The Zero-ETL Approach: Enhancing Data Agility and Insight
Bratislava WS - Pratikakis - NCSR - image analysis tools_pdf
1. IMPACT is supported by the European Community under the FP7 ICT Work Programme. The project is coordinated by the National Library of the Netherlands.
Tools for Document Image Analysis and Search
Ioannis Pratikakis, Basilis Gatos and Anastasios Kesidis
Computational Intelligence Laboratory
Institute of Informatics and Telecommunications
National Center for Scientific Research "Demokritos"
GR-153 10 Agia Paraskevi, Athens, Greece
May 7, 2010
Bratislava
2. IMPACT is supported by the European Community under the FP7 ICT Work Programme. The project is coordinated by the National Library of the Netherlands.
Word spotting Architecture
Document
corpus
The main operational parts of the Word
Spotting engine are: PRE-PROCESSING
Keywords
list
TR1
Image
enhancement
Segmented Synthetic Character
Marking character templates words keyword templates
TR2
Segmentation
Feature Feature
Feature extraction & word matching
extraction extraction
Similarity
measurement
User feedback Initial
ranking
results
Searching Final
ranking
results
User access control
Mark keyword instances in
documents
2
3. IMPACT is supported by the European Community under the FP7 ICT Work Programme. The project is coordinated by the National Library of the Netherlands.
For future inquiries :
Ioannis PRATIKAKIS (ipratika@iit.demokritos.gr)
Basilis GATOS (bgat@iit.demokritos.gr)
3