Fruit size nondestructive detection method based on orthogonal binocular machine vision

Abstract

The invention discloses a fruit size nondestructive detection method based on orthogonal binocular machine vision. Two industrial cameras with the orthogonal central axes are adopted to carry out image acquisition on an object; then an acquired image is subjected to preprocessing, characteristic quantity extraction and reasonable algorithm calculation through an MATLAB algorithm to obtain a top view standard contour graph and a side view standard contour graph; the side view standard contour graph is subjected to data processing to obtain the distance from the maximum fruit diameter surface tothe fruit bottom, which is called the height of the fruit diameter surface; the top view standard contour graph is subjected to data processing to obtain the calculated fruit diameter; by combining the height of the fruit diameter surface, a height proportion coefficient k is introduced for correcting the calculated fruit diameter to obtain the fruit diameter with a relatively small error; and then comparison is carried out based on the national fruit grading standard, so that the nondestructive measurement of the fruit size is realized. The method has the characteristics of standardization,high efficiency, high precision and damage detection, thereby having an important research significance.

Description

technical field [0001] The invention relates to the technical field of fruit detection, in particular to a nondestructive detection method for fruit size based on orthogonal binocular machine vision. Background technique [0002] At present, the classification of fruit size in China mainly relies on manual and mechanical implementation. The maximum axial diameter is measured by human eyes or vernier calipers as the fruit diameter. Due to the large difference in fruit shape, the maximum axial diameter is not easy to grasp. Manual grading errors are very large, and in the grading process, the work is cumbersome, the efficiency is low, and it is easy to cause serious damage to the fruit. At the same time, there are strong subjective factors. This kind of grading method can no longer meet the needs of fruit grading. [0003] In recent years, the detection method has gradually turned to the direction of machine vision, which can realize non-destructive testing, and has the charac...

AI Technical Summary

Problems solved by technology

[0002] At present, the classification of fruit size in China mainly relies on manual and mechanical implementation. The maximum axial diameter is measured by human eyes or vernier calipers as the fruit diameter. Due to the large difference in fruit shape, the maximum axial diameter is not easy to grasp. Manual grading errors are very large, and in the grading process, the work is cumbersome, the efficiency is low, and it is easy to cause serious damage to the fruit. At the same time, there are strong subjective factors. This kind of grading method can no longer meet the needs of fruit grading.

[0003] In recent years, the detection method has gradually turned to the direction of machine vision, which can realize non-destructive testing, and has the characteristics of high efficiency and high accuracy. Nowadays, machine vision technology is widely used in product classification, such as eggs, citrus, pears, etc. There are many varieties, different sizes and shapes, and less research on fruits with complex structures

Images