Ore particle size image segmentation method combining multi-feature and multi-level

Abstract

The invention discloses an ore particle size image segmentation method combining multi-feature and multi-level. In the segmentation method, bilateral filtering and local self-adaptive thresholding based on an integral image are first carried out for an image. Then, filtering and distance transformation are carried out for a binary image. Finally, after watershed transformation, the image and a binary image are overlaid to obtain a first layer segmentation. After the first layer segmentation, by use of a characteristic that adhesion of two ores leads to the presence of pits, a proposed circular template method is used for detecting all the initially segmented segment lines. If two sides of a segment line are provided with pits, the segment line is retained; and the incorrect segment line is removed otherwise. By use of the brightness and shape feature of the ore image for double-deck segmentation, an ideal result is obtained and therefore higher reliability is provided for subsequent particle size measurements. The ore particle size image segmentation method combining multi-feature and multi-level has the advantages of wide application range, good real-time, high precision, easy installation and low cost.

Description

technical field [0001] The invention relates to the field of image processing, and designs and implements a method for segmenting ore granularity images combining multi-features and multi-levels. Background technique [0002] Non-ferrous metals are an important part of contemporary energy, information technology and modern materials, and are widely used in national economy and national defense construction. However, the prominent problem facing us at present is that the crisis of mineral resources is becoming more and more serious. The proven reserves are far from meeting the needs of national economic development, and the degree of protection is poor, which seriously restricts our country's development strategy. At the same time, the scale of mining and dressing of non-ferrous metal mines in my country is small, and the level of automation is low, which leads to low utilization rate of mineral resources, directly causes the increase of production costs of enterprises, and m...

AI Technical Summary

Problems solved by technology

However, due to the complexity of the mining site, the particle size analysis of the collected ore images mainly has the following difficulties: 1. The lumens of the light sources at the mining site vary greatly, and the types and tastes of mining are different. To hundreds of millimeters, different exposure times, different shooting angles and positions lead to different image clarity. Images during high-speed transmission are prone to jitter, and the collected images are different environments, different content, and different light and dark images, which are difficult to process.

2. The content of the image is highly complex, some of which contain soil and water. How to accurately locate the numerous, mutually stacked, highly similar in color and shape, and mutually cohesive targets when the difference between the target and the background is small is another technology. difficulty

The reason why the current segmentation algorithm cannot be applied to the field of ore images is mainly because the methods used often only focus on the brightness features of the image, or other shape features of the image, and often use a single segmentation algorithm

From the above analysis, it can be seen that the ore target shape of the ore image is different, and the light and shade of the image are different. It is difficult to accurately segment the image simply by using one feature and a single method.

Images