Departamento de Informática da Universidade da Beira Interior
SOCIA Lab. – Soft Computing and Image Analysis Group
Department of Computer Science, University of Beira Interior, 6201-001 Covilhã, Portugal
September 06th, 2010: The
classification of the NICE.II best participants is available on the
contest website. Additionally, the full classification results were
sent by email to all participants.
Participants invited to publish their approach in the Pattern Recognition Letters Journal:
October 23th, 2009: The automatic JAVA Evaluation
Framework and the UBIRIS.v2 training data set composed by 1 000 iris images
and the corresponding segmentation maps are already available for
participants. Please download them at the bottom of the “Registered
Participants” web page.
· October 23th, 2009: The automatic JAVA Evaluation Framework and the UBIRIS.v2 training data set composed by 1 000 iris images and the corresponding segmentation maps are already available for participants. Please download them at the bottom of the “Registered Participants” web page.
· October 15th, 2009: In opposition to the NICE.I contest, the NICE:II Organizing Committee decided not to impose a deadline for the registration of new participants and for the deliverance of the training data. This time, as soon as participants register in the contest, they immediately receive the training data set and the automatic evaluation software.
· October 13th, 2009: The Pattern Recognition Letters Journal (Elsevier, ISI Web of KnowledgeSM indexed) officially accepted to publish a special issue with the NICE:II best participations. Thus, authors of the proposals that achieve the best 8 results will be invited to publish a paper describing their method.
· October 13th, 2009: The website of the NICE:II contest is online.
The UBIRIS databases were developed within the SOCIA Lab. (Soft Computing and Image Analysis Group) of the University of Beira Interior (Portugal). They contain visible wavelength iris images captured in heterogeneous lighting conditions, which leaded to the appearance of highly degraded images. These databases were downloaded by over 800 users (individuals and academic, research and commercial institutions) from over 70 different countries.
Fig. 1: Examples of UBIRIS images and of the corresponding iris segmentation maps.
The NICE.I was held by the SOCIA Lab. and focused in the segmentation and detection of noisy regions of visible wavelength degraded iris data. It received over 90 participants from 20 different countries and the best 10 participations were invited to publish their approach in a special issue of the Image and Vision Computing Journal (Elsevier). Also, all the remaining participants published their method in the Proceedings of the NICE.I contest (that will appear simoultaneously with the IVC special issue).
The NICE:II (Noisy Iris Challenge Evaluation - Part II) is the complementary part of its antecessor and aims to complete the Pattern Recognition process:
· It also operates on iris images similar to the ones of the UBIRIS.v2.
· It is exclusively focused in the signatures encoding and matching stages of degraded visible wavelength iris images previously segmented, according to the segmentation method that outperformed in the segmentation contest (NICE.I).
DI-UBI Bloco VI Rua Marquês de Ávila e Bolama P- 6201-001 Covilhã PORTUGAL