Fruit body outer contour deformity detection method

Abstract

The invention discloses a fruit body outer contour deformity detection method which comprises the following steps: S1, collecting a color image of a fruit outer contour, and converting the color imageinto a grayscale image; S2, performing image segmentation processing on the grayscale image, and extracting a boundary region of a fruit body in the image by adopting a canny algorithm; S3, pixel point coordinates of the fruit body boundary are obtained clockwise by adopting a pixel tracking method for the fruit body boundary; S4, judging the concavity and convexity of the outer contour of the fruit body by adopting a right-hand rule; and S5, comparing the number of concave property points of the outer contour of the fruit body with a preset threshold value to judge whether the fruit body isrejected or reserved. According to the method, the degree of concave-convex defects on the surface of the fruit body is detected by using software based on a computer, so that the abnormal fruit bodyis removed at a certain precision and speed, a good foundation is laid for subsequent classification, and the classification quality of the fruit body is improved.

Description

technical field [0001] The invention relates to the technical field of fruit body external defect detection, in particular to a method for detecting fruit body external contour deformity. Background technique [0002] In the fruit deformity detection technology, in the prior art, the blade mouth on the hardware moves on the elevator, and under the effect of pressing down the fruit, the blade can cut off the deformed part of the fruit. In addition, in the prior art defect detection method for fruit in the tank, the optical axis is irradiated along the tangential direction of the surface of the tank body, and diffuse reflection and shadows are generated on the concave-convex part to detect the defect part of the fruit body. However, the fruit body defect detection methods in the prior art are all based on industrial mechanical devices to detect fruit body defects, which not only requires hardware equipment for technical support, but also has low detection accuracy due to exter...

AI Technical Summary

Problems solved by technology

However, the fruit body defect detection methods in the prior art are all based on industrial mechanical devices to detect fruit body defects, which not only requires hardware equipment for technical support, but also has low detection accuracy due to external interference during the fruit body defect detection process. Even after defect detection, there are still deformed fruit bodies

Images