Domain Adaptation and GEneralization for Character Classification(DAGECC) Call for Papers

ICPR 2024 Competition on 
Domain Adaptation and GEneralization for Character Classification(DAGECC)!


This challenge will be hosted on Codabench and encompasses two
independent tracks on domain generalization and unsupervised domain
adaptation, utilizing two brand new datasets: Safran-MNIST-D and
Safran-MNIST- DLS. Both datasets comprise images of serial numbers
extracted from diverse avionic parts.
 

** To participate, please visit our competition website: DAGECC
(dagecc-challenge.github.io)

----------------------------------------------------------------------

*** Important Dates
-        Apr 30th, 2024 : Training Data released :Safran-MNIST-DLS (zenodo.org)
-        May 27th, 2024 : Open submissions on Codabench        
-        Jul 21st, 2024 : Close submissions
-        Jul 31st, 2024 : Winners announcement               
-        Aug 18th, 2024 : Report submission deadline (optional)
-        Dec 01st-05th, 2024 : ICPR event in Kolkata, India

----------------------------------------------------------------------

Background

Serial number recognition holds significant importance in various
industries, predominantly in quality control, tracking and tracing of
parts, and inventory management. However, executing successful serial
number recognition can pose substantial challenges due to the varied
surfaces on which the numbers are inscribed. Numbers may be etched,
painted, or stamped onto materials ranging from shiny metals,
transparent glasses, to rough-textured composites.

Domain adaptation and domain generalization come into play as
essential tools when addressing the multifaceted problem of character
recognition under varying conditions.

To address this challenge, we are introducing two new datasets:
Safran-MNIST-D and Safran-MNIST-DLS. Both datasets comprise images of
serial numbers extracted from diverse avionic parts manufactured by
SAFRAN. These datasets resemble the well-known MNIST dataset, but with
a focus to industrial contexts, encompassing variations in lighting
conditions, orientations, writing styles and surface textures.

We warmly invite both academic and industry professionals to
participate in this competition and offer their valuable expertise and
perspectives.

----------------------------------------------------------------------

* Prizes 

- Cash prizes and selected SAFRAN goodies will be awarded to the top 3
teams of each track.

- The lead author of the top 3 teams will also be invited to
contribute to the competition summary paper, which will be included in
the proceedings of ICPR 2024.
 

----------------------------------------------------------------------

Organizing committee
-        Frederic Jurie, Professor, University of Caen
-        Sylvie Le-Hegarat Mascle, Professor, University Paris-Saclay
-        Emanuel Aldea, Associate Professor, University Paris-Saclay
-        Jennifer Vandoni, Research Scientist, SafranTech, Paris
-        Sofia Marino, Research Scientist, SafranTech, Paris
-        Ichraq Lemghari, Ph.D. Student, University Paris-Saclay


For any questions, please contact dagecc.icpr24@gmail.com

Best regards,

DAGECC Organizers