgad College of Engineering14
  • 13. Character Scanning Step1: Invoking RealTerm using MATLAB Step2:Capturing co-ordinates and storing in .txt file 8/29/201315 Department of E&TC, Sinhgad College of Engineering
  • 14. Character Scanning Step 3: Importing saved .txt file into MATLAB Step 4: Differentiating between co-ordinates Step 5: Plotting captured co-ordinates of character 8/29/201316 Department of E&TC, Sinhgad College of Engineering
  • 15. Character Uniqueness: Letter Density Step 1: Dividing character into four quadrants Step 2: Calculating Ratio variables from density of respective quadrants 8/29/201317 Department of E&TC, Sinhgad College of Engineering
  • 16. Character Uniqueness: Letter Density Results 8/29/201318 Department of E&TC, Sinhgad College of Engineering
  • 17. Character Uniqueness: Horizontal Scanning Step 1: Creating 2-D image of scanned character Step 2: Horizontal scanning 8/29/201319 Department of E&TC, Sinhgad College of Engineering
  • 18. Character Uniqueness: Horizontal Scanning Results Step 3: Filtering unwanted data to horizontal density patches Letter E LetterT 8/29/201320 Department of E&TC, Sinhgad College of Engineering
  • 19. Character Uniqueness: Horizontal & Vertical Scanning 8/29/2013Department of E&TC, Sinhgad College of Engineering21  Following five parameters are obtained by horizontal scanning  Following five parameters obtained by vertical scanning 42 7 32 7 36 50 21 27 14 12
  • 20. Scanning Character 8/29/2013Department of E&TC, Sinhgad College of Engineering22 FeatureVector (FV) = [20 22 35 23 21 27 24 23 25 28]
  • 21. Training and validation 8/29/2013Department of E&TC, Sinhgad College of Engineering23  Input: 10 values obtained from horizontal and vertical scanning.  Hidden neurons: Decided such that it is minimum and achieve desired performance.  Output: Identity matrix of 26x26, each row for single alphabet.  Batch training:Altering the sequence of characters ten batches are formed.  Performance goal = 0.00000001.  Maximum epochs = 5000.
  • 22. Training and validation 8/29/2013Department of E&TC, Sinhgad College of Engineering24
  • 23. Result 8/29/2013Department of E&TC, Sinhgad College of Engineering25
  • 24. Design flow 8/29/2013Department of E&TC, Sinhgad College of Engineering26 1) Training of network 2) Testing i. Software ii. Hardware
  • 25. 8/29/2013Department of E&TC, Sinhgad College of Engineering27 X Extract the features from each uppercase English alphabet Create the batch containing mixed characters Decide targets for each character Set the performance goal Decide the maximum number of hidden neurons , P Initialize the number of hidden neurons , N=5 Train the network Performance achieved N<P N=N+1 STOP Save the NET Z YESNO NO YES
  • 26. 8/29/2013Department of E&TC, Sinhgad College of Engineering28
  • 27. MATLAB Coder: Savior 8/29/2013Department of E&TC, Sinhgad College of Engineering29
  • 28. Applications • Education (teachers, students) • Healthcare (doctors, nurses) • Insurance (sales representative) • Legal (lawyers) • Government ( staff) • Businessmen (for daily meeting) • Journalists • Architects • Receptionists 8/29/201330 Department of E&TC, Sinhgad College of Engineering
  • 29. Bill of material 8/29/2013Department of E&TC, Sinhgad College of Engineering31 Component Cost (in Rs.) ResistiveTouch Screen 300 Graphic Liquid Crystal Display 550 LPC2138 stack board 1100 Battery + Charger 400 PCB 200 Others 50 Total 2600 * All prices are indicative. In actual can vary by small amount
  • 30. Hardware Setup 8/29/2013Department of E&TC, Sinhgad College of Engineering32
  • 31. Hardware Setup 8/29/2013Department of E&TC, Sinhgad College of Engineering33
  • 32. Hardware Setup 8/29/2013Department of E&TC, Sinhgad College of Engineering34
  • 33. Hardware Setup 8/29/2013Department of E&TC, Sinhgad College of Engineering35
  • 34. References  S N Sivanandam, S Sumathi, S N Deepa,“Introduction to Neural Networks using MATLAB 6.0” ,Tata McGrawHill, 2nd Editon  Angkoon Phinyomark,“A CAD approach based onArtificial Neural Network”, Journal of IET,Volume 92, July 18  L. D. Jackel,“A Neural Network Approach to Handprint Character Recognition”  Sameh E. Rehan,“VLSI Implementation of a ModularANN Chip for Character Recognition”  KarinaTOSCANO, “Cursive Character Recognition System”  [HiroshiTanaka,“Hybrid Pen-Input Character Recognition System Based on  Integration of Online-Offline Recognition”  http://www.learnartificialneuralnetworks.com/backpropagation.html  http://www.learnartificialneuralnetworks.com/#Intro  http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html #Human andArtificial Neurones - investigating the similarities 8/29/201336 Department of E&TC, Sinhgad College of Engineering
  • 35. Thank you 8/29/2013Department of E&TC, Sinhgad College of Engineering37