基于计算机视觉的空瓶检测系统

基金项目:

北京市教育委员会资助项目（KM200310005012）.

详细信息

Study on Machine Vision Based on Bottle Inspecting System

College of Mechanical Engineering and Applied Electronics Technology, Beijing University of Technology, Beijing 100022, China

摘要: 为了利用数字图像处理技术实现空瓶缺陷的自动检测,对啤酒瓶缺陷的光学特征进行了分析,研究了检测过程中的图像获取、图像预处理、图像分割、缺陷识别、外围设备通信控制等关键技术,实现了一个适用于实验室环境的、基于计算机视觉的小型空瓶缺陷在线检测系统.实验结果表明,该系统可有效地检测出有缺陷或异物等不合格空瓶.
- 计算机视觉 /
- 图像处理 /
- 图像分割
Abstract: For the purpose of detecting bottle flaws automatically with the computer vision technology, this paper analyzes the optical characteristics of the bottle flaws and studies the technology of image acquisition, image pre-processing, image segmentation, flaw recognition and peripheral device communication and control in the procedure of flaw detection. It implement a on-line flaw detection system based on computer vision technology which is suitable for the lab environment. The result demonstrates that the system can effectively inspect the defective empty bottles.
- computer vision /
- image processing /
- image segmentation