Method for identifying articles in refrigerator, refrigerator and computer storage medium

Abstract

The invention provides a method for identifying articles in a refrigerator, the refrigerator and a computer storage medium, and the method comprises the steps: obtaining a plurality of refrigerator storage space images shot at the same point, and selecting one image as a reference image; article information in the reference image is detected, identified and identified; comparing the other images with the reference image, and segmenting the contents of the other images into similar areas and different areas according to the repetition between the other images and the reference image; and marking in the similar region by using the corresponding article information in the reference image, digging the different region image to carry out secondary detection and identification, and carrying out secondary marking. By comparing a plurality of images, dividing the difference areas in the images according to the repetition degree difference, and performing secondary matting identification on the difference areas, the identification accuracy of articles in the images is improved, and the occurrence of missed identification is reduced.

Description

technical field [0001] The invention relates to the field of refrigeration devices, in particular to a method for identifying items in a refrigerator, a refrigerator and a computer storage medium. Background technique [0002] With the development of intelligent household appliances, the identification of internal items has become a necessary function of only refrigerators. Generally, in order to realize the identification of the items inside the refrigerator, one or more cameras are installed in the internal storage space of the refrigerator for photographing the items, and the photographed photos are processed to generate an identification result. [0003] However, in the process of image detection and recognition, due to various reasons such as lighting, the camera itself, and the objects placed, the quality of phaseless imaging is not good enough, or the generalization ability of the image detection algorithm itself is not high enough, resulting in low recognition accura...

AI Technical Summary

Problems solved by technology

[0003] However, in the process of image detection and recognition, due to various reasons such as lighting, the camera itself, and placed objects, the quality of non-phase imaging is not good enough, or the generalization ability of the image detection algorithm itself is not high enough, resulting in low recognition accuracy. Missing recognition often occurs, especially when the position of the object in the front and rear images does not change, and the object detected in one of them is not detected in the other, which seriously affects the user experience

Images