NDLI: Open-Lexicon Language Modeling Combining Word and Character Levels

Please wait, while we are loading the content...

2014 14th International Conference on Frontiers in Handwriting Recognition

Table of contents

Message from Conference and Program Chairs

Conference Organization

Program Committee

Additional Reviewers

A Simple and Fast Word Spotting Method

Segmentation-Based Historical Handwritten Word Spotting Using Document-Specific Local Features

An Historical Handwritten Arabic Dataset for Segmentation-Free Word Spotting - HADARA80P

Text/Non-text Classification in Online Handwritten Documents with Recurrent Neural Networks

Handwritten/Printed Text Separation Using Pseudo-Lines for Contextual Re-labeling

Visual Perception of Unitary Elements for Layout Analysis of Unconstrained Documents in Heterogeneous Databases

A Novel Transcript Mapping Technique for Handwritten Document Images

Bleed-Through Removal by Learning a Discriminative Color Channel

Poset Description of Grid Features and Application to Off-Line Signature Verification

Cognitive Inspired Model to Generate Duplicated Static Signature Images

On-Line Signature Verification by Multi-domain Classification

Automatic Online Signature Verification Based Only on FHE Features: An Oxymoron?

A Robust Online Signature Based Cryptosystem

Hybrid Feature Selection for Historical Document Layout Analysis

LAMIS-MSHD: A Multi-script Offline Handwriting Database

Text Line Segmentation for Handwritten Documents Using Constrained Seam Carving

A Novel Feature Selection and Extraction Technique for Classification

Assisting Forensic Writer Verification by Visualizing Diversity of Digit Handwritings: An Approach by Multidimensional Scaling of Earth Mover's Distance

Online Handwritten Stroke Type Determination Using Descriptors Based on Spatially and Temporally Neighboring Strokes

Connected Bond Recognition for Handwritten Chemical Skeletal Structural Formulas

A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition

Applications of Recurrent Neural Network Language Model in Offline Handwriting Recognition and Word Spotting

A Coarse-to-Fine Approach for Layout Analysis of Ancient Manuscripts

Table Detection in Handwritten Chemistry Documents Using Conditional Random Fields

Novel Handwritten Words and Documents Databases of Five Middle Eastern Languages

A Comparison of Recognition Strategies for Printed/Handwritten Composite Documents

Recognition of Spatial Relations in Mathematical Formulas

Evaluating Threshold for Retraining Rule in Semi-supervised Learning Using Multi-expert System

A Path Planning for Line Segmentation of Handwritten Documents

Word-Graph and Character-Lattice Combination for KWS in Handwritten Documents

Improving Signature-Based Biometric Cryptosystems Using Cascaded Signature Verification-Fuzzy Vault (SV-FV) Approach

Evaluation of Geometric Context Models for Handwritten Numeral String Recognition

A Two Stage Approach for Handwritten Malayalam Character Recognition

Text Alignment from Bimodal Mathematical Expression Sources

Flexible Sequence Matching Technique: Application to Word Spotting in Degraded Documents

A New Method for Writer Identification Based on Histogram Symbolic Representation

Neuromuscular Representation and Synthetic Generation of Handwritten Whiteboard Notes

e-Crowds: A Mobile Platform for Browsing and Searching in Historical Demography-Related Manuscripts

A Semi-incremental Recognition Method for On-Line Handwritten English Text

Combination of Features for Efficient Recognition of Offline Handwritten Devanagari Words

An MQDF-CNN Hybrid Model for Offline Handwritten Chinese Character Recognition

Stroke Level User-Adaptation for Stroke Order Free Online Handwriting Recognition

A Graph Modeling Strategy for Multi-touch Gesture Recognition

Towards Style-Based Dating of Historical Documents

Off-Line Handwritten Bilingual Name Recognition for Student Identification in an Automated Assessment System

Fast and Robust Training of Recurrent Neural Networks for Offline Handwriting Recognition

Dropout Improves Recurrent Neural Networks for Handwriting Recognition

Handwritten Character Recognition by Alternately Trained Relaxation Convolutional Neural Network

