Machine vision-based carrot surface defect identification and quantification method

Abstract

The invention relates to a machine vision-based carrot surface defect identification and quantification method comprising pretreatment of carrot images; a carrot fracture defect identification and quantification method, a carrot bending defect identification and quantification method, a carrot cracking defect identification and quantification method, a carrot root defect identification and quantification method and a carrot wormhole defect identification and quantification method. The defect identification and quantification methods for carrot fracture, bending, cracking, roots and wormholes use a CCD camera to obtain carrot real-time images and perform defect identification and quantification on the obtained real-time images based on image processing technology, which overcomes the subjectivity of manual detection, improves the objectivity and accuracy of defect identification quantification, and can increase production efficiency and reduce production costs when applied to processingand grading of agricultural production.

Description

technical field [0001] The invention relates to the technical field of agricultural product processing, in particular to a method for identifying and quantifying carrot surface defects based on machine vision. Background technique [0002] The grading sales of carrots will help to improve the market competitiveness and sales price of carrots, and increase the profits of carrot production enterprises. At present, carrot sorting is mainly done manually. This kind of sorting method has low efficiency, strong subjectivity, and not strict standards, and has inherent defects of manual sorting. And with the rise of labor costs, the profits of carrot processing enterprises have been further compressed. Manual sorting can no longer meet the production requirements of carrot processing enterprises. [0003] Machine vision provides a high-efficiency, low-cost and real-time online detection and grading method for fruits and vegetables. Using machine vision to grade carrots online can ...

AI Technical Summary

Problems solved by technology

[0004] At present, there is no relatively mature carrot sorting method based on machine vision in China. According to the domestic trade industry standard of the People's Republic of China (SB / T10450-2007) and the requirements for the purchase and sale of carrots (issued by the Ministry of Commerce of the People's Republic of China on December 28, 2007), the carrot The key indicators of the purchase and sale level include distortion, bending, cracking, blackheads, and insect damage. The measurement standards are relatively vague, which brings difficulties to the defect detection of carrots. It is necessary to quantify the defect indicators of carrots.

Images