Natural Language Inspired Approach for Handwritten Text Line Detection in Legacy Documents

Size: px
Start display at page:

Download "Natural Language Inspired Approach for Handwritten Text Line Detection in Legacy Documents"

Transcription

1 Natural Language Inspired Approach for Handwritten Text Line Detection in Legacy Documents Vicente Bosch Alejandro Hector Toselli Enrique Vidal Pattern Recognition and Human Language Technologies group Universidad Politécnica de Valencia

2 Presentation Outline Introduction 1 Statistical Framework 2 Modelling 4 System Architecture 7 Experimental Setup and Results 12 Conclusions & Future Work 17 1

3 Introduction Document layout analysis (DLA) is an important task for any Document Retrieval Information System. Text line detection (TLD) is a DLA task that yields the physical locations. of text lines given an input page image; required for systems that require text line images as input. TLD in handwritten legacy documents is a difficult task due to: Handwritten text issues: variable inter-line spacing, overlapping and touching strokes of adjacent lines, etc Legacy document issues: smears, background variations, uneven illumination, humidity spots and bleed-through marks Current state of the art-methods are mostly based on heuristic approaches and require parameter tunning. We present a formal approach for text line detection in handwritten text based in machine-learning techniques. 2

4 Statistical Framework (1) We assume that the input image contains one or more paragraphs of single-column parallel text with no images or diagram figures which we mathematically represent as a sequence of observations o = o 1, o 2,..., o m. TLD problem can be formulated as the problem of finding the most likely text lines sequence, ĥ = h 1, h 2,..., h n, for a given input sequence o; which we can decompose using Bayes rule: ĥ = arg max h P (h o) = arg max h P (o h) P (h) 3

5 Statistical Framework (2) As the actual physical location (and not just the best label sequence) is required we rewrite the formula to obtain this: ĥ = arg max h P (o, b h) P (h) Which we can approximate by the dominant term, max b P (o, b h): (ˆb, b ĥ) arg max b,h P (h) P (o, b h) 4

6 Modelling (1) 5

7 Modelling (2) Two levels of modelling: Morphological: That model the page vertical regions, usually approximated by HMMs Syntactical: a Language Model (LM) that restrics how those vertical regions are composed to form an actual page, modelled as a stochastic finite state grammar (SFSG) Vertical region types: Blank Space (BS), Normal Line (NL), Inter Line (IL) and Non-Text Line LM allows us to force restricctions: NL+IL, NT+IL, BS, etc. Both modelling levels represented by finite-state automaton, can be integrated into a single global model on which our problem can be easily solved. 6

8 Modelling (3) HMM Sample: SFSG Sample: 7

9 System Overview Page Images Page layout corpus Preprocessing Cleaned Page Images Feature Extraction HMM Training LM Training Training Decoding Feature Vectors Off-line line HMMs LM Model Type label and Region position coordinates 8

10 Natural Language Inspired Approach for Handwritten Text Line Detection in Legacy Documents Valencia April 18, 2012 Preprocessing

11 Feature Extraction b0 b1 b2 b3 b4 b5 b6 b7 bf-2 bf-1 bf X1 XL h1 h2 h3 h4 h5 h6 h7 hf-2 hf-1 hf D 10

12 Feauture Extraction

13 Feauture Extraction 12

14 Corpus Description (1) Experiments are carried out with a corpus compiled from a XIX century Spanish manuscript identified as Cristo-Salvador (CS). Kindly provided by the Biblioteca Valenciana Digital (BiVaLDi). Small document composed of 53 colour images of text pages, scanned at 300 dpi and written by a single writer. We employ the so-called book partition: Training set is formed by the first 33 page images. Test set contains the 20 remaining pages. 13

15 Corpus Description (2) 14

16 Corpus Description (3) Number of: Training Test Total Pages Normal-text lines (NL) Blank Lines (BL) Non-text Lines (NT) Inter Lines (IL) Each page was annotated with a succession of reference labels (NL, NT, BL and IL). Vertical regions were delimited by executing standard methods for text line detection based on vertical projection profiles and manually verified/corrected. Labelling of the different regions was performed manually by an operator. 15

17 Evaluation Measures Quality of the text line detection was measured using the line error rate (LER). LER is performed by comparing the sequences of automatically obtained region labels with the corresponding reference label sequences. The LER is computed in the same way as the well known WER. 16

18 Experiments and Results Training and decoding parameters were empirically tuned. Three model languages where tested: Prior, Conditional and Line-number constrained LM LER(%) Prior 0.86 Conditional 0.70 LN-Constrained

19 Conclusions & Future Work We have presented a new approach for text line detection by using a statistical framework similar to that already employed in many topics of NLP. It avoids the traditional heuristics approaches usually adopted for this task. The proposed approach not only has up to par detection accuracy,with current state of the art solutions, but also yields baselines of better quality (visually closer to the actual line). Extend this approach not only to detect, but also to classify line-region types in order to determine for example titles, short lines, beginning and and end of paragraphs, etc. It is envisioned that the proposed stochastic framework serves as a cornerstone to implementing interactive approaches to line detection similar to those used for handwritten text transcription used in Multimodal interactive transcription systems. 18

20 Questions 19

Natural Language Inspired Approach for Handwritten Text Line Detection in Legacy Documents

