Authenticity identification method and system for Eriocheir sinensis based on deep learning

Abstract

The invention discloses an authenticity identification method and system for Eriocheir sinensis based on deep learning, and belongs to the technical field of deep learning. The method comprises the following steps: acquiring image data and identity (ID) of the eriocheir sinensis; preprocessing the image data to obtain a target image, and obtaining an original image according to the identity ID; respectively calculating the target image and the original image to obtain feature vectors, and calculating the similarity between the target image and the original image according to the feature vectors of the target image and the original image; and judging the authenticity of the Eriocheir sinensis corresponding to the target image according to the similarity. The system comprises a memory and a processor, wherein the processor executes a program stored in the memory to realize the method. According to the method, the defect that the authenticity identification accuracy of the eriocheir sinensis in the prior art is low is overcome, the authenticity identification of the eriocheir sinensis under any environmental condition can be realized, and the authenticity identification accuracy of the eriocheir sinensis can be further greatly improved.

Description

Technical field[0001]The present invention belongs to the field of depth learning technology, and more particularly to a truly identification method and system based on deep learning of Chinese velvet crabs.Background technique[0002]The large abdomen crabs have generally presented high-quality and high-end hairy crabs using ordinary hairy crabs (Chinese cock crabs). This high-quality hairy crab is pretending to cause consumers to buy hairy crabs that are charged, and they are impaired; and merchants will lead to damage to brand image. In order to solve this problem, we propose a hairy crab true orchestration judgment based on the depth study of hairy crab biological characteristics.[0003]Deep learning technology enables computer to handle certain image data, using training-out models to calculate the characteristic vector of the hairable crab, can determine whether the current two large abdominal crabs are the same hairy crab by the similarity of the characteristic vector to achieve...

AI Technical Summary

Problems solved by technology

However, the method of this program cannot identify the Chinese mitten crab under complex environmental conditions with poor accuracy, that is, the method of this program is not widely applicable

Images