Presentation is loading. Please wait.

Presentation is loading. Please wait.

Institut für Print- und Medientechnik der TU Chemnitz [Institute for Print and Media Technology Chemnitz University of Technology] Direktor: Prof. Dr.

Similar presentations


Presentation on theme: "Institut für Print- und Medientechnik der TU Chemnitz [Institute for Print and Media Technology Chemnitz University of Technology] Direktor: Prof. Dr."— Presentation transcript:

1 Institut für Print- und Medientechnik der TU Chemnitz [Institute for Print and Media Technology Chemnitz University of Technology] Direktor: Prof. Dr. Arved C. Hübler Reichenhainer Str Chemnitz Germany Tel: Fax: Vectorization of Glyphs and Their Representation in SVG for XML based Processing Stefan Pletschacher; Marcel Eckert; Arved C. Hübler

2 2 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Digitization of Historical Documents GEB1150

3 3 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Alphabet und Font Extraction

4 4 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Vectorization - Raster to Vector Conversion font assignment Vectorization RI P 41 hex OC R vector font encoded text e.g. ASCII bitmap graphic

5 5 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 DIA System und Workflow

6 6 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 DIA System und Workflow ฀ 0

7 7 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 DIA System und Workflow XM L

8 8 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Vectorization Approaches Contour based Skeleton based

9 9 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Applied Algorithms Pre-processing - Finding connected components (Region Growing) - Contour extraction (Contour following) Polygonal Approximation Based on Relaxation - Phase 1: Clustering of polygonal points - Phase 2: Relaxation (Error correction) Automatic Parameter Control - Rasterization of the resulting glyph images - Ascertaining a weighted error (Ground Truth) - Selecting appropriate vectorization parameters

10 10 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Finding Connected Components Ü Ö Ä % !

11 11 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Region Growing

12 12 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Contour Following white pixel black pixel starting point examination order

13 13 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Clustering of Polygonal Points

14 14 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Relaxation

15 15 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 SVG Representation

16 16 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Visual Quality

17 17 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Formal Quality Measurement - Ground Truth Error function - absolute number of wrong pixels - weighted by the distance to the next true component

18 18 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Results

19 19 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Adaptive Parameter Control

20 20 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Compression rates

21 21 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Conclusions Good vectorization results already with linear primitives High compression rates can be achieved Extracted fonts can be easily scaled and further formatted Known vectorization methods have been extended towards an adaptive system for automatic parameter control These methods can be applied for preservation and handling of unknown type faces in digitized documents Originals may be re-encoded using a document specific alphabet and font Direct integration into XML/SVG based processes possible Various output formats can be supported by means of XSL transformations

22 22 Pletschacher Vectorization of Glyphs and Their Representation in SVG for XML based Processing ELPUB 2006 Thank you very much! Questions


Download ppt "Institut für Print- und Medientechnik der TU Chemnitz [Institute for Print and Media Technology Chemnitz University of Technology] Direktor: Prof. Dr."

Similar presentations


Ads by Google