A Fruit Surface Defect Detection Method Based on Gradient Iterative Threshold Segmentation

Abstract

The invention discloses a method for detecting fruit surface defects by virtue of segmentation of a gradient iteration threshold. The method comprises the steps of firstly removing the background of an RGB color image, carrying out binaryzation on the RGB color image, independently extracting edges, carrying out expansion once to obtain an outline edge expansion image, converting the RGB color image into a gray level image, calculating a normalized gradient image, then carrying out gradient iteration calculation to obtain an image segmentation threshold, segmenting according to the image segmentation threshold to obtain a gradient binarization image, subtracting the outline edge expansion image from the gradient binarization image to obtain a difference image, and finally carrying out expansion hole filling corrosion and median filtering treatment on the difference image so as to obtain a fruit surface defect image. According to the method, the defect that different luminance characteristics of the surface are detected when the surface luminance of a globoid is not uniform is overcome; the image processing speed is high, and the program implementation is easy; and the method has application potential in the visual online detection of fruit and agricultural product quality computers.

Description

technical field [0001] The invention relates to a computer vision image processing method, in particular to a fruit surface defect detection method based on gradient iterative threshold segmentation. Background technique [0002] Surface defect detection is one of the important basis for fruit grading, which is strictly regulated in the fruit grading standards of countries all over the world. A large number of scholars at home and abroad have studied the detection of surface defects of fruits and agricultural products by means of computer vision. However, many agricultural products are spherical, and the gray value in the middle of the two-dimensional graphics is much larger than the gray value of the edge, which leads to difficulties in the detection of surface defect images. [0003] After searching the existing technologies, it is found that the methods are mainly divided into three categories: [0004] 1) The processing method based on the spherical gray scale model. F...

AI Technical Summary

Problems solved by technology

J.Blascoa et al. used multi-spectral imaging equipment for navel orange surface defect analysis. This method has high hardware cost and complexity (2007) (J.Blascoa,N.Aleixos.(2007).Citrus sorting by identification of the most common defects using multispectral computer vision. Journal of Food Engineering 83(2007) 384–393)

[0007] Existing methods have the problems of limited detection of surface defects and complex algorithms that are difficult to use for online detection or rely on complex hardware imaging technology with high cost. Therefore, new detection methods for fruit surface defects are needed

Images