Edge detection method with CNN
T. Yoshida, Junji Kawata, Tomohiro Tada, Akio Ushida, Jiro Morimoto · Society of Instrument and Control Engineers of Japan · 2004
In this paper, we propose an edge detection system with cellular neural network. Applications of this method to remotely sensed images are investigated. First, it is applied the image emphasis method to extract edge information. Next, it is made a binary image. Finally, it is applied the noise decrease method. The edge detection result show that this approach produces excellent results which are more realistic and noiseless compared with conventional edge detection methods.