利用阈值分割技术提取煤泥浮选泡沫图像的物理特征

探讨了煤泥浮选泡沫图像特征的提取方法，首先将RGB图像转化为灰度级图像，再采用直方图均衡化和局域中值滤波处理，以改善图像的对比度，利用阈值分割技术和二值化处理方法提取了气泡的个数，对亮点的面积，形状，周长进行了计算，求出了气泡的粒度分布，通过对51幅煤泥浮选泡沫图像的研究。发现该方法适用于亮点明显，气泡粒度大的图像，可以用来指导煤泥浮选的操作。

Threshold segmentation technology applied to get physical features of foam image from slime floatation

The paper discussed the method to get the foam image features of slime floatation. It is first to convert the RGB image in to a gray level image, then to use histogram equalization and local middle point filtration wave to improve contrast of the image. The threshold segmentation and thresholding can be applied to get the number of the bubbles and to calculate the area, sharp and perimeters of the bright points. It also can calculate the particles distribution of the bubbles. After a study on 51 foam images of the slime floatation, the method is suitable for the image with bright point and large bubbles and can guide the operation of the slime floatation.