Abstract
One of the important phases in Automatic License Plate Recognition (ALPR) is the recognition or decoding of license plate characters from segmented individual character images in to ASCII characters. The accuracy of the character recognition determines ultimately the performance of the system. Since the ALPR receives images from live traffic, a reconfigurable system is the best option for character recognition. In this paper, LP character recognition is attempted using the Kohonen Neural Network (KNN) which differs from the feed forward back propagation ANN neural network interms of how it is trained and how it recalls a pattern. The KNN does not use any sort of activation function or does not use any sort of a bias weight; the output from the KNN does not consist of the output of several neurons. When a pattern is presented to a KNN one of the output neurons is selected as a "winner". This ‘winning’ neuron is the output from the KNN. KNN consists of interconnected processing elements called neurons that work together to produce a LP ASCII Character output. The LP OCR system learns characters through training process.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have