Image processing method and device, computer equipment and storage medium

Abstract

The invention discloses an image processing method and device, computer equipment and a storage medium. The time complexity and the space complexity in image feature extraction are effectively reduced. The method comprises the steps of obtaining a grayscale image corresponding to a to-be-processed image; determining a difference value of gray values between all adjacent pixel points of the gray-scale image, wherein the difference value is a value reflecting a gray value difference degree between the adjacent pixel points; Taking an area corresponding to the adjacent pixel points of which the difference values are greater than or equal to a preset threshold value as a contour area of the to-be-processed image; according to a horizontal linear probe and the contour area, acquiring horizontalimage characteristics of the gray scale image in the horizontal direction, and according to a vertical linear probe and the contour area, acquiring vertical image characteristics of the gray scale image in the vertical direction; determining a target image feature according to the horizontal image feature and the vertical image feature; and taking the target image feature as a global image feature of the to-be-processed image.

Description

technical field [0001] The present application relates to the field of image processing, and in particular to an image processing method, device, computer equipment and storage medium. Background technique [0002] In order to facilitate image analysis, there are many algorithms for extracting image features, such as lbp, hog algorithm and other local feature extraction algorithms for extracting local features. It can be understood that the above extraction is a local feature, and in order to obtain the global feature of the image, it usually needs to be further solved to obtain the global feature of the image. In addition, there are also global feature extraction algorithms that are directly used to extract global features. However, in the above-mentioned traditional schemes, because the traditional technology uses neural network-like classification algorithms such as svm, this type of classification algorithm involves mathematical statistics, neural networks, etc. Network...

AI Technical Summary

Problems solved by technology

In addition, there are also global feature extraction algorithms that are directly used to extract global features. However, in the above-mentioned traditional schemes, because the traditional technology uses neural network-like classification algorithms such as svm, this type of classification algorithm involves mathematical statistics, neural networks, etc. Network, gradient calculation, etc., resulting in relatively high time complexity and space complexity for image extraction

Images