Application of image processing techniques for the extraction of vehicle number plates over ARM target board

Correct recognition of vehicles violating traffic rules and regulations is a major challenge in the present complex traffic environment. Automatic Number Plate Recognition (ANPR) systems plays an important role in the detection of such events. ANPR systems are typically standalone systems using the capabilities of embedded processors for correct recognition. The limited processing capabilities hinders the efficient determination of location of number plates in such images satisfying the real time criteria. This paper presents an adopted method for the image preprocessing, image detection and extraction of standardized white background vehicle number plates. Application of suitable Gaussian Filters along with other image preprocessing techniques, Binary jumps and Image differencing techniques have been carried out in this work. An ARM Cortex A8 processor with 1GHz processor and 512 MB RAM has been selected as the candidate embedded processor in this work. Experiments show that the proposed method posses over 90% accuracy.