ONLINE HANDWRITTEN GURMUKHI SCRIPT RECOGNITION AND ITS CHALLENGES R. K. SHARMA THAPAR UNIVERSITY, PATIALA.

Slides:



Advertisements
Similar presentations
Patient information extraction in digitized X-ray imagery Hsien-Huang P. Wu Department of Electrical Engineering, National Yunlin University of Science.
Advertisements

Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Handwritten Mathematical Symbol Recognition for Computer Algebra Applications Xiaofang Xie, Stephen M. Watt Dept. of Computer Science, University of Western.
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Word Spotting DTW.
ONLINE ARABIC HANDWRITING RECOGNITION By George Kour Supervised by Dr. Raid Saabne.
1 Probabilistic Artificial Neural Network For Recognizing the Arabic Hand Written Characters Khalaf khatatneh, Ibrahiem El Emary,and Basem Al- Rifai Journal.
Image Indexing and Retrieval using Moment Invariants Imran Ahmad School of Computer Science University of Windsor – Canada.
GMM-Based Multimodal Biometric Verification Yannis Stylianou Yannis Pantazis Felipe Calderero Pedro Larroy François Severin Sascha Schimke Rolando Bonal.
Multiple Criteria for Evaluating Land Cover Classification Algorithms Summary of a paper by R.S. DeFries and Jonathan Cheung-Wai Chan April, 2000 Remote.
Chapter 1: Introduction to Pattern Recognition
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John.
Pattern Recognition Topic 1: Principle Component Analysis Shapiro chap
Multiple Agents for Pattern Recognition Louis Vuurpijl
Data Mining on NIJ data Sangjik Lee. Unstructured Data Mining Text Keyword Extraction Structured Data Base Data Mining Image Feature Extraction Structured.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
Handwritten Thai Character Recognition Using Fourier Descriptors and Robust C-Prototype Olarik Surinta Supot Nitsuwat.
Statistical Learning: Pattern Classification, Prediction, and Control Peter Bartlett August 2002, UC Berkeley CIS.
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John Wiley.
(Off-Line) Cursive Word Recognition Tal Steinherz Tel-Aviv University.
Multiclass object recognition
Case Studies Dr Lee Nung Kion Faculty of Cognitive Sciences and Human Development UNIVERSITI MALAYSIA SARAWAK.
Handwriting Copybook Style Analysis Of Pseudo-Online Data Student and Faculty Research Day Mary L. Manfredi, Dr. Sung-Hyuk Cha, Dr. Charles Tappert, Dr.
: Chapter 10: Image Recognition 1 Montri Karnjanadecha ac.th/~montri Image Processing.
Pattern Recognition Vidya Manian Dept. of Electrical and Computer Engineering University of Puerto Rico INEL 5046, Spring 2007
Recognizing Deformable Shapes Salvador Ruiz Correa Ph.D. Thesis, Electrical Engineering.
Oriented Local Binary Patterns for Offline Writer Identification
Artificial Neural Nets and AI Connectionism Sub symbolic reasoning.
Loop Investigation for Cursive Handwriting Processing and Recognition By Tal Steinherz Advanced Seminar (Spring 05)
S EGMENTATION FOR H ANDWRITTEN D OCUMENTS Omar Alaql Fab. 20, 2014.
Compiled By: Raj G Tiwari.  A pattern is an object, process or event that can be given a name.  A pattern class (or category) is a set of patterns sharing.
COMPARISON OF IMAGE ANALYSIS FOR THAI HANDWRITTEN CHARACTER RECOGNITION Olarik Surinta, chatklaw Jareanpon Department of Management Information System.
Image Classification 영상분류
22CS 338: Graphical User Interfaces. Dario Salvucci, Drexel University. Lecture 10: Advanced Input.
