WO2019170007A1 - Image color adjustment method and device - Google Patents

Abstract

Embodiments of the present application provide an image color adjustment method and device. The method comprises: obtaining a color characteristic value of a strong color pixel point for each image block of a target image, the strong color pixel point being a pixel point for reflecting the color characteristics of the image block; adjusting a color parameter according to the color characteristic value of the strong color pixel point respectively corresponding to each image block of the target image; and performing color adjustment on the target image according to the adjusted color parameter. By means of the present invention, a small number of strong color pixel points that best reflect the color characteristics of a target image can be extracted from the image comprising a large number of pixel points, and a color parameter can be adjusted on the basis of the strong color pixel points. In this way, the calculation workload can be greatly reduced; moreover, the accuracy and adaptability of image color adjustment can also be ensured. Thus, the effect of image color adjustment may be better, and the efficiency of image color adjustment may be improved.

Description

Image color adjustment method and device Technical field

The present application relates to the field of electronic technologies, and in particular, to an image color adjustment method and apparatus.

Background technique

When photographing through a terminal device such as a digital camera or a mobile phone, the unprocessed original image has a problem of overall color cast (blue, yellow, or green), and the color of the deviation is affected by the color (color temperature) of the light source in the scene. To eliminate this overall color cast, you must pass the Auto White Balance (AWB) module. The Auto White Balance AWB module can calculate the color and color temperature of the light source in the photo environment to correct the image color cast and make the white object in the original scene. White appears in the image. However, after the image corrected by the automatic white balance AWB module, the white object will be white, but other colors are not accurate, and the saturation needs to be enhanced or weakened by other color adjustment modules to enhance the color style of the image.

In the existing color adjustment mode, the saturation of the image after being adjusted by the automatic white balance AWB module is adjusted according to the preset color parameter. However, in fact, the saturation of different images is different. If the existing color adjustment method is used, it is easy to cause over-saturation of the image color, that is, the color of some areas has reached the strongest, and it is impossible to separate the shade. Therefore, how to make the effect of image color adjustment better becomes an urgent problem to be solved.

Summary of the invention

The embodiment of the present application provides an image color adjustment method and device, so as to improve the effect of image color adjustment and improve the efficiency of image color adjustment.

In a first aspect, an embodiment of the present application provides an image color adjustment method, including:

Obtaining a color feature value of a strong color pixel for each image block of the target image, the target image is an image after automatic white balance correction, and the strong color pixel is a pixel point for characterizing the color characteristic of the image block;

Adjusting the color parameter according to the color feature value of the strong color pixel corresponding to each image block of the target image;

Color adjustment of the target image according to the adjusted color parameters.

In the technical solution, a small number of strong color pixels that best reflect the color characteristics of the image are extracted from the target image containing a large number of pixel points, and the color parameters are adjusted based on the strong color pixel points. First of all, due to the reduction of the number of pixels, the workload of the calculation can be greatly reduced. At the same time, since the strong color pixels can reflect the color characteristics of the target image, the accuracy and adaptability of the image color adjustment can be ensured. It can make the effect of image color adjustment better and improve the efficiency of image color adjustment.

In a first possible implementation manner of the first aspect, the image color adjustment device determines, according to a color feature value of the strong color pixel corresponding to each image block of the target image, a feature of the strong color pixel corresponding to each image block. Saturation; according to the characteristic saturation of the strong color pixel points corresponding to each image block of the target image, the color parameters are adjusted, so that the color pixels corresponding to the respective color image pixels of the target image are color-adjusted by the adjusted color parameters. After the adjustment, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated.

In the technical solution, the image color adjusting device cyclically adjusts the color parameter according to the characteristic saturation of the strongly colored pixel points adjusted each time, so that the color parameter can be made more precise, and the effect of the image color adjustment is better.

In conjunction with the first possible implementation of the first aspect, in a second possible implementation of the first aspect, the color parameter comprises a color correction parameter, a color enhancement parameter, or a tone adjustment parameter.

