WO2022121893A1

WO2022121893A1 - Image processing method and apparatus, and computer device and storage medium

Info

Publication number: WO2022121893A1
Application number: PCT/CN2021/136086
Authority: WO
Inventors: 谢朝毅; 谢亮
Original assignee: 影石创新科技股份有限公司
Priority date: 2020-12-07
Filing date: 2021-12-07
Publication date: 2022-06-16
Also published as: CN112541868A

Abstract

An image processing method and apparatus, and a computer device and a storage medium. The method comprises: performing image processing on an image to be processed to obtain a processed image (S202); acquiring color channel values corresponding to pixel points in the processed image, and compiling statistics on the color channel values to obtain a channel statistical value corresponding to the processed image (S204); acquiring a saturation enhancement pixel point in the processed image, and calculating, on the basis of color channel values of the saturation enhancement pixel point and the channel statistical value, channel color ratios corresponding to color channels of the saturation enhancement pixel point (S206); selecting the minimum value from among the channel color ratios corresponding to the color channels of the saturation enhancement pixel point as a color suppression ratio corresponding to the color channels of the saturation enhancement pixel point (S208); and performing color suppression processing on the color channels of the saturation enhancement pixel point on the basis of the color suppression ratio corresponding to the color channels of the saturation enhancement pixel point, so as to obtain a target image (S210). By means of the method, the image processing efficiency can be improved.

Description

Image processing method, apparatus, computer equipment and storage medium

technical field

The present application relates to the technical field of image processing, and in particular, to an image processing method, apparatus, computer equipment and storage medium.

Background technique

With the development of image processing technology, users have higher and higher requirements for image processing effects. For example, the requirements for the processing effect of saturation in image processing, saturation is an important factor for evaluating the effect of image processing. Saturation refers to the vividness of the color, also known as the purity of the color.

technical problem

For images or videos straight from the camera, if the dynamic range is not enough and the overall contrast of the image quality is not enough, the overall image or video will look blurry. The method cannot solve these problems well, and there are more or less distortions after processing. For example, the classic histogram equalization algorithm can improve the overall contrast of the image, but the contrast of the image will be oversaturated and the overall image quality will be degraded; there are also corresponding deep learning algorithms (such as DPED), which will lead to oversaturation of the overall image quality. Solid color overflow, etc.

To sum up, it can be seen that there is currently no image processing method that can automatically process the video or picture content captured by the user to achieve the effect of improving the dynamic range of the picture and improving the contrast and saturation. The current image processing method has image processing effects. Poor, the output image quality is low.

technical solutions

Based on this, it is necessary to provide an image processing method, device, computer equipment and storage medium that can improve the dynamic range of the picture, improve the contrast saturation, and improve the overall quality of the output image in response to the above technical problems.

An image processing method, the method comprising:

Perform image processing on the image to be processed to obtain a processed image;

Acquire the color channel value corresponding to each pixel in the processed image, perform statistics on the color channel value, and obtain the channel statistical value corresponding to the processed image;

Obtaining the saturation enhancement pixel points in the processed image, and calculating the channel color ratio corresponding to each color channel of the saturation enhancement pixel point based on the value of each color channel of the saturation enhancement pixel point and the channel statistical value;

The minimum value is selected from the channel color ratios corresponding to each color channel of the saturation boosting pixel as the color suppression ratio corresponding to each color channel of the saturation boosting pixel;

Color suppression processing is performed on each color channel of the saturation boosting pixel based on the color suppression ratio corresponding to each color channel of the saturation boosting pixel to obtain a target image.

In one of the embodiments, the acquiring the saturation enhancement pixels in the processed image includes:

obtaining a grayscale image corresponding to the image to be processed;

According to the pixel value of each pixel in the processed image and the pixel value of the pixel at the corresponding position in the grayscale image, determine the pixel boost ratio of each pixel in the processed image relative to the grayscale image;

Pixels whose pixel enhancement ratio is greater than a preset threshold in the processed image are used as saturation enhancement pixels.

In one of the embodiments, calculating the channel color ratio corresponding to each color channel of the saturation-boosted pixel based on the value of each color channel of the saturation-boosted pixel and the channel statistical value includes:

Calculate the change value of each color channel value of the saturation boosting pixel point relative to the channel statistical value;

Determine the adjustment weight corresponding to each color channel value of the saturation boosting pixel point according to the change value, and the color channel value adjustment weight has a negative correlation with the change value;

According to the adjustment weights corresponding to the respective color channel values of the saturation boosting pixels, the channel color ratios corresponding to the respective color channels of the saturation boosting pixels are calculated and obtained.

In one of the embodiments, according to the adjustment weights corresponding to the respective color channel values of the saturation enhancement pixels, the calculated channel color ratios corresponding to the respective color channels of the saturation enhancement pixels include:

Calculate the first ratio according to the product of the adjustment weight corresponding to each color channel value of the saturation boosting pixel and the pixel boosting ratio of the saturation boosting pixel;

The second ratio is obtained by subtracting the adjustment weight corresponding to each color channel value of the saturation boosting pixel from the preset value;

The first ratio and the second ratio are added to obtain the channel color ratio corresponding to each color channel of the saturation boosting pixel.

In one of the embodiments, the method further includes: acquiring pixels whose pixel values are greater than a preset threshold in the grayscale image as highlight pixels;

Multiply the pixel boost ratio corresponding to the highlight pixel point by the first coefficient to obtain a third ratio; the first coefficient and the pixel value of the pixel point corresponding to the highlight pixel point in the processed image are negative relationship;

Subtract the first coefficient from the preset value to obtain a fourth ratio;

The third ratio and the fourth ratio are added to obtain the channel color ratio corresponding to each color channel of the highlight pixel point.

