LIU Cong, WANG Chao, HOU Jianping, et al. Blood serum level detection in blood-collecting vessel based on image recognition[J]. 2021, (3): 149-152. DOI: 10.13873/J.1000-9787(2021)03-0149-04.
基于图像识别的采血管血清液位检测
摘要
系统通过工业相机采集采血管图像
对采集得到的图像进行中值滤波、RGB颜色分离、二值化、形态学处理、图像分割、液位识别
最终得到血清的上下液位的纵坐标。实验结果表明
所提方法具有较高的检测精度
液位检测结果精度可达到0.05 mm。通过血清上下液位的准确定位
可以用于调节仪器样本针采集血清
也可以根据血清高度对血清量不足进行提示。
Abstract
The system acquires the image of tubes through a industrial camera. Median filter
RGB color separation
binaryzation
morphological processing
image segmentation and serum level extraction are performed for the collected images. The vertical coordinates of top and bottom serum level is obtained. The experimental result shows that the method has a high accuracy
and measurement accuracy of serum levels can reach 0. 05 mm. The precise location of the top and bottom serum level can be used to adjust the instrument sample probe position and collect serum sample. The height of serum can be used to indicate serum deficiency.