Fruit and vegetable detection method and device, electronic equipment and computer readable medium

Abstract

The invention provides a fruit and vegetable detection method and device, electronic equipment and a computer readable medium. The method comprises the following steps: a data set generation step: collecting images of fruits and vegetables according to the quality of the fruits and vegetables so as to generate a data set based on the quality of the fruits and vegetables; a model training step of training a deep learning model based on the generated data set; and a detection step of detecting a to-be-detected fruit and vegetable image based on the trained deep learning model so as to identify the quality of fruits and vegetables in the to-be-detected fruit and vegetable image. The method provided by the invention can effectively and accurately detect the quality of fruits and vegetables.

Description

technical field [0001] The invention relates to a fruit and vegetable detection method, device, electronic equipment and computer readable medium. Background technique [0002] With the development of agricultural planting levels, the quality of different fruits and vegetables in the market is uneven. Usually, the price of fruits and vegetables with excellent quality (high-quality goods) is higher, while the price of fruits and vegetables with relatively poor quality is relatively low. It is precisely because of the price difference that it is particularly important for the quality inspection and classification of fruits and vegetables in the market, so as to avoid the phenomenon of shoddy or substandard quality. Nowadays, the methods for quality inspection of fruits and vegetables mainly include manual inspection and sorting methods, which are usually less efficient due to lack of intelligence and automation, and also introduce human subjective judgment, and the standards v...

AI Technical Summary

Problems solved by technology

However, the threshold value is different in different seasons and different environments, such as lighting environments. This method is implemented in a specific lighting environment that is artificially set. From another perspective, it shows that the scalability is not strong.

Images