An image-based food information provision method

Abstract

The invention discloses a method for providing food information based on images, which collects food images in advance, establishes food labels and food information corresponding to the food labels, and marks the food images, and receives the images to be recognized , by performing image saliency detection on it to obtain the main body area of ​​the image to be recognized, according to the main body area, the image to be recognized is matched with the food image in the database to obtain the food image with the highest similarity, and the food corresponding to the food image The label is used as the food label of the image to be recognized, and finally the food information of the image to be recognized is obtained through the food label; not only can the accuracy of identifying the main object be greatly improved, it can adapt to various compositions, and the food can be obtained only through the image Information brings great convenience to users and provides beneficial help for people's life and health.

Description

technical field [0001] The invention relates to an information processing method, in particular to an image-based food information providing method. Background technique [0002] At present, when we recognize the main object in the image, we mainly extract the image in the middle of the image for recognition, but when we shoot, in order to make the photos look better, we often use the "golden section" in the composition, which is widely available. It is a phenomenon in nature. Simply put, it is to place the main object of photography at about one-third of the picture, making people feel that the picture is harmonious and full of beauty. The "Golden Section" is also called the "Rule of Thirds". The "Rule of Thirds" is to divide the entire picture into three equal parts with two straight lines in the horizontal and vertical directions. We place the subject on any straight line. Or the intersection of straight lines is more in line with human visual habits. When shooting, you...

AI Technical Summary

Problems solved by technology

As a result, the error rate of image subject recognition remains high.

Health has always been one of our major concerns, but most of them have limited knowledge of food, some don’t even know the name, let alone query the corresponding information, so how to obtain food information by taking images and identifying food subjects All kinds of relevant information become the focus of our attention

Images