Rice grain counting method

Abstract

The invention discloses a rice grain counting method which comprises the following steps: reading a grain image, and preprocessing the grain image to obtain a grain binary image; performing statistics on a grain communication region of the grain binary image, deleting and filling the grain communication region, and performing statistics on a gray level histogram of the grain communication region; carrying out convolution operation on the gray histogram, and then carrying out curve fitting to obtain a fitted curve; according to the obtained fitting curve, determining a threshold value, calculating the area of the grain communication region, and obtaining an area distribution curve graph; according to the area distribution curve graph, calculating the area value of a single grain, and obtaining the total number of grains contained in the image by dividing the area of the grain communication region by the area of the single grain. According to the rice grain counting method, fine and expensive equipment is not needed, the cost is low, operation is easy, implementation is easy, when grain images are shot, certain-degree adhesion between grains is allowed, manual intervention is not needed, and the labor cost is saved.

Description

technical field [0001] The invention relates to the technical field of agricultural production, in particular to a method for counting rice grains. Background technique [0002] In agricultural production and research, it is often necessary to count the number of rice grains to further detect various morphological parameters of the grains. Manual counting is a more traditional way of counting. However, the disadvantage of manual counting is that when the counting time is too long, the human eyes are prone to visual fatigue after continuous high-intensity work. Not only is it difficult to ensure the accuracy of counting, but also the counting efficiency is low, and fast and accurate counting cannot be achieved requirements. Therefore, it is of great practical significance to realize the automatic statistics of the number of grains and improve the efficiency and accuracy of counting. [0003] In recent years, with the wide application of digital image processing and pattern...

AI Technical Summary

Problems solved by technology

[0006] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is that the existing grain counting is usually manual counting. When using image processing to count the grains, it is necessary to manually place the grains at intervals, which also consumes a lot of time. Manpower, and when there is grain sticking, the calculation accuracy is not high; the image processing method with accurate counting needs multiple expensive equipment assistance, and the operation requirements are relatively high

Images