A method for counting round particles based on Android platform

Abstract

The invention relates to a method for counting round-like particles based on an Android platform, and belongs to the technical field of image processing. Firstly, a binary image containing only round particles is extracted from the background based on the color difference feature; the cohesive and overlapping particle block area in the image is extracted and the particle block area is segmented for the first time with a segmentation method based on distance transformation and H-minima; an accurate The method of extracting the pores on the surface of the particles, and performing the second watershed segmentation on the particle block area after the holes are filled, removing noise points and a small amount of shadow areas through connected domain analysis, and finding the smallest circumscribed circle of the outermost contour of each particle and drawing it on In the original picture, the number of circles is the number of particles. The counting system of the present invention reduces the cost of hardware usage; the present invention greatly suppresses the over-segmentation and mis-segmentation caused by the traditional segmentation method, and can accurately detect a large number of tightly cohesive single-layer particles and simple two-layer round particles, and can obtain relatively High counting accuracy and counting efficiency.

Description

technical field [0001] The invention relates to a system and method for counting round particles based on an Android platform, belonging to the technical field of image processing. Background technique [0002] In various application fields such as agriculture, industry, and medical care, it is often necessary to count the number of round particles (such as crop seeds, steel bars, cells, etc.). The traditional method is to determine the number of particles through human judgment. Since the human eye is prone to fatigue after long-term high-intensity work, the accuracy of counting is difficult to guarantee, and it is difficult to achieve manual counting in many workplaces (such as pills on the industrial assembly line, cruising in the river) duck count). With the improvement of computer technology and image processing technology, there are many researches on the automatic analysis system of quasi-circular particles based on digital image processing. number. Among them, the...

AI Technical Summary

Problems solved by technology

The traditional method is to determine the number of particles through human judgment. Since the human eye is prone to fatigue after long-term high-intensity work, the accuracy of counting is difficult to guarantee, and it is difficult to achieve manual counting in many workplaces (such as pills on the industrial assembly line, cruising in the river) duck count)

Images