In one embodiment, performing image processing on the image to be processed to obtain the processed image includes:

Perform image processing on the image to be processed to obtain an intermediate image;

Obtain the first pixel point whose pixel value is less than the preset threshold in the grayscale image corresponding to the image to be processed, and use the pixel point corresponding to the first pixel point in the intermediate image as the second pixel point;

Obtain the noise suppression weight of the corresponding second pixel point according to the pixel value of the first pixel point in the grayscale image, and the pixel value and the noise suppression weight have a correlation;

Noise suppression is performed on the second pixel in the intermediate image according to the noise suppression weight to obtain a processed image.

Obtain the grayscale image corresponding to the image to be processed;

Performing a brightening process on the grayscale image to obtain a brightened image;

performing contrast enhancement processing on the grayscale image to obtain a contrast enhancement image;

Perform fusion processing on the grayscale image, the brightened image, and the contrast-enhanced image to obtain a processed image.

An image processing device, the device comprising:

The processing image acquisition module is used to perform image processing on the image to be processed to obtain the processed image;

a channel statistical value acquisition module, configured to acquire the color channel value corresponding to each pixel in the processed image, perform statistics on the color channel value, and obtain the channel statistical value corresponding to the processed image;

The channel color ratio acquisition module is used to acquire the saturation enhancement pixel points in the processed image, and based on the respective color channel values of the saturation enhancement pixel points and the channel statistical values, calculate and obtain each saturation enhancement pixel point. The channel color ratio corresponding to the color channel;

A color suppression ratio acquisition module, configured to select a minimum value from the channel color ratios corresponding to each color channel of the saturation boosting pixel as the color suppression ratio corresponding to each color channel of the saturation boosting pixel;

A target image acquisition module, configured to perform color suppression processing on each color channel of the saturation enhancement pixel based on the color suppression ratio corresponding to each color channel of the saturation enhancement pixel to obtain a target image.

A computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

Obtaining the color channel value corresponding to each pixel in the processed image, and performing statistics on the color channel value to obtain the channel statistical value corresponding to the processed image;

Acquire the saturation enhancement pixel points in the processed image, and calculate the channel color ratio corresponding to each color channel of the saturation enhancement pixel point based on the value of each color channel of the saturation enhancement pixel point and the channel statistical value;

Based on the color suppression ratios corresponding to the respective color channels of the saturation-enhanced pixels, color suppression processing is performed on the respective color channels of the saturation-enhanced pixels to obtain a target image.

A computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

beneficial effect

The above image processing method, device, computer equipment and storage medium, after image processing is performed on the image to be processed, a processed image is obtained, the color channel value corresponding to each pixel in the processed image is obtained, and the color channel value is counted. Obtain the channel statistical value corresponding to the processed image; and then obtain the saturation enhancement pixel in the above-mentioned processed image, and calculate the channel color ratio corresponding to the color channel based on each color channel value of the saturation enhanced pixel and the channel statistical value. The minimum value among the color ratios is selected as the color suppression ratio corresponding to the saturation enhancement pixel, so the color suppression processing can be performed on the pixels with high saturation, which improves the image processing effect.

Description of drawings

Fig. 1 is the application environment diagram of the image processing method in one embodiment;

Fig. 2 is a schematic flowchart of an image processing method;

FIG. 3 is a schematic flowchart of a method for obtaining saturation-boosting pixels in a processed image in one embodiment;

FIG. 4 is a schematic flowchart of a method for obtaining saturation-boosting pixels in a processed image in another embodiment;

FIG. 5 is a schematic flowchart of a method for obtaining saturation-boosting pixels in a processed image in another embodiment;

6 is a schematic flowchart of an image processing method in another embodiment;

7 is a schematic flowchart of an image processing method to obtain an image processing method in an embodiment;

8 is a schematic flowchart of a method for processing an image by performing image processing on an image to be processed in another embodiment;

9 is a structural block diagram of an image processing apparatus in one embodiment;

Figure 10 is a diagram of the internal structure of a computer device in one embodiment.

Embodiments of the present invention

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

The image processing method provided in this application can be applied to the application environment shown in FIG. 1 . The application environment includes an image capturing device 102 and a terminal 104 , wherein the image capturing device 102 and the terminal 104 are connected in communication. After the image acquisition device 102 collects the image to be processed, it is transmitted to the terminal 104, and the terminal 104 obtains the image to be processed. The terminal 104 can count the color channel values corresponding to each pixel of the obtained image to be processed, and obtain Process the channel statistics corresponding to the image; and obtain the saturation enhancement pixels in the processed image, and calculate the channel color ratio corresponding to the color channel based on the respective color channel values and the channel statistics of the above saturation enhancement pixels; Select the minimum value among the channel color ratios corresponding to each color channel corresponding to the pixel, as the color suppression ratio corresponding to the saturation boosting pixel; perform color suppression processing on the saturation boosting pixel based on the color suppression ratio corresponding to the saturation boosting pixel , get the target image. The image capturing device 102 may be, but is not limited to, various devices having an image capturing function, and may be distributed outside the terminal 104 or inside the terminal 104 . For example: various cameras, scanners, various cameras, and image capture cards distributed outside the terminal 104 . The terminal 104 may be, but is not limited to, various cameras, personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices.

It can be understood that the method provided by the embodiment of the present application may also be executed by a server.

In one embodiment, as shown in FIG. 2, an image processing method is provided, and the method is applied to the terminal in FIG. 1 as an example for description, including the following steps:

Step 202: Perform image processing on the image to be processed to obtain a processed image.

The processed image refers to an image after image processing.

Specifically, the terminal may use the image acquired in real time as the image to be processed, and the display effect of the image to be processed is not ideal, so it is necessary to perform image processing on the image to be processed to obtain the processed image.

In one embodiment, the terminal may also obtain the processed image by acquiring the to-be-processed image from the memory storing the image, and performing image processing on the to-be-processed image.

In one embodiment, a grayscale image may be obtained by performing grayscale processing on the image to be processed, and a brightened image may be obtained by performing a brightening process on the grayscale image, and a contrast enhancement process may be performed on the grayscale image to obtain a contrast enhanced image. The brightness image, the brightened image and the contrast enhanced image are fused to obtain the intermediate processed image, and the intermediate processed image obtained at this time can be used as the processed image.