Natural Language Inspired Approach for Handwritten Text Line Detection in Legacy Documents Natural Language Inspired Approach for Handwritten Text Line Detection in Legacy Documents Vicente Bosch Campos vbosch@iti.upv.es Alejandro Héctor Toselli ahector@iti.upv.es Enrique Vidal evidal@iti.upv.es

More information

Interactive Handwritten Text Recognition and Indexing of Historical Documents: the transcriptorum Project

Interactive Handwritten Text Recognition and Indexing of Historical Documents: the transcriptorum Project Interactive Handwritten Text Recognition and ing of Historical Documents: the transcriptorum Project Alejandro H. Toselli ahector@prhlt.upv.es Pattern Recognition and Human Language Technology Reseach

More information

Contents. Resumen. List of Acronyms. List of Mathematical Symbols. List of Figures. List of Tables. I Introduction 1

Contents. Resumen. List of Acronyms. List of Mathematical Symbols. List of Figures. List of Tables. I Introduction 1 Contents Agraïments Resum Resumen Abstract List of Acronyms List of Mathematical Symbols List of Figures List of Tables VII IX XI XIII XVIII XIX XXII XXIV I Introduction 1 1 Introduction 3 1.1 Motivation...

More information

OnLine Handwriting Recognition

OnLine Handwriting Recognition OnLine Handwriting Recognition (Master Course of HTR) Alejandro H. Toselli Departamento de Sistemas Informáticos y Computación Universidad Politécnica de Valencia February 26, 2008 A.H. Toselli (ITI -

More information

Handwritten Text Recognition

Handwritten Text Recognition Handwritten Text Recognition M.J. Castro-Bleda, S. España-Boquera, F. Zamora-Martínez Universidad Politécnica de Valencia Spain Avignon, 9 December 2010 Text recognition () Avignon Avignon, 9 December

More information

Handwritten Text Recognition

Handwritten Text Recognition Handwritten Text Recognition M.J. Castro-Bleda, Joan Pasto Universidad Politécnica de Valencia Spain Zaragoza, March 2012 Text recognition () TRABHCI Zaragoza, March 2012 1 / 1 The problem: Handwriting

More information

Viterbi Based Alignment between Text Images and their Transcripts

Viterbi Based Alignment between Text Images and their Transcripts Viteri Based Alignment etween Text Images and their Transcripts Alejandro H. Toselli, Verónica Romero and Enrique Vidal Institut Tecnològic d Informàtica Universitat Politècnica de València Camí de Vera

More information

Workshop: Automatisierte Handschriftenerkennung

Workshop: Automatisierte Handschriftenerkennung Workshop: Automatisierte Handschriftenerkennung Joan Andreu Sánchez Pattern Recognition and Human Language Research group (Technical University of Valencia) Günter Mühlberger, Sebastian Colutto, Philip

More information

TRAINING ON-LINE HANDWRITING RECOGNIZERS USING SYNTHETICALLY GENERATED TEXT

TRAINING ON-LINE HANDWRITING RECOGNIZERS USING SYNTHETICALLY GENERATED TEXT TRAINING ON-LINE HANDWRITING RECOGNIZERS USING SYNTHETICALLY GENERATED TEXT Daniel Martín-Albo, Réjean Plamondon * and Enrique Vidal PRHLT Research Center Universitat Politècnica de València * Laboratoire

More information

Handwritten word verification by SVM-based hypotheses re-scoring and multiple thresholds rejection

Handwritten word verification by SVM-based hypotheses re-scoring and multiple thresholds rejection Author manuscript, published in "International Conference on Frontiers in Handwriting Recognition (2010)" Handwritten word verification by SVM-based hypotheses re-scoring and multiple thresholds rejection

More information

Document downloaded from: This paper must be cited as:

Document downloaded from:   This paper must be cited as: Document downloaded from: http://hdl.handle.net/1/0 This paper must be cited as: The final publication is available at https://doi.org/.0/s00-01-- Copyright Springer-Verlag Additional Information Neural

More information

A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling For Handwriting Recognition

A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling For Handwriting Recognition A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling For Handwriting Recognition Théodore Bluche, Hermann Ney, Christopher Kermorvant SLSP 14, Grenoble October

More information

Stochastic Segment Modeling for Offline Handwriting Recognition

Stochastic Segment Modeling for Offline Handwriting Recognition 2009 10th nternational Conference on Document Analysis and Recognition tochastic egment Modeling for Offline Handwriting Recognition Prem Natarajan, Krishna ubramanian, Anurag Bhardwaj, Rohit Prasad BBN

More information

Compiler Construction

Compiler Construction Compiler Construction Lecture 2: Lexical Analysis I (Introduction) Thomas Noll Lehrstuhl für Informatik 2 (Software Modeling and Verification) noll@cs.rwth-aachen.de http://moves.rwth-aachen.de/teaching/ss-14/cc14/

More information

Text lines and snippets extraction for 19th century handwriting documents layout analysis

Text lines and snippets extraction for 19th century handwriting documents layout analysis Author manuscript, published in "2009 10th International Conference on Document Analysis and Recognition, Barcelona : Spain (2009)" Text lines and snippets extraction for 19th century handwriting documents

