CN111738949B - Image brightness adjusting method and device, electronic equipment and storage medium - Google Patents

Abstract

The present application discloses a method, device, electronic device and storage medium for adjusting image brightness, which relates to the fields of artificial intelligence, deep learning and image processing, and can be specifically applied to fundus image screening. The specific scheme is: obtaining an observed image; wherein the observed image is an image in a red, green and blue color space; separating a background image corresponding to the observed image from the observed image; determining a display parameter value corresponding to the observed image according to the background image; and adjusting the brightness of the observed image according to the display parameter value corresponding to the observed image. The embodiment of the present application can intelligently select a suitable display parameter value according to the brightness distribution of the observed image itself, thereby making the brightness distribution of the observed image more reasonable.

Description

Image brightness adjustment method, device, electronic device and storage medium

Technical Field

The present application relates to the field of computer technology, and further to the fields of artificial intelligence, deep learning, and image processing, and in particular to an image adjustment method, device, electronic device, and storage medium.

Background technique

Fundus image adaptive brightness adjustment technology refers to automatic adjustment based on the brightness distribution of the fundus image itself, so that the image quality meets the unified standard. In actual business scenarios, due to factors such as differences in image acquisition equipment models, insufficient lighting, too small dynamic range of imaging sensors, and technician photography skills, the fundus images obtained by the image acquisition equipment have uneven brightness distribution and poor quality. There is a gap between the fundus images that actually enter the algorithm model and the fundus images required by the model in the initial training stage, which will affect the performance of the entire system. Therefore, before the fundus images are input into the algorithm model, the acquired fundus images need to be preprocessed to reduce the impact of the image acquisition equipment on the original fundus images.

In the prior art, most of them focus on enhancing retinal blood vessels to achieve better blood vessel segmentation by increasing the contrast between blood vessels and retinal background in grayscale and color retinal images. Contrast-based enhancement methods mainly include three methods: histogram-based, filter-based, and transformation-based. For example, histogram matching between the red channel and the green channel is used as a preprocessing step for blood vessel segmentation, which can improve the contrast of overall dark features such as blood vessels, but reduce the contrast between bright objects and tiny dark objects such as microaneurysms (MAs). Enhancement using matched filters can improve local contrast and help blood vessel segmentation, but it cannot maintain the fidelity of the image, and it will also affect other structures present in the image. The enhancement method based on contourlet transform is less effective in areas with poor contrast in fundus images. In addition, brightness-based enhancement methods include: color retinal image enhancement based on neighborhood (Colour Retinal Image Enhancement based on Domain Knowledge) and color retinal image enhancement based on brightness and contrast adjustment (Color Retinal Image Enhancement Based on Luminosity and Contrast Adjustment). In the brightness-based enhancement method, fixed display parameter values are used to adjust the brightness of different observed images, and the appropriate display parameter values cannot be intelligently selected according to the brightness distribution of the observed image itself.

Summary of the invention

The present application provides a method, apparatus, device and storage medium for adjusting image brightness, which can intelligently select appropriate display parameter values according to the brightness distribution of the observed image itself, thereby making the brightness distribution of the observed image more reasonable.

In a first aspect, the present application provides a method for adjusting image brightness, the method comprising:

Acquire an observed image; wherein the observed image is an image in a red, green, and blue color space;

Separating a background image corresponding to the observed image from the observed image;

Determine a display parameter value corresponding to the observed image according to the background image;

The brightness of the observed image is adjusted according to the display parameter value corresponding to the observed image.

In a second aspect, the present application provides a device for adjusting image brightness, the device comprising: an acquisition module, a separation module, a determination module and an adjustment module; wherein:

The acquisition module is used to acquire an observed image; wherein the observed image is an image in a red, green and blue color space;

The separation module is used to separate the background image corresponding to the observation image from the observation image;

The determination module is used to determine the display parameter value corresponding to the observed image according to the background image;

The adjustment module is used to adjust the brightness of the observed image according to the display parameter value corresponding to the observed image.

In a third aspect, an embodiment of the present application provides an electronic device, including:

one or more processors;

a memory for storing one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement the method for adjusting the image brightness described in any embodiment of the present application.

In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the method for adjusting the image brightness described in any embodiment of the present application is implemented.

The technology according to the present application solves the technical problem that in the prior art, fixed display parameter values are used to adjust the brightness of different observation images, and appropriate display parameter values cannot be intelligently selected according to the brightness distribution of the observation image itself. The technical solution provided by the present application can intelligently select appropriate display parameter values according to the brightness distribution of the observation image itself, thereby making the brightness distribution of the observation image more reasonable.

It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.

FIG1 is a schematic flow chart of a method for adjusting image brightness provided in Embodiment 1 of the present application;

FIG. 2( a ) is a schematic diagram of the locations of sampling points in a fundus image provided in Example 1 of the present application;

FIG2( b ) is a schematic diagram showing the distribution of sampling points in the fundus image provided in Example 1 of the present application;

FIG3 is a schematic flow chart of a method for adjusting image brightness according to a second embodiment of the present application;

FIG4 is a schematic diagram of the structure of a background image provided in Example 2 of the present application;

FIG5 is a schematic diagram of a flow chart of a method for adjusting image brightness provided in Embodiment 3 of the present application;

FIG6( a ) is a schematic diagram of the structure of a brightness drift factor provided in Embodiment 3 of the present application;

FIG6( b ) is a schematic diagram of the structure of the contrast drift factor provided in Example 3 of the present application;

FIG7 is a schematic diagram of the structure of a convolution kernel provided in Example 3 of the present application;

FIG8 is a schematic diagram showing the comparison of image brightness before and after adjustment provided in Example 3 of the present application;

FIG9 is a schematic diagram of the structure of an apparatus for adjusting image brightness provided in Embodiment 4 of the present application;

FIG10 is a schematic diagram of the structure of a separation module provided in Example 4 of the present application;

FIG11 is a schematic diagram of the structure of a determination module provided in Embodiment 4 of the present application;

FIG12 is a schematic diagram of the structure of an adjustment module provided in Embodiment 4 of the present application;

FIG. 13 is a block diagram of an electronic device for implementing the method for adjusting image brightness according to an embodiment of the present application.

