Submit Search
Upload
IRJET- Classification of Hindi Maatras by Encoding Scheme
•
1 like
•
23 views
IRJET Journal
Follow
https://www.irjet.net/archives/V6/i3/IRJET-V6I3846.pdf
Read less
Read more
Engineering
Report
Share
Report
Share
1 of 4
Download now
Download to read offline
Recommended
The Framework of Image Recognition based on Modified Freeman Chain Code
The Framework of Image Recognition based on Modified Freeman Chain Code
CSCJournals
Classifier fusion method to recognize
Classifier fusion method to recognize
IJCI JOURNAL
Critical Review on Off-Line Sinhala Handwriting Recognition
Critical Review on Off-Line Sinhala Handwriting Recognition
Amila Wijayarathna
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)
IJERD Editor
Role Model of Graph Coloring Application in Labeled 2D Line Drawing Object
Role Model of Graph Coloring Application in Labeled 2D Line Drawing Object
Waqas Tariq
A MULTI-STREAM HMM APPROACH TO OFFLINE HANDWRITTEN ARABIC WORD RECOGNITION
A MULTI-STREAM HMM APPROACH TO OFFLINE HANDWRITTEN ARABIC WORD RECOGNITION
IJNLC Int.Jour on Natural Lang computing
A MULTI-STREAM HMM APPROACH TO OFFLINE HANDWRITTEN ARABIC WORD RECOGNITION
A MULTI-STREAM HMM APPROACH TO OFFLINE HANDWRITTEN ARABIC WORD RECOGNITION
ijnlc
Offline Signiture and Numeral Recognition in Context of Cheque
Offline Signiture and Numeral Recognition in Context of Cheque
IJERA Editor
Recommended
The Framework of Image Recognition based on Modified Freeman Chain Code
The Framework of Image Recognition based on Modified Freeman Chain Code
CSCJournals
Classifier fusion method to recognize
Classifier fusion method to recognize
IJCI JOURNAL
Critical Review on Off-Line Sinhala Handwriting Recognition
Critical Review on Off-Line Sinhala Handwriting Recognition
Amila Wijayarathna
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)
IJERD Editor
Role Model of Graph Coloring Application in Labeled 2D Line Drawing Object
Role Model of Graph Coloring Application in Labeled 2D Line Drawing Object
Waqas Tariq
A MULTI-STREAM HMM APPROACH TO OFFLINE HANDWRITTEN ARABIC WORD RECOGNITION
A MULTI-STREAM HMM APPROACH TO OFFLINE HANDWRITTEN ARABIC WORD RECOGNITION
IJNLC Int.Jour on Natural Lang computing
A MULTI-STREAM HMM APPROACH TO OFFLINE HANDWRITTEN ARABIC WORD RECOGNITION
A MULTI-STREAM HMM APPROACH TO OFFLINE HANDWRITTEN ARABIC WORD RECOGNITION
ijnlc
Offline Signiture and Numeral Recognition in Context of Cheque
Offline Signiture and Numeral Recognition in Context of Cheque
IJERA Editor
Pattern Recognition of Japanese Alphabet Katakana Using Airy Zeta Function
Pattern Recognition of Japanese Alphabet Katakana Using Airy Zeta Function
Editor IJCATR
C basics
C basics
sridevi5983
Isolated Arabic Handwritten Character Recognition Using Linear Correlation
Isolated Arabic Handwritten Character Recognition Using Linear Correlation
Editor IJCATR
Unit 3
Unit 3
GunasundariSelvaraj
Face Alignment Using Active Shape Model And Support Vector Machine
Face Alignment Using Active Shape Model And Support Vector Machine
CSCJournals
Mca 205
Mca 205
smumbahelp
C7 agramakirshnan2
C7 agramakirshnan2
Jasline Presilda
ARABIC HANDWRITTEN CHARACTER RECOGNITION USING STRUCTURAL SHAPE DECOMPOSITION
ARABIC HANDWRITTEN CHARACTER RECOGNITION USING STRUCTURAL SHAPE DECOMPOSITION
sipij
Devnagari document segmentation using histogram approach
Devnagari document segmentation using histogram approach
Vikas Dongre
DEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH
DEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH
ijcseit
Recognition of Tifinaghe Characters Using a Multilayer Neural Network
Recognition of Tifinaghe Characters Using a Multilayer Neural Network
CSCJournals
Double Precision Floating Point Multiplier using Verilog
Double Precision Floating Point Multiplier using Verilog
IRJET Journal
Computer Graphics and Virtual Reality
Computer Graphics and Virtual Reality
chirag patil
Grid Based Feature Extraction for the Recognition of Indian Currency Notes
Grid Based Feature Extraction for the Recognition of Indian Currency Notes
Karthik Nayak
Fy secondsemester2016
Fy secondsemester2016
Ankit Dubey
Fy secondsemester2016