More information

Keyword Spotting in Document Images through Word Shape Coding

Keyword Spotting in Document Images through Word Shape Coding 2009 10th International Conference on Document Analysis and Recognition Keyword Spotting in Document Images through Word Shape Coding Shuyong Bai, Linlin Li and Chew Lim Tan School of Computing, National

More information

Segmentation free Bangla OCR using HMM: Training and Recognition

Segmentation free Bangla OCR using HMM: Training and Recognition Segmentation free Bangla OCR using HMM: Training and Recognition Md. Abul Hasnat, S.M. Murtoza Habib, Mumit Khan BRAC University, Bangladesh mhasnat@gmail.com, murtoza@gmail.com, mumit@bracuniversity.ac.bd

More information

Mono-font Cursive Arabic Text Recognition Using Speech Recognition System

Mono-font Cursive Arabic Text Recognition Using Speech Recognition System Mono-font Cursive Arabic Text Recognition Using Speech Recognition System M.S. Khorsheed Computer & Electronics Research Institute, King AbdulAziz City for Science and Technology (KACST) PO Box 6086, Riyadh

More information

CHAPTER 3 SYSTEM DESCRIPTION

CHAPTER 3 SYSTEM DESCRIPTION 39 CHAPTER 3 SYSTEM DESCRIPTION This chapter exhibits the overview of the system with specifications. It also furnishes the purpose of using the untapped descriptive statistics measures and detailed description

More information

Revealing the Modern History of Japanese Philosophy Using Digitization, Natural Language Processing, and Visualization

Revealing the Modern History of Japanese Philosophy Using Digitization, Natural Language Processing, and Visualization Revealing the Modern History of Japanese Philosophy Using Digitization, Natural Language Katsuya Masuda *, Makoto Tanji **, and Hideki Mima *** Abstract This study proposes a framework to access to the

More information

CHAPTER 8 COMPOUND CHARACTER RECOGNITION USING VARIOUS MODELS

CHAPTER 8 COMPOUND CHARACTER RECOGNITION USING VARIOUS MODELS CHAPTER 8 COMPOUND CHARACTER RECOGNITION USING VARIOUS MODELS 8.1 Introduction The recognition systems developed so far were for simple characters comprising of consonants and vowels. But there is one

More information

An Efficient Feature Extraction Algorithm for the Recognition of Handwritten Arabic Digits

An Efficient Feature Extraction Algorithm for the Recognition of Handwritten Arabic Digits An Efficient Feature Extraction Algorithm for the Recognition of Handwritten Arabic Digits Ahmad T. AlTaani Abstract In this paper, an efficient structural approach for recognizing online handwritten digits

More information

A Hidden Markov Model for Alphabet Soup Word Recognition

A Hidden Markov Model for Alphabet Soup Word Recognition A Hidden Markov Model for Alphabet Soup Word Recognition Shaolei Feng 1 Nicholas R. Howe 2 R. Manmatha 1 1 University of Massachusetts, Amherst 2 Smith College Motivation: Inaccessible Treasures Historical

More information

Ground-Truth Production in the transcriptorium Project

Ground-Truth Production in the transcriptorium Project 2014 11th IAPR International Workshop on Document Analysis Systems Ground-Truth Production in the transcriptorium Project B. Gatos and G. Louloudis Inst. of Inf. and Telecommunications National Centre

More information

Dynamic Time Warping

Dynamic Time Warping Centre for Vision Speech & Signal Processing University of Surrey, Guildford GU2 7XH. Dynamic Time Warping Dr Philip Jackson Acoustic features Distance measures Pattern matching Distortion penalties DTW

More information

Leveraging Set Relations in Exact Set Similarity Join

Leveraging Set Relations in Exact Set Similarity Join Leveraging Set Relations in Exact Set Similarity Join Xubo Wang, Lu Qin, Xuemin Lin, Ying Zhang, and Lijun Chang University of New South Wales, Australia University of Technology Sydney, Australia {xwang,lxue,ljchang}@cse.unsw.edu.au,

More information

A Multimodal Framework for the Recognition of Ancient Tamil Handwritten Characters in Palm Manuscript Using Boolean Bitmap Pattern of Image Zoning

A Multimodal Framework for the Recognition of Ancient Tamil Handwritten Characters in Palm Manuscript Using Boolean Bitmap Pattern of Image Zoning A Multimodal Framework for the Recognition of Ancient Tamil Handwritten s in Palm Manuscript Using Boolean Bitmap Pattern of Zoning E.K.Vellingiriraj, Asst. Professor and Dr.P.Balasubramanie, Professor

More information

Confidence Measures: how much we can trust our speech recognizers

Confidence Measures: how much we can trust our speech recognizers Confidence Measures: how much we can trust our speech recognizers Prof. Hui Jiang Department of Computer Science York University, Toronto, Ontario, Canada Email: hj@cs.yorku.ca Outline Speech recognition

More information

Candidate Document Retrieval for Web-scale Text Reuse Detection

Candidate Document Retrieval for Web-scale Text Reuse Detection Candidate Document Retrieval for Web-scale Text Reuse Detection Matthias Hagen Benno Stein Bauhaus-Universität Weimar matthias.hagen@uni-weimar.de SPIRE 2011 Pisa, Italy October 19, 2011 Matthias Hagen,

