Recognition and sorting method of coal gangue based on gangue-free image filtering and blob analysis

Abstract

The invention discloses a method for identifying and sorting coal gangue based on gangue-free image filtering and BLOB analysis, comprising the following steps: collecting images of coal, and using computer software to calculate the third-order moments of the images received by an industrial computer to evaluate the third-order moments of the images to obtain the third-order moments of the images Moment evaluation value, compare the third-order moment evaluation value of the image with the set initial threshold, perform BLOB analysis on the image, and obtain the coordinates of the point in the upper left corner of the largest partition, the width and height of the distribution; the area where the partition is located Local evaluation of the third-order moment is performed on the scope to judge whether the current gangue is the marked gangue that has already sent an instruction. If so, no processing is performed. If not, a picking instruction is sent; the robot picks gangue. The invention can transition from the analysis of the whole image to the accurate analysis and judgment of the local attention area, reduces the interference of the background and stray objects to the identification, effectively identifies the coal gangue, and is beneficial to popularization and application.

Description

technical field [0001] The invention relates to the technical field of coal gangue, in particular to a coal gangue identification and sorting method based on gangue-free image filtering and BLOB analysis. Background technique [0002] In the coal gangue intelligent sorting system, the identification of moving coal and gangue on the conveyor belt is a key technology. The BLOB analysis method based on image threshold segmentation and connected domain marking can solve the problem of difficult extraction of edge contour points in coal gangue detection. It can locate the coal gangue distribution area, but for image processing with many BLOB partitions, it takes up more memory space and consumes more computing time, and the background of the coal transmission line is more complicated due to pollution. If the image is real-time BLOB analysis not only takes up a lot of computer time, but also may cause the program to jump out and make an error due to excessive memory usage, which a...

AI Technical Summary

Problems solved by technology

[0002] In the coal gangue intelligent sorting system, the identification of moving coal and gangue on the conveyor belt is a key technology. The BLOB analysis method based on image threshold segmentation and connected domain marking can solve the problem of difficult extraction of edge contour points in coal gangue detection. It can locate the coal gangue distribution area, but for image processing with many BLOB partitions, it takes up more memory space and consumes more computing time, and the background of the coal transmission line is more complicated due to pollution. If the image is real-time BLOB analysis not only takes up a lot of computer time, but also may cause the program to jump out and make an error due to excessive memory usage, which affects the online real-time detection of coal gangue

Images