Online Kinect Handwritten Digit Recognition Based on Dynamic Time Warping and Support Vector Machine Journal of Information & Computational Science, 2015.
Handwritten Recognition with Neural Network Chatklaw Jareanpon, Olarik Surinta Mahasarakham University.
1 Pattern Recognition Pattern recognition is: 1. A research area in which patterns in data are found, recognized, discovered, …whatever. 2. A catchall.
Chapter 4: Pattern Recognition. Classification is a process that assigns a label to an object according to some representation of the object’s properties.
PROJECT PROPOSAL DIGITAL IMAGE PROCESSING TITLE:- Automatic Machine Written Document Reader Project Partners:- Manohar Kuse(Y08UC073) Sunil Prasad Jaiswal(Y08UC124)
Comparison of Handwritings Miroslava Božeková Thesis supervisor: Doc. RNDr. Milan Ftáčnik, CSc.
COMP322/S2000/L171 Robot Vision System Major Phases in Robot Vision Systems: A. Data (image) acquisition –Illumination, i.e. lighting consideration –Lenses,
Reporter: 資訊所 P Yung-Chih Cheng ( 鄭詠之 ).  Introduction  Data Collection  System Architecture  Feature Extraction  Recognition Methods  Results.
Signature Verification
Marwan Al-Namari 1 Digital Representations. Bits and Bytes Devices can only be in one of two states 0 or 1, yes or no, on or off, … Bit: a unit of data.
COMP135/COMP535 Digital Multimedia, 2nd edition Nigel Chapman & Jenny Chapman Chapter 2 Lecture 2 – Digital Representations.
Scanned Documents INST 734 Module 10 Doug Oard. Agenda Document image retrieval  Representation Retrieval Thanks for David Doermann for most of these.
Pattern Recognition NTUEE 高奕豪 2005/4/14. Outline Introduction Definition, Examples, Related Fields, System, and Design Approaches Bayesian, Hidden Markov.
Handwriting Recognition
Pattern Recognition. What is Pattern Recognition? Pattern recognition is a sub-topic of machine learning. PR is the science that concerns the description.
Arabic Handwriting Recognition Thomas Taylor. Roadmap  Introduction to Handwriting Recognition  Introduction to Arabic Language  Challenges of Recognition.
1 A Statistical Matching Method in Wavelet Domain for Handwritten Character Recognition Presented by Te-Wei Chiang July, 2005.
 Handwritten character recognition is a frontier area for research for the past few decades  OCR-process of translation of images of handwritten shorthand.
By: Shane Serafin.  What is handwriting recognition  History  Different types  Uses  Advantages  Disadvantages  Conclusion  Questions  Sources.
Face Detection 蔡宇軒.
Machine Learning Artificial Neural Networks MPλ ∀ Stergiou Theodoros 1.
Optical Character Recognition
Signature Recognition Using Neural Networks and Rule Based Decision Systems CSC 8810 Computational Intelligence Instructor Dr. Yanqing Zhang Presented.
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Online Signature Verification
Introduction Characteristics Advantages Limitations
Supervised Time Series Pattern Discovery through Local Importance
Image Segmentation Classify pixels into groups having similar characteristics.
Pattern Recognition Sergios Theodoridis Konstantinos Koutroumbas
Pearson Lanka (Pvt) Ltd.
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John.
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John.
Recognizing Deformable Shapes
Automatic Handwriting Generation
Presentation transcript:

