Method for carrying out adaptive computing on importance weights of low-level features of image

Abstract

The invention discloses a method for carrying out adaptive computing on importance weights of low-level features of an image, which is used for ensuring the visual integrity of a sensitive target in the process of image compression. In the invention, according to an image, the optimal compression parameters are adaptively computed, wherein the image comprises four low-level features such as color, gradient, brightness and center distance; in the process of computing the importance weight of color, an image to be processed is subjected to color histogram statistics, and a weight function is established for computing the weight of color according to frequencies; in the process of computing the importance weight of gradient, the image is divided into blocks, the gradient of pixels in each block is computed, then the orientation of the obtained gradient is subjected to histogram statistics, and an inter-block orientation change rule is computed so as to determine the importance weight of gradient; in the process of computing the importance weight of brightness, the image to be processed is divided into two parts, the brightness value of each part is computed, and the part with a larger value is taken as the main reference basis for weight computing; and in the process of computing the importance weight of position, a fixed value is assigned, and finally, corresponding weight parameters of each low-level feature are obtained.

Description

technical field [0001] The invention is a method capable of automatically calculating important areas in an image, and in particular relates to the adaptive calculation of weight coefficients of various underlying features of the image in the process of identifying important areas of the image, and belongs to the technical field of computer vision. Background technique [0002] When people observe and understand images, they will instinctively divide them into important areas (areas of visual interest, such as the main part of an image, buildings, flowers and birds, people in portrait photography, etc.) and non-important areas. The subjective visual quality of the image often depends on the visual quality of important areas, and the degradation of non-important areas is often not easy to be noticed, and has little impact on the visual quality of the entire image. Therefore, the method of extracting important regions in an image is of great significance in application fields ...

AI Technical Summary

Problems solved by technology

Although this type of method can realize the automatic extraction of important regions, there are still deficiencies: 1) Because only a single underlying feature is used, the extraction of important regions is sometimes inaccurate; 2) Because it uses fixed coefficients, the All kinds of images are not universal

Although this method overcomes the shortcomings of only using a single bottom-level feature of the image, it uses fixed empirical values ​​when selecting the weight coefficients of each bottom-level feature, so it cannot adapt well to changes in different image textures, colors, etc. Universality needs to be improved

Images