Detailed ways

The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

Embodiment 1

FIG1 is a flow chart of a method for adjusting image brightness provided in Embodiment 1 of the present application. The method can be performed by an image brightness adjustment device or electronic device. The device or electronic device can be implemented by software and/or hardware. The device or electronic device can be integrated into any smart device with network communication function. As shown in FIG1 , the method for adjusting image brightness can include the following steps:

S101, obtaining an observed image; wherein the observed image is an image in a red, green and blue color space.

In a specific embodiment of the present application, an electronic device can obtain an observed image; wherein the observed image is an image in a red, green, and blue color space (i.e., RGB space). The RGB space is based on the three basic colors of red, green, and blue, and performs different degrees of superposition to produce rich and wide colors, so it is commonly known as the three-primary color model. The RGB space is the most commonly used model in life, and most televisions, computer monitors, etc. use this model. Any color in nature can be mixed from the three colors of red, green, and blue, and most of the colors people see in real life are mixed colors.

S102: Separate a background image corresponding to the observed image from the observed image.

In a specific embodiment of the present application, the electronic device can separate the background image corresponding to the observed image from the observed image. Specifically, the electronic device can first separate the green channel (i.e., G channel) image corresponding to the observed image from the observed image; then calculate the mean and standard deviation of each pixel point in the G channel image; wherein the pixel points in the G channel image include: sampling points and non-sampling points; then, based on the mean and standard deviation of each pixel point in the G channel image and the pixel value of each pixel point, separate the background image corresponding to the G channel image from the G channel image.

FIG2(a) is a schematic diagram of the positions of sampling points in the fundus image provided in Example 1 of the present application. As shown in FIG2(a), based on the characteristics that the central area has better illumination and the peripheral area has relatively poor illumination, fewer points can be collected as sampling points in the central area and more points can be collected as sampling points in the peripheral area. The units of the horizontal and vertical axes in FIG2(a) are the basic units of pixels.

Figure 2(b) is a schematic diagram of the distribution of sampling points in the fundus image provided by Example 1 of the present application. As shown in Figure 2(b), a polar coordinate system is established with the center point of the fundus image as the origin, and the sampling points of the fundus image are distributed on five circles with the origin of the polar coordinates as the center; because the position of each sampling point is fixed, the angle and radius of each sampling point relative to the origin can be known in advance, so that the polar coordinates of each sampling point can be obtained, and then the rectangular coordinates of each sampling point can be calculated according to the conversion relationship between polar coordinates and rectangular coordinates.

S103: Determine a display parameter value corresponding to the observed image according to the background image.

In a specific embodiment of the present application, the electronic device can determine the display parameter value corresponding to the observed image based on the background image; the display parameter value is the gamma value. Specifically, the electronic device can first calculate the brightness drift factor corresponding to each pixel in the background image based on the predetermined window size and the pixel value of each pixel in the background image; and then determine the gamma value corresponding to the observed image based on the brightness drift factor corresponding to each pixel in the background image.

S104: Adjust the brightness of the observed image according to the display parameter value corresponding to the observed image.

In a specific embodiment of the present application, the electronic device can adjust the brightness of the observed image according to the display parameter value corresponding to the observed image. Specifically, the electronic device can first calculate the brightness gain matrix of the observed image according to the gamma value corresponding to the observed image; and then adjust the brightness of the observed image according to the brightness gain matrix.

The method for adjusting the image brightness proposed in the embodiment of the present application first obtains the observed image; then separates the background image corresponding to the observed image from the observed image; then determines the display parameter value corresponding to the observed image according to the background image; and finally adjusts the brightness of the observed image according to the display parameter value corresponding to the observed image. That is to say, the present application can determine the display parameter value corresponding to the observed image in the background image corresponding to the observed image, so that the brightness of the observed image can be adjusted according to the display parameter value corresponding to the observed image. In the existing method for adjusting the image brightness, a fixed display parameter value is used to adjust the brightness of different observed images, and the appropriate display parameter value cannot be intelligently selected according to the brightness distribution of the observed image itself. Because the present application adopts the technical means of separating the background image corresponding to the observed image from the observed image, and determining the display parameter value corresponding to the observed image according to the background image, it overcomes the technical problem that the fixed display parameter value is used to adjust the brightness of different observed images in the prior art, and the appropriate display parameter value cannot be intelligently selected according to the brightness distribution of the observed image itself. The technical solution provided by the present application can intelligently select the appropriate display parameter value according to the brightness distribution of the observed image itself, so that the brightness distribution of the observed image is more reasonable; and the technical solution of the embodiment of the present application is simple and convenient to implement, easy to popularize, and has a wider range of application.

Embodiment 2

FIG3 is a flow chart of a method for adjusting image brightness provided in Embodiment 2 of the present application. As shown in FIG3 , the method for adjusting image brightness may include the following steps:

S301, obtaining an observed image; wherein the observed image is an image in a red, green and blue color space.

