Answers are grounded in this paper and cite their sources.
With the rise of food safety traceability, unmanned supermarkets and autonomous shopping, the automatic identification technology of agricultural products such as vegetables in circulation and sales has become an urgent problem. This paper designs an intelligent vegetable identification system based on MobileNet to solve intelligent identification problem of vegetable sales in supermarkets. The system includes main control core, visual processing module, pressure sensor, voice broadcasting module and display module. When the system detects that there are vegetables to be weighed, the visual processing module completes the classification of vegetables, broadcasts the name, unit price and total price of vegetables by voice, and displays the weight, unit price and total price by OLED. The machine vision processing module is constructed by deep separable convolution (DSC). It realizes the separation of channels and regions, so it has high computing efficiency and is more suitable for embedded devices with low memory space. The experimental results show that the overall recognition rate of five vegetables reaches 97.33% under three kinds of illumination. The system has the advantages of stability, intelligence and convenience.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2022) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: