Detailed PDF Version Click Here

Links to Talks
Day 1
Session 1
1. Style Based Retrieval for Ancient Syriac Manuscripts (PDF)
2. TSV-LR: Topological signature vector-based lexicon reduction for fast recognition of pre-modern Arabic subwords (PDF)
3. Mining Historical Archives for Near-Duplicate Figures (PDF)
4. User-Assisted Alignment of Arabic Historical Manuscripts (PDF)
5. Transcription Alignment of Latin Manuscripts using Hidden Markov Models (PDF)
6. The CADAL Calligraphic Database (PDF)

Session 2
1. Linking the Past: Discovering Historical Social Networks from Documents and Linking to a Genealogical Database (PDF)
2. Automatic indexing of French handwritten census registers for probate genealogy (PDF)
3. Enabling Search for Facts and Implied Facts in Historical Documents (PDF)
4. Performing Information Extraction to Improve OCR Error Detection in Semi-structured Historical Documents (PDF)
5. Data Mining Medieval Documents by Word Spotting (PDF)
6. Keyword spotting approach using Blurred Shape Model-based descriptors (PDF)

Session 3
1. Rule based document understanding of historical books using a hybrid fuzzy classification system (PDF)
2. Combining Statistical and Geometrical Classifiers for Text Extraction in Multispectral Document Images (PDF)
3. Grid-Based Modelling and Correction of Arbitrarily Warped Historical Document Images for Large-Scale Digitisation (PDF)
4. Towards a Faithful Visualization of Historical Books on E-book Readers (PDF)
5. Text Line Segmentation for Gray Scale Historical Document Images (PDF)
6. Image Processing for Historical Newspaper Archives (PDF)

Day 2
Session 4
1. Development of Nom Character Segmentation for Collecting Patterns from Historical Document Pages (PDF)
2. Character Segmentation for Information Extraction from Ancient Palm Leaf Manuscripts in Thailand (PDF)
3. Thanatos:Automatically Retrieving Information from Death Certificates in Brazil (PDF)

Session 5
1. IMPACT: Centre of Competence in Text Digitisation (PDF)
2. An Experimental Workflow Development Platform for Historical Document Digitisation and Analysis (PDF)
3. HistDoc v. 2.0 - Enhancing a Platform to Process Historical Documents (PDF)
4. A Design of a Preprocessing Framework for Large Database of Historical Documents (PDF)