In conjunction with the first possible implementation of the first aspect, in a third possible implementation of the first aspect, the color parameter includes a color correction parameter, a color enhancement parameter, and a tone adjustment parameter; and the image color adjustment device is configured according to the target image The image saturation parameter is adjusted according to the feature saturation of the strong color pixel points corresponding to each image block, so that the color image of the color pixel corresponding to each image block of the target image is corrected by the color correction parameter of the adjusted color correction parameter, and the target image The characteristic saturation of the corresponding strong color pixel points of each image block is not saturated; the color enhancement parameter is adjusted according to the characteristic saturation of each color pixel point after the color correction of the adjusted color correction parameter, so that the After the color correction of the color correction parameters of the adjusted color correction parameters, the color saturation of the adjusted color enhancement parameters is enhanced, and the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated; The characteristic saturation of each strong color pixel after the color enhancement of the adjusted color enhancement parameter is Adjusting the adjustment parameters to adjust, after the color enhancement of the adjusted color enhancement parameter is adjusted, the color tone of the adjusted color tone adjustment parameter is adjusted, and each image block of the target image corresponds to the strong color pixel point respectively. Characteristic saturation is not saturated.

In conjunction with the first or second possible implementation of the first aspect, in a fourth possible implementation manner of the first aspect, the image color adjusting device respectively corresponds to the strong color pixel points corresponding to the image blocks of the target image Feature saturation, adjusting the color parameter; obtaining the first pixel of the strong color pixel with the feature saturation higher than the first saturation threshold in each of the strong color pixels after the color adjustment of the adjusted color parameter The number of points; when the number of first pixels is greater than or equal to the first number threshold, the color parameter is lowered until the number of first pixels is less than the first number threshold.

In conjunction with the first or second possible implementation of the first aspect, in a fifth possible implementation manner of the first aspect, the image color adjustment apparatus respectively corresponds to the strong color pixel points corresponding to the image blocks of the target image Feature saturation, adjusting the color parameter; obtaining the pixel points of the strong color pixels in the M high saturation range of each of the strong color pixels after the color adjustment of the adjusted color parameter Quantity; M high saturation ranges are preset saturation ranges from top to bottom for multiple saturation ranges, M is a positive integer greater than 1; at least one of M high saturation ranges When the number of pixels corresponding to the target high saturation range is greater than or equal to the second threshold corresponding to the target high saturation range, the color parameter is lowered until the number of pixels corresponding to the M high saturation ranges is less than M high saturations. The range corresponds to a second number of thresholds.

In conjunction with the first or second possible implementation of the first aspect, in a sixth possible implementation manner of the first aspect, the image color adjustment apparatus respectively corresponds to the strong color pixel points corresponding to the image blocks of the target image Feature saturation, adjusting the color parameter; obtaining the pixel points of the strong color pixels in the M high saturation range of each of the strong color pixels after the color adjustment of the adjusted color parameter The weight parameter corresponding to the quantity and the M high saturation ranges respectively; the M high saturation ranges are the saturation ranges of the top M after the predetermined plurality of saturation ranges are sorted from high to low, and M is greater than 1 An integer; the number of second pixels is calculated, and the number of the second pixels is a sum of values obtained by multiplying the number of pixels corresponding to each high saturation range by the weight parameter corresponding to each high saturation range; when the second pixel is When the number is greater than or equal to the third number threshold, the color parameter is lowered until the number of second pixels is less than the third number threshold.

In conjunction with the first to sixth possible implementations of the first aspect, in a seventh possible implementation manner of the first aspect, the image color adjustment device further includes a strong color pixel corresponding to each image block of the target image The feature saturation is compared with the first saturation threshold, and the number of the third pixel points is determined. The number of the third pixel points is that the corresponding feature saturation of the strong color pixel corresponding to each image block of the target image is smaller than the first saturation threshold. The number of strong color pixels; determining that the number of third pixels is less than the fourth number threshold.

