Image similarity judgment method, electronic equipment and storage medium

Abstract

The invention discloses an image similarity judgment method, which comprises the following steps of: graying processing: obtaining a vector image to be judged, graying the vector image to be judged, enabling the vector image to be judged to present a black-white-gray state, and adaptively scaling the vector image to be judged to a standard size; A pixel point distribution comparison step, dividingthe vector image to be judged into n * m square areas to obtain a square matrix corresponding to the vector image to be judged, performing pixel point distribution comparison with the square matrix corresponding to each standard size image stored in the image library, and judging the similarity of the vector image according to the pixel point distribution condition of the square matrix of the corresponding specification. The invention further discloses electronic equipment and a storage medium, and the image similarity judgment method, the electronic equipment and the storage medium can obtain an ideal vector graph similarity judgment result, so that vector graph similarity judgment is more accurate.

Description

technical field [0001] The invention relates to the field of image recognition and comparison, and in particular, to an image similarity judgment method, an electronic device and a storage medium. Background technique [0002] The similarity comparison of images is mainly realized by calculating the similarity between two images. At present, the image similarity calculation is performed by scoring the similarity of content between two images, and the similarity of the content of the images is judged according to the level of the score. When humans and AI robots draw together, they usually first judge the human hand-drawn line art graphics, find the most similar image in the graphics or hand-drawn style of the current hand-drawn line art from the AI ​​robot's image library, and then carry out the process. The next co-painting. However, when judging and matching the similarity of the hand-drawn vector line draft images, because everyone has their own drawing habits, for exam...

AI Technical Summary

Problems solved by technology

However, when judging and matching the similarity of hand-drawn vector line draft images, since everyone has their own drawing habits, for example, they also use their hands to draw "L" graphics on the touch screen, and some people draw "L" The corners of "" will be sharper, and the vertical lines will be straighter, while the corners of "L" drawn by some people will be smoother, or the vertical lines will be arc-shaped with a certain radian, so when comparing the similarity of such hand-drawn vector graphics certain degree of difficulty

However, the currently commonly used image similarity judgment method is not ideal for detection.

For example: the method of histogram matching, the histogram reflects the probability distribution of the gray value of the image pixel, the effect is not ideal for judging the position of the pixel, that is, what kind of object exists in the image and what is the shape.

Its image similarity calculation based on feature points judges whether two images are consistent by finding the number of matching points. This algorithm is better at finding matching points for an object and images obtained from different angles to judge similarity. The similarity judgment effect of various vector graphics with different shapes and different inflection points based on the hand-painting habits of different people is not ideal

Images