ICDAR-2009 Tutorial

Interactive Multimodal Transcription of Handwritten Text Images

Tutorial Slides


I Introduction
icdarInteracTranscrTut09-I2p.pdf (235K)
I-p Off-line HTR in practice
icdarInteracTranscrTut09-Ip2p.pdf (2.0M)
II Computer-Assisted Transcription of Text Images (CATTI)
icdarInteracTranscrTut09-II2p.pdf (181K)
II-p CATTI in practice
icdarInteracTranscrTut09-IIp2p.pdf (178K)
III Multimodality in CATTI (MM-CATTI)
icdarInteracTranscrTut09-III2p.pdf (949K)
III-p Demostration of a complete MM-CATTI System in a real HTR task
MM-CATTI demo overview
MM-CATTI demo screencast overview

Practical Guide

The aim of this practice guide is to get familiar with the use of HTK (Hidden Markov Model ToolKit) applied in handwritten text recognition (HTR), and further, in computer assisted transcription of handwritten text (CATTI). In addition, brief explanations about the use of some homemade tools for image preprocessing and features extraction implemented for HTR will be given.

By far the most important software in this practice is "The Hidden Markov Model Toolkit (HTK), version 3.4", which (including its documentation) can be downloaded from http://htk.eng.cam.ac.uk.

In addition, in order to train n-grams language models, the software SRI Language Modeling Toolkit (SRILM) is required.

Furthermore, as this practice is completely developed in Linux, it is assumed that there is a prior knowledge and experience using this operating system and handling the standard GNU-Linux tools such as bash, awk, netpbm, xv, etc.

Guide: Exp-Guide.pdf (177K)

IAM Handwriting Database, http://www.iam.unibe.ch/fki/databases/iam-handwriting-database
Spanish-Number Corpus, SpanishNumbers.tar.bz2 (1.1M)
HTR processing tools, HTR-toolsUtils.tar.bz2 (24K)
IAMDB CATTI output, CATTI_IAMDB.log (379K)

Dr. Alejandro H. Toselli and Dr. Enrique Vidal.