Further, in one embodiment, the intermediate processed image obtained by the fusion processing of the grayscale image, the brightened image and the contrast enhanced image in the above-mentioned embodiment is selected, and noise suppression processing may be further performed, and the obtained processed image is used as the processing image. image.

Further, in the above embodiment, noise suppression processing is performed on the intermediate processed image (ie, the intermediate image), which may specifically be:

Obtaining the first pixel point in the grayscale image corresponding to the image to be processed whose pixel value is less than the preset threshold, and using the pixel point corresponding to the first pixel point in the intermediate image as the second pixel point;

The noise suppression weight of the corresponding second pixel point is obtained according to the pixel value of the first pixel point in the grayscale image, and the pixel value and the noise suppression weight have a correlation;

Step 204: Acquire color channel values corresponding to each pixel in the processed image, perform statistics on the color channel values, and obtain channel statistical values corresponding to the processed image.

The color channel value refers to the value of each channel after each pixel is divided into three channels: R (red), G (green), and B (blue). The value of each channel can be represented using the corresponding pixel value for each channel. For example, for a certain pixel, the color channel values of the RGB three channels are 199, 237 and 204 respectively. The channel statistics value refers to the color channel value that can reflect the overall data characteristics of the color channel value. The channel statistics can refer to the average of the three color channel values, or the median, etc.

Specifically, the terminal can acquire the processed image, use its own pixel point analysis software or analysis tool to detect the color channel value corresponding to each pixel point, and obtain the channel statistical value corresponding to the processed image through calculation.

Step 206: Acquire the saturation enhancement pixels in the processed image, and calculate the channel color ratio corresponding to each color channel of the saturation enhancement pixel based on the value of each color channel and the channel statistics value of the saturation enhancement pixel.

Wherein, the saturation-enhanced pixel points refer to the pixel points whose saturation degree of the processed image point is improved relative to the saturation degree of the original pixel degree point in the to-be-processed image. The channel color ratio refers to the respective proportions of the RGB three-channel colors in each pixel corresponding to each pixel.

Specifically, after acquiring the color channel value corresponding to each pixel point, the channel statistics value corresponding to the processed image is obtained by calculation, and the saturation enhancement pixel point in the processed image is acquired, and based on the saturation enhancement pixel point in the processed image, the obtained Channel color ratio.

In one embodiment, the color saturation of a certain channel of the image has a positive correlation with the absolute value of the difference between the corresponding channel statistical values. The greater the absolute value of the difference between the color channel value and the processed image, the higher the color saturation of a certain channel of the image. For example, the greater the absolute value of the difference between the red color channel value represented by R in the three RGB channels and the processed image, the higher the red saturation of the R channel, and the redder the red in the image.

Step 208: Select the minimum value from the channel color ratios corresponding to each color channel of the saturation boosting pixel as the color suppression ratio corresponding to each color channel of the saturation boosting pixel.

The color suppression ratio refers to a ratio used to suppress excessive color saturation. By establishing a functional relationship between the ratio and the corresponding channel color, the image processing effect can be improved.

Specifically, because the channel color ratio is a value greater than 1, the closer the value is to 1, the higher the saturation of the image, so the minimum value selected in the channel color ratio is the value closest to 1, and this value is used as color suppression Ratio, based on this color suppression ratio, the color suppression processing is performed on the saturation enhancement pixels to obtain the target image.

Step 210 , performing color suppression processing on each color channel of the saturation boosting pixel based on the color suppression ratio corresponding to each color channel of the saturation boosting pixel to obtain a target image.

In one embodiment, after the color suppression ratio is obtained, a functional relationship is established between the pixel value of the saturation boosting pixel and the color suppression ratio, so as to obtain the pixel value of the pixel obtained after the functional relationship is established, so as to play the role of color The effect of the processing is suppressed, and the target image is obtained.

In one embodiment, establishing a functional relationship between the saturation enhancement pixel and the color suppression ratio may be that the color suppression ratio is used as a coefficient, and the pixel value of the saturation enhancement pixel is multiplied by the color suppression ratio, so as to obtain the suppressed pixel, Thereby obtaining the target image.

In the above image processing method, after image processing is performed on the image to be processed, a processed image is obtained, the color channel value corresponding to each pixel in the processed image is obtained, and the channel corresponding to the processed image is obtained by counting the color channel values. Statistical value; then by obtaining the saturation enhancement pixels in the above-mentioned processed image, the channel color ratio corresponding to the color channel is calculated based on the value of each color channel of the saturation enhancement pixel and the channel statistical value, and the minimum value is selected from the channel color ratio. , as the color suppression ratio corresponding to the saturation enhancement pixel, so the color suppression processing can be performed on the pixel with high saturation, which improves the image processing effect.

In one embodiment, as shown in FIG. 3 , the step of acquiring and processing the saturation-boosting pixels in the image includes:

Step 302: Obtain a grayscale image corresponding to the image to be processed.

Here, the grayscale image refers to an image in which the image is divided into several levels from black to white. Grayscale image can make the transition of the image more smooth and delicate.

In one embodiment, the image to be processed may be correspondingly converted to obtain a converted grayscale image. A grayscale image corresponding to the image to be processed can be obtained by performing corresponding mathematical operations on the image to be processed. For example, to represent a grayscale image as Gray, and to represent the channel color values of the three channels of the image pixel to be processed as R, G, and B, respectively, floating-point arithmetic can be used: Gray=R*0.3+G*0.59+B *0.11, the grayscale image is obtained by calculation.

Step 304, according to the pixel value of each pixel in the processed image and the pixel value of the pixel at the corresponding position in the grayscale image, determine the pixel boost ratio of each pixel in the processed image relative to the grayscale image.

The pixel enhancement ratio refers to the enhancement degree of the pixel value of each pixel point in the processed image relative to the pixel value of the pixel point at the corresponding position in the grayscale image.

