Fish4Knowledge Project Files

% -----------------------------------------------------------------------
% Fish4Label: an online game for collecting ground truth for fish species
% recognition.
%
% Copyright (C) 2013  Jiyin He
%
% This software is distributed under the terms
% of the GNU General Public License 2.0.
% 
% Permission to use, copy, and distribute this software for
% any purpose without fee is hereby granted, provided that this entire
% notice is included in all copies of any software which is or includes
% a copy or modification of this software and in all copies of the
% supporting documentation for such software.
%
% This software is being provided "as is", without any express or
% implied warranty.  In particular, the authors do not make any
% representation or warranty of any kind concerning the merchantability
% of this software or its fitness for any particular purpose."
%
% Contact: jiyinhe@gmail.com
% ----------------------------------------------------------------------

a) What does this component do? 

This is a labeling game for collecting fish species recognition ground truth. 
It is developed using the Django framework.
A living demo can be found here: http://f4k.project.cwi.nl/fishlabeling/accounts/login/

For a description of the system, see:
http://dl.acm.org/citation.cfm?id=2491792

2. How is the component interfaced with other F4K system components? 

This is a standalone application. 

3. How to run it? and what parameters are allowed?

To deploy this game or adapt it for other purpose, the following information may be useful:
 - Django tutorial: http://www.djangoproject.com/
 - Modules required: django-registration

All parameter settings are configured in the settings.py file. See the example_settings.py file for example configurations.  

The corresponding database tables can be generated by running:

$python manage.py syncdb

The database needs to be filled. An example script to setup the database: 
exp_setup.py

4. Content and modules

4.1 example_settings.py: 
The example file for settings.py. 
For details of settings.py, see: https://docs.djangoproject.com/en/1.5/topics/settings/ 

4.2 exp_setup.py: 
Example script for setting up the database

4.3 manage.py: 
Django's commandline utility for admin tasks, it's automatically generated for each django project.
For details of manage.py: see: https://docs.djangoproject.com/en/1.5/ref/django-admin/

4.4 urls.py:
It contains url configration for the Django project.
For details of url.py, see: https://docs.djangoproject.com/en/1.5/topics/http/urls/ 

4.5 wsgi.py 
The WSGI configure for the project. It's automatically generated for each django project.

4.4 media/:  
This directory contains the css, javascripts, and images used by the game user interface. In particular, the following 2 directories should contain the fish images used in the game:

IMAGES/: the images to be labeled, e.g., extracted from F4K videos
species_imgs/: the candidate label images with species names.   

Considering the size of the images, these are not included in the source code.

4.5 static/:
Static files used in the game interface. 

4.6 templates/:
The HTML templates for the game user interface. 
For more details about Django templates, see: https://docs.djangoproject.com/en/1.5/ref/templates/api/

4.7 categorization/:
The fish species categorization application. It contains:
admin.py: This script customizes the project admin site  
models.py: This script contains the database definition    
urls.py: This script contains the url configuration for the categorization application 
views.py: This script processes user's request and returns response


5. Related research papers:

Jiyin He, Jacco van Ossenbruggen, and Arjen P. de Vries. 2013. Do you need experts in the crowd?: a case study in image annotation for marine biology. In Proceedings of the 10th Conference on Open Research Areas in Information Retrieval (OAIR '13), pages 57-60.
http://dl.acm.org/citation.cfm?id=2491763

Jiyin He, Jacco van Ossenbruggen, and Arjen P. de Vries. 2013. Fish4label: accomplishing an expert task without expert knowledge. In Proceedings of the 10th Conference on Open Research Areas in Information Retrieval (OAIR '13),  pages 211-212. 
http://dl.acm.org/citation.cfm?id=2491792