Self-adaption improved gradient information-based fruit surface defect detection method

Abstract

The invention discloses a self-adaption improved gradient information-based fruit surface defect detection method. The method comprises removing background of a RGB color image, carrying out binaryzation, individually extracting edge, carrying out expansion once to obtain a contour edge expansion image, converting the color image into a gray level image, carrying out calculation to obtain a normalized gradient image, carrying out statistics by a gradient histogram so that gradient information self-adaption improvement is realized, automatically calculating an image segmentation threshold value, acquiring an improved gradient binary image by image threshold segmentation, removing the contour edge expansion image of the improved gradient binary image to obtain a difference image, carrying out expansion hole-filling corrosion and median filtering treatment on the difference image to obtain a fruit surface defect image. The method realizes detection of surface different brightness characteristic defects under the condition of nonuniform globoid surface brightness, utilizes image segmentation threshold self-adaption calculation, is free of artificial selection, can be realized easily, and has an application potential in fruit and agricultural product quality machine vision on-line detection.

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 self-adaptive improved gradient information. 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. ...

AI Technical Summary

Problems solved by technology

J.Blascoa et al. used multi-spectral imaging equipment to analyze the surface defects of navel oranges. 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