S302: Separate a green channel image corresponding to the observed image from the observed image.

In a specific embodiment of the present application, the electronic device can separate the G channel image corresponding to the observed image from the observed image. Because the G channel image retains a large amount of contrast information, a background image extraction operation is performed on the G channel, and the pixel points of the background image are extracted from the observed image using the mean and standard deviation of the sampling points.

S303, calculating the mean and standard deviation of each pixel in the green channel image; wherein the pixel points in the green channel image include: sampling points and non-sampling points.

In a specific embodiment of the present application, the electronic device can calculate the mean and standard deviation of each pixel point in the G channel image; wherein the pixel points in the G channel image include: sampling points and non-sampling points. Specifically, the electronic device can first calculate the mean and standard deviation of each sampling point in the G channel image according to the predetermined window size corresponding to each sampling point; then calculate the mean and standard deviation of each non-sampling point in the G channel according to the mean and standard deviation of each sampling point in the G channel. Assume that the distances from the center of the five circles shown in FIG2(b) are _d1 , _d2 , _d3 , _d4 , _d5 , respectively, and the window sizes corresponding to the sampling points on the five circles are _w1 , _w2 , _w3 , _w4 , _w5 , respectively. Therefore, the electronic device can calculate the mean and standard deviation of each sampling point in the G channel image according to the window size corresponding to each sampling point; then perform bilinear interpolation calculation between the sampling points to obtain the mean μ(x, y) and variance σ(x, y) of all pixel points. Since the distances between different sampling points and the center of the circle are different, the window sizes used for different pixel points are also different. In the actual use process, it is not limited to these five circles, so the window size is not limited to the five values of _d1 - _d5 .

S304: Separate a background image corresponding to the green channel image from the green channel image according to the mean and standard deviation of each pixel point in the green channel image and the pixel value of each pixel point.

In a specific embodiment of the present application, the electronic device can separate the background image corresponding to the G channel image in the G channel image according to the mean and standard deviation of each pixel point in the G channel image and the pixel value of each pixel point. Figure 4 is a structural schematic diagram of the background image provided in the second embodiment of the present application. As shown in Figure 4, the electronic device can first extract a pixel point from the pixels in the G channel image as the current pixel point, and then calculate the Mahalanobis distance corresponding to the current pixel point according to the mean and standard deviation of the current pixel point and the pixel value of the current pixel point; if the Mahalanobis distance corresponding to the current pixel point is less than or equal to the preset threshold, the electronic device can use the current pixel point as a pixel point in the background image corresponding to the G channel image; if the Mahalanobis distance corresponding to the current pixel point is greater than the preset threshold, the electronic device can use the current pixel point as a pixel point in the foreground image corresponding to the G channel image; repeat the above operation until each pixel point in the G channel image is determined as a pixel point in the background image or a pixel point in the foreground image. Specifically, the electronic device can calculate the Mahalanobis distance corresponding to the current pixel point according to the following formula: Among them, D(x,y) represents the Mahalanobis distance corresponding to the current pixel; G(x,y) represents the pixel value of the current pixel; μ(x,y) represents the mean of the current pixel; σ(x,y) represents the standard deviation of the current pixel.

S305: Determine display parameter values corresponding to the observed image according to the background image.

In a specific embodiment of the present application, the electronic device can determine the display parameter value corresponding to the observed image based on the background image. Specifically, the electronic device can first calculate the brightness drift factor corresponding to each pixel in the background image based on a predetermined window size and the pixel value of each pixel in the background image; and then determine the gamma value corresponding to the observed image based on the brightness drift factor corresponding to each pixel in the background image.

S306: Adjust the brightness of the observed image according to the display parameter value corresponding to the observed image.

The method for adjusting the image brightness proposed in the embodiment of the present application first obtains the observed image; then separates the background image corresponding to the observed image from the observed image; then determines the display parameter value corresponding to the observed image according to the background image; and finally adjusts the brightness of the observed image according to the display parameter value corresponding to the observed image. That is to say, the present application can determine the display parameter value corresponding to the observed image in the background image corresponding to the observed image, so that the brightness of the observed image can be adjusted according to the display parameter value corresponding to the observed image. In the existing method for adjusting the image brightness, a fixed display parameter value is used to adjust the brightness of different observed images, and the appropriate display parameter value cannot be intelligently selected according to the brightness distribution of the observed image itself. Because the present application adopts the technical means of separating the background image corresponding to the observed image from the observed image, and determining the display parameter value corresponding to the observed image according to the background image, it overcomes the technical problem that the fixed display parameter value is used to adjust the brightness of different observed images in the prior art, and the appropriate display parameter value cannot be intelligently selected according to the brightness distribution of the observed image itself. The technical solution provided by the present application can intelligently select the appropriate display parameter value according to the brightness distribution of the observed image itself, so that the brightness distribution of the observed image is more reasonable; and the technical solution of the embodiment of the present application is simple and convenient to implement, easy to popularize, and has a wider range of application.

Embodiment 3

FIG5 is a flow chart of a method for adjusting image brightness provided in Embodiment 3 of the present application. As shown in FIG5 , the method for adjusting image brightness may include the following steps:

S501, obtaining an observed image; wherein the observed image is an image in a red, green and blue color space.

S502: Separate a green channel image corresponding to the observed image from the observed image.

S503, calculating the mean and standard deviation of each pixel in the green channel image; wherein the pixel points in the green channel image include: sampling points and non-sampling points.

