Number Plate Recognition for Vehicular Surveillance System Using an Improved Segmentation

Number Plate Recognition systems are used to track and monitor the moving vehicles by automatically extracting the number plates. The objective of this system is to recognize vehicles based on license plate information. Number plate recognition is part of vehicle identification system. Now a days it has wide range of applications like traffic surveillance, access control etc. The images of passing vehicles are taken at surveillance system and those images will be processed. The Proposed method uses simple morphological open and close operations using different structuring elements for plate feature extraction, Labeling the connected pixels, searching the plate location based on Geometrical conditions, segmenting the number plate and character recognition with Neural Network of Multilayer Perceptron. We have proposed a new method for plate segmentation based on Labeling. This method has been tested using a database of Indian number plates and results achieved have shown the high detection rate than existing methods.