Fy secondsemester2016
Ankit Dubey
CORBA IDL
CORBA IDL
Roy Antony Arnold G
ListMyPolygons 0.6
ListMyPolygons 0.6
Riccardo W. Monfardini
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Editor IJCATR
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Editor IJCATR
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Editor IJCATR
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Editor IJCATR
More Related Content
What's hot
Pattern Recognition of Japanese Alphabet Katakana Using Airy Zeta Function
Pattern Recognition of Japanese Alphabet Katakana Using Airy Zeta Function
Editor IJCATR
C basics
C basics
sridevi5983
Isolated Arabic Handwritten Character Recognition Using Linear Correlation
Isolated Arabic Handwritten Character Recognition Using Linear Correlation
Editor IJCATR
Unit 3
Unit 3
GunasundariSelvaraj
Face Alignment Using Active Shape Model And Support Vector Machine
Face Alignment Using Active Shape Model And Support Vector Machine
CSCJournals
Mca 205
Mca 205
smumbahelp
C7 agramakirshnan2
C7 agramakirshnan2
Jasline Presilda
ARABIC HANDWRITTEN CHARACTER RECOGNITION USING STRUCTURAL SHAPE DECOMPOSITION
ARABIC HANDWRITTEN CHARACTER RECOGNITION USING STRUCTURAL SHAPE DECOMPOSITION
sipij
Devnagari document segmentation using histogram approach
Devnagari document segmentation using histogram approach
Vikas Dongre
DEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH
DEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH
ijcseit
Recognition of Tifinaghe Characters Using a Multilayer Neural Network
Recognition of Tifinaghe Characters Using a Multilayer Neural Network
CSCJournals
Double Precision Floating Point Multiplier using Verilog
Double Precision Floating Point Multiplier using Verilog
IRJET Journal
Computer Graphics and Virtual Reality
Computer Graphics and Virtual Reality
chirag patil
Grid Based Feature Extraction for the Recognition of Indian Currency Notes
Grid Based Feature Extraction for the Recognition of Indian Currency Notes
Karthik Nayak
Fy secondsemester2016
Fy secondsemester2016
Ankit Dubey
Fy secondsemester2016
Fy secondsemester2016
Ankit Dubey
CORBA IDL
CORBA IDL
Roy Antony Arnold G
What's hot
(17)
Pattern Recognition of Japanese Alphabet Katakana Using Airy Zeta Function
Pattern Recognition of Japanese Alphabet Katakana Using Airy Zeta Function
C basics
C basics
Isolated Arabic Handwritten Character Recognition Using Linear Correlation
Isolated Arabic Handwritten Character Recognition Using Linear Correlation
Unit 3
Unit 3
Face Alignment Using Active Shape Model And Support Vector Machine
Face Alignment Using Active Shape Model And Support Vector Machine
Mca 205
Mca 205
C7 agramakirshnan2
C7 agramakirshnan2
ARABIC HANDWRITTEN CHARACTER RECOGNITION USING STRUCTURAL SHAPE DECOMPOSITION
ARABIC HANDWRITTEN CHARACTER RECOGNITION USING STRUCTURAL SHAPE DECOMPOSITION
Devnagari document segmentation using histogram approach
Devnagari document segmentation using histogram approach
DEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH
DEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH
Recognition of Tifinaghe Characters Using a Multilayer Neural Network
Recognition of Tifinaghe Characters Using a Multilayer Neural Network
Double Precision Floating Point Multiplier using Verilog
Double Precision Floating Point Multiplier using Verilog
Computer Graphics and Virtual Reality
Computer Graphics and Virtual Reality
Grid Based Feature Extraction for the Recognition of Indian Currency Notes
Grid Based Feature Extraction for the Recognition of Indian Currency Notes
Fy secondsemester2016
Fy secondsemester2016
Fy secondsemester2016
Fy secondsemester2016
CORBA IDL
CORBA IDL
Similar to IRJET- Classification of Hindi Maatras by Encoding Scheme
ListMyPolygons 0.6
ListMyPolygons 0.6
Riccardo W. Monfardini
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Editor IJCATR
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Editor IJCATR
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Editor IJCATR
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Editor IJCATR
IRJET- Advanced Character based Recognition and Phone Handling for Blind ...
