G-SOM
- The G-SOM program is a tool to generate and handle Self-Organizing Map (SOM) -based classifiers.
- The program was developed as a part of Catie project by Toni Piirainen at University of Oulu.
In visual surface inspection application, the problem often faced is the collection an labelling of training material. The manual labelling of training samples requires much effort and is error prone since the defect classes may appear diffucult to discriminate even for a human. Frequent changes in the inspected material or imaging conditions may lead to unpractical often repeating training material collection cycles.
The SOM-based approach supports the labelling of training data, simplifies the retraining for changing material or imaging conditions, provides an intuative user's interface, and is computationally attractive for real-time applications.
G-SOM features
- Easy to do SOM initialization, teaching and labelling
- Multiple SOM's open at one time
- Images of data samples
- Automated training material labelling
- Confusion matrix
- Image SOM
- Because it is done with java, it works in Windows #, Unix, Linux...
Related links
The CATIE Project Home Page
