Shape Matching and Alphanumeric Recogination for Vehicle Identification

Abstract

Object recognition is the challenging problem in the real world application. Object recognition can be achieved through the shape matching. Shape matching is preceded by detecting the edges of the objects from the images, finding the correspondence between the shapes, measuring the dissimilarity between the shapes using the correspondence and classifying the object into classes by using this dissimilarity measures.

In this system we present a full-featured license plate detection and recognition system. The system is implemented on an embedded DIP platform and processes an Image in real-time. It consists of detection and a character recognition module. Detected license plates are segmented into individual characters by using a syntactic approach.

Character classification is performed with support dissimilarity measures. The major advantages of our system are its real-time capability and that it does not require any additional sensor input (e.g. from infrared sensors) except image.