A Fast System for Dropcap Image Retriev

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)

Book 46
Page 1385
Graphics 4755 (3.4/page)
Foreground pixel 63 textual 37 graphical
Graphics type 41 dropcap 59 others

• 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

1. 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.
2. V. D. Gesu and V. Starovoitov. Distance based
   function for image comparison. Pattern
   Recognition Letters (PRL), 20(2)207-214, 1999.
3. S. Loncaric. A survey of shape analysis
   techniques. Pattern Recognition (PR),
   31(8)983-1001, 1998.
4. R. Pareti and N. Vincent. Global discrimination
   of graphics styles. In Workshop on Graphics
   Recognition (GREC), pages 120-128, 2005.
5. 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.
6. 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