With reference to the first aspect and the first to seventh possible implementation manners of the first aspect, in an eighth possible implementation manner of the first aspect, the image color adjustment device acquires a pixel corresponding to each image block of the target image At least one target pixel whose brightness is higher than the first brightness threshold; N high saturation pixels are determined from the at least one target pixel, and the N high saturation pixels are at least one target pixel from which the reference saturation is high After the low ordering, the top N target pixel points, N is a positive integer greater than or equal to 1; according to the color values of the N high-saturation pixel points in each image block of the target image, the image blocks corresponding to the target image are respectively determined. The color feature value of a strong color pixel.

In this technical solution, the pixel point whose brightness is higher than the first brightness threshold is filtered to filter the pixel point whose brightness is too low. Because the pixels with too low brightness are actually invisible to the naked eye, the saturation of such pixels may affect the adjustment of the color of the image, so this scheme can avoid the deviation of the color of the entire image.

In conjunction with the eighth possible implementation of the first aspect, in a ninth possible implementation manner of the first aspect, the image color adjustment device acquires, in each pixel block of the target image, a hue corresponding to the first hue range And at least one target pixel having a brightness higher than the first brightness threshold.

In this technical solution, color adjustment can be performed for a certain color or color range.

With reference to the ninth possible implementation manner of the first aspect, in a tenth possible implementation manner of the first aspect, the image color adjustment device acquires scene information corresponding to the target image, and determines the scene information according to the scene information corresponding to the target image. Corresponding to the first hue range to be adjusted.

With reference to the eighth to the tenth possible implementation manners of the first aspect, in the eleventh possible implementation manner of the first aspect, the reference saturation is saturation; or the reference saturation is the saturation and the brightness The combined value determined.

With reference to the eighth to eleventh possible implementation manners of the first aspect, in a twelfth possible implementation manner of the first aspect, when N is equal to 1, determining a high corresponding to each image block of the target image The color value of the saturated pixel is a color feature value of a strong color pixel corresponding to each image block of the target image;

When N is greater than 1, an average value of color values of N high-saturation pixel points corresponding to each image block of the target image is respectively calculated; and an average value of color values of N high-saturation pixel points corresponding to each image block of the target image is determined. A color feature value of a strong color pixel corresponding to each image block of the target image.

A second aspect of the present application provides an image color adjustment device. It includes a cache processor, a memory, and optionally a communication interface. The processor is coupled to the memory and communication interface, for example, the processor can be coupled to the memory and communication interface via a bus. The communication interface is used to communicate with other devices. The memory is used to store program code, directory data, and the like. The processor is operative to perform any of the possible implementations of the first aspect or the first aspect described above.

A third aspect of the present application provides another image color adjustment apparatus, including an acquisition module, a parameter adjustment module, and a color adjustment module, and optionally a comparison module. The above modules are used to implement the processor in the second aspect. The image color adjustment device implements any of the above first aspect or the first aspect of the first aspect through the above module.

In a fourth aspect, the present application provides a computer program product comprising: computer program code for causing a computer to perform the method of any of the possible implementations of the first aspect described above when the computer program code is run on a computer.

In a fifth aspect, the present application provides a computer readable medium storing program code for causing a computer to perform the method of the implementation of the first aspect described above when the computer program code is run on a computer.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background art, the drawings to be used in the embodiments of the present application or the background art will be described below.

1 is a schematic structural diagram of an image color adjustment system according to an embodiment of the present application;

2 is a schematic flow chart of an image color adjustment method provided by an embodiment of the present application;

3 is a schematic flow chart of another image color adjustment method provided by an embodiment of the present application;

4a is an example of a strong color pixel point feature saturation histogram provided by an embodiment of the present application;

FIG. 4b is another example of a strong color pixel dot feature saturation histogram provided by an embodiment of the present application; FIG.

FIG. 5 is a schematic structural diagram of an image color adjustment apparatus according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of another image color adjustment apparatus according to an embodiment of the present application.

