Border Detection on Remote Sensing Satellite Data Using Self-Organizing Maps

In this paper, a new approach to Mediterranean Water Eddy border detection is proposed. Kohonen self-organizing maps (SOM) are used as data mining tools to cluster image pixels through an unsupervised process. The clusters are visualized on the SOM internal map. From the visualization, the borders can be detected through an interactive way. As a result, interesting patterns are visible on the images. The proposed SOM approach is tested on Atlantic Ocean satellite data and compared with conventional gradient edge detectors. Keywords remote sensing satellite data, border detection, self-organizing map (SOM), clustering, gradient edge detector

• Type: Conference
• Year: 2003
• Where: EPIA
• Authors: Nuno M. C. Marques, Ning Chen
• Keywords: Border Detection, EPIA 2003, Gradient Edge Detector, Self-Organizing Map