S504: Separate a background image corresponding to the green channel image from the green channel image according to the mean and standard deviation of each pixel point in the green channel image and the pixel value of each pixel point.

During the image acquisition process, the image brightness and contrast will produce deformation on the original image, and finally the image observed by the human eye is obtained. This deformation can be described by the following observation model: I(x,y)＝C(x,y)×I ⁰ (x,y)+L(x,y); where I(x,y) represents the pixel value of each pixel in the observed image; I ⁰ (x,y) represents the pixel value of each pixel in the original image; C(x,y) represents the contrast drift factor corresponding to each pixel in the original image; L(x,y) represents the brightness drift factor corresponding to each pixel in the original image. Furthermore, the original image refers to an ideal fundus image that does not contain the influence of non-uniform brightness and contrast. The original image can be regarded as a superposition of an ideal background image and a foreground image: Among them,/> Represents the pixel value of each pixel in the foreground image; Represents the pixel value of each pixel in the background image. In the foreground image of the original fundus image, /> It is the foreground of the retinal area of the fundus, including the vascular structure, optic disc, optic cup and any visible lesions;/> It is the background of the retinal area of the fundus, and does not contain vascular structures, optic discs, optic cups, and any visible lesions. According to the above observation model description, the formula for the original image can be obtained: /> It can be seen that if the real brightness drift factor L(x,y) and contrast drift factor C(x,y) corresponding to each pixel in the original image can be determined, the pixel value I ⁰ (x,y) of each pixel in the original image can be obtained according to the above formula. However, the real brightness drift factor L(x,y) and contrast drift factor C(x,y) corresponding to each pixel in the original image are usually unknown and can only be estimated from the pixel value I(x,y) of each pixel in the observed image. Therefore, the above formula of the original image can be changed to the following form: Among them, I ^0' (x, y) is an estimate of the pixel value of each pixel in the original image; L'(x, y) is an estimate of the brightness drift factor corresponding to each pixel in the original image; C'(x, y) is an estimate of the contrast drift factor corresponding to each pixel in the original image. In order to obtain I ^0' (x, y), L'(x, y) and C'(x, y) must be estimated. The characteristics of the foreground image vary greatly, while the background image changes slowly, which can be modeled using a normal distribution: Among them, μ _b is the ideal uniform brightness value of the background image; σ _b reflects the natural variation characteristics of the background image in the spatial domain.

S505: Calculate a brightness drift factor corresponding to each pixel in the background image according to a predetermined window size and a pixel value of each pixel in the background image.

In a specific embodiment of the present application, the electronic device can calculate the mean and standard deviation of each pixel in the background image based on a predetermined window size _w0 and the pixel value G(x, y) of each pixel in the background image, where the mean of each pixel is the brightness drift factor L'(x, y) corresponding to each pixel; the standard deviation of each pixel is the contrast drift factor C'(x, y) corresponding to each pixel.

Figure 6(a) is a schematic diagram of the structure of the brightness drift factor provided in Example 3 of the present application; Figure 6(b) is a schematic diagram of the structure of the contrast drift factor provided in Example 3 of the present application. As shown in Figures 6(a) and 6(b), w ₀ ∈(15,25), the mean and standard deviation of each pixel point (x,y) in the window w ₀ ×w ₀ are calculated, and the mean is the brightness drift factor corresponding to the pixel point; the standard deviation is the contrast drift factor corresponding to the pixel point. The units of the horizontal and vertical coordinates in Figures 6(a) and 6(b) are the basic units of pixels.

In a specific embodiment of the present application, when the electronic device calculates the mean and standard deviation of each sampling point, the traditional double-layer loop traversal method is very time-consuming, and it takes 1.1 seconds to extract a background image. The present application uses convolution multiplication to replace the loop of image pixels, which greatly improves the code efficiency.

Figure 7 is a schematic diagram of the structure of the convolution kernel provided in Example 3 of the present application. As shown in Figure 7, a convolution kernel k of (w,w) is set, then L'(x,y) can be obtained by multiplying k and the G channel image G(x,y) by convolution: L'(x,y) = k × G(x,y); for C'(x,y):

Then/> Among them, i represents the order of each pixel in the G channel image; N represents the number of pixels in the G channel image; _xi represents the pixel value of the i-th pixel; μ is the arithmetic mean of the i-th pixel to the N-th pixel. This application reduces the background image extraction process from 1.1 seconds to 0.06 seconds, which is 18.3 times faster. The entire adaptive brightness adjustment process only takes 0.2 seconds, and supports real-time amplification during training.

S506: Determine a display parameter value corresponding to the observed image according to a brightness drift factor corresponding to each pixel point in the background image.

