Image detection method, device, electronic device and computer readable medium

Abstract

Embodiments of the present disclosure disclose an image detection method, device, electronic equipment, and computer-readable medium. A specific implementation of the method includes: acquiring a first item image and a second item image of the item to be detected; performing image feature extraction processing on the first item image and the second item image respectively to obtain the first item image vector and The second item image vector; the above-mentioned first item image vector and the above-mentioned second item image vector are fused to generate a fusion vector; the above-mentioned fusion vector is input into a pre-trained image detection model to obtain an image detection result; the above-mentioned image The detection result is sent to the settlement device with display function and storage function for settlement processing. This embodiment realizes the detection of the items acquired by the user from multiple angles, and improves the accuracy of the detection results of the items. Thus, the error rate of item settlement is reduced.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to an image detection method, device, electronic equipment, and computer-readable medium. Background technique [0002] With the development of Internet technology, more and more automatic vending cabinets appear. When users obtain items through the vending cabinet, the vending cabinet usually uses traditional RFID (Radio Frequency Identification, radio frequency identification) technology to detect the items obtained by the user, and perform settlement processing according to the detection results. [0003] However, the following technical problems usually exist in the above-mentioned detection method: [0004] First, it is impossible to detect the items obtained by users from multiple angles, resulting in low accuracy of the detection results of the items, resulting in a high error rate of item settlement; [0005] Second, the traditional radio f...

AI Technical Summary

Problems solved by technology

[0004] First, it is impossible to detect the items obtained by users from multiple angles, resulting in low accuracy of the detection results of the items, resulting in a high error rate of item settlement;

[0005] Second, the traditional radio frequency identification technology does not comprehensively consider the relationship between the various information included in the image when performing item detection, which in turn makes the accuracy of item detection low and further causes the error rate of item settlement to be high

Images