The A2iA Multi-lingual Text Recognition System at the Second Maurdor Evaluation

Irrelevant Variability Normalization via Hierarchical Deep Neural Networks for Online Handwritten Chinese Character Recognition

Writer Adaptation Using Bottleneck Features and Discriminative Linear Regression for Online Handwritten Chinese Character Recognition

A Tibetan Component Representation Learning Method for Online Handwritten Tibetan Character Recognition

Using Off-Line Features and Synthetic Data for On-Line Handwritten Math Symbol Recognition

Large Improvement in Line-Direction-Free and Character-Orientation-Free On-Line Handwritten Japanese Text Recognition

OHRS-MEWA: On-Line Handwriting Recognition System with Multi-environment Writer Adaptation

Open-Lexicon Language Modeling Combining Word and Character Levels

An Intelligent Sample Selection Approach to Language Model Adaptation for Hand-Written Text Recognition

A Bayesian Approach to Script Independent Multilingual Keyword Spotting

Learning-Free Text-Image Alignment for Medieval Manuscripts

A Database of On-Line Handwritten Mixed Objects Named "Kondate"

Automatic Handwritten Indian Scripts Identification

Segmentation-Free Keyword Spotting for Bangla Handwritten Documents

Word Spotting Using Radial Descriptor

Constrained AdaBoost for Totally-Ordered Global Features

Word Spotting in Handwritten Text Using Contour-Based Models

Offline Hand-Written Musical Symbol Recognition

Writing Type and Language Identification in Heterogeneous and Complex Documents

Real-Time Segmentation of On-Line Handwritten Arabic Script

Pixel Level Handwritten and Printed Content Discrimination in Scanned Documents

A Neural Network Based Distance Function for the k-Nearest Neighbor Classifier

Feature Weighted Support Vector Machines for Writer-Independent On-Line Signature Verification

An Interactive Tool for Forensic Handwriting Examination

Improving Isolated Digit Recognition Using a Combination of Multiple Features

Segmentation of Touching Component in Arabic Manuscripts

A Machine Learning Approach to Detection of Core Region of Online Handwritten Bangla Word Samples

Segmentation of Historical Handwritten Documents into Text Zones and Text Lines

Grouping Historical Postcards Using Query-by-Example Word Spotting

On the Influence of Key Point Encoding for Handwritten Word Spotting

Generation of Enhanced Synthetic Off-Line Signatures Based on Real On-Line Data

Page Segmentation for Historical Handwritten Document Images Using Color and Texture Features

Improvement of Context Dependent Modeling for Arabic Handwriting Recognition

Mathematical Symbol Hypothesis Recognition with Rejection Option

Deep-Belief-Network Based Rescoring Approach for Handwritten Word Recognition

A Feature Extraction Method for Cursive Character Recognition Using Higher-Order Singular Value Decomposition

Later Added Strokes or Text - Fraud Detection in Documents Written with Ballpoint Pens

Document Binarization Using Topological Clustering Guided Laplacian Energy Segmentation

A Reevaluation and Benchmark of Hidden Markov Models

Improvements in Sub-character HMM Model Based Arabic Text Recognition

Training of On-Line Handwriting Text Recognizers with Synthetic Text Generated Using the Kinematic Theory of Rapid Human Movements

Towards Unsupervised Learning for Handwriting Recognition

Progress in the Raytheon BBN Arabic Offline Handwriting Recognition System

Recognition System for On-Line Sketched Diagrams

Rejecting Both Segmentation and Classification Errors in Handwritten Form Processing

Are Sparse Representation and Dictionary Learning Good for Handwritten Character Recognition?