IRJET- Advanced Character based Recognition and Phone Handling for Blind ...
IRJET Journal
IRJET- Two Layer QR Code with Picture Embedding
IRJET- Two Layer QR Code with Picture Embedding
IRJET Journal
HSI Classification: Analysis
HSI Classification: Analysis
IRJET Journal
Ashish garg research paper 660_CamReady
Ashish garg research paper 660_CamReady
Ashish Garg
Segmentation and recognition of handwritten digit numeral string using a mult...
Segmentation and recognition of handwritten digit numeral string using a mult...
ijfcstjournal
Ijetcas14 399
Ijetcas14 399
Iasir Journals
Design and Analysis of High Performance Floating Point Arithmetic Unit
Design and Analysis of High Performance Floating Point Arithmetic Unit
ijtsrd
IRJET - Handwritten Bangla Digit Recognition using Capsule Network
IRJET - Handwritten Bangla Digit Recognition using Capsule Network
IRJET Journal
The automatic license plate recognition(alpr)
The automatic license plate recognition(alpr)
eSAT Publishing House
Design of 32-bit Floating Point Unit for Advanced Processors
Design of 32-bit Floating Point Unit for Advanced Processors
IJERA Editor
The automatic license plate recognition(alpr)
The automatic license plate recognition(alpr)
eSAT Journals
IRJET- Image based Approach for Indian Fake Note Detection by Dark Channe...
IRJET- Image based Approach for Indian Fake Note Detection by Dark Channe...
IRJET Journal
IRJET- Partition Method for DFA Minimization
IRJET- Partition Method for DFA Minimization
IRJET Journal
IRJET - License Plate Detection using Hybrid Morphological Technique and ...
IRJET - License Plate Detection using Hybrid Morphological Technique and ...
IRJET Journal
The automatic license plate recognition(alpr)
The automatic license plate recognition(alpr)
eSAT Publishing House
Similar to IRJET- Classification of Hindi Maatras by Encoding Scheme
(20)
ListMyPolygons 0.6
ListMyPolygons 0.6
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
Duplicate Code Detection using Control Statements
IRJET- Advanced Character based Recognition and Phone Handling for Blind ...
IRJET- Advanced Character based Recognition and Phone Handling for Blind ...
IRJET- Two Layer QR Code with Picture Embedding
IRJET- Two Layer QR Code with Picture Embedding
HSI Classification: Analysis
HSI Classification: Analysis
Ashish garg research paper 660_CamReady
Ashish garg research paper 660_CamReady
Segmentation and recognition of handwritten digit numeral string using a mult...
Segmentation and recognition of handwritten digit numeral string using a mult...
Ijetcas14 399
Ijetcas14 399
Design and Analysis of High Performance Floating Point Arithmetic Unit
Design and Analysis of High Performance Floating Point Arithmetic Unit
IRJET - Handwritten Bangla Digit Recognition using Capsule Network
IRJET - Handwritten Bangla Digit Recognition using Capsule Network
The automatic license plate recognition(alpr)
The automatic license plate recognition(alpr)
Design of 32-bit Floating Point Unit for Advanced Processors
Design of 32-bit Floating Point Unit for Advanced Processors
The automatic license plate recognition(alpr)
The automatic license plate recognition(alpr)
IRJET- Image based Approach for Indian Fake Note Detection by Dark Channe...