More information

Patent Terminlogy Analysis: Passage Retrieval Experiments for the Intellecutal Property Track at CLEF

Patent Terminlogy Analysis: Passage Retrieval Experiments for the Intellecutal Property Track at CLEF Patent Terminlogy Analysis: Passage Retrieval Experiments for the Intellecutal Property Track at CLEF Julia Jürgens, Sebastian Kastner, Christa Womser-Hacker, and Thomas Mandl University of Hildesheim,

More information

Binarization-free Text Line Extraction for Historical Manuscripts

Binarization-free Text Line Extraction for Historical Manuscripts Binarization-free Text Line Extraction for Historical Manuscripts Nikolaos Arvanitopoulos and Sabine Süsstrunk School of Computer and Communication Sciences, EPFL, Switzerland 1 Introduction Nowadays,

More information

A Modular System to Recognize Numerical Amounts on Brazilian Bank Cheques

A Modular System to Recognize Numerical Amounts on Brazilian Bank Cheques A Modular System to Recognize Numerical Amounts on Brazilian Bank Cheques L. S. Oliveira ½, R. Sabourin ½, F. Bortolozzi ½ and C. Y. Suen ½ PUCPR Pontifícia Universidade Católica do Paraná (PPGIA-LARDOC)

More information

Semi-Supervised Clustering with Partial Background Information

Semi-Supervised Clustering with Partial Background Information Semi-Supervised Clustering with Partial Background Information Jing Gao Pang-Ning Tan Haibin Cheng Abstract Incorporating background knowledge into unsupervised clustering algorithms has been the subject

More information

Topics for Today. The Last (i.e. Final) Class. Weakly Supervised Approaches. Weakly supervised learning algorithms (for NP coreference resolution)

Topics for Today. The Last (i.e. Final) Class. Weakly Supervised Approaches. Weakly supervised learning algorithms (for NP coreference resolution) Topics for Today The Last (i.e. Final) Class Weakly supervised learning algorithms (for NP coreference resolution) Co-training Self-training A look at the semester and related courses Submit the teaching

More information

Machine Learning in GATE

Machine Learning in GATE Machine Learning in GATE Angus Roberts, Horacio Saggion, Genevieve Gorrell Recap Previous two days looked at knowledge engineered IE This session looks at machine learned IE Supervised learning Effort

More information

Document Image Restoration Using Binary Morphological Filters. Jisheng Liang, Robert M. Haralick. Seattle, Washington Ihsin T.

Document Image Restoration Using Binary Morphological Filters. Jisheng Liang, Robert M. Haralick. Seattle, Washington Ihsin T. Document Image Restoration Using Binary Morphological Filters Jisheng Liang, Robert M. Haralick University of Washington, Department of Electrical Engineering Seattle, Washington 98195 Ihsin T. Phillips

More information

Overview of ImageCLEF Mauricio Villegas (on behalf of all organisers)

Overview of ImageCLEF Mauricio Villegas (on behalf of all organisers) Overview of ImageCLEF 2016 Mauricio Villegas (on behalf of all organisers) ImageCLEF history Started in 2003 with a photo retrieval task 4 participants submitting results In 2009 we had 6 tasks and 65

More information

Automatic Detection of Change in Address Blocks for Reply Forms Processing

Automatic Detection of Change in Address Blocks for Reply Forms Processing Automatic Detection of Change in Address Blocks for Reply Forms Processing K R Karthick, S Marshall and A J Gray Abstract In this paper, an automatic method to detect the presence of on-line erasures/scribbles/corrections/over-writing

More information

Final Exam 1, CS154. April 21, 2010

Final Exam 1, CS154. April 21, 2010 Final Exam 1, CS154 April 21, 2010 Exam rules. The exam is open book and open notes you can use any printed or handwritten material. However, no electronic devices are allowed. Anything with an on-off

More information

Compiler Construction

Compiler Construction Compiler Construction Thomas Noll Software Modeling and Verification Group RWTH Aachen University https://moves.rwth-aachen.de/teaching/ss-16/cc/ Conceptual Structure of a Compiler Source code x1 := y2

More information

DATA EMBEDDING IN TEXT FOR A COPIER SYSTEM

DATA EMBEDDING IN TEXT FOR A COPIER SYSTEM DATA EMBEDDING IN TEXT FOR A COPIER SYSTEM Anoop K. Bhattacharjya and Hakan Ancin Epson Palo Alto Laboratory 3145 Porter Drive, Suite 104 Palo Alto, CA 94304 e-mail: {anoop, ancin}@erd.epson.com Abstract

More information

SEMICCA: A NEW SEMI-SUPERVISED PROBABILISTIC CCA MODEL FOR KEYWORD SPOTTING

SEMICCA: A NEW SEMI-SUPERVISED PROBABILISTIC CCA MODEL FOR KEYWORD SPOTTING SEMICCA: A NEW SEMI-SUPERVISED PROBABILISTIC CCA MODEL FOR KEYWORD SPOTTING Giorgos Sfikas, Basilis Gatos Computational Intelligence Laboratory / IIT NCSR Demokritos 15310 Athens, Greece Christophoros

More information

Preface MOTIVATION ORGANIZATION OF THE BOOK. Section 1: Basic Concepts of Graph Theory