Specifically, the pixel value of the pixel point is a numerical value, and there is a positive correlation between the numerical value and the saturation, through which the processing image can be determined to determine the pixel enhancement ratio of the processing image relative to the grayscale image.

In one embodiment, the pixel value of the processed image to determine the pixel enhancement ratio of the processed image relative to the grayscale image can be represented by the multiple relationship between the pixel value of each pixel point in the processed image and the pixel value of the corresponding pixel point in the grayscale image. . For example, assuming that the pixel value of each pixel of the processed image is represented as I, the pixel value of the pixel at the corresponding position in the grayscale image is represented as I1, and the processing image determines that the pixel enhancement ratio of the processed image relative to the grayscale image is represented as ratio _src , then The relationship between the three can be expressed as: ratio _src= (I+1)/(I1+1)

Step 306 , the pixels whose pixel enhancement ratio is greater than the preset threshold in the processed image are regarded as saturation enhancement pixels.

Among them, the preset threshold refers to the set critical value. When it is greater than the critical value, the pixels that meet the conditions are used as saturation enhancement pixels; when it is less than the critical value, the pixels that meet the conditions do not need to be used as saturation enhancement pixels. pixel.

Specifically, after obtaining the pixel boost ratio, the pixels that need to be increased in saturation can be screened out in the form of a preset threshold, and the saturation of the screened out pixels can be adjusted.

In one embodiment, the preset threshold value can be set to a fixed value, and when it is greater than the fixed value, the pixels that meet the conditions are screened out as the pixels whose saturation is to be improved; it can be understood that when it is less than this fixed value, Then the pixels that meet the conditions are not used as pixels to enhance the saturation. For example, if the fixed value is 1, the pixel boost ratio is ratio _src , and when ratio _src is greater than 1, the corresponding pixels in the processed image that meet the conditions will be screened out for saturation boost processing; when ratio _src is less than 1, it will satisfy the The pixels in the processed image under this condition do not undergo saturation enhancement processing.

In this embodiment, the pixel enhancement ratio of the processed image relative to the grayscale image is determined by determining the processing image, a preset threshold is set for the pixel enhancement ratio, and the saturation enhancement pixels are screened out through the preset threshold, so that the saturation enhancement can be accurately determined. The purpose of improving the pixel point.

In one embodiment, as shown in FIG. 4 , the steps are based on the value of each color channel and the statistical value of the channel of the pixel point of saturation enhancement, and the calculated channel color ratio corresponding to each color channel of the pixel point of saturation enhancement includes:

Step 402: Calculate the change value of each color channel value of the saturation boosting pixel point relative to the channel statistical value.

In one embodiment, the change value of the color channel value of each saturation-boosting pixel point relative to the channel statistical value may be a difference value of the color channel value of each saturation-boosting pixel point relative to the channel statistical value. For example, assuming that the color channel value of any saturation boosting pixel is c, the channel statistic value is avg, and the change value of the color channel value of the corresponding saturation boosting pixel relative to the channel statistic value is d, then d is expressed as: d =c-avg

Step 404: Determine the adjustment weights corresponding to each color channel value of the saturation boosting pixel point according to the change value, and the adjustment weight of the color channel value has a negative correlation with the change value.

The adjustment weight refers to the degree of importance that needs to be adjusted for each color channel value of each saturation enhancement pixel. It has a negative correlation with the change value, the larger the change value, the smaller the adjustment weight, and the smaller the change value, the larger the adjustment weight.

In one embodiment, the adjustment weight may be represented by a functional relationship between the change value and the adjustment weight. For example, if any channel adjustment weight is expressed as w(c,avg), the functional relationship between the change value d and the color channel value adjustment weight w(c,avg) can be expressed as:

Step 406: Calculate the channel color ratio corresponding to each color channel of the saturation boosting pixel according to the adjustment weight corresponding to each color channel value of the saturation boosting pixel.

Specifically, through the adjustment weight w(c, avg) corresponding to the saturation enhancement pixel, and the pixel enhancement ratio ratio _src , the channel color ratio ratio _c corresponding to the color channel of each saturation enhancement pixel can be calculated.

In one embodiment, there is a positive correlation between the adjustment weight corresponding to each color channel value of the saturation boosting pixel and the channel color ratio corresponding to each color channel of the saturation boosting pixel, and the value of each color channel of the saturation boosting pixel The larger the corresponding adjustment weight, the higher the channel color ratio corresponding to each color channel of the saturation boosting pixel.

For example, the channel color ratio ratio _c corresponding to each color channel of the saturation boosting pixel can be expressed as:

ratio _c = ratio _src *w(c,avg)+(1-w(c,avg))*1

In this embodiment, the adjustment weight corresponding to each color channel value of each saturation enhancement pixel is obtained by the change value of each color channel value of the saturation enhancement pixel relative to the channel statistical value, and the channel color ratio can be obtained by adjusting the weight. the goal of.

In one embodiment, as shown in FIG. 5 , the steps are based on the adjustment weights corresponding to the respective color channel values of the saturation boosting pixels, and the calculated channel color ratios corresponding to the respective color channels of the saturation boosting pixels include:

Step 502: Calculate the first ratio according to the product of the adjustment weight corresponding to each color channel value of the saturation boosting pixel and the pixel boosting ratio of the saturation boosting pixel.

Specifically, the first ratio is expressed as ratio _c1 , which can be calculated by the following formula:

ratio _c1 = ratio _src *w(c,avg)

Step 504, using the preset value to subtract the adjustment weight corresponding to each color channel value of the saturation boosting pixel to obtain the second ratio.

Specifically, the second ratio is expressed as ratio _c2 , and the default value is e, then ratio _c2 can be expressed as:

ratio _c2 =ew(c,avg)

In one embodiment, the preset value e may be 1, and the second ratio ratio _c2 may be expressed as:

ratio _c2 =1-w(c,avg)

Step 506 , adding the first ratio and the second ratio to obtain the channel color ratio corresponding to each color channel of the pixel point with increased saturation.

