作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (04): 209-211. doi: 10.3969/j.issn.1000-3428.2007.04.073

• 人工智能及识别技术 • 上一篇    下一篇

基于信息融合技术的集装箱号码自动识别系统

潘 巍1,王阳生2,杨宏戟3   

  1. (1. 首都师范大学信息工程学院,北京 100037; 2. 中国科学院自动化研究所模式识别国家重点实验室,北京100080; 3. Software Technology Research Laboratory, De Montfort University, Leicester, England LE19BH)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-02-20 发布日期:2007-02-20

Automatic Container Code Recognition System Based on Information Fusion Technology

PAN Wei 1, WANG Yangsheng 2, YANG Hongji 3   

  1. (1. Institute of Information Engineering, Capital Normal University, Beijing 100037; 2. State Key Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080; 3. Software Technology Research Laboratory, De Montfort University, Leicester England LE19BH)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-02-20 Published:2007-02-20

摘要: 运用信息融合技术进行集装箱号码自动识别系统的设计。根据集装箱号码的特性、组成规律及分布特点,在预处理阶段,采用了基于产生式规则的融合算法。该算法采用串行融合的方式并生成了一系列的规则,能够快速准确地输出具有较高质量的号码分割图,为后续的特征提取和号码识别提供更精确的信息。使用了3种不同类型的特征提取方法,分别生成基于神经网络的分类器,并将各自的分类结果通过D-S证据理论进行融合以完成最终的决策,提高了系统的识别率。该系统对光线与阴影具有较强的鲁棒性,结构简单、快捷有效,在实验中得到了满意的效果。

关键词: 信息融合, 自动识别, 集装箱

Abstract: This paper introduces a simple and valid automatic container code recognition system based on information fusion. According to the characteristics and distribution rules of container codes, a series of production rules are proposed to divide the codes more properly thus provides more precise information for feature extraction and code classification. In order to get higher correct rate, three neural networks classifiers with three different feature exaction methods are used separately, then the results are fused by D-S evidence theory to get final decision. The system is robust to varying light and shadows and gets satisfied results in experiments.

Key words: Information fusion, Automatic recognition, Container