Preface MOTIVATION ORGANIZATION OF THE BOOK. Section 1: Basic Concepts of Graph Theory xv Preface MOTIVATION Graph Theory as a well-known topic in discrete mathematics, has become increasingly under interest within recent decades. This is principally due to its applicability in a wide range

More information

A Syntactic Methodology for Automatic Diagnosis by Analysis of Continuous Time Measurements Using Hierarchical Signal Representations

A Syntactic Methodology for Automatic Diagnosis by Analysis of Continuous Time Measurements Using Hierarchical Signal Representations IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS PART B: CYBERNETICS, VOL. 33, NO. 6, DECEMBER 2003 951 A Syntactic Methodology for Automatic Diagnosis by Analysis of Continuous Time Measurements Using

More information

Recognition of online captured, handwritten Tamil words on Android

Recognition of online captured, handwritten Tamil words on Android Recognition of online captured, handwritten Tamil words on Android A G Ramakrishnan and Bhargava Urala K Medical Intelligence and Language Engineering (MILE) Laboratory, Dept. of Electrical Engineering,

More information

Initial Results in Offline Arabic Handwriting Recognition Using Large-Scale Geometric Features. Ilya Zavorin, Eugene Borovikov, Mark Turner

Initial Results in Offline Arabic Handwriting Recognition Using Large-Scale Geometric Features. Ilya Zavorin, Eugene Borovikov, Mark Turner Initial Results in Offline Arabic Handwriting Recognition Using Large-Scale Geometric Features Ilya Zavorin, Eugene Borovikov, Mark Turner System Overview Based on large-scale features: robust to handwriting

More information

A Simple Text-line segmentation Method for Handwritten Documents

A Simple Text-line segmentation Method for Handwritten Documents A Simple Text-line segmentation Method for Handwritten Documents M.Ravi Kumar Assistant professor Shankaraghatta-577451 R. Pradeep Shankaraghatta-577451 Prasad Babu Shankaraghatta-5774514th B.S.Puneeth

More information

Stochastic Language Models for Style-Directed Layout Analysis of Document Images

Stochastic Language Models for Style-Directed Layout Analysis of Document Images IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 12, NO. 5, MAY 2003 583 Stochastic Language Models for Style-Directed Layout Analysis of Document Images Tapas Kanungo, Senior Member, IEEE, and Song Mao, Member,

More information

Automated Extraction of Event Details from Text Snippets

Automated Extraction of Event Details from Text Snippets Automated Extraction of Event Details from Text Snippets Kavi Goel, Pei-Chin Wang December 16, 2005 1 Introduction We receive emails about events all the time. A message will typically include the title

More information

Machine Learning (CSMML16) (Autumn term, ) Xia Hong

Machine Learning (CSMML16) (Autumn term, ) Xia Hong Machine Learning (CSMML16) (Autumn term, 28-29) Xia Hong 1 Useful books: 1. C. M. Bishop: Pattern Recognition and Machine Learning (2007) Springer. 2. S. Haykin: Neural Networks (1999) Prentice Hall. 3.

More information

Designing a Semantic Ground Truth for Mathematical Formulas

Designing a Semantic Ground Truth for Mathematical Formulas Designing a Semantic Ground Truth for Mathematical Formulas Alan Sexton 1, Volker Sorge 1, and Masakazu Suzuki 2 1 School of Computer Science, University of Birmingham, UK, A.P.Sexton V.Sorge@cs.bham.ac.uk,

More information

Compiler Design Overview. Compiler Design 1

Compiler Design Overview. Compiler Design 1 Compiler Design Overview Compiler Design 1 Preliminaries Required Basic knowledge of programming languages. Basic knowledge of FSA and CFG. Knowledge of a high programming language for the programming

More information

Recognition-based Segmentation of Nom Characters from Body Text Regions of Stele Images Using Area Voronoi Diagram

Recognition-based Segmentation of Nom Characters from Body Text Regions of Stele Images Using Area Voronoi Diagram Author manuscript, published in "International Conference on Computer Analysis of Images and Patterns - CAIP'2009 5702 (2009) 205-212" DOI : 10.1007/978-3-642-03767-2 Recognition-based Segmentation of

More information

HMM-Based On-Line Recognition of Handwritten Whiteboard Notes

HMM-Based On-Line Recognition of Handwritten Whiteboard Notes HMM-Based On-Line Recognition of Handwritten Whiteboard Notes Marcus Liwicki and Horst Bunke Institute of Computer Science and Applied Mathematics University of Bern, Neubrückstrasse 10, CH-3012 Bern,

More information

Page 1. Interface Input Modalities. Lecture 5a: Advanced Input. Keyboard input. Keyboard input

Page 1. Interface Input Modalities. Lecture 5a: Advanced Input. Keyboard input. Keyboard input Interface Input Modalities Lecture 5a: Advanced Input How can a user give input to an interface? keyboard mouse, touch pad joystick touch screen pen / stylus speech other more error! harder! (?) CS 530:

More information

Mobile Human Detection Systems based on Sliding Windows Approach-A Review

Mobile Human Detection Systems based on Sliding Windows Approach-A Review Mobile Human Detection Systems based on Sliding Windows Approach-A Review Seminar: Mobile Human detection systems Njieutcheu Tassi cedrique Rovile Department of Computer Engineering University of Heidelberg

More information

Learning to Segment Document Images

Learning to Segment Document Images Learning to Segment Document Images K.S. Sesh Kumar, Anoop Namboodiri, and C.V. Jawahar Centre for Visual Information Technology, International Institute of Information Technology, Hyderabad, India Abstract.