Detailed ways

The embodiments of the present application are described below in conjunction with the accompanying drawings in the embodiments of the present application.

Please refer to FIG. 1. FIG. 1 is a schematic structural diagram of an image color adjustment system according to an embodiment of the present application. For example, the system may be an image signal processor (ISP). The image color adjustment system includes an automatic white balance AWB module 101 and a color adjustment module 102. The color adjustment module may specifically include a color correction (CC) 1021, a color enhancement module (CE) 1022, and a three-dimensional lookup table. At least one of a module (3D lookup table, 3DLut) 1023. In the embodiment of the present application, the input image is first corrected by the automatic white balance AWB module 101, and according to the saturation, brightness, and hue parameters of each pixel of the image corrected by the automatic white balance AWB module 101, it is determined that the correction can be represented. The color feature value of the strong color pixel of the color feature of the image is formed, that is, a strong color map is formed, the color parameter of the color adjustment module 102 is adjusted according to the strong color map, and then the image corrected by the automatic white balance AWB module 101 is formed. The color adjustment module 102 is input to the adjusted color adjustment module to obtain an output image with good color effect. When the color adjustment module 102 includes the color correction CC module 1021, the color enhancement CE module 1022, and the three-dimensional lookup table 3DLut module 1023, the image corrected by the automatic white balance AWB module 101 is sequentially subjected to the color correction CC module 1021 in order. The adjustment of the enhanced CE module 1022 and the three-dimensional lookup table 3DLut module 1023. It should be noted that the Gamma module 1024 may be aligned through the brightness before being adjusted by the 3D lookup table 3DLut module 1023.

Referring to FIG. 2, FIG. 2 is a schematic flowchart diagram of an image color adjustment method according to an embodiment of the present application, where the method includes but is not limited to the following steps:

S201. Acquire a color feature value of a strong color pixel for each image block of the target image.

The target image is an image after automatic white balance correction. The automatic white balance AWB module can calculate the color and color temperature of the light source in the photographing environment to correct the image color shift, so that the white object in the original scene appears white in the image. That is to say, the image after the unprocessed original image is processed by the automatic white balance AWB module is the target image.

The target image is composed of a plurality of pixel points in the plurality of image blocks, each pixel point has a corresponding color value, and the image color adjusting device is based on the color value corresponding to the plurality of pixel points in each image block of the target image. A color value of a strong color pixel corresponding to each image block may be obtained, and a strong color pixel corresponding to one image block is a pixel point that can represent the color characteristic of the image block. For example, if the target image has A*B image blocks, then there are A*B strong color pixels, and the image composed of A*B strong color pixels can be called “strong color map”, and the strong color map can be Fully represents the color characteristics of the target image before it has been subjected to color correction processing. That is to say, the image color adjusting means extracts a "small image" including a plurality of strong color pixel points capable of reflecting the color characteristics of the target image from the target image, which is a "large image" including a plurality of pixel points.

In a possible implementation manner, S201 may specifically include S2011-S2013:

S2011: Acquire at least one target pixel point in which a brightness of each pixel block corresponding to each image block of the target image is higher than a first brightness threshold.

According to the color value of the pixel, the brightness, saturation, and hue corresponding to each pixel point can be obtained. For example, the color value can be an RGB parameter of the RGB color space that converts the RGB parameters of the RGB color space into HSL (or HSV) parameters of the HSL (or HSV) color space. Here, R, G, and B represent the values of the red, green, and blue primary colors in each pixel. H, S, and L (or V) represent the values of the three parameters of hue, saturation, and brightness, respectively. .

In the embodiment of the present application, the pixel point whose brightness is higher than the first brightness threshold is filtered to filter the pixel point whose brightness is too low. Because the pixels whose brightness is too low are actually invisible to the naked eye, if the adjustment of the color of the image is affected due to the saturation of such pixel points, the color of the entire image may be deviated.

