Université d'Orléans


     Overview     Challenge Structure Organizers            Data        
Metrics Results Contact & Questions News


Using one or several texture features from published or new proposed texture characterization methods; participants are invited to use the Support Vector Machine (SVM) as classifier to classify the different data of the Challenge. Partcipants may use any environment to classify with SVM.  For participants who wish, assistance will be provided to use the software environment R for statistical analysis (http://www.r-project.org/). Here you will find a short tutorial on SVM training and testing with R.

In a first step, participants are invited to calibrate the classifier to reach the best score with 116 subjects, half of which from osteoporotic patients and the other half from control subjects.

In a second step, using the previous calibration parameters and 58 new test images for blind classification, participants will have to identify OP patients and CT subjects.

Participants are invited to submit three things:

1) The classification results of 116 training and test images (half OP and half CT)

Deadline: February 16th, 2014

In this step, participants will be asked to provide the following classification rates:

-- TP (True Positive, which is the number of OP people correctly identified),

-- FP (False Positive, which is the number of CT people incorrectly identified),

-- TN (True Negative, which is the number of CT people correctly identified),

-- FN (False Negative, which is the number of OP people incorrectly identified),

-- Sn (True positive rate or sensitivity) as Sn = TP/(TP + FN),

-- Sp (Specificity or True Negative Rate) as Sp = TN/(FP + TN).

2) The classification results of 58 blind test images

Deadline: March 2nd, 2014

In this step, challenge participants are asked to classify the blind test subjects as either osteoporotic patients or control subjects. The results should be submitted as a CSV file where:

- the first column contains the name of each image,

- the second column contains the classification result for each image (1 for osteoporotic, 0 for control), and

- the following columns with the texture feature values for each image.

3) Abstract

Deadline: March 2nd, 2014

An extended abstract (2 pages maximum) explaining the methodology used and the SVM classifier characteristics (used features for the classifier).