Presentation is loading. Please wait.

Presentation is loading. Please wait.

Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Fast.

Similar presentations


Presentation on theme: "Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Fast."— Presentation transcript:

1 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Fast Building of Region Graph from SVG Mathieu Delalandre, Zouba Karim, Norolala Ramangaseheno Supervisors Tony Pridmore (IPI, Nottingham University, UK) Eric Trupin (PSI, Rouen University, France)

2 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 <rect x="400" y="100" width="400“ height="200" fill="yellow" stroke="navy" stroke-width="10" /> (a)(b) Common formats : AI (Adobe Illustrator) SVG (Scalable Vector Graphic) WMF (Windows Metafile) EPS (Encapsulted PostScript) DXF (AutoCAD) ClipArt Flash Example WMF pen EPS plane Introduction What are Vector Graphics ? ClipArt Cheese

3 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Introduction Vector Graphics Indexing & Retrieval (1/2) Vector graphics are growing on Web and databases [Mong’03] [Chen’04] [Kang’04] … Few I&R systems have been developed (> 2000) [Love-01] [Sciascio’04] [Dosch’04] [Fonseca’05] [Rusiñol’05] [Zakaria’05] … Vector Graphics Features Extraction Matching Index Ranking

4 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Introduction Vector Graphics Indexing & Retrieval (2/2) Line Graph [Dosch’04] [Zakaria’05] … Symbol recognition Region Graph [Fonseca’05] [Rusiñol’05].. Document indexing Our works  region graph extraction for SVG Indexing and Retrieval  large sized data  a fast approach Two steps : unformat SVG and region graph building

5 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Unformat SVG Unformat process, what is it ? Example: overlapped rectangles L1 L2 R3 R1 R2 L3 L4 <rect x="400" y="100" width="400" height="200" fill="blue" /> <rect x="650" y="200" width="400" height="200" fill="yellow" /> R2 R1 R3 ? to unformat (or to broke) SVG

6 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 filtering Parsing for line extraction SVG document Unformat SVG Overview of our approach set of (joined) lines set of no joined lines

7 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Unformat SVG Why using a filtering step you see 5 lines you have 9 lines

8 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Unformat SVG Our filtering process l 1 includes l 2 l 1 same as l 2 l 1 joins l 2 (a) (b) (a) (b) (a) (b) l 1 intersects and overlaps l 2 l 1 intersects only l 2

9 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Unformat SVG Examples of results crossing point merged lines

10 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Region Graph Building How it works ? K Lines Line Graph Finding regions and their links

11 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Region Graph Building Approaches used in the literature Approaches based on graph handling [Fonseca’05].. region detection = problem of finding minimum length cycles inside a graph

12 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Based on [Weindorf’01] works : using vectorial information Definition: direct angle = anticlockwise Region Graph Building Our approach (1/3) L1 L5 L2L4 L3 L1 L4L5L2 L3 Vector Graphic document Line Graph e b e b e e e: end of a Line b: beginning of a Line α:Direct angle between 2 Lines be e b b b e b b e e L1 L4L2L5 L3 Specialized Line Graph α(2-1) α(1-2) b2,e1 e1,b2 e4,b1 b1,e4

13 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 [Clementini’93] aba b a b b a adjacencyoverlapstrict and tangential inclusion Region Graph Building Our approach (2/3) ab neighboring R1 Ymax Ymin Xmin Xmax R2 [Xmin Xmax] & [Ymin Ymax]

14 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Region Graph Building Our approach (3/3)

15 Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Conclusion and Perspectives Conclusion First system dealing with unformating problems First system allowing to build region graph from large sized documents and from large sized databases Perspectives Extend to curves and arcs processing Extend built graphs with neighboring relations Reduce the unformat complexity step using a zone sorting algorithm Use it for retrieval and indexing (not only graph building)


Download ppt "Image Processing and Interpretation Group University of Nottingham Eureka Meeting, L3i Laboratory, La Rochelle University Tuesday 20th April 2006 Fast."

Similar presentations


Ads by Google