Automatic identification system and method for an automatic rotary cabinet based on deep learning

Abstract

The invention discloses an automatic rotary cabinet automatic identification system and method based on deep learning, relates to the field of intelligent logistics, and constructs a set of cargo automatic identification visual system by combining a digital image processing technology and an artificial intelligence deep learning theory. Preprocessing such as smoothing, gray scale stretching, restoration, denoising, enhancement, edge detection and central normalization is conducted on collected goods through the digital image processing technology, the visual effect of the image is improved, and the accuracy of the visual recognition system is improved. The visual identification system adopts an improved model based on a deep convolutional neural network, and can automatically extract the category and position information of the goods in the digital image to realize automatic classification and labeling of the goods in the image. According to the invention, intelligent identification and recording of warehouse entering and exiting of cargoes of the rotary cabinet are realized, manual additional operation is not needed, the production efficiency is greatly improved, and the rotary cabinet RFID electronic tag can be used as improvement and substitution of the existing rotary cabinet RFID electronic tag technology.

Description

technical field [0001] The invention belongs to the field of intelligent logistics, and in particular relates to an automatic identification system and method for an automatic rotary cabinet based on deep learning. Background technique [0002] With the development of the domestic economy, my country's warehousing and logistics industry has also developed rapidly, and the market has higher and higher requirements for the intelligent transformation of logistics equipment. In recent years, with the emergence of storage revolving cabinets, the inventory management efficiency and land area utilization rate of storage have been greatly improved. However, most of the equipment remains at the level of automation and requires frequent participation of people in the control, which cannot reach the level of intelligence. When the goods are put into the warehouse of the automatic revolving cabinet, it is usually necessary to post a QR code or an electronic label to identify the identit...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a system and method for automatic identification of automatic rotary cabinets based on deep learning to solve the problems of low manual verification efficiency, high manpower and time consumption proposed in the above-mentioned background technology

Manual verification is subject to many interference factors and low accuracy

Images