Image detection method for automatically detecting straws left in grains

Abstract

The invention discloses an image detection method for automatically detecting straws left in grains. The method herein includes the following steps: firstly acquiring an original image; performing adaptive average filtering on the original image, blurring the image, configuring the blurred image as a background image; subtracting the background image with the original image, obtaining an edge enhanced image; converting the edge enhanced image to a gray image, performing adaptive gray equalization, and performing variance binaryzation on the maximum intraclass variance, also acquiring a binaryimage, performing open-operation on the binary image and remove noisy points; performing connected domain labeling on the binary image, performing initial screening on straw targets by comparing the number of the pixel points in the connected domain; drawing the minimal bounding rectangular of the connected domain, screening the straw targets in accordance with the length of the diagonal line of the rectangular; and drawing the profiles of the straws in the original image. According to the invention, the method herein can reduce the influence on the result of the detection by stacking and illumination; and overcomes the difficulty of differentiating similar colors by using the infrared method.

Description

technical field [0001] The invention relates to image processing technology, in particular to an image processing method for quickly and automatically detecting residual straw in grains processed by a threshing machine. Background technique [0002] At present, when the agricultural machinery is harvesting rice, it needs to peel the rice. During the peeling process, there will be a lot of broken straw in the piles of grains, so it needs to be screened repeatedly to remove the straw. , so that the number of broken straws is within the allowable range. In the traditional method, when judging whether the crushed straw is sieved clean, it can only be observed with human eyes, and then it is determined whether it needs to be sieved again. This method is not only inefficient but also has subjective errors. There are factors such as high temperature, noise, and insecurity in the production site environment. Applying image processing technology to the automatic detection of residu...

AI Technical Summary

Problems solved by technology

Third, the image processing is also affected by the illumination, because uneven illumination leads to errors in the results of image processing

Method (1) requires that there is basically no stacking in the straw and grain images, and the processing situation is not ideal in the case of stacking

Method (2) requires a near-infrared camera, which is expensive and not suitable for commercialization

Images