IRJET- Image based Approach for Indian Fake Note Detection by Dark Channe...
IRJET- Partition Method for DFA Minimization
IRJET- Partition Method for DFA Minimization
IRJET - License Plate Detection using Hybrid Morphological Technique and ...
IRJET - License Plate Detection using Hybrid Morphological Technique and ...
The automatic license plate recognition(alpr)
The automatic license plate recognition(alpr)
More from IRJET Journal
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
IRJET Journal
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
IRJET Journal
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
IRJET Journal
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil Characteristics
IRJET Journal
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
IRJET Journal
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
IRJET Journal
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
IRJET Journal
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
IRJET Journal
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADAS
IRJET Journal
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
IRJET Journal
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
IRJET Journal
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
IRJET Journal
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare System
IRJET Journal
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridges
IRJET Journal
React based fullstack edtech web application
React based fullstack edtech web application
IRJET Journal
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
IRJET Journal
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
IRJET Journal
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
IRJET Journal
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
IRJET Journal
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
IRJET Journal
More from IRJET Journal
(20)
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil Characteristics
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADAS
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare System
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridges
React based fullstack edtech web application
React based fullstack edtech web application
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Recently uploaded
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Christo Ananth
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
ranjana rawat
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur High Profile
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
SIVASHANKAR N
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptx
upamatechverse
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
ranjana rawat
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
Suhani Kapoor
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
rakeshbaidya232001
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptx
Asutosh Ranjan
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control
Roadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and Routes
M Maged Hegazy, LLM, MBA, CCP, P3O
result management system report for college project
result management system report for college project
Tonystark477637
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptx
upamatechverse
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
Suhani Kapoor
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
sivaprakash250
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
ranjana rawat
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Suman Mia
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Christo Ananth
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
ranjana rawat
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )
Tsuyoshi Horigome
Recently uploaded
(20)
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptx
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptx
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
Roadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and Routes
result management system report for college project
result management system report for college project
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptx
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )
IRJET- Classification of Hindi Maatras by Encoding Scheme
1.
International Research Journal
of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7373 Classification of Hindi Maatras By Encoding Scheme Ashna Joysi Gaikwad1, Dr. Neeta Nathani2 1Research Scholar, Gyan Ganga College Of Technology, Jabalpur, MP, India 2Assistant Professor, Gyan Ganga College Of Technology, Jabalpur, MP, India ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - Hindi vowels are appended to the consonants in the form of modifiers or maatras. The modifiers may be present at top or bottom level resulting in top modifiers or ascenders and lower modifiers or descenders. For an optical recognition system these modifiers are firstly segmented then classified. The proposed method is a novel approach that classifies the modifiers with the help of codes. Each modifier is segmented from the character then is processed with encoding steps. The end product of the encoding steps result in a distinctive code for each modifier. The proposed method classifies the modifiers easily with less space and time by using the structural property of each modifiers. The method has been tested on printed and handwritten modifiers and has found to yield 95.23% and 90.47% accuracy for descenders and ascenders respectively. Key Words: Hindi character segmentation, Hindi Modifier segmentation, Optical character recognition, Pattern classification,Hindi