In a specific embodiment of the present application, the electronic device can determine the display parameter value corresponding to the observed image based on the brightness drift factor corresponding to each pixel in the background image. Specifically, the electronic device can extract the brightness drift factor L'(x, y) corresponding to each pixel, sort them in order from small to large, and then obtain the p1th percentile value and the p2th percentile value in the sorting result, respectively recorded as: img_percentile_p1 and img_percentile_p2; wherein, p1＜p2; determine the gamma value corresponding to the brightness distribution of the observed image I(x, y) according to the value range of img_percentile_p1 and img_percentile_p2. Preferably, the value range of p1 is: 70～100; the value range of p2 is: 10～40. Further, if the numerical value corresponding to the second percentile is smaller than the first numerical value, the electronic device may determine the gamma value corresponding to the observed image as a gamma value within the first gamma value set; if the numerical value corresponding to the first percentile is greater than the second numerical value, the electronic device may determine the gamma value corresponding to the observed image as a gamma value within the second gamma value set; if the numerical value corresponding to the first percentile is smaller than the third numerical value and the numerical value corresponding to the second percentile is greater than the fourth numerical value, the electronic device may determine the gamma value corresponding to the observed image as a gamma value within the third gamma value set; wherein the first numerical value is smaller than the fourth numerical value; the fourth numerical value is smaller than the third numerical value; and the third numerical value is smaller than the second numerical value. For example, if img_percentile_p2 is lower than the first threshold th1 (the value range of th1 is: 15~45), the gamma value is g1 (the value range of g1 is: 1.9~2.2); if img_percentile_p1 is higher than the second threshold th2 (the value range of th2 is: 170~200), the gamma value is g2 (the value range of g2 is: 0.5~0.8); if img_percentile_p1 is lower than the third threshold th3 (the value range of th3 is: 140~160) and img_percentile_p2 is higher than the fourth threshold th4 (the value range of th4 is: 70~90), the gamma value is g3 (the value range of g3 is: 0.9~1.1); in other cases, the gamma value is g4 (the value range of g4 is: 1.5~1.8).

S507: Adjust the brightness of the observed image according to the display parameter value corresponding to the observed image.

In a specific embodiment of the present application, the electronic device can adjust the brightness of the observed image according to the display parameter value corresponding to the observed image. Specifically, the electronic device can first calculate the brightness gain matrix of the observed image according to the gamma value corresponding to the observed image; and then adjust the brightness of the observed image according to the brightness gain matrix. Since the RGB channels contain both brightness information and color information, they are interrelated. In order to obtain a color-independent brightness gain matrix, the observed image can be first converted from the RGB space to the HSV space; then the gamma value corresponding to the observed image is used to adjust the brightness of each pixel in the V channel image corresponding to the observed image; and then the brightness value V' after adjustment and the brightness value V before adjustment of each pixel in the V channel image are determined to be the brightness gain matrix G(x,y)=V'/V of the observed image. In order to enhance the brightness while ensuring that the color information remains unchanged, the three channels of R, G, and B should be adjusted in the same proportion: Among them, r'(x,y) is the brightness value of each pixel in the R channel image after adjustment; r(x,y) is the brightness value of each pixel in the R channel image before adjustment; g'(x,y) is the brightness value of each pixel in the G channel image after adjustment; g(x,y) is the brightness value of each pixel in the G channel image before adjustment; b'(x,y) is the brightness value of each pixel in the B channel image after adjustment; b(x,y) is the brightness value of each pixel in the B channel image before adjustment. So by applying G(x,y) to the RGB channels respectively, we get the image after brightness adjustment. If the gamma value is corrected directly in the RGB space, the color information will also be changed. The brightness gain matrix is based on gamma value correction and is a more reasonable way to increase brightness. The choice of gamma value determines the direction of image brightness adjustment.

FIG8 is a schematic diagram of the comparison of the image brightness before and after adjustment provided by the third embodiment of the present application. As shown in FIG8, it can be seen that the originally dark places are adjusted to the normal brightness level, while the originally bright places, such as the optic disc area, remain unchanged, and the brightness distribution of the adjusted image is uniform. For a normal fundus image whose original image brightness distribution is very uniform, the gamma value will also be automatically taken as 1, that is, the original distribution will not be changed. The present application can adjust the image brightness according to the image's own brightness distribution, so that the image is close to the training set distribution, thereby effectively responding to various actual combat scenarios, so that the automatic screening system can perform disease screening more accurately and with high quality, and minimize misdiagnosis caused by low quality; while adaptively adjusting the brightness distribution, the original image color distribution is not changed, and the naturalness of the fundus image is retained; in addition, the present application is time-efficient and supports real-time enhancement during training; while the existing methods are all relatively long, and cannot support online processing during model training; moreover, the present application can also perform reverse enhancement, that is, a reverse gamma value is determined according to the brightness distribution of the original image itself, so as to simulate the low-quality image in the real scene during the training process, so that the model is more robust to fundus images with uneven brightness distribution.

The method for adjusting the image brightness proposed in the embodiment of the present application first obtains the observed image; then separates the background image corresponding to the observed image from the observed image; then determines the display parameter value corresponding to the observed image according to the background image; and finally adjusts the brightness of the observed image according to the display parameter value corresponding to the observed image. That is to say, the present application can determine the display parameter value corresponding to the observed image in the background image corresponding to the observed image, so that the brightness of the observed image can be adjusted according to the display parameter value corresponding to the observed image. In the existing method for adjusting the image brightness, a fixed display parameter value is used to adjust the brightness of different observed images, and the appropriate display parameter value cannot be intelligently selected according to the brightness distribution of the observed image itself. Because the present application adopts the technical means of separating the background image corresponding to the observed image from the observed image, and determining the display parameter value corresponding to the observed image according to the background image, it overcomes the technical problem that the fixed display parameter value is used to adjust the brightness of different observed images in the prior art, and the appropriate display parameter value cannot be intelligently selected according to the brightness distribution of the observed image itself. The technical solution provided by the present application can intelligently select the appropriate display parameter value according to the brightness distribution of the observed image itself, so that the brightness distribution of the observed image is more reasonable; and the technical solution of the embodiment of the present application is simple and convenient to implement, easy to popularize, and has a wider range of application.

