Article labeling method and device, electronic device and storage medium

Abstract

The embodiment of the invention relates to the technical field of machine vision, and discloses an article labeling method and device, an electronic device and a storage medium. The method comprises the following steps: generating a binary article labeling model for labeling a target object and a non-target object; inputting a plurality of to-be-labeled pictures; wherein the target objects in theto-be-labeled picture are labeled with categories, and each target object in the to-be-labeled picture containing the target object is one type; and automatically labeling the to-be-labeled picture through the binary article labeling model to obtain position information of the target object, and taking the labeled category as the category of the target object output by the binary article labelingmodel. According to the embodiment of the invention, article labeling can be realized more quickly with low cost.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to an item labeling method and device, electronic equipment and a storage medium. Background technique [0002] With the development of artificial intelligence and machine learning technology, unattended stores have begun to appear. The operation of unattended stores needs to rely on object detection technology. Target detection technology is a branch of the field of machine vision, which is mainly used to identify the position and category of the target object on the picture. At present, common methods of object detection include: traditional object detection methods and object detection frameworks based on deep learning. Existing object detection frameworks are mainly supervised learning. The supervised learning method is to generate a function to map the input to the appropriate output through the corresponding relationship between a part of the input data and the outpu...

AI Technical Summary

Problems solved by technology

Since there are thousands of items in real life, using the above labeling method, it is necessary to relabel and update the model for items that have not appeared in the model, which consumes a lot of manpower and material resources

At the same time, when there are too many types of items, the accuracy of the above labeling methods will drop sharply due to the similarity between items.

Images