Optionally, in a possible implementation scenario, the target pixel needs to satisfy the condition that the hue conforms to the first hue range in addition to the brightness being higher than the first brightness threshold, that is, S2011 may further be: acquiring the target image. The hue in each image block conforms to the first hue range and at least one target pixel whose brightness is higher than the first brightness threshold. In one design, the first hue range may be preset. For example, if the user prefers to perform color adjustment for the red portion of the image, then the first hue range may be preset to a red corresponding hue range, thereby obtaining the target image. The target pixel points that match the hue range corresponding to the red color are selected. In another design, the first hue range may be determined according to a scene corresponding to the target image. Then, the scenario information corresponding to the target image may be acquired first, and then the first hue range to be adjusted corresponding to the scenario information is determined according to the scenario information. For example, the scene information corresponding to the target image may be determined by the scene recognition as a blue sky scene, and the first hue range may be a hue range corresponding to the blue color, so that the target image is matched with the target corresponding to the hue range corresponding to the blue color. pixel.

S2012, determining N high-saturation pixel points from at least one target pixel.

The N high-saturation pixel points are the top N target pixel points after the reference saturation is sorted from high to low in at least one target pixel, and N is a positive integer greater than or equal to 1. In one design, the reference saturation can be saturation. That is to say, the saturation corresponding to at least one target pixel point included in each image block of the target image is sorted, and the top N target pixel points of the saturation ranking are obtained as N high-saturation pixel points. In another design, the reference saturation may also be a composite value determined by the sum of saturation and brightness. For example, the following formula may be used to determine the integrated value corresponding to the pixel:

Comprehensive value = a*S+b*L

Where S is the saturation of the pixel, L is the brightness of the pixel, a is the weight of the saturation, and b is the weight of the brightness. It should be noted that a is usually much larger than b. Thereby, the integrated values corresponding to the at least one target pixel point included in each image block of the target image are sorted, and the top N target pixel points of the integrated value are obtained as N high saturated pixel points. If there is a target pixel with the same saturation, the design can select a target pixel with a higher brightness as the high saturation pixel.

For example, the reference saturation ranking corresponding to multiple target pixel points in a target image block is shown in Table 1. Assuming N is 1, then target pixel 1 is a highly saturated pixel; assuming N is 2, then target pixel 1 and target pixel 2 are 2 highly saturated pixels.

Target pixel	Characteristic saturation	Color value
Target pixel 1	65	(R1, G1, B1)
Target pixel 2	63	(R2, G2, B2)
Target pixel 3	59	(R3, G3, B3)
......	......	......

Table 1: Reference saturation ranking table corresponding to at least one target pixel in the target image block (example)

S2013: Determine, according to color values of N high-saturation pixel points in each image block of the target image, color feature values of one strong color pixel corresponding to each image block of the target image.

When N is equal to 1, each image block corresponds to only one high-saturation pixel, and then the color value of the high-saturation pixel corresponding to each image block of the target image is determined to be a strong color pixel corresponding to each image block of the target image. Color feature value. When N is greater than 1, each image block has N high-saturation pixel points, and the average value of the color values of the N high-saturation pixel points corresponding to each image block of the target image may be respectively calculated, and each target image is determined. The average value of the color values of the N highly saturated pixels corresponding to the image block is the color feature value of the strong color pixel corresponding to each image block of the target image.

Taking Table 1 as an example, when N is 1, the color value of the highly saturated pixel is the color feature value of the strong color pixel, that is, the color value corresponding to the target pixel point 1 of the first reference saturation (R1, G1, B1); When N is 2, the color eigenvalue of the strong color pixel is the average of the color values of the two highly saturated pixels (target pixel 1 and target pixel 2), ie (R1+R2)/2 , (G1+G2)/2, (B1+B2)/2.

S202. Adjust a color parameter according to a color feature value of a strong color pixel corresponding to each image block of the target image.