More information

Annotation of Human Motion Capture Data using Conditional Random Fields

Annotation of Human Motion Capture Data using Conditional Random Fields Annotation of Human Motion Capture Data using Conditional Random Fields Mert Değirmenci Department of Computer Engineering, Middle East Technical University, Turkey mert.degirmenci@ceng.metu.edu.tr Anıl

More information

HTR Part II: Handwritten Text Recognition

HTR Part II: Handwritten Text Recognition HTR Part II: Handwritten Text Recognition Preprocessing and Feature Extraction for Off-Line Continuous HTR Alejandro H. Toselli & PRHLT-Group Departamento de Sistemas Informáticos y Computación Universidad

More information

Handwriting recognition for IDEs with Unicode support

Handwriting recognition for IDEs with Unicode support Technical Disclosure Commons Defensive Publications Series December 11, 2017 Handwriting recognition for IDEs with Unicode support Michal Luszczyk Sandro Feuz Follow this and additional works at: http://www.tdcommons.org/dpubs_series

More information

ADVANCES in NATURAL and APPLIED SCIENCES

ADVANCES in NATURAL and APPLIED SCIENCES ADVANCES in NATURAL and APPLIED SCIENCES ISSN: 1995-0772 Published BYAENSI Publication EISSN: 1998-1090 http://www.aensiweb.com/anas 2017 May 11(7):pages 57-63 Open Access Journal English Cursive Hand

More information

HEURISTIC OPTIMIZATION USING COMPUTER SIMULATION: A STUDY OF STAFFING LEVELS IN A PHARMACEUTICAL MANUFACTURING LABORATORY

HEURISTIC OPTIMIZATION USING COMPUTER SIMULATION: A STUDY OF STAFFING LEVELS IN A PHARMACEUTICAL MANUFACTURING LABORATORY Proceedings of the 1998 Winter Simulation Conference D.J. Medeiros, E.F. Watson, J.S. Carson and M.S. Manivannan, eds. HEURISTIC OPTIMIZATION USING COMPUTER SIMULATION: A STUDY OF STAFFING LEVELS IN A

More information

Document Structure Analysis in Associative Patent Retrieval

Document Structure Analysis in Associative Patent Retrieval Document Structure Analysis in Associative Patent Retrieval Atsushi Fujii and Tetsuya Ishikawa Graduate School of Library, Information and Media Studies University of Tsukuba 1-2 Kasuga, Tsukuba, 305-8550,

More information

Refinement of digitized documents through recognition of mathematical formulae

Refinement of digitized documents through recognition of mathematical formulae Refinement of digitized documents through recognition of mathematical formulae Toshihiro KANAHORI Research and Support Center on Higher Education for the Hearing and Visually Impaired, Tsukuba University

More information

OCR For Handwritten Marathi Script

OCR For Handwritten Marathi Script International Journal of Scientific & Engineering Research Volume 3, Issue 8, August-2012 1 OCR For Handwritten Marathi Script Mrs.Vinaya. S. Tapkir 1, Mrs.Sushma.D.Shelke 2 1 Maharashtra Academy Of Engineering,

More information

RESTORATION OF DEGRADED DOCUMENTS USING IMAGE BINARIZATION TECHNIQUE

RESTORATION OF DEGRADED DOCUMENTS USING IMAGE BINARIZATION TECHNIQUE RESTORATION OF DEGRADED DOCUMENTS USING IMAGE BINARIZATION TECHNIQUE K. Kaviya Selvi 1 and R. S. Sabeenian 2 1 Department of Electronics and Communication Engineering, Communication Systems, Sona College

More information

AUTHOR COPY. Audio-video based character recognition for handwritten mathematical content in classroom videos

AUTHOR COPY. Audio-video based character recognition for handwritten mathematical content in classroom videos Integrated Computer-Aided Engineering 21 (2014) 219 234 219 DOI 10.3233/ICA-140460 IOS Press Audio-video based character recognition for handwritten mathematical content in classroom videos Smita Vemulapalli

More information

Automatic State Machine Induction for String Recognition

Automatic State Machine Induction for String Recognition Automatic State Machine Induction for String Recognition Boontee Kruatrachue, Nattachat Pantrakarn, and Kritawan Siriboon Abstract One problem of generating a model to recognize any string is how to generate

More information

An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation

An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation Hugo Larochelle, Dumitru Erhan, Aaron Courville, James Bergstra, and Yoshua Bengio Université de Montréal 13/06/2007

More information

Handling Place References in Text

Handling Place References in Text Handling Place References in Text Introduction Most (geographic) information is available in the form of textual documents Place reference resolution involves two-subtasks: Recognition : Delimiting occurrences

More information

Explicit fuzzy modeling of shapes and positioning for handwritten Chinese character recognition