Specifically, the channel color ratio is expressed as ratio _c , the first ratio is expressed as ratio _c1 , and the second ratio is expressed as ratio _c2 , then the channel color ratio ratio _c can be expressed as:

ratio _c = ratio _c1 + ratio _c2

In this embodiment, the first ratio is obtained by multiplying the adjustment weight corresponding to each color channel value of the saturation boosting pixel and the pixel boosting ratio of the saturation boosting pixel, and the preset value is used to subtract the saturation boosting pixel corresponding to The purpose of obtaining the channel color ratio corresponding to the color channel can be achieved through the first ratio and the second ratio, so as to select the minimum value in the color ratio of the channel as the color suppression ratio, and use the color suppression ratio Perform color suppression processing on the image to obtain the target image.

In one embodiment, as shown in Figure 6, the step image processing method further includes:

Step 602: Acquire the pixel points whose pixel value is greater than the preset threshold in the grayscale image, as the highlight pixel points.

Among them, the highlight pixel refers to the pixel with higher pixel value.

Specifically, by setting a preset threshold for pixel values, pixels with pixel values greater than the preset threshold are regarded as highlight pixels; pixels with pixel values less than or equal to the preset threshold are not included in the range of highlight pixels. It can be understood that the highlight pixels have an impact on the quality of the image. The more highlight pixels there are in the image, the worse the image quality.

Step 604: Multiply the pixel boost ratio corresponding to the highlight pixel point by the first coefficient to obtain a third ratio;

Specifically, the pixel enhancement ratio corresponding to the highlight pixel is expressed as ratio _src , the first coefficient is expressed as f, and the third ratio is expressed as ratio _c3 , then the third ratio expressed as ratio _c3 can be expressed as:

ratio _c3 = ratio _src *f

The first coefficient f has a negative correlation with the pixel value I of the pixel point at the corresponding position of the highlight pixel point in the processed image. The first coefficient f can be expressed as:

α=255 - preset threshold

In one embodiment, the preset threshold may be 230, and pixels with pixel values greater than 230 in the grayscale image are used as highlight pixels. The first coefficient f can be obtained by a preset threshold.

Step 606 , subtract the first coefficient from the preset value to obtain a fourth ratio.

Specifically, the preset value is identified as g, and the fourth ratio is expressed as ratio _c4 , then the fourth ratio ratio _c4 is expressed as:

ratio _c4 = gf

In one embodiment, the preset value is 1, and the fourth ratio ratio _c4 is expressed as:

ratio _c4 = 1-f

Step 608 , adding the third ratio and the fourth ratio to obtain the channel color ratio corresponding to each color channel of the highlight pixel point.

Specifically, the channel color ratio corresponding to the color channel of the highlight pixel is expressed as ratio _c' , then ratio _c' is expressed as:

ratio _c' =ratio _c3 +ratio _c4

In one embodiment, the three channels are respectively multiplied by the ratio ratio _c' to obtain the channel color ratio corresponding to the color channel of the highlight pixel point.

In one embodiment, the three channels are multiplied by this ratio, and the maximum value in the obtained result is greater than 255, then the pixel value on the channel is forced to be set to 255, and the ratio of 255 to the above-mentioned maximum value is calculated. two channel

Multiply the result of this ratio to get the channel color ratio corresponding to the color channel of the highlight pixel.

In this embodiment, the highlight pixels are selected by setting a preset threshold, and the channel color ratio corresponding to the color channel of the highlight pixel can be obtained through the functional relationship between the pixel boost ratio corresponding to the highlight pixel and the corresponding coefficient. the goal of.

In one embodiment, as shown in FIG. 7 , the steps of performing image processing on the image to be processed to obtain the processed image include:

Step 702: Perform image processing on the image to be processed to obtain an intermediate image.

The intermediate image refers to an image before the image to be processed is processed, but the processed image required by the user has not been obtained.

Specifically, the intermediate image may be a fused image, and the fused image is an image obtained by performing fusion processing on the images to be processed.

Step 704: Obtain a first pixel whose pixel value is less than a preset threshold in the grayscale image corresponding to the image to be processed, and use the pixel corresponding to the first pixel in the intermediate image as the second pixel.

Specifically, the terminal can obtain the pixel value in the grayscale image corresponding to the image to be processed through the pixel value obtaining tool, and obtain the pixel value smaller than the preset threshold by comparing the obtained pixel value with the preset threshold value stored at the local end. The first pixel point, and the pixel point corresponding to the first pixel point in the intermediate image is used as the second pixel point.

In one embodiment, the preset threshold value of a pixel point may be 64, and the terminal acquires a pixel point whose pixel value is less than 64 in the grayscale image as the first pixel point, and simultaneously acquires the first pixel point in the intermediate image corresponding to the first pixel point. two pixels.

Step 706: Obtain the noise suppression weight of the corresponding second pixel point according to the pixel value of the first pixel point in the grayscale image, and the pixel value and the noise suppression weight have a correlation.

Specifically, the noise suppression weight of the second pixel can be expressed as w, the pixel value of the first pixel in the grayscale image can be expressed as I ₁ , and β is a preset threshold, then the noise suppression weight of the second pixel is w can be expressed as:

w=(I ₁ /β) ² *2+1.0-(I ₁ /β) ² , I ₁ <β

In one embodiment, the preset threshold β is 64, and the pixel value less than 64 can be regarded as a dark area image, and the noise suppression weight w of the second pixel is obtained by selecting the preset threshold.

Step 708: Perform noise suppression on the second pixel in the intermediate image according to the noise suppression weight to obtain a processed image.

Specifically, after the noise suppression weight is obtained by calculation, the grayscale image is adjusted by the noise suppression weight to obtain the processed image. It can be understood that the processed image can be used as the target image to obtain the previous intermediate image.