The color parameter is a parameter used to adjust the color of the image. According to the color feature values of the strong color pixels, the image color adjusting device can determine the feature saturation of each strong color pixel point. When the feature saturation of each strong color pixel point is large, the color of the target image is relatively strong. You can reduce the color parameters to avoid oversaturation of the image. Adjusting the color parameters in the embodiments of the present application may include reducing the color parameters. Further, the color parameter may include a color correction parameter, a color enhancement parameter, or a tone adjustment parameter, and the color parameter may further include a color correction parameter, a color enhancement parameter, and a tone adjustment parameter. Among them, the color correction parameter is used to correct the image color, the color enhancement parameter is used to enhance the image color, and the tone adjustment parameter is used to change the image color tone. In a possible implementation manner, the color parameter adjusted by the image color adjustment device may be a color parameter of the color adjustment module. The color adjustment module may be any one or two of a color correction module, a color enhancement module, and a three-dimensional lookup table module, and may also include a color correction module, a color enhancement module, and a three-dimensional lookup table module. The method for adjusting the color parameters of different module designs can be specifically referred to the following description.

By adopting the method, a small number of strong color pixels which best reflect the color characteristics of the image can be extracted from the target image containing a large number of pixel points, and the color parameters are adjusted based on the strong color pixel points. First of all, due to the reduction of the number of pixels, the workload of the calculation can be greatly reduced. At the same time, since the strong color pixels can reflect the color characteristics of the target image, the accuracy and adaptability of the image color adjustment can be ensured. Therefore, the method can make the effect of image color adjustment better and improve the efficiency of image color adjustment.

In one possible design, S202 may specifically be:

Determining a feature saturation of a strong color pixel corresponding to each image block according to a color feature value of each of the image blocks corresponding to each image block of the target image; and correspondingly selecting a strong color pixel point according to each image block of the target image Feature saturation, the color parameter is adjusted, so that each color block corresponding to each image block of the target image is color-adjusted by the adjusted color parameter, and each image block of the target image corresponds to a strong color pixel The characteristic saturation is not saturated.

In a first possible implementation scenario of such a design, the color parameter may refer to any one of a color correction parameter, a color enhancement parameter, and a tone adjustment parameter. Correspondingly, in a first possible implementation of the design, the color adjustment module may be a black box internally including a plurality of small adjustment modules, and the color parameters correspond to the entire color adjustment module. That is, the color adjustment module corresponds to a color parameter as a whole. In this implementation scenario, the color adjustment module may be any one of a color correction module, a color enhancement module, and a three-dimensional lookup table module. Correspondingly, the color parameter may be respectively corresponding to the color correction module, the color enhancement module, and the three-dimensional lookup table module. Any of color correction parameters, color parameters, and tone adjustment parameters. For example, if the color adjustment module is a color correction module, the color correction parameter corresponding to the color correction module is adjusted until the color saturation of the adjusted color parameter, and the characteristic saturation of the strong color pixel corresponding to each image block of the target image respectively. But saturated.

In the first possible implementation scenario, first, the image color adjusting device may adjust the color of each strong color pixel according to the preset color parameter, and obtain the characteristics of the output color adjusted color pixels. Saturation; adjust the color parameters according to the characteristic saturation of the strong color pixels corresponding to each image block; then, according to the adjusted color parameters, perform the color-adjusted color pixels after the last output Color adjustment, obtain the characteristic saturation of each color pixel point after the color adjustment of the output, and so on, cyclically adjust the color parameter until the color of the adjusted color parameter is adjusted, and each image block of the target image The characteristic saturation of the corresponding strong color pixel points is not saturated, indicating that the adjustment of the color parameter adjustment corresponding to the target image is completed, and the target image may be color-adjusted according to the adjusted color parameter.

Similarly, in the manner implemented by the color adjustment module, the image color adjustment device may input each strong color pixel into the color adjustment module to obtain the characteristics of each strong color pixel adjusted according to the preset color parameter color. Saturation; adjust the color parameters of the color adjustment module according to the characteristic saturation of each color pixel after the color adjustment; then, input the color pixels after the color output of the last output is adjusted by the color parameter After the color adjustment module, the characteristic saturation of each color pixel point after the color adjustment of the output is obtained, and so on, the color parameter of the color adjustment module is cyclically adjusted until the color parameter of the adjusted color adjustment module After the color adjustment, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated.

