基于分形维数和隐马尔科夫特征的车牌识别

耿庆田1; 赵宏伟1

doi:10.3788/OPE.20132112.3198

您当前的位置：

首页 >

文章列表页 >

基于分形维数和隐马尔科夫特征的车牌识别

信息科学 | 更新时间：2020-08-12

- 基于分形维数和隐马尔科夫特征的车牌识别
- License Plate Recognition Based on Fractal and Hidden Markov Feature
- 光学精密工程 2013年21卷第12期页码：3198-3204
- 作者机构：
  
  长春师范大学计算机科学与技术学院2. 吉林大学计算机科学与技术学院
- 作者简介：
- 基金信息：
  
  吉林省科技发展计划资助项目(20126016)
- DOI：10.3788/OPE.20132112.3198
  中图分类号： TP391.4
- 收稿日期：2013-07-09，
  
  修回日期：2013-08-23，
  
  网络出版日期：2013-12-25，
  
  纸质出版日期：2013-12-25
- 稿件说明：
移动端阅览
耿庆田赵宏伟. 基于分形维数和隐马尔科夫特征的车牌识别[J]. 光学精密工程, 2013,21(12): 3198-3204

GENG Qing-Tian ZHAO Hong-wei. License Plate Recognition Based on Fractal and Hidden Markov Feature[J]. Editorial Office of Optics and Precision Engineering, 2013,21(12): 3198-3204
耿庆田赵宏伟. 基于分形维数和隐马尔科夫特征的车牌识别[J]. 光学精密工程, 2013,21(12): 3198-3204 DOI： 10.3788/OPE.20132112.3198.

GENG Qing-Tian ZHAO Hong-wei. License Plate Recognition Based on Fractal and Hidden Markov Feature[J]. Editorial Office of Optics and Precision Engineering, 2013,21(12): 3198-3204 DOI： 10.3788/OPE.20132112.3198.

摘要

针对现有车牌识别方法中车牌二值化和车牌字符识别效率不高的问题，提出一种基于分形维数和隐马尔科夫特征的车牌识别算法。该方法基于分形维数和隐马尔科夫特征并利用联合OC_SVM和MC_SVM的方法进行车牌识别。实验中，基于分形维数进行车牌的二值化处理；利用隐马尔科夫特征办法进行字符特征提取，然后利用多重分类器进行字符识别。对字符、英文字母和阿拉伯数字分别进行了800幅、800幅和1600幅图像的识别，得到的结果显示该算法对字符、英文字母和阿拉伯数字的识别率分别为98%、98.5%和98.9%

对各种不同的车牌整体识别的平均识别率高于90.60%。该方法识别效率高、鲁棒性强，为车牌识别的准确性提供了保证。

Abstract

Because existing license plate recognition algorithm has lower efficiency in the binarization and character recognition

a license plate recognition algorithm based on fractal dimension and hidden Markov features was proposed. The algorithm is based on fractal dimension and hidden Markov features

and uses the joint classification of OC_SVM and MC_SVM to recognize license plates. In experiments

the fractal dimension was used complement the binarization of the license plate

the hidden Markov features were taken to extract character features and a multi-classifier was utilized to recognize the character. 800 Chinese character images

800 English letter images and 1600 Arabic numeral images were recognized

obtained results show that the recognition rates of Chinese characters

English letters and Arabic numerals are 98%

98.5% and 98.9%

respectively

the average recognition rate of license plates is more than 90.60%.It concludes that the method has higher efficiency

better accuracy and stronger robustness

and it can provide a guarantee for license plate recognition.

