Creating edge detectors by evolutionary reinforcement learning

— In this article we present results from experiments where a edge detector was learned from scratch by EANT2, a method for evolutionary reinforcement learning. The detector is constructed as a neural network that takes as input the pixel values from a given image region—the same way that standard edge detectors do. However, it does not have any perimage parameters. A comparison between the evolved neural networks and two standard algorithms, the Sobel and Canny edge detectors, shows very good results.

• Type: Conference
• Year: 2008
• Where: CEC
• Authors: Nils T. Siebel, Sven Grünewald, Gerald Sommer
• Keywords: Artificial Intelligence, CEC 2008, Edge Detectors, Neural Networks, Standard Edge Detectors