Apple postharvest field classification detection method and system based on embedded technology

Abstract

The invention relates to the implementation process of an apple postharvest field classification detection method and system based on the embedded technology. The detection system mainly comprises an ARM processor, a stepping motor module, an image acquisition module, and a classification executing module. The stepping motor module is used to transfer apples in a rolling manner. A CMOS can be used to acquire the image of the whole pericarp of an apple and transfer the image to the ARM through a USB, and matching can be performed the image and an established classifier to realize the apple defect and size detection, and a control signal is sent to the classification executing mechanism. The classifier is an improved AdaBoost algorithm based on Haar-like features, risk factors are introduced, so the algorithm has advantages of better robustness and adaptivity. The improved genetic algorithm is adopted to perform optimization on the weighted values of samples, and improved crossover operators and improved mutation operators are adopted, so the convergence ability of the genetic algorithm can be ensured, and the optimization ability of the algorithm can be improved. According to the invention, the apple defect and size rapid and accurate classification can be ensured.

Description

technical field [0001] The invention relates to the technical field of non-destructive testing of agricultural products, in particular to a rapid detection system and method for apple skin defects and sizes. Background technique [0002] my country is a large country of fruit trees in the world, with a long history of cultivation and rich resources, ranking among the top in the world. However, due to insufficient post-harvest treatment, it is difficult to guarantee the quality of export and lack of competitiveness in the international market. There are many reasons for this, one of which is important The means of detection and classification are backward. [0003] Post-harvest field pre-sorting of apples refers to a process in which fruit farmers classify and inspect post-harvest apples in the field. On the one hand, it can help fruit growers to achieve graded sales of apples and improve economic benefits; on the other hand, it can reduce cross-infection between diseased app...

AI Technical Summary

Problems solved by technology

Although the apple grading detection system has been applied to the market at home and abroad, the upper computer is mainly a PC, which is bulky, not easy to carry, and expensive, ranging from milli

Images