Image enhancement method fusing edge gray histogram and human eye visual perception characteristics

Abstract

The invention discloses an image enhancement method fusing an edge gray histogram and human eye visual perception characteristics. The method comprises the following steps: respectively calculating the gradient in the row direction and the gradient in the column direction of each pixel position in an image, and the total gradient of the pixel position; sorting the total gradients of all pixel positions, finding out the maximum total gradient, and setting a gradient threshold; comparing the total gradient of all pixel positions with a gradient threshold value, marking all image edge pixels of which the total gradient of the pixel positions is greater than the gradient threshold value, and counting the number of edge pixels with the same gray level in all marked image edge pixels to obtain an edge gray level histogram; calculating cumulative probability distribution of which the edge gray level is smaller than a set value; calculating perception sensitivity factors of human eyes under different brightness backgrounds by considering the visual nonlinear characteristics of the human eyes, and performing normalization processing to obtain an optimal gray level adjustment reference value; thus, obtaining an enhanced image. The visual effect of the image is remarkably improved.

Description

technical field [0001] The invention relates to an image enhancement method. In particular, it relates to an image enhancement method that fuses edge gray histograms and human visual perception characteristics. Background technique [0002] In real life, due to factors such as poor lighting in the shooting environment and insufficient performance of imaging equipment, the obtained images are prone to blurred details, color distortion, low contrast, and more noise. These degraded images are very important for image analysis. with great difficulty in understanding. For example, in the analysis of medical images, due to the consideration of patient safety inspection and the limitation of image information collection capabilities of medical equipment, the clarity and contrast of various medical images obtained are not ideal, which directly affects the accuracy of doctors' pathological diagnosis. Obviously, it is of great practical significance to enhance a large number of degr...

AI Technical Summary

Problems solved by technology

[0004] Although the image enhancement effect of the improved algorithm has been improved, there are still two common problems in these algorithms, which affect the enhancement performance of the algorithm

The first is the problem of analyzing the data. The analysis data of GHE and its series of improved algorithms is the histogram of the image. The image histogram is only a simple statistical result of each gray level in the image, and does not truly reflect the information portrayed by each gray level. Therefore, adjusting the gray level based on the probability distribution of the number of gray levels cannot guarantee the effective stretching of the gray level dynamic range that is important for information description.

Secondly, research on human visual perception has found that there are significant differences in the sensitivity of the human eye to information of different brightness backgrounds, the ability to perceive gray deviations in darker brightness backgrounds is weak, and the perception of gray deviations in moderate or brighter backgrounds is relatively weak. strong ability

However, GHE and its series of improved algorithms are based on the assumption that the background sensitivity of the human eye to different brightness is the same, so that the detailed information in a large number of dark backgrounds cannot be effectively enhanced.

Images