Class identification method for foods in refrigerator, and refrigerator

Abstract

The invention provides a class identification method for foods in a refrigerator, and the refrigerator. An identification area is formed in a storage department of the refrigerator and a hyperspectral imaging device with a shooting angle facing the identification area is arranged. The class identification method comprises the following steps: controlling the hyperspectral imaging device to shoot the foods placed in the identification area, and acquiring hyperspectral data obtained through the shooting; extracting image characteristic information and characteristic spectrum information from the hyperspectral data; and matching the image characteristic information with the characteristic spectrum information by virtue of a preset identification model to determine the classes of the foods. According to the scheme, the hyperspectral imaging device is arranged in the refrigerator, the hyperspectral data of the foods is obtained through the shooting, class identification for the foods is carried out by comprehensively utilizing the image information and the spectrum information, and the identification accuracy is high.

Description

technical field [0001] The invention relates to the technical field of storage, in particular to a method for identifying the type of food inside a refrigerator and the refrigerator. Background technique [0002] With the progress of society and the improvement of people's living standards, consumers not only pay attention to the nutritional value and safety of food when purchasing food, but also consider factors such as price, taste, appearance and freshness, and the role of refrigerators has changed from simply storing The preservation of freshness has gradually transformed into a food management center and a family nutrition center, which also poses new challenges to refrigerators. At the same time, it also provides opportunities for the application of various intelligent identification technologies on refrigerators. The way to understand the types of ingredients stored in the refrigerator has also changed from opening the refrigerator door to actually checking to intelli...

AI Technical Summary

Problems solved by technology

The automatic identification technologies currently applied to refrigerators include radio frequency identification and image recognition. Radio frequency identification is to post radio frequency identification codes on the ingredients put in the refrigerator, and use the radio frequency identification device installed on the refrigerator to identify them. This technology requires the purchased ingredients It itself contains a radio frequency identification code, but most of the food currently on the market does not contain a radio frequency identification code, especially vegetables and fruits do not contain an identification code, so this technology is subject to great application restrictions

[0004] Image recognition technology has also been applied to refrigerators, but the correct recognition rate is low. Since this technology mainly relies on the recognition of the color of the food image or the difference in the shape and texture of the food, it is difficult to correctly identify food with similar colors and shapes. , such as oranges and oranges are difficult to distinguish, and the recognition result is citrus, so the correct rate of this technology needs to be further improved

Images