Embodiment 4

FIG9 is a schematic diagram of the structure of an apparatus for adjusting image brightness provided in Embodiment 4 of the present application. As shown in FIG9 , the apparatus 900 includes: an acquisition module 901, a separation module 902, a determination module 903 and an adjustment module 904;

The acquisition module 901 is used to acquire an observed image; wherein the observed image is an image in a red, green and blue color space;

The separation module 902 is used to separate the background image corresponding to the observation image from the observation image;

The determination module 903 is used to determine the display parameter value corresponding to the observed image according to the background image;

The adjustment module 904 is used to adjust the brightness of the observed image according to the display parameter value corresponding to the observed image.

FIG10 is a schematic diagram of the structure of the separation module provided in the fourth embodiment of the present application. As shown in FIG10 , the separation module 902 includes: a separation submodule 9021 and a first calculation submodule 9022;

The separation submodule 9021 is used to separate a green channel image corresponding to the observation image from the observation image;

The first calculation submodule 9022 is used to calculate the mean and standard deviation of each pixel in the green channel image; wherein the pixel points in the green channel image include: sampling points and non-sampling points;

The separation submodule 9021 is further used to separate the background image corresponding to the green channel image from the green channel image according to the mean value and standard deviation of each pixel point in the green channel image and the pixel value of each pixel point.

Furthermore, the first calculation submodule 9022 is specifically used to calculate the mean and standard deviation of each sampling point in the green channel image according to the predetermined window size corresponding to each sampling point; and calculate the mean and standard deviation of each non-sampling point in the green channel according to the mean and standard deviation of each sampling point in the green channel.

Furthermore, the determination module 903 is further configured to sample the observed image to obtain sampling points of the observed image; and determine the window size corresponding to each sampling point according to the distance between each sampling point in the observed image and the center point.

Furthermore, the separation submodule 9021 is specifically used to extract a pixel point from the pixels in the green channel image as the current pixel point, and calculate the Mahalanobis distance corresponding to the current pixel point according to the mean and standard deviation of the current pixel point and the pixel value of the current pixel point; if the Mahalanobis distance corresponding to the current pixel point is less than or equal to a preset threshold, the current pixel point is used as a pixel point in the background image corresponding to the green channel image; if the Mahalanobis distance corresponding to the current pixel point is greater than the preset threshold, the current pixel point is used as a pixel point in the foreground image corresponding to the green channel image; and the above operations are repeated until each pixel point in the green channel image is determined as a pixel point in the background image or a pixel point in the foreground image.

FIG11 is a schematic diagram of the structure of the determination module provided in the fourth embodiment of the present application. As shown in FIG11 , the determination module 903 includes: a second calculation submodule 9031 and a determination submodule 9032; wherein,

The second calculation submodule 9031 is used to calculate the brightness drift factor corresponding to each pixel in the background image according to a predetermined window size and a pixel value of each pixel in the background image;

The determination submodule 9032 is used to determine the display parameter value corresponding to the observed image according to the brightness drift factor corresponding to each pixel point in the background image.

Furthermore, the determination submodule 9032 is specifically used to sort the brightness drift factors corresponding to all the pixels in the background image according to the brightness drift factors corresponding to each pixel in the background image; determine the numerical value corresponding to the first percentile and the numerical value corresponding to the second percentile in the sorted brightness drift factors; wherein the first percentile is smaller than the second percentile; and determine the display parameter value corresponding to the observed image according to the distribution range of the numerical value corresponding to the first percentile and/or the numerical value corresponding to the second percentile.

Furthermore, the determination submodule 9032 is specifically used to determine the display parameter value corresponding to the observed image as a display parameter value within a first display parameter value set if the value corresponding to the second percentile is smaller than the first value; to determine the display parameter value corresponding to the observed image as a display parameter value within a second display parameter value set if the value corresponding to the first percentile is larger than the second value; to determine the display parameter value corresponding to the observed image as a display parameter value within a third display parameter value set if the value corresponding to the first percentile is smaller than a third value and the value corresponding to the second percentile is larger than a fourth value; wherein the first value is smaller than the fourth value; the fourth value is smaller than the third value; and the third value is smaller than the second value.

FIG12 is a schematic diagram of the structure of the adjustment module provided in the fourth embodiment of the present application. As shown in FIG12, the adjustment module 904 includes: a third calculation submodule 9041 and an adjustment submodule 9042; wherein,

The third calculation submodule 9041 is used to calculate the brightness gain matrix of the observed image according to the display parameter value corresponding to the observed image;

The adjustment submodule 9042 is used to adjust the brightness of the observed image according to the brightness gain matrix.

Furthermore, the third calculation submodule 9041 is specifically used to convert the observed image from the red, green and blue color space into a hue, saturation and brightness space; use the display parameter value corresponding to the observed image to adjust the brightness of each pixel in the brightness channel image corresponding to the observed image; and determine the brightness gain matrix of the observed image based on the brightness value of each pixel in the brightness channel image after adjustment and the brightness value before adjustment.

The above-mentioned image brightness adjustment device can execute the method provided by any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in this embodiment, please refer to the image brightness adjustment method provided by any embodiment of the present application.

Embodiment 5

According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

As shown in Figure 13, it is a block diagram of an electronic device according to the method for adjusting the image brightness of an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and/or required herein.

As shown in Figure 13, the electronic device includes: one or more processors 1301, memory 1302, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input/output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and/or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). In Figure 13, a processor 1301 is taken as an example.

