License plate recognition using Kohonen neural network algorithm / Norfaeza Mat Noor

License plate recognition is one of important techniques that can be used for the
identification vehicles. It is useful in many applications such as entrance admission,
security, parking control, traffic enforcement, and toll gate automation. This paper
focuses on the development of the character recognition for license plate number. In the
development of this system, several stages have to be executed. The preprocessing is
implemented by using MATLAB tool to preprocess the images to become as an input to
the network in binary form. For the recognition of the license plate number, the
Kohonen self-organizing map is used to recognize the license plate number with using
Euclidean distance to determine best-matching unit and employed two dimensional
Kohonen layer map. It is easily trained and has attractive properties such as topological
ordering and good generalization. Experiments are performed to determine the network
parameter beside to measure the performance of Kohonen neural network. The test result
of the prototype was shown with 78.57% accuracy.
Keyword: License plate recognition, Kohonen self-organizing map, Euclidean distance