论文部分内容阅读
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 5 1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
Firstly, the RGB image is transformed into a grayscale image, and then the histogram equalization and local median filtering are used to improve the contrast of the image. The threshold segmentation technique and two The value processing method extracts the number of bubbles, and calculates the area, shape and perimeter of the bright spots, and obtains the particle size distribution of the bubbles. Through the study of 5 1 slime flotation froth image, we find that this method is suitable for the image with obvious bright spots and large bubble size, which can be used to guide the slime flotation operation