Madonne Talk Tours University

1
A Fast System for Dropcap Image Retrieval

• Mathieu Delalandre and Jean-Marc Ogier
• L3i, La Rochelle University, France
• mathieu.delalandre_at_univ-lr.fr

2
Short CV
3
Short CV

• Personal Information
• Mathieu Delalandre, 32 years old, Married
• Academic Degrees
• 1995-1998 Lic.Sc In Industrial Computing Rouen
  University, France
• 1998-2001 M.Sc in Computer Science Rouen
  University, France
• Research Experiences (5 years, Graphics
  Recognition)
• 04/01-09/01 Master PSI Laboratory (Rouen,
  France)
• 10/01-04/05 PhD PSI Laboratory (Rouen, France)
• 05/05-09/05 Post-doc SCSIT (Nottingham,
  England)
• 10/05-10/06 Post-doc L3i Laboratory (La
  Rochelle, France)
• 11/06-12/06 Post-doc PSI Laboratory (Rouen,
  France)
• 01/07-12/09 Post-doc CVC (Barcelone, Spain)

mais aussi des bandeaux, portraits, armoiries,
fleurons, marques
4
Introduction

• - Old books
• - Old graphics retrieval
• - Our problem

5
IntroductionOld books

• Old books
• - Old graphics retrieval
• Our problem

• Old books of XV and XVI centuries
• Samples

• Example of digitized database
• (BVH, CESR Tours)

• Old Graphics

6
IntroductionOld graphics retrieval

• Old books
• - Old graphics retrieval
• Our problem

• System overview
• General architecture

• Samples

Pareti05 Graphics style Zip law
Uttama05 Document layout MST

• Retrieval criterion

Baudrier05 Sub image Hausdorff distance
Bigun96 Stroke image Radiogram orientation
7
IntroductionOur problem (1/2)

• Old books
• - Old graphics retrieval
• Our problem

• Context
• MAsse de DOnnées issues de la Numérisation du
  patrimoiNE (MADONNE) Project
• Bibliothèques Virtuelles Humanistes (BVH)
• du Centre dEtudes Supérieures de la Renaissance
  (CESR)

• Wood Plug Tracking

8
IntroductionOur problem (2/2)

• Old books
• - Old graphics retrieval
• Our problem

• Problem features
• No scaled, no oriented
• Noise
• Offset
• Complexity
• Accuracy
• Scalability

• Descriptor choice

• To scalar Loncaric98
• Hough, Radon, Zernike, Hu, Fourrier
• Scaled and
• orientation invariant
• fast
• local

• To image Gesu99
• Template matching, Hausdorff distance
• no scaled and orientation invariant
• global (scene)

9
Our system
10
Our systemFormatting

• Digitalization problems Lawrence00
• Problem sources
• Several image providers
• Several digitalization tools
• Length of process
• Human supervised
• QUEID QUery Engine on Image Database

• OLDB (Ornamental Letters Database)
• Before (oldb.jpg)
• After

11
Our systemCompression

• Run based compression
• Run Length Encoding (RLE)
• Compression rate

• OLDB results
• Fixed threshold binarisation
• Both RLE

• RLE Types

12
Our systemCentering and comparison

• Centering

• OLDB results

• Comparison

while x2 ? x1 handle image 2 while x1 ? x2
handle image 1
13
In progress
14
In progress

• Our problem
• Current time ? 40 s
• Wished time lt 4 s

• First system
• Level 1 image sizes
• Level 2 black, white pixels
• Level 3 RLE comparison

To use a system approach
To use a lossless compression

• Selection algorithm

• Key idea

Speed
if ?1 - ?2 lt 0 push x, cluster while ?1 -
?2 lt 0 next
Depth
15
In progress

• OLDB results

• Run based signature

• To decrease variability

To add a level
To work on selection
16
In progress

• Query example

• Performance evaluation

• Criterion ?
• Scalability
• Accuracy
• Time processing

Benchmark system
17
Conclusions and perspectives
18
Conclusions et perspectives

• Conclusions
• Dropcap image retrieval wood tracking
• Formatting image database (QUEID)
• Fast approach, two features
• RLE comparison (?7 to ?9)
• Top-down strategy (?2 to ?20)
• Results ? 10 s for 2000 images (300 Mo)
• Perspectives
• Working on RLE signature
• Benchmark system for performance evaluation

19
Bibliography
20
Bibliography

• J. Bigun, S. Bhattacharjee, and S. Michel.
  Orientation radiograms for image retrieval An
  alternative to segmentation. In International
  Conference on Pattern Recognition (ICPR),
  volume 3, pages 346-350, 1996.
• V. D. Gesu and V. Starovoitov. Distance based
  function for image comparison. Pattern
  Recognition Letters (PRL), 20(2)207-214, 1999.
• S. Loncaric. A survey of shape analysis
  techniques. Pattern Recognition (PR),
  31(8)983-1001, 1998.
• R. Pareti and N. Vincent. Global discrimination
  of graphics styles. In Workshop on Graphics
  Recognition (GREC), pages 120-128, 2005.
• S. Uttama, M. Hammoud, C. Garrido, P. Franco, and
  J. Ogier. Ancient graphic documents
  characterization. In Workshop on Graphics
  Recognition (GREC), pages 97-105, 2005.
• E. Baudrier, G. Millon, F. Nicolier, and S. Ruan.
  A fast binary-image comparison method with
  local-dissimilarity quantification. In
  International Conference on Pattern Recognition
  (ICPR), volume 3, pages 216- 219, 2006.

21
Thanks