Picture similarity calculation method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence and discloses a picture similarity calculation method and device, computer equipment and a storage medium. The picture similarity calculation method comprises steps of determining whether targets of the same type exist in a first picture and a second picture or not according to a first target detection result of the first picture and a second target detection result of the second picture; obtaining a first target sub-graph and a second target sub-graph from the first picture and the second picture when it is determined that the same type of target exists; calculating the sub-image similarity of the first target sub-image and the second target sub-image, determining the image similarity between the first image and the second image according to the sub-image similarity, and outputting the image similarity and the sub-image similarity; and when it is determined that the same type of target does not exist, performing edge detection on the first picture and the second picture, calculating picture similarity between the first picture and the second picture, and outputting the picture similarity. According to the method, accuracy of the similarity of the pictures can be improved, and similarity of the pictures can be explained.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular to a method, device, computer equipment and storage medium for calculating image similarity. Background technique [0002] In intellectual property litigation cases, trademark and commercial poster infringement cases are not uncommon. How to judge whether the defendant's trademark and commercial poster pictures constitute plagiarism or infringement of the plaintiff's work, the key is to evaluate the similarity of the two pictures and give the evaluation basis. The current common image similarity judgment method is usually to use cosine similarity to calculate the similarity of two images after zooming and grayscale processing, but this method is too rough, and only compares and calculates the pixel values ​​​​of the images. The accuracy of similarity judgment is not high. With the rise of machine learning technology, image processing technology based on deep le...

AI Technical Summary

Problems solved by technology

The current common image similarity judgment method is usually to use cosine similarity to calculate the similarity of two images after zooming and grayscale processing, but this method is too rough, and only compares and calculates the pixel values ​​​​of the images. The accuracy of similarity judgment is not high

With the rise of machine learning technology, image processing technology based on deep learning began to be applied to the evaluation of picture similarity. This method improves the accuracy, but the deep learning model is like a black box, inputting two pictures and the model will output a similarity. The results of the degree evaluation cannot give the explanation and scoring basis for the similarity calculation, which makes the judgment result not intuitive enough

Images