job.vandoeselaar@ivdnt.org, Author at IMPACT Centre of Competence

IMPACT Workshop in Rouen: exchanging views, finding synergies

The workshop kicked off this morning with a welcome by organizer Thierry Paquet of the University of Rouen, who has been involved in OCR related research for a long time. There is a good mix of attendants here, people from digital library research, OCR specialists, industry like ABBYY and Jouve, language specialists, image scientists… and … Continue reading

IMPACT Workshop: 31 March 2011, Rouen

This one day workshop will disseminate the latest progress achieved in the field of Optical Character Recognition systems (OCR) within the framework of various digitization projects for Digital Libraries.

Toekomst van IMPACT: Centre of Competence – Hildelies Balk #impactdemo

Hildelies Balk gives the final presentation of the IMPACT Demo day. She talks about the future of IMPACT: the IMPACT Centre of Competence in Text Digitisation will be launched in the near future. This Centre will make sure the knowledge and results of IMPACT will be sustained and further developed up to three years after … Continue reading

Lieke Ploeger over IMPACT Online – #Impactdemo

Useful information on how to find & follow IMPACT through Twitter, LinkedIn, Youtube, Vimeo etc.! Follow us and help building our knowledge base through the helpdesk! All your input will be used to build the knowledge base. Visit our conference in London where the final results will be shown. More information on the website: http://www.impact-project.eu

IMPACT Framework en Evaluatie – Clemens Neudecker #impactdemo

Clemens Neudecker, IMPACT technical project manager, presents the IMPACT Framework that enables end users to interact with IMPACT tools and applications in a clear and consistent way. The Framework consists of open source software components and is based on open standards.

Functional Extension Parser (FEP) – Lotte Wilms #impactdemo

[slideshare id=6971431&doc=feplottewilms-110218053224-phpapp02] De Functional Extension Parser (FEP) is een IMPACT tool voor structurele annotatie van documenten, ontwikkeld door de Universiteit van Innsbruck (UIBK). Er is een regelset gebouwd om bijvoorbeeld paginanummer’s, koptitels en voetnoten te kunnen identificeren. Ook kan de tool de bedrukte tekstgedeelten herkennen of een gelinkte inhoudsopgave maken, wat handig is voor het … Continue reading

Interactief postcorrectie systeem – Jesse de Does #impactdemo

Jesse de Does van het INL presenteert nog een manier van postcorrectie: de correctie van meerdere woorden met dezelfde fout. Hier is een speciale postcorrectie tool voor ontwikkeld in IMPACT door de Universiteit van Munchen (LMU). Zonder specifieke verrijking van de tekst kan deze tool een profiel maken van patronen in een tekst, en bijvoorbeeld … Continue reading

Computerlexica in OCR en zoekmachines – Katrien Depuydt van INL op #IMPACTDemo

Computerlexicon Wat doen lexica in IMPACT Gereedschappen voor het bouwen van lexica Resultaten Demonstratie zoeken

CONCERT crowdsourcing tool – Lotte Wilms & Ewoud Sanders #impactdemo

Manual correction of OCR is expensive and time-consuming. That’s why IBM has developed the CONCERT tool in IMPACT, a crowdsourcing tool with which users can correct OCR results in a very efficient way. The focus is on productivity – the Adaptive OCR engine is trained on the basis of the corrections, which lowers the number of errors.

Experimentele OCR – Lotte Wilms #impactdemo

IMPACT also develops three experimental OCR tools: Wordspotting (developed by NCSR Demokritos) – based on the recognition of complete words Inventory Extraction (developed by the University of Innsbruck) – makes use of character clustering Typewritten OCR (developed by PRImA, Universiteit van Salford) – for typewritten documents