Segmentation of touching characters in printed Devnagari and Bangla scripts using fuzzy multifactorial analysis

Existence of touching characters in scanned documents is a major problem in designing an effective character segmentation procedure for OCR systems. In this paper, new techniques are presented for identification and segmentation of touching characters. The techniques are based on fuzzy multifactorial analysis. A predictive algorithm is developed for effectively selecting cut-points to segment touching characters. Initially, our proposed method has been applied for segmenting touching characters that appear in Devnagari (Hindi) and Bangla, two major scripts in the Indian sub-continent. The results obtained from a test-set of considerable size show that a high recognition rate can be achieved with a reasonable amount of computations.

• Publication year

  2001

• Venue

  Proceedings of Sixth International Conference on Document Analysis and Recognition

• Publication date

  2001-09-10

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICDAR.2001.953899
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A complete printed Bangla OCR system

  1998cited by this paper
• Skew Angle Detection of Digitized Indian Script Documents

  1997cited by this paper
• An OCR system to read two Indian language scripts: Bangla and Devnagari (Hindi)

  1997cited by this paper
• A Survey of Methods and Strategies in Character Segmentation

  1996cited by this paper
• Fuzzy Sets and Fuzzy Decision-Making

  1995cited by this paper
• Segmentation of touching characters in printed document recognition

  1993influential reference
• The Document Spectrum for Page Layout Analysis

  1993cited by this paper
• On the segmentation of touching characters

  1993cited by this paper
• Cut classification for segmentation

  1993cited by this paper
• Skew Correction of Document Images Using Interline Cross-Correlation

  1993cited by this paper
• Omnidocument technologies

  1992cited by this paper
• A shape analysis model with applications to a character recognition system

  1992cited by this paper
• Segmentation methods for character recognition: from segmentation to document structure analysis

  1992cited by this paper
• Major components of a complete text reading system

  1992influential reference
• A review of segmentation and contextual analysis techniques for text recognition

  1990cited by this paper
• A factor spaces approach to knowledge representation

  1990cited by this paper
• Multifactorial functions in fuzzy sets theory

  1990cited by this paper
• On the Recognition of Printed Characters of Any Font and Size

  1987cited by this paper
• A method of detecting the orientation of aligned components

  1986cited by this paper
• Compilers: Principles, Techniques, and Tools

  1986cited by this paper
• Character readers and pattern recognition

  1968cited by this paper

• WORD LEVEL TEXT RECOGNITION FOR OVERLAPPING CHARACTERS USING BIDIRECTIONAL TEMPORAL CONVOLUTIONAL NETWORK AND WAVELET TRANSFORM

  2025cites this paper
• Transformer-Based Bidirectional Attention Network for Segmentation-Free Word-Level Text Recognition with Overlapping Characters

  2025cites this paper
• Precise Segmentation and Recognition of Multilingual Script in Government Document Images

  2025cites this paper
• Enhancing Handwritten Telugu Text Detection: An Application of ResNet Models

  2025cites this paper
• Devanagari Character Recognition: A Comprehensive Literature Review

  2025cites this paper
• Computationally efficient ResNet based Telugu handwritten text detection

  2024cites this paper
• Computationally efficient handwritten Telugu text recognition

  2024cites this paper
• Comparative analysis, classification, and segmentation of the handwritten Gujarati conjuncts depending on the structural properties of the constituent characters

  2023cites this paper
• Data extraction from scanned invoice documents in multiple languages

  2023cites this paper
• Hyper Parameter Optimization of CRNN for Printed Devanagari Script Recognition using Taguchi's Method

  2023cites this paper
• Character Segmentation of Devnagari Script in Printed Document Images using Projection Profiles

  2023cites this paper
• Takri touching text segmentation using statistical approach

  2023cites this paper
• Combining Multiple Feature Extraction and Classification Methods to Study Performance of Handwritten Sanskrit Character Recognition

  2023cites this paper
• IDENTIFICATION AND SEGMENTATION OF TOUCHING BRAHMI CHARACTERS FROM DEGRADED DIGITAL ESTAMPAGE IMAGES USING ENSEMBLE CLASSIFIER

  2021influential citation
• Deep Wavelet Neural Network based Robust Text Recognition for Overlapping Characters

