Fruit appearance defect real-time on-line detection system and detection method

Abstract

The invention relates to the technical field of agricultural product nondestructive test, and especially relates to a fruit appearance defect real-time on-line detection system and a fruit appearance defect detection method. The detection system comprises a delivering unit used for rotating fruit to be detected and horizontally moving the fruits passing an image acquisition position; an image acquisition unit comprising a light box arranged on the delivering unit and positioned at the image acquisition position and a CCD camera positioned in the light box, a sensor arranged on at least one side of the delivering unit and used for detecting whether the fruit is arriving the image acquisition position, and a computer. An image acquisition card used for controlling the CCD camera for taking fruit surface images is arranged in the computer. An image sorting model used for analyzing the acquired fruit surface images and for determining whether the fruit is qualified is pre-stored in the computer. According to the invention, analysis treatment is only carried out upon the surface images taken by the CCD camera, and detection and grading of the fruits can be rapidly and accurately carried out.

Description

technical field [0001] The invention relates to the technical field of non-destructive testing of agricultural products, in particular to a detection system and a detection method for real-time on-line detection of appearance defects of approximately spherical fruits. Background technique [0002] my country is a big fruit producing and consuming country. At present, the annual fruit output has exceeded 100 million tons, ranking first in the world. With the in-depth reform of the rural economic system and the development of the market economy, fruit production will increase significantly year by year. At present, before the fruit enters the market, fruit processing and packaging companies usually have to test and grade the external quality of the fruit, such as size, shape, color and surface defects. The existing fruit detection and grading generally adopts the manual screening method, which requires a large number of laborers, has low work efficiency, and the subjective j...

AI Technical Summary

Problems solved by technology

However, in actual production applications, the purchase cost of the spectrometer is high, and the amount of collected information is also very large, and contains too much redundant information. If it is applied in real time online, the processing speed is very slow, resulting in a very slow detection speed

Images