A Novel Algorithm of Character Segmentation in License Plates Recognition

The LPR(License Plate Recognition) system consists of three steps:license plate locating,character segmentation and character recognition.Character segmentation is an important step in a LPR system.There are many factors that cause the character segmentation task difficult,such as image noise,plate frame,rivet,space mark,plate rotation and illumination variance.This paper presents a new algorithm for character segmentation.Firstly,characters top-bottom edges can be obtained by searching from middle to end.And then,the single characters can be segmented using one-dim cycle clearing and prior knowledge.The experiment results show the good performance of the segmentation algorithm.