The memory 1302 is a non-transient computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable the at least one processor to perform the method for adjusting the image brightness provided in the present application. The non-transient computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to perform the method for adjusting the image brightness provided in the present application.

The memory 1302, as a non-transient computer-readable storage medium, can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions/modules corresponding to the method for adjusting the image brightness in the embodiment of the present application (for example, the acquisition module 901, separation module 902, determination module 903 and adjustment module 904 shown in FIG. 9). The processor 1301 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 1302, that is, implements the method for adjusting the image brightness in the above method embodiment.

The memory 1302 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created according to the use of the electronic device of the method for adjusting the image brightness, etc. In addition, the memory 1302 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1302 may optionally include a memory remotely arranged relative to the processor 1301, and these remote memories may be connected to the electronic device of the method for adjusting the image brightness via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The electronic device of the method for adjusting image brightness may further include: an input device 1303 and an output device 1304. The processor 1301, the memory 1302, the input device 1303 and the output device 1304 may be connected via a bus or other means, and FIG13 takes the bus connection as an example.

The input device 1303 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device of the image brightness adjustment method, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 1304 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and/or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and/or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and/or data to a programmable processor.

To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

According to the technical solution of the embodiment of the present application, the observation image is first obtained; then the background image corresponding to the observation image is separated from the observation image; then the display parameter value corresponding to the observation image is determined according to the background image; finally, the brightness of the observation image is adjusted according to the display parameter value corresponding to the observation image. That is to say, the present application can determine the display parameter value corresponding to the observation image in the background image corresponding to the observation image, so that the brightness of the observation image can be adjusted according to the display parameter value corresponding to the observation image. In the existing image brightness adjustment method, the brightness of different observation images is adjusted using a fixed display parameter value, and the appropriate display parameter value cannot be intelligently selected according to the brightness distribution of the observation image itself. Because the present application adopts the technical means of separating the background image corresponding to the observation image from the observation image, and determining the display parameter value corresponding to the observation image according to the background image, it overcomes the technical problem that the brightness of different observation images is adjusted using a fixed display parameter value in the prior art, and the appropriate display parameter value cannot be intelligently selected according to the brightness distribution of the observation image itself. The technical solution provided by the present application can intelligently select the appropriate display parameter value according to the brightness distribution of the observation image itself, so that the brightness distribution of the observation image is more reasonable; and the technical solution of the embodiment of the present application is simple and convenient to implement, easy to popularize, and has a wider range of application.

It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims (18)

1. A method for adjusting brightness of an image, the method comprising:

obtaining an observation image; wherein the observed image is an image of red, green and blue color space;

separating a background image corresponding to the observed image from the observed image;

calculating brightness drift factors corresponding to all pixel points in the background image according to the predetermined window size and the pixel values of all pixel points in the background image; ordering the brightness drift factors corresponding to all the pixel points according to the brightness drift factors corresponding to all the pixel points in the background image; determining a value corresponding to the first percentile and a value corresponding to the second percentile in the sorted brightness drift factors; wherein the first percentile is less than the second percentile; according to the value corresponding to the first percentile and/or the distribution interval of the value corresponding to the second percentile, determining the display parameter value corresponding to the observed image;

And adjusting the brightness of the observation image according to the display parameter value corresponding to the observation image.

2. The method of claim 1, wherein separating a background map from the observed image comprises:

separating a green channel image corresponding to the observation image from the observation image;

calculating the mean value and standard deviation of each pixel point in the green channel image; wherein, the pixel point in the green channel image includes: sampling points and non-sampling points;

and separating a background image corresponding to the green channel image from the green channel image according to the mean value and standard deviation of each pixel point in the green channel image and the pixel value of each pixel point.

3. The method of claim 2, wherein the calculating the mean and standard deviation of each pixel in the green channel image comprises:

calculating the mean value and standard deviation of each sampling point in the green channel image according to the predetermined window size corresponding to each sampling point;

and calculating the mean value and the standard deviation of each non-sampling point in the green channel according to the mean value and the standard deviation of each sampling point in the green channel.

4. A method according to claim 3, characterized in that before said calculating the mean and standard deviation of the respective sampling points in the green channel image, the method further comprises:

sampling the observation image to obtain each sampling point of the observation image;

and determining the size of a window corresponding to each sampling point according to the distance between each sampling point and the center point in the observed image.

5. The method according to claim 2, wherein the separating the background image corresponding to the green channel image from the green channel image according to the mean and standard deviation of each pixel point and the pixel value of each pixel point includes:

extracting a pixel point from the pixel points in the green channel image as a current pixel point, and calculating the mahalanobis distance corresponding to the current pixel point according to the mean value and standard deviation of the current pixel point and the pixel value of the current pixel point;

if the mahalanobis distance corresponding to the current pixel point is smaller than or equal to a preset threshold value, the current pixel point is used as one pixel point in the background image corresponding to the green channel image; if the mahalanobis distance corresponding to the current pixel point is larger than the preset threshold value, the current pixel point is used as one pixel point in the foreground image corresponding to the green channel image; and repeatedly executing the operation until each pixel point in the green channel image is determined as the pixel point in the background image or the pixel point in the foreground image.

6. The method according to claim 1, wherein determining the display parameter value corresponding to the observed image for the distribution interval of the values corresponding to the first percentile and/or the values corresponding to the second percentile comprises:

if the value corresponding to the second percentile is smaller than the first value, determining the display parameter value corresponding to the observed image as one display parameter value in the first display parameter value set;

if the value corresponding to the first percentile is larger than the second value, determining the display parameter value corresponding to the observation image as one display parameter value in a second display parameter value set;

if the value corresponding to the first percentile is smaller than the third value and the value corresponding to the second percentile is larger than the fourth value, determining the display parameter value corresponding to the observed image as one display parameter value in a third display parameter value set; wherein the first value is less than the fourth value; the fourth value is less than the third value; the third value is less than the second value.

