Research on the License Plate Recognition Based on Image Processing
In order to enhance the effects of license plate recognition in intellectual transport domain,this article carries out positioning,partitioning and characteristics extracting on license plate images that have been collected,so as to realize the function of license plate character recognizing.In order to boost the contrast on a license plate and to reduce noises,methods of gray degree reinforcing and filtering treating are adopted to carry out gray degree transformation; in order to accurately position the location of license plate characters,adopt Ostu algorithm to work out global threshold value,extract image edges,and make a second positioning on the license plate with projection method,thus a binary license plate image can be acquired; partition characters according to peak-group characteristics of vertical projecting figures,and adopt improved template-matching algorithm to realize accurate and efficient license plate recognizing.The research findings of this article have important theoretical values and practical application significance.
edge detection Canny operator morphology projection segmentation template matching character recognition
Chaofeng Lan Fengchen Li Yingjian Jin Xuemei Sui Shouqiang Kang Liping Zhang
School of Electrical and Electronic Engineering, Harbin University of Science and Technology Harbin Energy Science and engineering, Harbin Institute of Technology, 150001, China School of Electrical and Electronic Engineering, Harbin University of Science and Technology Harbin Sono Scape, Co., Ltd, Shenzhen, China Country
国际会议
秦皇岛
英文
731-734
2015-09-18（万方平台首次上网日期，不代表论文的发表时间）