License plate recognition and detection using Machine Learning

Abstract

Building an effective tactic to identify characters from images with fewer error rate is the big task. Aim of this paper is to furnish an algorithm to generate error free recognition of text from the given input image and also it help in document digitizing and prevention to the hand written text recognition. Optical Character Recognition is the intensive research topic for more than 4 decades, it is the time consuming and labor intensive work of inputting the data through keyboard. Hence this paper discusses about mechanical or electronic conversion of scanned images, text which contain graphics, image captured by camera, scanned images and the recognition of images where characters may be broken or smeared . The optical character recognition is the desktop based application developed using Java IDE and mysql as a database. The proposed algorithm gained 93.42% accuracy when applied on different data sets. In pre-processing and post processing neural network techniques are used to remove noise from the image and classification are used to recognized the characters. Back propagation algorithm are used for the training of neural network, feature extraction has performed by template matching and hamming distance.