A novel and robust method for automatic license plate recognition system based on pattern recognition

Abstract

In this paper, for finding the place of plate, a real time and fast method is expressed. In our suggested method, the image is taken to HSV color space; then, it is broken into blocks in a stable size. In frequent process, each block, in special pattern is probed. With the appearance of pattern, its neighboring blocks according to geometry of plate as a candidate are considered and increase blocks, are omitted. This operation is done for all of the uncontrolled blocks of images. First, all of the probable candidates are exploited; then, the place of plate is obtained among exploited candidates as density and geometry rate. In probing every block, only its lip pixel is studied which consists 23.44% of block area. From the features of suggestive method, we can mention the lack of use of expensive operation in image process and its low dynamic that it increases image process speed. This method is examined on the group of picture in background, distance and point of view. The rate of exploited plate reached at 99.33% and character recognition rate achieved 97%.