Nondestructive testing method and system for internal structure of fruit, electronic equipment and medium

Abstract

The invention relates to the technical field of nondestructive testing of agricultural products, and aims to provide a nondestructive testing method and system for an internal structure of a fruit, electronic equipment and a medium. The method comprises the following steps: constructing a primary fruit element recognition model based on a neural network; obtaining a first fruit image and first labeling information corresponding to the first fruit image, and performing optimization processing on the primary fruit element recognition model through the first fruit image and the first labeling information to obtain an optimized fruit element recognition model; obtaining a to-be-detected fruit image, and inputting the to-be-detected fruit image into the optimized fruit element recognition model for processing to obtain final labeling information corresponding to the to-be-detected fruit image; and obtaining a redrawing image corresponding to the to-be-detected fruit image according to the final labeling information. According to the invention, nondestructive testing of the internal structure of the fruit can be realized, and an important basis is provided for the quality requirement of the fruit.

Description

technical field [0001] The invention relates to the technical field of nondestructive testing of agricultural products, in particular to a nondestructive testing method, system, electronic equipment and medium for the internal structure of fruits. Background technique [0002] Existing techniques for judging the pulp of durian and other fruits are mainly based on the appearance and outline of the human eye, which has great uncertainty, and it is difficult to judge the size of the pulp, the size of the core, whether there is empty room, whether there are insects and the thickness of the shell, etc. To solve this technical problem, in the prior art, there has been a non-destructive testing technology for agricultural products. After imaging shell fruits such as durian, jackfruit, coconut or dragon fruit, the size, number, proportion, etc. of the fruit pulp can be measured and provided. Show to consumers to reduce information asymmetry problems such as consumers do not know the...

AI Technical Summary

Problems solved by technology

[0003] At present, in the direction of computer vision, artificial intelligence and machine learning technology are developing rapidly, which are widely used in medical, industrial and other fields, but there is no large-scale machine learning case in the field of fruit imaging

In addition, due to the particularity of the fruit itself, the existing segmentation techniques such as medical images are not suitable for fruit imaging, so that the existing techniques cannot be applied to the identification of the internal structure of fruits

Images