Explicit fuzzy modeling of shapes and positioning for handwritten Chinese character recognition 2009 0th International Conference on Document Analysis and Recognition Explicit fuzzy modeling of and positioning for handwritten Chinese character recognition Adrien Delaye - Eric Anquetil - Sébastien

More information

Discriminative Training of Decoding Graphs for Large Vocabulary Continuous Speech Recognition

Discriminative Training of Decoding Graphs for Large Vocabulary Continuous Speech Recognition Discriminative Training of Decoding Graphs for Large Vocabulary Continuous Speech Recognition by Hong-Kwang Jeff Kuo, Brian Kingsbury (IBM Research) and Geoffry Zweig (Microsoft Research) ICASSP 2007 Presented

More information

Constraint Satisfaction Problems

Constraint Satisfaction Problems Constraint Satisfaction Problems [These slides were created by Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All CS188 materials are available at http://ai.berkeley.edu.] What is Search

More information

Constructing Empirical Models for Automatic Dialog Parameterization

Constructing Empirical Models for Automatic Dialog Parameterization Constructing Empirical Models for Automatic Dialog Parameterization Mikhail Alexandrov 1, Xavier Blanco 1, Natalia Ponomareva 2, and Paolo Rosso 2 1 Universidad Autonoma de Barcelona, Spain 2 Universidad

More information

Speech Technology Using in Wechat

Speech Technology Using in Wechat Speech Technology Using in Wechat FENG RAO Powered by WeChat Outline Introduce Algorithm of Speech Recognition Acoustic Model Language Model Decoder Speech Technology Open Platform Framework of Speech

More information

Comparison of Bernoulli and Gaussian HMMs using a vertical repositioning technique for off-line handwriting recognition

Comparison of Bernoulli and Gaussian HMMs using a vertical repositioning technique for off-line handwriting recognition 2012 International Conference on Frontiers in Handwriting Recognition Comparison of Bernoulli and Gaussian HMMs using a vertical repositioning technique for off-line handwriting recognition Patrick Doetsch,

More information

Conditional Random Fields and beyond D A N I E L K H A S H A B I C S U I U C,

Conditional Random Fields and beyond D A N I E L K H A S H A B I C S U I U C, Conditional Random Fields and beyond D A N I E L K H A S H A B I C S 5 4 6 U I U C, 2 0 1 3 Outline Modeling Inference Training Applications Outline Modeling Problem definition Discriminative vs. Generative

More information

From Handwriting Recognition to Ontologie-Based Information Extraction of Handwritten Notes

From Handwriting Recognition to Ontologie-Based Information Extraction of Handwritten Notes From Handwriting Recognition to Ontologie-Based Information Extraction of Handwritten Notes Marcus Liwicki 1, Sebastian Ebert 1,2, and Andreas Dengel 1,2 1 DFKI, Trippstadter Str. 122, Kaiserslautern,

More information

Part 5 Program Analysis Principles and Techniques

Part 5 Program Analysis Principles and Techniques 1 Part 5 Program Analysis Principles and Techniques Front end 2 source code scanner tokens parser il errors Responsibilities: Recognize legal programs Report errors Produce il Preliminary storage map Shape

More information

CS 314 Principles of Programming Languages. Lecture 3

CS 314 Principles of Programming Languages. Lecture 3 CS 314 Principles of Programming Languages Lecture 3 Zheng Zhang Department of Computer Science Rutgers University Wednesday 14 th September, 2016 Zheng Zhang 1 CS@Rutgers University Class Information

More information

Languages and Compilers

Languages and Compilers Principles of Software Engineering and Operational Systems Languages and Compilers SDAGE: Level I 2012-13 3. Formal Languages, Grammars and Automata Dr Valery Adzhiev vadzhiev@bournemouth.ac.uk Office:

More information

Final Exam 2, CS154. April 25, 2010

Final Exam 2, CS154. April 25, 2010 inal Exam 2, CS154 April 25, 2010 Exam rules. he exam is open book and open notes you can use any printed or handwritten material. However, no electronic devices are allowed. Anything with an on-off switch

More information

A Bambara Tonalization System for Word Sense Disambiguation Using Differential Coding, Segmentation and Edit Operation Filtering

A Bambara Tonalization System for Word Sense Disambiguation Using Differential Coding, Segmentation and Edit Operation Filtering A Bambara Tonalization System for Word Sense Disambiguation Using Differential Coding, Segmentation and Edit Operation Filtering Luigi (Y.-C.) Liu Damien Nouvel ER-TIM, INALCO, 2 rue de Lille, Paris, France

More information

Robust Phase-Based Features Extracted From Image By A Binarization Technique

Robust Phase-Based Features Extracted From Image By A Binarization Technique IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 18, Issue 4, Ver. IV (Jul.-Aug. 2016), PP 10-14 www.iosrjournals.org Robust Phase-Based Features Extracted From

More information

Extracting and Composing Robust Features with Denoising Autoencoders

Extracting and Composing Robust Features with Denoising Autoencoders Presenter: Alexander Truong March 16, 2017 Extracting and Composing Robust Features with Denoising Autoencoders Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol 1 Outline Introduction

More information

Input Validation Testing: A Requirements-Driven, System level, Early Lifecycle Technique

