将数学形态学中的高帽变换算法应用于液位高度的检测之中。利用形态学高帽变换,并选用大结构元素,对具有复杂背景的比色皿中的液位图像和分层液位图像进行处理,实现了液位高度的快速准确检测。实验结果表明,该方法适用于医学生化分析仪比色皿中样品液位高度的检测,其原理也可以用于其他工业装置中的液位高度检测。 The high-hat transformation algorithm in mathematical morphology is applied to the detection of liquid level. Using the morphological high-cap transformation, and selecting large structural elements, liquid level images and layered liquid level images in the cuvette with complex backgrounds are processed to achieve fast and accurate detection of liquid level height. The experimental results show that this method is suitable for the detection of sample liquid level in the cuvette of medical biochemical analyzer. The principle can also be used for the liquid level detection in other industrial devices.