In one embodiment, the intermediate image may be processed through a noise suppression weight, and the intermediate image may be controlled within a range of twice the pixel value of the image to be processed. For example, if the intermediate image is represented as I _enhance and the processed image is represented as I, then I can be represented as:

In this embodiment, by acquiring the intermediate image, and acquiring the first pixel point within the preset threshold in the grayscale image, the corresponding second pixel point in the intermediate image, and the noise suppression weight, the pixel value of the processed image can be controlled within Within twice the pixel value of the image to be processed, so that the image with the pixel value less than the preset threshold can improve the brightness, make the details more prominent, and prevent color faults due to excessive pixel value difference.

In one embodiment, as shown in FIG. 8 , the steps of performing image processing on the image to be processed to obtain the processed image include:

Step 802: Obtain a grayscale image corresponding to the image to be processed.

In one embodiment, after the terminal acquires the to-be-processed image, the to-be-processed image is converted into a grayscale image, and the conversion method includes a component method, a maximum value method, a weighted average method, and the like.

In one embodiment, a weighted average method can be used to convert the image to be processed into a grayscale image, and the pixel values of the three RGB channels in the image to be processed are weighted and averaged according to different weights to obtain a grayscale image. For example, the pixel value of a grayscale image is represented as I ₁ (i,j), and the pixel values of the RGB three-channel color in the image to be processed are R(i,j), G(i,j) and B(i,j respectively ), then the pixel value I ₁ (i,j) of the grayscale image can be expressed as:

I1(i,j)=0.299R(i,j)+0.578G(i,j)+0.114B(i,j)

Step 804 , performing brightening processing on the grayscale image to obtain a brightened image.

Specifically, the brightened image corresponding to the grayscale image can be obtained through the functional relationship between the pixel value of the grayscale image and the pixel value of the brightened image. For example, a brightened image is represented by I ₂ , a grayscale image is represented by I ₁ , and a and b are represented as independent variables, and the two have the following functional relationship:

In one embodiment, the independent variable a can take the value of 2, and the independent variable b can take the value of 20. Through the selection of the independent variable and the above-mentioned functional relationship, more details can be obtained after the grayscale image is brightened. Brighten the image.

Step 806: Perform contrast enhancement processing on the grayscale image to obtain a contrast enhanced image.

Specifically, a low-pass filter map I _guide can be obtained through guide filtering through a grayscale image, and an intermediate image v ₁ with enhanced contrast can be obtained through the low-pass filter map I _guide :

v ₁ =(I _guide -127.5)*c+127.5

The guided filter is a low-pass filter.

In one embodiment, the independent variable c can be selected as 1.2, which enables the contrast ^- enhanced intermediate image v1 to retain more image details.

In one embodiment, the difference calculation is performed between the grayscale image and the above-mentioned intermediate image, so as to obtain more image details, and the detail enhancement coefficient k _detail is set to obtain an enhanced intermediate image v ₂ with prominent details, The formula is expressed as:

v ₂ =v ₁ +(I ₁ -v ₁ )*k _detail

In one embodiment, in order to obtain a high-quality grayscale image, the detail enhancement coefficient k _detail may be set to 4. On the basis of this detail enhancement coefficient, the processed image details are more prominent and the effect of image processing is improved.

In one embodiment, a preset upper and lower limit is set for the intermediate processing image v ₂ , the upper limit is represented as val _max , and the lower limit is represented as val _min , which is represented by the formula:

val _max =I ₁ *k _detail

val _min =I ₁ *k _detail -(k _detail -1)

Get the contrast-enhanced image I3:

Step 808: Perform fusion processing on the grayscale image, the brightened image, and the contrast-enhanced image to obtain a processed image.

In one embodiment, the processed image may be obtained by weighted fusion of the grayscale image, the brightened image, and the contrast-enhanced image. Denote the grayscale image as I ₁ , the brightened image as I ₂ and the contrast-enhanced image as I ₃ , the corresponding weight map of I ₁ , I ₂ and I ₃ can be expressed by the following formula:

In one embodiment, the weight maps corresponding to the grayscale image I ₁ , the brightened image I ₂ and the contrast-enhanced image I ₃ are set as w ₁ , w ₂ and w ₃ , respectively,

By the parameters in w ₁ , w ₂ and w ₃

And the setting of parameter δ can make the value of each pixel in the weight map corresponding to I ₁ , I ₂ and I ₃ closer to the pixel mean of each image.

Normalize the same position of the above three weight maps, and convert the weights into decimals between 0 and 1. Specifically, the three weights corresponding to the position are added up, and each weight is changed to the current weight value divided by the weight sum; for example, the weights of the weights w1, w2 and w3 are {3.52.54}, then normalized and converted to { 0.350.250.4}. The transformed weights are set as new weights at the corresponding positions to form a weight map. Multi-scale fusion or multi-resolution fusion of weight map and grayscale image, brightened image and contrast-enhanced image is performed to obtain the processed image. It can be understood that the processed image at this time may be a fused image serving as an intermediate image.

In this embodiment, the purpose of obtaining a fused image can be achieved by converting the image into a grayscale image, a brightened image, and a contrast-enhanced image, respectively, for fusion processing, and weighted fusion of the images.

In one embodiment, the fused image obtained in the above embodiment can be used as the processed image in step 202 , and the above fused image can also be used as the processed image in step 202 after the noise suppression processing in steps 702 to 708 in FIG. 7 . Process images.

It should be understood that although the steps in the flowcharts of FIGS. 1-8 are shown in sequence according to the arrows, these steps are not necessarily executed in the sequence shown by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIGS. 1-8 may include multiple steps or multiple stages. These steps or stages are not necessarily executed and completed at the same time, but may be executed at different times. The execution of these steps or stages The order is also not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the steps or phases within the other steps.

