Automatic fruit and vegetable inspection method and system, electronic equipment and computer readable medium

Abstract

An automatic fruit and vegetable inspection method comprises the following steps: a fruit and vegetable video acquisition step: acquiring a video of fruits and vegetables to be inspected; a video processing step: processing the video into a plurality of pictures; a primary identification step: using a primary identification neural network to select pictures containing fruits and vegetables from the plurality of pictures; a feature extraction step: extracting a feature map of the image of the fruit and vegetable by using a feature extraction neural network for the selected image containing the fruit and vegetable; and a quality detection step: detecting a plurality of attributes of the fruits and vegetables based on the feature map by using a quality detection neural network. Image information containing various fruit and vegetable categories is collected to generate a training data set, and a neural network is trained based on the training data set to obtain a primary recognition neural network, a feature extraction neural network and a quality detection neural network. According to the automatic fruit and vegetable inspection method, intelligent inspection can be carried out on agricultural products by using a mobile phone to shoot videos, the inspection cost is saved, and the application range of automatic inspection is widened.

Description

technical field [0001] The invention relates to the field of computer vision recognition, in particular to a method, system, electronic device and computer-readable medium for automatic inspection of fruits and vegetables based on machine vision recognition. Background technique [0002] Although the output is huge, the proportion of agricultural products in the e-commerce field is relatively low. This is because the indirect and non-face-to-face nature of online transactions leads to information asymmetry in the transaction process, and the low matching degree between product quality and sales price limits the e-commerce of agricultural products. Development in the field of business. [0003] At present, in the process of agricultural product trading, manual inspection is mainly relied on to determine the quality of agricultural products, etc. The results of inspection are subjective, which wastes manpower and the inspection results are unreliable. With the development of ...

AI Technical Summary

Problems solved by technology

[0002] Although the output is huge, the proportion of agricultural products in the e-commerce field is relatively low. This is because the indirect and non-face-to-face nature of online transactions leads to information asymmetry in the transaction process, and the low matching degree between product quality and sales price limits the e-commerce of agricultural products. Development in the business field

[0003] At present, in the process of agricultural product trading, manual inspection is mainly relied on to determine the quality of agricultural products, etc. The results of inspection are subjective, which wastes manpower and the inspection results are unreliable

With the development of artificial intelligence, some automatic inspection or sorting methods have appeared, but they have the disadvantages of complex inspection equipment structure and high cost, and are not suitable for large-scale use in the process of agricultural product transactions

Images