Modifier Classification 1.INTRODUCTION Hindi language is a part of Devnagri script consisting of 33 consonants (vyanjans) and 13 vowels or swaras. Segmentation and classification of Hindi character is easy due to the blank space present between the characters but the presence of modifiers make the segmentation process complex. For classification either the modifiers as a whole were used or in the form feature vectors. In either case the OCR system becomes complex[1]. Some modifiers have similar shapes above the header line or shiroreka irrespective of the position of vertical bar along the characters. Hence to simplify the segmentation and classification of modifiers, the modifiers are converted to codes directly, a particular code for each modifier. The distinctive codes are sufficient in themselves to classify the modifiers without an actual classifier. The rest of the paper is organized as : Section 1 introduces the complexity of modifiers and the need for its classification. This section is elaborated in Section 2. Section 3 deals with existing techniques for modifier segmentation and the proposed method is described in Section 4. Section 5 includes results and related discussions and Section 6 concludes the paper. 2. HINDI LANGUAGE AND THE MODIFIERS The modifiers are integral part of Hindi language. Hindi is written in Devnagri script which has a horizontal bar over every word which is known as header line. The structure of a Hindi word is distributed in zones: top zone, middle zone and lower zone. This can be seen by figure 1. Fig -1: Zones of a Hindi Word The top zone is completely reserved for the upper modifiers and the lower zone is reserved for the lower modifiers or descender. Fig -2: Modifiers Figure 2 shows the positioning of each modifiers. Even though there are other modifiers present along with some special symbols this work deals with the above modifier which are commonly used. It must be noted that in case of ascenders there are some modifiers which are similar in upper zone unless their bar in middle zone is taken. For example e and o from figure 2 are same except the middle part of o. Such arrangements of modifiers make them robust to various segmentation process. If projection profile[2] is considered, the method derives only the upper part of the ascender which results in miss classification. Hence a new method is used to solve this problem. 3. LITERATURE REVIEW The commonly used method for modifier segmentation is projection profile. This technique uses the density of object pixels in a region. This method was used by Garg, Kaur and Jindal in [3]. The removal of header line removes the ascenders from middle region. The modifiers present in the top zone are separated by spaces. Using these blank spaces the modifiers are derived from the word. For descenders the mean height of the character is used as a delimiter.The above method gave accurate result but there was no
2.
International Research Journal
of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7374 provision for middle bars of the ascenders. Bag and Krishna in [4] suggest that after removal of header line the appropriate joining from the modifier to their middle bar can be done.This was achieved by using the width of the character and middle bar. As usual the middle bar is the thinnest object in the middle zone this was joined to their respective modifiers. For descender segmentation the character with greater height is taken and by using a 3 by 3 window the descender is derived. 4. PROPOSED METHOD The proposed method deals with the segmentation as well as classification of the modifiers. Due to the positioning of the ascenders and descenders two separate algorithm are used. 4.1 ALGORITHM FOR ASCENDER CLASSIFICATION There are three encoding levels for ascender classification each one giving a single value. Level 1: Input: Character with ascender i) Remove the header line ii) Store ascender and middle portion in separate cells iii) Find the number of objects present in the middle portion, if only one character is present (as in modifier e and ai) then Level 1 code = 3 , end the process. iv) If more than one objects are present(a character and a middle bar) then find width of each object. v) The middle bar will always be thinnest. Find the position of the thinner object. If it is present before the character (as in modifier i) then Level 1 code = 1, else it is present beyond the character then Level 1 code = 2.End. The graphical representation of level 1 encoding with an example is shown if figure 3. Fig -3: Level 1 Algorithm Level 2: Input: Upper modifier i) The modifier stored in a separate cell is firstly skeletonize[5]. ii) The middle row from the skeletonized modifier is derived, iii) Number of object pixels are counted in middle row iv) If only one object pixel is found then modifiers e and o are present(figure 2). For such modifiers Level 2 code = 1 is assigned. v) for the rest of modifiers Level 2 code = 2 is assigned, End. For modifier o only one object is obtained in selected window in figure 4 so code obtained is 1 where as in modifier i two objects are found. Fig -4: Level 2 Algorithm Level 3: Input: Skeletonized Modifier i) The portion of skeletonized modifier which is last five rows and first three columns is taken,[6] ii) Object pixels will be present for modifiers with both the ends joined to header line. iii) If object pixels are present then Level 3 code = 1 is assigned else Level 3 code = 0 is assigned.End Fig -5: Level 3 Algorithm Figure 5, shows the codes of modifiers i and e. So the encoding scheme for upper modifier can be tabulated in Table 1.
3.
