Automatic car registration plate recognition using fast Hough transform

Abstract

The development of automatic car registration plate recognition will provide greater efficiency for vehicle monitoring in automatic zone access control. Plate recognition will avoid the need to equip vehicles with special RF tags, since all vehicles possess a unique registration number plate. Also the proposed recognition system can be used in conjunction with a tag system for higher security. There are a number of techniques which have been used for car registration plate characters recognition. These systems include BAM (Bi-directional Associative Memories) neural network character recognition and pattern matching of characters as two character recognition techniques which will be discussed in this paper. The object of this paper is to explore the potential of using Fast Hough Transform (FHT) in vehicle registration plate recognition. Image processing techniques have been used to extract plate characters, then FHT algorithm is applied to every character in the image for recognition and identification. The FHT used in the paper is an efficient, fast and simple algorithm to identify characters, without requiring a relatively large memory.