Vegetable processing and sorting system and method

Abstract

The invention belongs to the technical field of vegetable processing and sorting, and discloses a vegetable processing and sorting system and method. The vegetable processing and sorting system comprises a video monitoring module, a main control module, a cleaning module, a vegetable image classification module, an image feature extraction module, a vegetable recognition module, a vegetable rating module, a screening module, a conveying module and a display module. According to the system, a full connection layer is added in the convolutional neural network model through the vegetable image classification module, the target convolutional neural network model is established and trained, and the to-be-identified vegetable images are classified based on the trained target convolutional neural network model, so that the accuracy of vegetable image classification is improved; meanwhile, when the vegetable images are collected through the vegetable recognition module, corresponding sample images are obtained, the sample images are amplified, the first sample image set is obtained, a large number of sample images do not need to be collected, the collection amount of the sample images can be effectively reduced, and meanwhile the efficiency of establishing the image database is improved.

Description

technical field [0001] The invention belongs to the technical field of vegetable processing and sorting, and in particular relates to a vegetable processing and sorting system and method. Background technique [0002] At present, vegetable processing uses vegetables as raw materials. After pretreatments such as washing, peeling, cutting (or not peeling, cutting) and blanching, physical, chemical and biological methods are used to make food for preservation. Processing process. Harvested vegetables are still living organisms, and they continue to carry out various complex life activities during storage, the most important of which is respiration. With the progress of respiration, organic substances such as sugar, starch and acid contained in vegetables are continuously consumed due to being oxidized into carbon dioxide and water. At the same time, vegetables contain a lot of water and various nutrients, which are extremely favorable conditions for the growth and reproductio...

AI Technical Summary

Problems solved by technology

[0004] (1) The accuracy of vegetable image classification is not high during the sorting process of the existing vegetable processing and sorting system.

[0005] (2) The existing technology uses deep learning to train robots to intelligently recognize vegetables, but it relies on a large number of collected samples, and the recognition rate is relatively low

Images