关键词

Keywords

references

［1］LI B, ZENG ZH Y, ZHOU J ZH. An adaptive license plate recognition system design methodology ［J］. Microelectronics & Computer, 2009, 26(4): 217-221.［2］ANAGNOSTOPOULOS C, ANAGNOSTOPOULOS I, PSOROULAS I, et al.. License plate recognition from still images and video sequences: a survey［J］. IEEE Transactions on Intelligent Transportation Systems, 2008, 9(3):377-391.［3］GIANNOUKOS I, ANAGNOSTOPOULOS C,LOUMOS V,et al.. Operator context scanning to support high segmentation rates for real time license plate recognition［J］. Pattern Recognition, 2010, 43, 3866-3878.［4］JIAO J B, YEQ X, HUANG Q M. A configurablemethod formulti-style license plate recognition［J］. Pattern Recognition, 2009, 42:358-369.［5］FARAD J F, REZAIE A H. A morphological-based license plate location ［C］. IEEE International Conference on Image Processing, 2006:57-60.［6］PATNAIK S, PAUNWALA C N, SHAH M,et al.. Novel edge mapping for license plate detection［C］. WCECS, 2011,10:19-21.［7］HUANG Y P, CHEN CH H, CHANG Y T. An intelligent strategy for checking the annual inspection status of motorcycles based on license plate recognition ［C］. Expert Systems with Applications, 2009, 36:9260-9267.［8］刘希佳, 陈宇, 王文生, 等. 小目标识别的小波阈值去噪方法［J］. 中国光学,2012, 5(3):248-256.LIU X J, CHEN Y, WANG W S, et al.. De-noising algorithm of wavelet threshold for small target detection［J］.Chinese Optics. 2012, 5(3):248-256.(in Chinese) ［9］赵星, 王芳, 杨勇,等. 集成成像三维显示系统显示性能的研究进展［J］. 中国光学,2012, 5(3) 209-221.ZHAO X, WANG F, YANG Y, et al.. Research progress of display performance of integral imaging three-dimensional display system［J］.Chinese Optics. 2012, 5(3):209-221.(in Chinese) ［10］孙辉, 李志强. 基于相位相关的匀速直线运动模糊图像位移参数估计［J］. 中国光学,2012, 5(2) 174-180.SUN H, LI Z Q. Estimation of displacement parameters for uniform linear motion-blurred images based on phase-only correlation［J］.Chinese Optics. 2012, 5(2) 174-180. (in Chinese) ［11］杨利红, 赵变红, 张星祥,等. 点扩散函数高斯拟合估计与遥感图像恢复［J］. 中国光学,2012, 5(2):181-188.YANG L H, ZHAO B H, ZHANG X X, et al.. Gaussian fitted estimation of point spread function and remote sensing image restoration［J］.Chinese Optics, 2012, 5(2):181-188. (in Chinese) ［12］宋建中. 图像处理智能化的发展趋势［J］.中国光学2011, 4(5):431-440.SONG J Z. Development trend of image processing intelligence［J］.Chinese Optics, 2011, 4(5):431-440. (in Chinese) .［13］WANG SH ZH, ZHAO S L, LAN K M, et al.. Multiple vehicles license plate tracking and recognition via isotropic dilation ［C］. CICSYN, 2011:54-59.［14］OUYANG J,LIU P.License plate character recognition based on BP neural network algorithm ［J］. Optoc & Optpelectronic Technology,2012, 5(10):67-71.［15］YAO ZH J, YI W D. Image super-resolution approach for license-plate recognition ［J］. Journal of Graduate University of Chinese Academy of Sciences,2013, 30(1):137-143.［16］邱家涛, 李玉山, 初秀琴. 稳定运动物体视频的特征方法［J］. 光学精密工程,2012,20(10):2300-2307.QIU J T, LI Y S, CHU X Q.. Feature-based approach for stabilizing videos with moving objects ［J］. Opt.Precision Eng., 2012, 20(10):2300-2307. (in Chinese) ［17］秦翰林,周慧鑫,刘群昌,等. 采用多尺度隐式马尔可夫模型的红外图像背景抑制［J］. 光学精密工程, 2011, 19(8)：1950-1956.QIN H L, ZHOU H X, LIU Q C, et al.. Suppression of infrared image background by multiscale hidden Markov model ［J］. Opt. Precision Eng., 2011,19(8)：1950-1956. (in Chinese)

浏览量

333

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合分形几何特征Resnet遥感图像建筑物分割

Si₃N₄陶瓷旋转超声磨削加工的表面摩擦特性

全景海域图像中的圆形海天线提取

采用脉冲耦合神经网络的改进显著性区域提取方法

采用局部分形的高效图像分割方法在红外云图处理中的应用