Fruit surface defect detection method and system based on brightness correction and color classification

Abstract

The invention relates to a brightness correction and color classification-based fruit surface defect detection method and system. The method includes the following steps that: a R component image in an RGB image of fruit to be detected is extracted, brightness correction is performed on the R component image, so that the brightness of the R component image can be uniform; HSI transform is performed on the RGB image, so that an H value in the HSI transform corresponding to each pixel in the RGB image is obtained, the H values are compared with the H values of preset colors, so that the color of each pixel can be judged; and the color of each pixel is compared with a preset threshed value corresponding to the color, so that judgment can be performed, a defective region to be confirmed is obtained from the R component image which has been subjected to the brightness correction, the gray values of all pixels except the defective region to be confirmed in the R component image are zeroed, and based on further judgment, the gray values of recognized fruit stem / calyx regions in the defective region to be confirmed are zeroed, and finally, a defective region of the surface of the fruit can be obtained. With the method and the system of the invention adopted, the accuracy of fruit defect detection can be improved.

Description

technical field [0001] The invention relates to the field of vegetable and fruit detection, in particular to a method and system for detecting fruit surface defects based on brightness correction and color classification. Background technique [0002] my country's total fruit output ranks first in the world, and the output of apples and pears ranks first in the world. But at present, my country's fruit export volume accounts for a relatively low proportion of fruit output, which is mainly due to its relatively backward post-harvest processing technology. Taking apples as an example, apple dealers only roughly grade apples by size, and the grading methods mainly rely on manual work. Grading, the grading results are not accurate enough, and with the increase of labor costs, the cost of manual grading will become higher and higher. Using machine vision technology to classify apples can not only reduce labor costs, but also improve detection efficiency and detection accuracy. A...

AI Technical Summary

Problems solved by technology

[0003] One of the main reasons why apple surface defects cannot be detected online is that apples are usually spherical or ellipsoidal. At the edge of the apple, the angle between the reflection direction of light and the camera is very large. According to Lambert’s law of light reflection, from the direction of the camera, The brightness of the edge area of ​​the apple is low, and the gray value of the edge area is low in the collected apple image, and the remarkable feature of the apple surface defect is that it usually has a low gray value, which leads to the low gray value of the apple image. Both the edge area and the surface defect area of ​​the apple have low grayscale features, making it difficult to distinguish the two through image processing techniques

At the same time, because the fruit stem / calyx area of ​​the apple also shows low grayscale features in the image, this further increases the difficulty of detecting apple surface defects. Since the surface of the apple is a spherical curved surface, the middle area of ​​the apple image is caused The uneven distribution of brightness and edge area makes it difficult to accurately detect surface defect information in apple images

At the same time, due to the low gray value of the dark red area on the surface of the apple, the dark red area is easily detected as a defect area.

Therefore, there is no existing method to improve the accuracy of detecting fruit defects.

Images