In one embodiment, as shown in FIG. 9, an image processing apparatus 900 is provided, including: a processed image acquisition module 902, a channel statistical value acquisition module 904, a channel color ratio acquisition module 906, a color suppression ratio acquisition module 908 and Target image acquisition module 910, wherein:

A processed image acquisition module 902, configured to perform image processing on the image to be processed to obtain a processed image;

A channel statistical value acquisition module 904, configured to acquire color channel values corresponding to each pixel in the processed image, perform statistics on the color channel values, and obtain channel statistics corresponding to the processed image;

The channel color ratio acquisition module 906 is used to acquire the saturation enhancement pixels in the processed image, and calculate the channel corresponding to each color channel of the saturation enhancement pixels based on the calculation of each color channel value and the channel statistical value of the saturation enhancement pixels. color ratio;

The color suppression ratio acquisition module 908 is used to select the minimum value from the channel color ratios corresponding to each color channel of the saturation boosting pixel as the color suppression ratio corresponding to each color channel of the saturation boosting pixel;

The target image acquisition module 910 is configured to perform color suppression processing on each color channel of the saturation boosted pixel based on the color suppression ratio corresponding to each color channel of the saturation boosted pixel to obtain a target image.

In one embodiment, the channel color ratio obtaining module 906 is further configured to obtain a grayscale image corresponding to the image to be processed;

According to the pixel value of each pixel in the processed image and the pixel value of the pixel at the corresponding position in the grayscale image, determine the pixel enhancement ratio of each pixel in the processed image relative to the grayscale image;

The pixels whose pixel enhancement ratio is greater than the preset threshold in the processed image are regarded as saturation enhancement pixels.

In one embodiment, the channel color ratio acquisition module 906 is further configured to calculate the change value of each color channel value of the saturation boosting pixel point relative to the channel statistical value;

Determine the adjustment weight corresponding to each color channel value of the saturation enhancement pixel according to the change value, and the adjustment weight of the color channel value has a negative correlation with the change value;

According to the adjustment weights corresponding to the value of each color channel of the saturation boosting pixel, the channel color ratio corresponding to each color channel of the saturation boosting pixel is calculated.

In one embodiment, the channel color ratio obtaining module 906 is further configured to calculate the first ratio according to the product of the adjustment weight corresponding to each color channel value of the saturation boosting pixel and the pixel boosting ratio of the saturation boosting pixel;

The first ratio and the second ratio are added to obtain the channel color ratio corresponding to each color channel of the pixel point with increased saturation.

In one embodiment, the image processing apparatus further includes: a highlight pixel point acquisition module, a third ratio acquisition module, a fourth ratio acquisition module, and a channel color ratio acquisition module, wherein:

The highlight pixel point acquisition module is used to acquire the pixel points whose pixel value is greater than the preset threshold in the grayscale image, as the highlight pixel point;

The third ratio acquisition module is used to multiply the pixel boost ratio corresponding to the highlight pixel by the first coefficient to obtain a third ratio; the first coefficient and the pixel value of the pixel corresponding to the highlight pixel in the processed image are negative relationship;

a fourth ratio obtaining module, used for subtracting the first coefficient from the preset value to obtain the fourth ratio;

The channel color ratio acquisition module is used for adding the third ratio and the fourth ratio to obtain the channel color ratio corresponding to each color channel of the highlight pixel.

In one embodiment, the processing image acquisition module is further used to:

Obtain the first pixel point in the grayscale image corresponding to the image to be processed whose pixel value is less than the preset threshold, and use the pixel point corresponding to the first pixel point in the intermediate image as the second pixel point;

In one embodiment, the processing image acquisition module is further used to:

Obtain the grayscale image corresponding to the image to be processed;

Brighten the grayscale image to obtain a brightened image;

Perform contrast enhancement processing on the grayscale image to obtain a contrast enhanced image;

The grayscale image, the brightened image and the contrast-enhanced image are fused to obtain the processed image.

For the specific limitation of the image processing apparatus, reference may be made to the limitation of the image processing method above, which will not be repeated here. Each module in the above-mentioned image processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided, and the computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 10 . The computer equipment includes a processor, memory, a communication interface, a display screen, and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with an external terminal, and the wireless communication can be realized by WIFI, operator network, NFC (Near Field Communication) or other technologies. The computer program implements an image processing method when executed by a processor. The display screen of the computer equipment may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment may be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the shell of the computer equipment , or an external keyboard, trackpad, or mouse.

Those skilled in the art can understand that the structure shown in FIG. 10 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory and a processor, a computer program is stored in the memory, and the processor implements the following steps when executing the computer program:

Obtain the color channel value corresponding to each pixel in the processed image, and perform statistics on the color channel value to obtain the channel statistical value corresponding to the processed image;

Acquire the saturation enhancement pixel points in the processed image, and calculate the channel color ratio corresponding to each color channel of the saturation enhancement pixel point based on the value of each color channel and the channel statistics value of the saturation enhancement pixel point;

Select the minimum value from the channel color ratios corresponding to each color channel of the saturation boosting pixel as the color suppression ratio corresponding to each color channel of the saturation boosting pixel;

Color suppression processing is performed on each color channel of the saturation boosted pixel based on the color suppression ratio corresponding to each color channel of the saturation boosted pixel to obtain a target image.

In one embodiment, the processor further implements the following steps when executing the computer program:

Obtain the grayscale image corresponding to the image to be processed;

Calculate the change value of each color channel value of the saturation boosting pixel relative to the channel statistical value;

According to the adjustment weight corresponding to each color channel value of the saturation boosting pixel, the channel color ratio corresponding to each color channel of the saturation boosting pixel is calculated.

