基于图像特征的车脸栅格的定位方法  

Localization method of car face grid based on image features

作　　者：张有芬 李玉惠[1,2] 潘艺 ZHANG You-fen LI Yu-hui PAN Yi(School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China Intelligent Image Processing Research Center of Intelligent Transportation System Engineering Technology Research Center of Yunnan Province, Kunming 650500, China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500 [2]云南省智能交通系统工程技术研究中心智能图像处理研究室,云南昆明650500

出　　处：《传感器与微系统》2017年第9期64-66,共3页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(61363043)

摘　　要：为了解决智能交通系统中车型识别的瓶颈,找到能够准确定位车标的方法,提出了在Adaboost算法定位出的车脸的基础上,对车脸图像进行二值化处理,经过二值化图像的水平梯度和垂直梯度的投影定位栅格的方法,为后续车标的识别提供了一种新的方法。经过实验验证:方法无论从理论上还是实际应用中,具有重要的意义。In order to solve the bottleneck of vehicle recognition in intelligent transportation system,and find a way to accurately locate the vehicle logo,a new method is presented based on the Adaboost algorithm to locate the car face. After binaryzation image processing,projection of the horizontal gradient and vertical gradient of the binaryzation image is used to locate the grid,provide a new method for identification of the subsequent logo.Experimental results show that this method is of great significance both in theory and in practice.

关 键 词：ADABOOST 车标识别 车标定位 栅格定位 

分 类 号：TN919[电子电信—通信与信息系统]