  2021cites this paper
• A Hybrid Character Recognition Approach Using Fuzzy Logic and Stroke Bayesian Program Learning With Naïve Bayes in Industrial Environments

  2020cites this paper
• Optimal Character Segmentation for Touching Characters in Tamil Language Palm Leaf Manuscripts using Horver Method

  2020cites this paper
• A Shape-Based Character Segmentation Using Artificial Neural Network for Mizo Script

  2020cites this paper
• Advanced Applications on Bilingual Document Analysis and Processing Systems

  2020cites this paper
• A complete character recognition and transliteration technique for Devanagari script

  2020cites this paper
• Treatment Effect Analysis on Shallow Buried Bias Slope Section of Tunnel Based on Fuzzy Comprehensive Evaluation

  2020cites this paper
• A Hybrid Hindi Printed Document Classification System Using SVM and Fuzzy: An Advancement

  2019cites this paper
• Robust Character Segmentation and Recognition Schemes for Multilingual Indian Document Images

  2019cites this paper
• Feature Extraction and Classification Techniques of MODI Script Character Recognition

  2019influential citation
• Handwritten multilingual word segmentation using polygonal approximation of digital curves for Indian languages

  2019cites this paper
• Deep Learning Based Real Time Devanagari Character Recognition

  2019cites this paper
• Segmentation of Frequently Used Handwritten Gujarati Conjunctive Alphabet

  2019cites this paper
• Collaborative Deep Neural Network for Printed Text Recognition of Indian Languages

  2019influential citation
• Improved Zoning and Cropping Techniques Facilitating Segmentation

  2018cites this paper
• An Efficient Character Segmentation Approach for Handwritten Hindi Text

  2018cites this paper
• Gurmukhi Word Recognition Using Deep Neural Networks

  2018cites this paper
• A Novel Handwritten Gurmukhi Character Recognition System Based on Deep Neural Networks

  2018cites this paper
• Zone-Wise Segmentation and Lexicon-Driven Recognition for Printed Myanmar Characters

  2018cites this paper
• Soft Clustering for Segmenting Touching Characters in Printed Scripts

  2018cites this paper
• Multilingual Character Segmentation and Recognition Schemes for Indian Document Images

  2018influential citation
• Visualizing and Understanding Customized Convolutional Neural Network for Recognition of Handwritten Marathi Numerals

  2018cites this paper
• Optical Character Recognition for Hindi

  2018cites this paper
• Assamese Character Recognition using Texture and Diagonal Orientation features with Artificial Neural Network

  2018cites this paper
• Discrete Cosine Transform-Based Feature Selection for Marathi Numeral Recognition System

  2018cites this paper
• Connected Component Analysis Based Two Zone Approach for Bangla Character Segmentation

  2018cites this paper
• Hindi Text Document Classification System Using SVM and Fuzzy

  2018cites this paper
• A fuzzy approach to segment touching characters

  2017cites this paper
• Efficient segmentation of printed tamil script into characters using projection and structure

  2017cites this paper
• Printed text recognition using BLSTM and MDLSTM for Indian languages

  2017cites this paper
• Writer Identification From Offline Isolated Handwritten Gurumukhi Characters Kanu

  2017cites this paper
• Review of Text Extraction Algorithms for Scene-text and Document Images

  2017cites this paper
• Improving Classical OCRs for Brahmic Scripts Using Script Grammar Learning

  2017influential citation
• A new method for segmentation of pre-detected Devanagari words from the scene images: Pihu method

  2017cites this paper
• Handwritten Numeral Identification System Using Pixel Level Distribution Features

  2017cites this paper
• Segmentation based Optical Character Recognition for Handwritten Marathi characters

  2017cites this paper
• Conversion and Recognition of Handwritten Devnagari Character String into Printed Character String Using KNN

  2017cites this paper
• A Novel Shape-Based Character Segmentation Method for Devanagari Script

  2017cites this paper
• Marathi Numeral Identification System in Devanagari Script Using 1D Discrete Cosine Transform

  2017cites this paper
• Automatic segmentation of content and noncontent based handwritten Marathi text document

  2016cites this paper
• Preparation of a Dataset and Issues Related with Recognition of Optical Character in Assamese Script

  2016cites this paper
• Machine Recognition Script : Character and Word Level Analysis

  2016cites this paper
• Chinese/English mixed Character Segmentation as Semantic Segmentation

