基于改进的LBP的低分辨率车牌汉字识别  

Low-Resolution Chinese Character Recognition of Vehicle License Plate Based on an Improved LBP

作　　者：王叶[1] 张洪刚[1] 方旭[1] 郭军[1] 

机构地区：[1]北京邮电大学模式识别与智能系统实验室,北京100876

出　　处：《中文信息学报》2009年第5期86-91,共6页Journal of Chinese Information Processing

摘　　要：低分辩率的车牌汉字识别是字符识别中的一个难题。随着智能交通和模式识别技术的发展,传统的基于二值图的识别方法已不能满足实际要求。该文采用基于灰度图的汉字识别方法,避免了在传统二值化过程中不必要的结构信息丢失。该文将局域二值模式(Local Binary Patterns,LBP)算子运用于字符识别,使得车牌汉字的识别率由过去的74.25%提高到98.80%;并在已有的局域二值模式算子的基础上提出了一种改进的局部二值模式(Advanced Local Binary Pattern,ALBP)算法,使得汉字的识别时间大幅度缩短。实验结果表明,该文提出的方法对于低质量的车牌灰度汉字具有较强的鲁棒性,与传统识别方法相比,识别准确率和识别速度都有了较大的改进。Low resolution Chinese character recognition of vehicle license plate is a challenge issue in the character recognition. With the development of intelligent traffic, the traditional approaches based on binary images cannot meet the practical requirement. This paper applied a gray-scale image based recognition approach, avoiding the undesired structural information loss from the traditional blnarization process. We introduce Local Binary Patterns （LBP） into Chinese characters recognition for the first time and achieve good results. In addition, we present an improved and efficient Advanced LBP（ALBP） operator as feature extraction, which further improves the processing speed. Experiments prove our approach is robust against low quality characters, and it is more adaptive than conventional approach both on precision （from 74.25% to 98.80） and recognition speed.

关 键 词：人工智能 模式识别 汉字识别 ALBP 识别准确率 识别速度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]