ONLINE HANDWRITTEN GURMUKHI SCRIPT RECOGNITION AND ITS CHALLENGES R. K. SHARMA THAPAR UNIVERSITY, PATIALA

Handwriting Recognition System The technique by which a computer system can recognize characters and other symbols written by hand in natural handwriting is called handwriting recognition (HWR) system.

Types of HWR systems HWR Off-line HWR  Handwritten Document is scanned and then recognized by the machine, is called off-line handwriting recognition.  Handwritten Documents are recognized while being written, it is called on-line handwriting recognition. On-line HWR

COMPLEXITY Increasing

Handwriting Recognition System  Writer dependent  Writer independent  Closed-vocabulary  Open-vocabulary

A general recognition procedure for On-line HWR Data Collection & Preprocessing Features Extraction & Segmentation Recognition Methods & Post-processing

Data Collection Input Pen Writing Store pen movements Text/Other file created Text/Other file to be converted to a suitable format

Need of an application for selected hardware device Pre-developed applications do not support the features for user requirements, i.e., storing all pixels information for written text, deletion and addition of strokes w.r.t. user requirements, scaling the written text etc. Own GUI for user requirements needs to be developed.

Size Normalization Centering of text Interpolating missing points Smoothing of Text Slant Correction Resampling of points Preprocessing

Feature Extraction A feature extractor designed by Govindaraju converts chain code image into feature vectors and then used in recognition phase. Hu et al. worked with point oriented features like stroke tangents for handwriting recognition. Hu et al. also proposed a method where high-level features were extracted and then combined with local-features at each sample point. These introduced features were capable of covering large input pattern and had invariance properties. Rocha designed feature extractor that reduced dimension of the problem and provided structural description of a character shape that consists of specification of its features and their special inter-ralations.

Feature extractor designed by S.W. Lee extracted four directional feature vectors with kirsch masks and one global feature vector linearly compressed from normalized input image. Kirsch masks were also used by Chaos in recognition of handwritten Numerals. Blumenstein introduced a feature extraction technique for the recognition of segmented handwritten characters. A hybrid feature extraction method proposed by PiFuei that was capable of providing an effective feature set of full dimension for the multiclass cases.

Feature Categories Features Low-Level or Local (directions, positions, slope, area, slant etc.) High-Level or Global (loops, crossings, Headline, straight line, dots etc.)

back Devices based features  Time taken by the pen device for capturing a stroke is one of the features as each stroke has its own complexity. If suitable information is collected about each stroke time span, it may help in recognition process.  Density of points in a stroke is device dependent.  Directions of pen movement in a stroke might be helpful in recognition.  Stroke area covered.  Pressure of the pen movements.

Features’ Properties  Features giving better results may vary from one script to another script.  A method that gives good results for a script may not do so for other scripts.  There is no standard method for computing features of a language.  Features should vary to a reasonable extent.  Features must be available from different users handwriting.  Features should be measurable through algorithms.  Features are selected in such a way that they represent the handwriting well and emphasize the inter-class differences and intra-class similarities.

CategoryMethodResearchers StatisticalHidden Markov Model, Support Vector Machine Amlan kundu and Parambir Bahl (1988); Beigi (1994); Bellegarda (1994); Beim (2001); Connell and Jain (2002); Rigoll (1996); Subrahmonia (1996) Neural NetworkTDNNGuyon (1992); Schomaker (1993); Morasso (1995); Yeager (1998) Syntactical and Structural Decision TreeKerrick and Bovik(1988); Chan and Yeung(1999); Jung and Kim(2000) Elastic MatchingDynamic ProgrammingPalvidis(1997); Wakahara and Odaka(1997); Webster and Nakagawa(1998) Recognition methods

CategoryAdvantagesDisadvantages StatisticalModels temporal relationship well. Requires very large amount of training data Neural NetworkClassification time is fast.Does not model temporal relationship well. Syntactical and StructuralLess training data and robust for WI system. Feature choice is manual and highly script dependent. Elastic MatchingPowerful high level features. Not good for the system, where large variations exists in handwriting. Advantages and disadvantages of Recognition methods

Post Processing  Other important Aspect  Language rules An Efficient Post Processing Algorithm for Online Handwritten Gurmukhi Character Recognition using Set Theory”, International Journal of Pattern Recognition and Artificial Intelligence, 27(4), (1-17), 2013 by Ravinder Kumar and R.K. Sharma  Language Models

Challenges Reverse Handwriting Zone wise stroke predictions Confusing Strokes Prediction of half Akshras for example: Pairi ‘ ਹ ’, Pairi ‘ ਵ ’ New Classes in Handwritten Words New Features, Selection from existing features New Classifiers / Hybrid Classifiers

THANK YOU ALL !!!!!