欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2013, Vol. 30 ›› Issue (1): 137-143.DOI: 10.7523/j.issn.1002-1175.2013.01.021

• 简报 • 上一篇    

一种用于车牌识别的图像超分辨率算法

姚振杰, 易卫东   

  1. 中国科学院研究生院, 北京 100049
  • 收稿日期:2012-03-07 修回日期:2012-03-16 发布日期:2013-01-15
  • 通讯作者: 姚振杰
  • 基金资助:

    中国科学院百人计划(99T300CEA2);国家科技重大专项(2010ZX03006-001-02)和国家高技术研究发展计划(2009AA12Z143)资助

Image super-resolution approach for license-plate recognition

YAO Zhen-Jie, YI Wei-Dong   

  1. Graduate University, Chinese Academy of Sciences, Beijing 100049, China
  • Received:2012-03-07 Revised:2012-03-16 Published:2013-01-15

摘要:

仿效人类的视觉认知过程,提出面向目标的图像超分辨率算法.只需从一幅车牌图像就可以恢复目标的细节信息.该算法使用先检测、后重建的思路,通过联合稀疏编码建立目标高低分辨率图像片之间的关系,以目标可以稀疏表示为先验,检测到目标区域后,通过压缩感知重建图像.实验表明,重建图像的峰值信噪比(PSNR)较传统方法约有2dB的改善.此外,还验证了超分辨率重建改善了车牌识别结果,可以消除20%的错误识别字符.

关键词: 面向目标, 超分辨率, 压缩感知, 稀疏编码, 邻接特征

Abstract:

An object-oriented image super-resolution approach is proposed, which imitates visual cognition of human beings. The reconstruction procedure needs only a single image of the license plate. In the training stage, the corresponding relationship between high and low image patches is built by combined sparse coding. After an object is detected, the low resolution object image is reconstructed by compressing sensing under assumption of sparse representation. Experimental results on license plate images show that the PSNR is improved by nearly 2 dB compared to conventional non-object oriented strategy, and 20% of misrecognized characters are correctly recognized after reconstruction.

Key words: object oriented, super-resolution, compressed sensing, sparse coding, neighbor feature

中图分类号: