基于图像识别的铝塑包装材料边缘检测-包装工程.PDFVIP

第38 卷 第 13 期 包 装 工 程 2017 年7 月 PACKAGING ENGINEERING ·154 · 基于图像识别的铝塑包装材料边缘检测 刘俊琪 （许昌学院，许昌 461000 ） 摘要： 目的 为了提高铝塑类包装材料的边缘检测精度，基于图像识别技术设计一种边缘检测方法。方 法 介绍Canny 边缘检测算法，针对其双阈值选择比较困难、边缘检测精度不高等问题，利用Ostu 算法 实现高、低阈值的选取。基于FPGA （现场可编程门阵列）和DSP （数字信号处理器）搭建一种图像检 测系统，并给出系统框图及FPGA 内部结构，即异步FIFO 模块、串入并出模块、像素窗口刷新模块、 数据处理模块以及配套电路等，并以药品铝塑泡罩包装为例进行实验研究。结果 改进的Canny 算法在 保证处理速度的前提下，所检测图像清晰细致，能够得到完整边缘。结论 该方法具有准确度高、稳定 可靠、识别速度快等特点，可满足包装过程产品检测要求。 关键词：边缘检测；图像识别；铝塑材料；Canny 算法 中图分类号：TB484.4; TB487 文献标识码：A 文章编号： 1001-3563(2017)13-0154-05 Edge Detection of Aluminum-Plastic Packaging Materials Based on Image Recognition LIU Jun-qi (Xuchang University, Xuchang 461000, China) ABSTRACT: The work aims to improve the edge detection accuracy of aluminum-plastic packaging materials, and de- sign an edge detection method based on image recognition technology. The Canny edge detection algorithm was intro- duced. As for such problems as difficult double threshold choice and the low edge detection accuracy, high and low thre- sholds were selected based on Ostu algorithm. An image detection system was built based on FPGA (field-programmable gate array) and DSP (digital signal processor), and the system block diagram and the FPGA internal structure were given, namely asynchronous FIFO module, serial-in parallel-out module, pixel window refresh module, data processing module and matching circuits etc. The experimental studies were carried on with aluminum-plastic bubble cap drug package as example. The experimental results showed that the improved Canny algorithm could obtain clear and detailed