River crab producing area tracing method and system

Abstract

The invention provides a method and a system for tracing the origin of river crabs. The method comprises the following steps: acquiring carapace images of purchased target river crabs; and uploading the carapace image of the target river crab to a block chain, and determining target origin traceability information of the target river crab by calling a traceability smart contract deployed on the block chain. The system executes the method. According to the method, the image classification technology is applied to river crab producing area identification and source tracing, the phenomenon that a traditional crab buckle anti-counterfeiting mode is easily counterfeited and utilized later is avoided, the market order confusion caused by producing area counterfeiting of illegal merchants can be prevented, and thus the legitimate rights and interests of consumers and merchants are maintained.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method and system for tracing the origin of river crabs. Background technique [0002] Compared with general agricultural products, characteristic agricultural products with regional characteristics have great advantages in terms of shape and quality; they have obvious regional characteristics, excellent quality and special effects. Driven by economic interests, some unscrupulous merchants falsified origins and fished in troubled waters, causing certain damage to consumers' rights and interests. [0003] Among them, high-quality crabs have a high reputation, and their prices are much higher than crabs from other origins. Lawbreakers will sell crabs by means of counterfeit brands, which seriously affects the normal order of the Chinese mitten crab industry and the legitimate rights and interests of producers and consumers. Therefore, the research on the identificatio...

AI Technical Summary

Problems solved by technology

The analysis found that detection methods based on artificially designed features (color, shape, texture, etc.) need to artificially select feature parameters and design feature extraction methods, and the selection of features requires a lot of experiments and experience, which is seriously energy-consuming. Others based on deep learning The recognition accuracy of the image classification model is not high enough

[0008] At the same time, the current anti-counterfeiting of river crabs mainly relies on crab clasps printed with anti-counterfeiting marks such as barcodes or QR codes. This method is highly reproducible, and there is a risk of malicious forgery or secondary recycling by illegal traders, and the traceability verification results are not credible.

On the other hand, it is not conducive to the healthy development of the industry to pretend to be the origin of river crabs by "bathing"

Images