Input Validation Testing: A Requirements-Driven, System level, Early Lifecycle Technique Input Validation Testing: A Requirements-Driven, System level, Early Lifecycle Technique Jane Hayes Jeff Offutt SAIC George Mason University jane.e.hayes@cpmx.saic.com ofut@gmu.edu Support from U.S.National

More information

Math Information Retrieval: User Requirements and Prototype Implementation. Jin Zhao, Min Yen Kan and Yin Leng Theng

Math Information Retrieval: User Requirements and Prototype Implementation. Jin Zhao, Min Yen Kan and Yin Leng Theng Math Information Retrieval: User Requirements and Prototype Implementation Jin Zhao, Min Yen Kan and Yin Leng Theng Why Math Information Retrieval? Examples: Looking for formulas Collect teaching resources

More information

Using Corner Feature Correspondences to Rank Word Images by Similarity

Using Corner Feature Correspondences to Rank Word Images by Similarity Using Corner Feature Correspondences to Rank Word Images by Similarity Jamie L. Rothfeder, Shaolei Feng and Toni M. Rath Multi-Media Indexing and Retrieval Group Center for Intelligent Information Retrieval

More information

FLL: Answering World History Exams by Utilizing Search Results and Virtual Examples

FLL: Answering World History Exams by Utilizing Search Results and Virtual Examples FLL: Answering World History Exams by Utilizing Search Results and Virtual Examples Takuya Makino, Seiji Okura, Seiji Okajima, Shuangyong Song, Hiroko Suzuki, Fujitsu Laboratories Ltd. Fujitsu R&D Center

More information

Recognition of Tables and Forms

Recognition of Tables and Forms Recognition of Tables and Forms Bertrand Coüasnon, Aurélie Lemaitre To cite this version: Bertrand Coüasnon, Aurélie Lemaitre. Recognition of Tables and Forms. Handbook of Document Image Processing and

More information

A Visualization Tool to Improve the Performance of a Classifier Based on Hidden Markov Models

A Visualization Tool to Improve the Performance of a Classifier Based on Hidden Markov Models A Visualization Tool to Improve the Performance of a Classifier Based on Hidden Markov Models Gleidson Pegoretti da Silva, Masaki Nakagawa Department of Computer and Information Sciences Tokyo University

More information

Overview of the 5th International Competition on Plagiarism Detection

Overview of the 5th International Competition on Plagiarism Detection Overview of the 5th International Competition on Plagiarism Detection Martin Potthast, Matthias Hagen, Tim Gollub, Martin Tippmann, Johannes Kiesel, and Benno Stein Bauhaus-Universität Weimar www.webis.de

More information

ActiveClean: Interactive Data Cleaning For Statistical Modeling. Safkat Islam Carolyn Zhang CS 590

ActiveClean: Interactive Data Cleaning For Statistical Modeling. Safkat Islam Carolyn Zhang CS 590 ActiveClean: Interactive Data Cleaning For Statistical Modeling Safkat Islam Carolyn Zhang CS 590 Outline Biggest Takeaways, Strengths, and Weaknesses Background System Architecture Updating the Model

More information

Artwork Specifications EcoGrips

Artwork Specifications EcoGrips Artwork Specifications EcoGrips Eco-Products wants to help you promote your brand. We know that combining more sustainable products with innovative, cutting edge custom branding will help you engage with

More information

Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction

Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction Stefan Müller, Gerhard Rigoll, Andreas Kosmala and Denis Mazurenok Department of Computer Science, Faculty of

More information

Applying Machine Learning to Real Problems: Why is it Difficult? How Research Can Help?

Applying Machine Learning to Real Problems: Why is it Difficult? How Research Can Help? Applying Machine Learning to Real Problems: Why is it Difficult? How Research Can Help? Olivier Bousquet, Google, Zürich, obousquet@google.com June 4th, 2007 Outline 1 Introduction 2 Features 3 Minimax

More information

Keywords Connected Components, Text-Line Extraction, Trained Dataset.

Keywords Connected Components, Text-Line Extraction, Trained Dataset. Volume 4, Issue 11, November 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Language Independent

More information

A Fast Approximated k Median Algorithm

A Fast Approximated k Median Algorithm A Fast Approximated k Median Algorithm Eva Gómez Ballester, Luisa Micó, Jose Oncina Universidad de Alicante, Departamento de Lenguajes y Sistemas Informáticos {eva, mico,oncina}@dlsi.ua.es Abstract. The

More information

Lecture 7: Neural network acoustic models in speech recognition

Lecture 7: Neural network acoustic models in speech recognition CS 224S / LINGUIST 285 Spoken Language Processing Andrew Maas Stanford University Spring 2017 Lecture 7: Neural network acoustic models in speech recognition Outline Hybrid acoustic modeling overview Basic

More information

Taming Text. How to Find, Organize, and Manipulate It MANNING GRANT S. INGERSOLL THOMAS S. MORTON ANDREW L. KARRIS. Shelter Island

Taming Text. How to Find, Organize, and Manipulate It MANNING GRANT S. INGERSOLL THOMAS S. MORTON ANDREW L. KARRIS. Shelter Island Taming Text How to Find, Organize, and Manipulate It GRANT S. INGERSOLL THOMAS S. MORTON ANDREW L. KARRIS 11 MANNING Shelter Island contents foreword xiii preface xiv acknowledgments xvii about this book

More information