7. The method according to claim 1, wherein adjusting the brightness of the observed image according to the display parameter value corresponding to the observed image comprises:

Calculating a brightness gain matrix of the observation image according to the display parameter value corresponding to the observation image;

and adjusting the brightness of the observed image according to the brightness gain matrix.

8. The method of claim 7, wherein calculating a brightness gain matrix of the observed image based on the display parameter values corresponding to the observed image comprises:

converting the observed image from the red, green, and blue color space to a hue saturation brightness space;

adjusting the brightness of each pixel point in the brightness channel image corresponding to the observed image by using the display parameter value corresponding to the observed image;

and determining a brightness gain matrix of the observed image according to the brightness value of each pixel point in the brightness channel image after adjustment and the brightness value before adjustment.

9. An apparatus for adjusting brightness of an image, the apparatus comprising: the device comprises an acquisition module, a separation module, a determination module and an adjustment module; wherein,

the acquisition module is used for acquiring an observation image; wherein the observed image is an image of red, green and blue color space;

the separation module is used for separating a background image corresponding to the observation image from the observation image;

The determining module is used for determining a display parameter value corresponding to the observation image according to the background image; wherein the determining module comprises: the second calculation submodule and the determination submodule; the second calculation sub-module is used for calculating brightness drift factors corresponding to all pixel points in the background image according to the predetermined window size and the pixel values of all pixel points in the background image; the determination submodule is used for sequencing the brightness drift factors corresponding to all the pixel points according to the brightness drift factors corresponding to all the pixel points in the background image; determining a value corresponding to the first percentile and a value corresponding to the second percentile in the sorted brightness drift factors; wherein the first percentile is less than the second percentile; according to the value corresponding to the first percentile and/or the distribution interval of the value corresponding to the second percentile, determining the display parameter value corresponding to the observed image;

the adjusting module is used for adjusting the brightness of the observation image according to the display parameter value corresponding to the observation image.

10. The apparatus of claim 9, wherein the separation module comprises: a separation sub-module and a first calculation sub-module; wherein,

The separation submodule is used for separating a green channel image corresponding to the observation image from the observation image;

the first computing submodule is used for computing the mean value and standard deviation of each pixel point in the green channel image; wherein, the pixel point in the green channel image includes: sampling points and non-sampling points;

the separation submodule is further used for separating a background image corresponding to the green channel image from the green channel image according to the mean value and standard deviation of each pixel point in the green channel image and the pixel value of each pixel point.

11. The apparatus according to claim 10, wherein:

the first calculating submodule is specifically used for calculating the mean value and standard deviation of each sampling point in the green channel image according to the window size corresponding to each predetermined sampling point; and calculating the mean value and the standard deviation of each non-sampling point in the green channel according to the mean value and the standard deviation of each sampling point in the green channel.

12. The apparatus according to claim 11, wherein:

the determining module is further used for sampling the observation image to obtain each sampling point of the observation image; and determining the size of a window corresponding to each sampling point according to the distance between each sampling point and the center point in the observed image.

13. The apparatus according to claim 10, wherein:

the separation submodule is specifically configured to extract a pixel point from pixel points in the green channel image as a current pixel point, and calculate a mahalanobis distance corresponding to the current pixel point according to a mean value and a standard deviation of the current pixel point and a pixel value of the current pixel point; if the mahalanobis distance corresponding to the current pixel point is smaller than or equal to a preset threshold value, the current pixel point is used as one pixel point in the background image corresponding to the green channel image; if the mahalanobis distance corresponding to the current pixel point is larger than the preset threshold value, the current pixel point is used as one pixel point in the foreground image corresponding to the green channel image; and repeatedly executing the operation until each pixel point in the green channel image is determined as the pixel point in the background image or the pixel point in the foreground image.

14. The apparatus according to claim 9, wherein:

the determining submodule is specifically configured to determine a display parameter value corresponding to the observed image as one display parameter value in the first display parameter value set if the value corresponding to the second percentile is smaller than the first value; if the value corresponding to the first percentile is larger than the second value, determining the display parameter value corresponding to the observation image as one display parameter value in a second display parameter value set; if the value corresponding to the first percentile is smaller than the third value and the value corresponding to the second percentile is larger than the fourth value, determining the display parameter value corresponding to the observed image as one display parameter value in a third display parameter value set; wherein the first value is less than the fourth value; the fourth value is less than the third value; the third value is less than the second value.

15. The apparatus of claim 9, wherein the adjustment module comprises: a third calculation sub-module and an adjustment sub-module; wherein,

the third calculation sub-module is used for calculating a brightness gain matrix of the observed image according to the display parameter value corresponding to the observed image;

and the adjustment submodule is used for adjusting the brightness of the observation image according to the brightness gain matrix.

16. The apparatus according to claim 15, wherein:

the third calculation sub-module is specifically configured to convert the observed image from the red, green and blue color space to a hue saturation brightness space; adjusting the brightness of each pixel point in the brightness channel image corresponding to the observed image by using the display parameter value corresponding to the observed image; and determining a brightness gain matrix of the observed image according to the brightness value of each pixel point in the brightness channel image after adjustment and the brightness value before adjustment.

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.