Combining Local Features for Offline Writer Identification

Writer Identification Using a Statistical and Model Based Approach

Writer Identification in Music Score Documents without Staff-Line Removal

Development of Handwriting Individuality: An Information-Theoretic Study

Local Co-occurrence and Contrast Mapping for Document Image Binarization

Binarization of Degraded Document Images Based on Combination of Contrast Images

Automatic Signature Stability Analysis and Verification Using Local Features

Automatic Detection of Handwritten Texts from Video Frames of Lectures

Handwriting Normalization by Zone Estimation Using HMM/ANNs

Recent Advances in Offline Signature Identification

An Approach of Strike-Through Text Identification from Handwritten Documents

Binarization: A Tool for Text Localization

An Active Contour Based Method for Image Binarization: Application to Degraded Historical Document Images

A Novel Approach of Bangla Handwritten Text Recognition Using HMM

Automatic Line Segmentation and Ground-Truth Alignment of Handwritten Documents

Arabic Font Recognition Based on a Texture Analysis

Towards Arabic Handwritten Word Recognition via Probabilistic Graphical Models

Comparison of MRF and CRF for Text/Non-text Classification in Japanese Ink Documents

Semiautomatic Text Baseline Detection in Large Historical Handwritten Documents

A Sparse Coding Based Approach for the Resolution Enhancement and Restoration of Printed and Handwritten Textual Images

Gabor Filters for Degraded Document Image Binarization

A New Text-Independent GMM Writer Identification System Applied to Arabic Handwriting

A Noisy-Or Discriminative Restricted Boltzmann Machine for Recognizing Handwriting Style Development

User Interaction Optimization for an Evolving Classifier of Handwritten Gesture Commands

Seam Carving for Text Line Extraction on Color and Grayscale Historical Manuscripts

Scribal Attribution Using a Novel 3-D Quill-Curvature Feature Histogram

Online Signature Verification Based on Kolmogorov-Smirnov Distribution Distance

Document Writer Analysis with Rejection for Historical Arabic Manuscripts

Graph Based Re-ranking Method with Application to Handwritten Digits

Multiple Training - One Test Methodology for Handwritten Word-Script Identification

An Application of LBF Energy in Image/Video Frame Text Detection

Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation

Recognizing Glagolitic Characters in Degraded Historical Documents

ICFHR 2014 Competition on Handwritten Digit String Recognition in Challenging Datasets (HDSRC 2014)

ICFHR2014 Competition on Handwritten Text Recognition on Transcriptorium Datasets (HTRtS)

ICFHR 2014 Competition on Recognition of On-Line Handwritten Mathematical Expressions (CROHME 2014)

ICFHR2014 Competition on Arabic Writer Identification Using AHTID/MW and KHATT Databases

ICFHR2014 Competition on Word Recognition from Historical Documents: ANncestry Word REcognition from Segmented Historical Documents (ANWRESH)

ICFHR2014 Competition on Handwritten Document Image Binarization (H-DIBCO 2014)

ICFHR 2014 Competition on Handwritten Keyword Spotting (H-KWS 2014)

Publisher's Information

2012 International Conference on Frontiers in Handwriting Recognition

2010 12th International Conference on Frontiers in Handwriting Recognition

Ninth International Workshop on Frontiers in Handwriting Recognition

Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition

Open-Lexicon Language Modeling Combining Word and Character Levels

Content Provider	IEEE Xplore Digital Library
Author	Kozielski, M. Matysiak, M. Doetsch, P. Schloter, R. Ney, H.
Copyright Year	2014
Description	Author affiliation: Human Language Technol. & Pattern Recognition Group, RWTH Aachen Univ., Aachen, Germany (Kozielski, M.; Matysiak, M.; Doetsch, P.; Schloter, R.; Ney, H.)
Abstract	In this paper we investigate different n-gram language models that are defined over an open lexicon. We introduce a character-level language model and combine it with a standard word-level language model in a back off fashion. The character-level language model is redefined and renormalized to assign zero probability to words from a fixed vocabulary. Furthermore we present a way to interpolate language models created at the word and character levels. The computation of character-level probabilities incorporates the across-word context. We compare perplexities on all words from the test set and on in-lexicon and OOV words separately on corpora of English and Arabic text.
Starting Page	343
Ending Page	348
File Size	166132
Page Count	6
File Format	PDF
ISBN	9781479943357
ISSN	21676445
e-ISBN	9781479943340
DOI	10.1109/ICFHR.2014.64
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2014-09-01
Publisher Place	Greece
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Context Vocabulary Computational modeling Training Interpolation Standards Speech recognition
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in