The first ratio is calculated according to the product of the adjustment weight corresponding to the saturation boosting pixel and the boosting ratio of the saturation boosting pixel;

Acquire the pixels whose pixel values are greater than the preset threshold in the grayscale image as highlight pixels;

The pixel boost ratio corresponding to the highlight pixel is multiplied by the first coefficient to obtain a third ratio; the first coefficient has a negative correlation with the pixel value of the pixel at the corresponding position of the highlight pixel in the processed image;

Use the preset value to subtract the first coefficient to obtain the fourth ratio;

Obtain the grayscale image corresponding to the image to be processed;

Brighten the grayscale image to obtain a brightened image;

In one embodiment, a computer-readable storage medium is provided on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

In one embodiment, the computer program further implements the following steps when executed by the processor:

Obtain the grayscale image corresponding to the image to be processed;

The first ratio is calculated according to the product of the adjustment weight corresponding to each color channel value of the saturation boosting pixel and the pixel boosting ratio of the saturation boosting pixel;

Multiply the pixel boost ratio corresponding to the highlight pixel point with the first coefficient to obtain a third ratio; the first coefficient is in a negative correlation with the pixel value of the pixel point corresponding to the highlight pixel point in the processed image;

Obtain the grayscale image corresponding to the image to be processed;

Brighten the grayscale image to obtain a brightened image;

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium , when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the various embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, or optical memory, and the like. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (Static RandomAccess Memory, SRAM) or dynamic random access memory (Dynamic RandomAccess Memory, DRAM).

The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, all It is considered to be the range described in this specification.

The above examples only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims

An image processing method, characterized in that the method comprises:

Perform image processing on the image to be processed to obtain a processed image;

Acquire the color channel value corresponding to each pixel in the processed image, perform statistics on the color channel value, and obtain the channel statistical value corresponding to the processed image;

Acquire the saturation enhancement pixel points in the processed image, and calculate the channel color ratio corresponding to each color channel of the saturation enhancement pixel point based on the value of each color channel of the saturation enhancement pixel point and the channel statistical value;

The minimum value is selected from the channel color ratios corresponding to each color channel of the saturation boosting pixel as the color suppression ratio corresponding to each color channel of the saturation boosting pixel;

Based on the color suppression ratios corresponding to the respective color channels of the saturation-enhanced pixels, color suppression processing is performed on the respective color channels of the saturation-enhanced pixels to obtain a target image.
The method according to claim 1, wherein the acquiring the saturation-enhanced pixel points in the processed image comprises:

obtaining a grayscale image corresponding to the image to be processed;

According to the pixel value of each pixel in the processed image and the pixel value of the pixel at the corresponding position in the grayscale image, determine the pixel boost ratio of each pixel in the processed image relative to the grayscale image;

Pixels whose pixel enhancement ratio is greater than a preset threshold in the processed image are used as saturation enhancement pixels.
The method according to claim 2, wherein the channel color corresponding to each color channel of the saturation-enhanced pixel is calculated based on the value of each color channel of the saturation-enhanced pixel and the channel statistical value Ratios include:

Calculate the change value of each color channel value of the saturation boosting pixel point relative to the channel statistical value;

Determine the adjustment weight corresponding to each color channel value of the saturation boosting pixel point according to the change value, and the color channel value adjustment weight has a negative correlation with the change value;

According to the adjustment weights corresponding to the respective color channel values of the saturation boosting pixels, the channel color ratios corresponding to the respective color channels of the saturation boosting pixels are calculated and obtained.
The method according to claim 3, wherein, according to the adjustment weight corresponding to each color channel value of the saturation boosting pixel, the channel color corresponding to each color channel of the saturation boosting pixel is calculated and obtained Ratios include:

Calculate the first ratio according to the product of the adjustment weight corresponding to each color channel value of the saturation boosting pixel and the pixel boosting ratio of the saturation boosting pixel;

The second ratio is obtained by subtracting the adjustment weight corresponding to each color channel value of the saturation boosting pixel from the preset value;

The first ratio and the second ratio are added to obtain the channel color ratio corresponding to each color channel of the pixel point with increased saturation.
The method according to claim 2, wherein the method further comprises:

Acquiring pixels whose pixel values are greater than a preset threshold in the grayscale image as highlight pixels;

Multiply the pixel boost ratio corresponding to the highlight pixel point by the first coefficient to obtain a third ratio; the first coefficient and the pixel value of the pixel point corresponding to the highlight pixel point in the processed image are negative relationship;

Subtract the first coefficient from the preset value to obtain a fourth ratio;

The third ratio and the fourth ratio are added to obtain the channel color ratio corresponding to each color channel of the highlight pixel point.
The method according to claim 1, wherein performing image processing on the image to be processed to obtain the processed image comprises:

Perform image processing on the image to be processed to obtain an intermediate image;

acquiring the first pixel point whose pixel value is less than a preset threshold in the grayscale image corresponding to the image to be processed, and using the pixel point corresponding to the first pixel point in the intermediate image as the second pixel point;

Obtain the noise suppression weight of the corresponding second pixel point according to the pixel value of the first pixel point in the grayscale image, and the pixel value and the noise suppression weight have a correlation;

Noise suppression is performed on the second pixel in the intermediate image according to the noise suppression weight to obtain a processed image.
The method according to claim 1 or 6, wherein performing image processing on the image to be processed to obtain the processed image comprises:

Obtain the grayscale image corresponding to the image to be processed;

Performing a brightening process on the grayscale image to obtain a brightened image;

performing contrast enhancement processing on the grayscale image to obtain a contrast enhancement image;

Perform fusion processing on the grayscale image, the brightened image, and the contrast-enhanced image to obtain a processed image.
An image processing device, characterized in that the device comprises:

The processing image acquisition module is used to perform image processing on the image to be processed to obtain the processed image;

A channel statistical value acquisition module, configured to acquire color channel values corresponding to each pixel in the processed image, perform statistics on the color channel values, and obtain channel statistical values corresponding to the processed image;

The channel color ratio acquisition module is used to acquire the saturation enhancement pixel points in the processed image, and based on each color channel value of the saturation enhancement pixel point and the channel statistical value, calculate each saturation enhancement pixel point. The channel color ratio corresponding to the color channel;

The color suppression ratio acquisition module is used to select the minimum value from the channel color ratios corresponding to each color channel of the described saturation enhancement pixel, as the color suppression ratio corresponding to each color channel of the described saturation enhancement pixel;

A target image acquisition module, configured to perform color suppression processing on each color channel of the saturation enhancement pixel based on the color suppression ratio corresponding to each color channel of the saturation enhancement pixel to obtain a target image.
A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when the processor executes the computer program.
A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.