Ultra Fast Object Counting Based-on Cellular Neural Network

Vision based counter systems are very important tools in industries. Movement of objects on conveyer systems at a high speed requires an accordingly very fast processing. Therefore, traditional methods for object counting are not efficient due to the fact that they are generally slow. In this paper a CNN based method for counting objects. Simulation results for this method shows that this system is very applicable for object counting at very high speed conveyers. By just a few reconfigurations in CNN templates coefficients, we are able to modify this system for other similar applications. Keywords— Cellular Neural Network; Image Processing; Object counting; Simulation.