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 |
NICE.I Protocol 1. Overview. In order to participate in the NICE.I
contest, an application executable and a registration form should be
submitted. The executable should receive the path of a close-up iris image
(through command-line arguments) and perform its segmentation, distinguishing
between the regions of the iris unobstructed by any type of noise and all the
remaining ones. 1.1. The application executable can be written
in any programming language and must run in standalone mode, in one of the
operating systems:”Windows XP, Service Pack 2” or ”Fedora Core 6”. 1.2. There will be no internet access
during the NICE.I evaluation. Thus, the application executable will need to
be installed and executed without access to the internet. 1.3. An overview of the task demanded to
the NICE.I participants is given in figure 1. Receiving the pathname of a
close-up and noisy iris image (in “.tiff” format), the executable should
produce a correspondent binary image (with the same name, size and in “.bmp”
format), where the pixels that correspond to the noise-free regions of the
iris appear as black (intensity=0) and all the remaining ones appear as white
(intensity=255). Figure
1: NICE.I fundamental task. 2. Registration. Each NICE.I participant will receive
a username. This username will be used as the name of the submitted
executable. 2.1. Each participant is allowed to submit
one single algorithm and executable. 2.2. NICE.I participation agreement. The
application form must be signed by the corresponding participant and sent to
the contest email address. 3. Evaluation. The NICE.I contest will be evaluated
trough a Java framework built within the SOCIA Lab and within the UBIRIS.v2
data set. 3.1. The evaluation framework will be
available to NICE.I participants, in order to facilitate the training and
tuning of the iris segmentation algorithms. 3.2. Together with the evaluation
framework, a data set of noisy iris images (portion of the UBIRIS.v2 database)
will be given, with have close characteristics to the images used in the
evaluation stage. Additionally, the set of the correspondent and manually
classified “.bmp” images will be given, to enable automatic evaluation. 3.2.1. The image format of the provided data
set of input images is “.tiff”. 3.2.2. The images produced by the
segmentation algorithms must have the same name as the respective input
images and format “.bmp”. These will be compared to the manually classified
images by the contest framework.
|
|
|
fghfghfghfgh
DI-UBI Bloco VI Rua Marquês de Ávila e Bolama P- 6201-001
Covilhã PORTUGAL