International Research Journal
of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7375 Table -1: Encoding Scheme of Ascenders 4.2 ALGORITHM FOR DESCENDER CLASSIFICATION The descenders are only present in lower zone. These can be derived by the height of the character. The character with descender is taller than the rest of the characters. Hence using this information the descender is segmented from the character. The method covers the following descenders shown in figure 6: Fig -6: Lower Modifiers Level 1: Input : Segmented Descender (i)Find the width of the descender and calculate the threshold width, Wth = Width * 0.7, (ii)Find the last object pixel in the center row, (iii)Compare the threshold width with number of last object pixel obtained in (ii), (iv)If Wth < last pixel then the right side of the descender is empty , only ra modifier of figure 6 fulfill this condition , so Level 1 code = 1, (v)Conversely if Wth > last point then Level 1 code = 0 is assigned. End Fig -7: Width of Descender The blue line in figure 7 shows the middle row of each modifier ending at last object pixel. The black line under each descenders shows the actual width. Comparison between the width of middle row and width of descender the code is assigned. Level 2: Input : Segmented Descender For modifiers u and u: , another level of code is derived. The space at the lower right end is considered. From this region the presence of object is checked. If object is present then Level 2 code = 9 is assigned else 1 is assigned. Fig -8: Presence of object in lower right end From all three modifiers in figure 8 only u has no objects in lower right end. This difference is used to assign different character. Table -2: Encoding Scheme of Descenders 5. RESULT AND DISCUSSIONS The proposed method was applied on Hindi modifiers from handwritten as well as printed modifiers. The proposed method is implemented using MATLAB and the findings can be tabulated. Following figures shows the implemented output for both the modifiers. Since each modifier has a different code, this method can be used for classification also. Fig -9: Encoded Output for Ascender
4.
International Research Journal
of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7376 Fig -10: Encoded Output for Descender The proposed method was tested on 7 different texts containing each of the specified Hindi modifiers with words. The codes obtained from the method were validated by assigning true mark (T) for correct ones and false mark (F) for the incorrect. The outcome is tabulated as follows: Table -3: Classification Accuracy of the Modifiers The classification accuracy for descender and ascender is 95.23% and 90.47% respectively. Overall accuracy is 92.06% Some modifiers like (u) and (e)had bigger loop, as a result they are miss classified. The skewed strokes of (au) make it appear joint and thus yielding incorrect code. 6. CONCLUSION The proposed method is a novel approach for classification of the Hindi modifiers. The method converts each modifier image into a distinctive code directly . As each modifier has a different code this method can be used as a classification method without feature extraction. The encoding algorithm contains different tiers for each level of codes. The algorithm can be used in the combination of codes and images as well. But using this scheme it must be noted that the modifiers must not be distorted, noisy or irregular. 7. FUTURE SCOPE The method can be expanded to classify the modifiers of other Devnagri languages. This technique can be improved to deal with the distorted and irregular shaped modifiers.Using this approach the Hindi characters may be classified . REFRENCES [1]Garg N.K,Kaur L, Jindal MK. The Hazards in Segmentation of Handwritten Hindi Text[J]. Journal of Computer Application,2011,29(2):0975-8887 [2]Anupama M, Rupa CH, Reddy ES.Character Segmentation for Telgu Document Using Multiple Histogram Projection[J]. Journal of Computer Science and Technology Graphic and Vision,2013,13(5):0975-4350 [3]Garg N.K,Kaur L, Jindal MK.Segmentation of Handwritten Hindi Text[J]. International Journal of Computer Application,2010,01(4):0975-8887 [4] Bag S. and Krishna A.,Character Segmentation of Hindi Unconstrained Handwritten Words Springer International Publishing, LNCS,2015, 9448:247-260 [5]Nixon M, Aguado A. Feature Extraction and Image Processing, 2nd Edition,ELSEVIER [6]Lempitsky V, Kohli P, Rother C, Sharp T[R]. Image Segmentation with Bounding Box Prior, Microsoft Research, Cambridge,2013 [7]Puneet, Garg NK. Binarization Technique Used for Grey Scale Image[J]. International Journal of Computer Application, 2013,71(1):0975-8887 [8]Nixon M, Aguado A. Feature Extraction and Image Processing, 2nd Edition,ELSEVIER.
Download now