  2016cites this paper
• A Novel Approach Towards Devanagari Transliteraton Using Statistical and Structural Feature Extraction

  2016cites this paper
• A fuzzy approach for segmentation of touching characters

  2016cites this paper
• Segmentation of Unconstrained Handwritten Hindi Words Using Polygonal Approximation

  2016cites this paper
• A Comparative Analysis of Particle Swarm Optimization and Support Vector Machines for Devnagri Character Recognition: An Android Application☆

  2016cites this paper
• An efficient way for segmentation of Bangla characters in printed document using curved scanning

  2016cites this paper
• A study for handwritten Devanagari word recognition

  2016cites this paper
• Marathi numeral recognition using statistical distribution features

  2015cites this paper
• Performance evaluation of classification techniques for Devanagari script

  2015cites this paper
• Handwritten Devanagari Script Segmentation: A non-linear Fuzzy Approach

  2015cites this paper
• Character Segmentation of Hindi Unconstrained Handwritten Words

  2015cites this paper
• Segmentation of touching modifiers and consonants in middle region of handwritten Hindi text

  2015cites this paper
• Comparative analysis of zoning based methods for Gujarati handwritten numeral recognition

  2015cites this paper
• Zernike Moment Feature Extraction for Handwritten Devanagari (Marathi) Compound Character Recognition

  2014cites this paper
• A Research Proposal on Recognition of Degraded Devanagari Text Submitted to LOVELY PROFESSIONAL UNIVERSITY in partial fulfillment of the requirement for the award of degree of DOCTOR OF PHILOSOPHY (Ph.D.) IN (Computer Science and Engineering) Submitted by:

  2014influential citation
• Segmentation of Touching Telugu Characters under Noisy Environment

  2014cites this paper
• Online Handwritten Devnagari Word Recognition using HMM based Technique

  2014cites this paper
• Handwritten Devnagri Script Recognition: A Review

  2014cites this paper
• Feature combination for binary pattern classification

  2014cites this paper
• Character Recognition of Gujarati and Devanagari Script : A Review

  2014cites this paper
• Methods and strategies on off-line cursive touched characters segmentation: a directional review

  2014cites this paper
• 7. Development of OHWR System for Bangla

  2014cites this paper
• IMPROVEMENT OF TELUGU OCR BY SEGMENTATION OF TOUCHING CHARACTERS

  2014cites this paper
• Challenging Issues in Devanagari Script Recognition

  2014cites this paper
• WORD RECOGNITION IN INDIC SCRIPTS

  2014cites this paper
• Offline Handwritten Sanskrit Character Recognition Using Hough Transform and Euclidean Distance

  2014cites this paper
• Survey on Character Recognition using OCR Techniques

  2014cites this paper
• A survey on optical character recognition for Bangla and Devanagari scripts

  2013cites this paper
• A SURVEY OF TELUGU OCR SYSTEM

  2013cites this paper
• Optical Character Recognition for Hindi Language Using a Neural-network Approach

  2013cites this paper
• Devanagari Text Recognition: A Transcription Based Formulation

  2013cites this paper
• A Survey on Touching Character Segmentation

  2013influential citation
• A Research Survey on Sanskrit Offline Handwritten Character Recognition

  2013cites this paper
• Signature matching with automated cheque system

  2013cites this paper
• Zernike moment feature extraction for handwritten Devanagari compound character recognition

  2013cites this paper
• Segmentation of Touching Conjunct Consonants in Telugu using Minimum Area Bounding Boxes

  2013cites this paper
• Efficient Touching Text Line Segmentation in Tamil Script Using Horizontal Projection

  2013cites this paper
• A Research Survey of Devnagari Handwritten Word Recognition

  2013cites this paper
• Handwritten Segmentation in Bangla Script: A Review of Offline Techniques

  2013cites this paper
• BengalI Optical Character Recognition using self organizing map

  2012cites this paper
• Segmentation of Touching Hand written Telugu Characters by using Drop Fall Algorithm

  2012cites this paper
• Segmentation of Touching Characters in Handwritten Devanagari Script

  2012cites this paper
• A brief review and survey of feature extraction methods for Devnagari OCR

  2012cites this paper
• An approach to divide pre-detected Devanagari words from the scene images into characters

  2012cites this paper