| 基于图像匹配和验证识别的元件型号检测 |
| |
| 引用本文： | 张慧,罗兵.基于图像匹配和验证识别的元件型号检测[J].五邑大学学报(自然科学版),2013(4):63-67. |
| |
| 作者姓名： | 张慧 罗兵 |
| |
| 作者单位： | 五邑大学信息工程学院,广东江门529020 |
| |
| 基金项目： | 广东省产学研项目（20108090400026） |
| |
| 摘 要： | 电子制造业的电路板元件贴片安装检测中，需要根据元件上的字符图像来检测其型号是否正确．现有的整体匹配方法误检率高，且无法检测不同批次字符字体差异的元件．本文设计了位置校正后字符匹配的快速检测方法，对于更换元件批次后的字体差异则采用字符图像分割后进行验证性识别，并重新建模．实验结果表明了本方法具有高效，无漏检，误检率低等特点．
|
| 关 键 词： | 光字符验证 光字符识别 图像匹配 贴片安装技术 神经网络 |
SMT Components Model Inspection Based on Character and Image Matching and Verification |
| |
| ZHANG Hui,LUO Bing.SMT Components Model Inspection Based on Character and Image Matching and Verification[J].Journal of Wuyi University(Natural Science Edition),2013(4):63-67. |
| |
| Authors: | ZHANG Hui LUO Bing |
| |
| Institution: | (School of Information Engineering, Wuyi University, Jiangmen 529020, China) |
| |
| Abstract: | In the installation and testing of circuit board components, the component model has to be identified based on the characters and images on the components. The existing holistic matching method is prone to high false detection rate and cannot test components of different batches and of different characters and fonts. This paper presents a method for rapid detection of character matching after position correction. Identification of font differences is conducted of replaced batches of components after character and image segmentation and remodeling. The experimental results show that this method has the advantages of high efficiency, zero missing rate and low false detection rate. |
| |
| Keywords: | optical character verification optical character recognition image matching mountedtechnology neural network |
| 本文献已被 维普 等数据库收录！ |