In a second possible implementation scenario of the design, the color adjustment module includes a color correction module, a color enhancement module, and a three-dimensional lookup table module, and the color parameters may include color correction parameters, color enhancement parameters, and tone adjustment parameters. That is, the image color adjustment device needs to adjust the color parameter corresponding to the color correction module, the color parameter corresponding to the color enhancement module, and the color parameter corresponding to the three-dimensional lookup table module.

In the second possible implementation scenario, the image color adjustment device sequentially adjusts the color correction parameter, the color enhancement parameter, and the tone adjustment parameter. First, the image color adjustment device adjusts the color correction parameters according to the feature saturation of the strong color pixel points corresponding to the image blocks of the target image, so that the respective color image pixels corresponding to the image blocks of the target image are adjusted. After the color correction of the color correction parameter, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated; then, the characteristics of each strong color pixel point after the color correction according to the adjusted color correction parameter Saturation, the color enhancement parameter is adjusted, so that after the color correction of the color correction parameters of the adjusted color correction parameter is adjusted, the color of the adjusted color enhancement parameter is enhanced, and each image block of the target image is correspondingly strong. The characteristic saturation of the color pixel is not saturated; finally, the tone adjustment parameter is adjusted according to the characteristic saturation of each color pixel after the color enhancement parameter of the adjusted color enhancement parameter, so that the adjusted color enhancement parameter is adjusted. After the color enhancement of each color pixel is adjusted, the tone adjustment parameter is adjusted after the tone adjustment The characteristic saturation of the strong color pixel points corresponding to the respective image blocks of the target image is not saturated.

Similarly, in the manner implemented by the color adjustment module, the color correction module, the color enhancement module, and the three-dimensional lookup table module respectively adjust color correction parameters, color enhancement parameters, and tone adjustment parameters.

In a third possible implementation scenario of the design, the color adjustment module may be any two of a color correction module, a color enhancement module, and a three-dimensional lookup table module. Accordingly, the color parameters may include color correction parameters, color enhancements. Any of the parameters and tone adjustment parameters. For a specific adjustment method, reference may be made to the implementation method of the second possible implementation scenario of the foregoing design, that is, sequentially adjusting any two parameters of the color correction parameter, the color enhancement parameter, and the tone adjustment parameter until the output is adjusted. After the color adjustment of the color parameter, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated. Similarly, the color parameters corresponding to any two of the color correction module, the color enhancement module, and the three-dimensional lookup table module can be adjusted.

In a first possible implementation manner of the design, the image color adjusting device adjusts the color parameter according to the feature saturation of the strong color pixel corresponding to each image block of the target image; and obtains the adjusted color parameter. In the color-adjusted color pixels, the corresponding feature saturation is higher than the first pixel threshold of the first saturation threshold; when the first pixel number is greater than or equal to the first threshold , reducing the color parameter until the number of first pixels is less than the first number threshold.

In a first possible implementation manner, the image color adjusting device performs color adjustment on each of the strong color pixel points (ie, the strong color image) obtained in S201, and then, according to the color characteristic values of the color pixels after the color adjustment, The characteristic saturation corresponding to each color pixel point after the color adjustment is determined. Obtaining, according to the characteristic saturation of each strong color pixel, the number of first pixels of the strong color pixel whose feature saturation is higher than the first saturation threshold. The first saturation threshold may be a preset threshold for measuring whether the feature saturation is too high. Correspondingly, the number of the strong color pixel points whose feature saturation is too high in the feature saturation corresponding to each strong color pixel point is obtained as the first pixel point number. When the number of the first pixel number is greater than or equal to the first number threshold, it can be considered that there are too many strong color pixels in the strong color map whose feature saturation is too high, so the color parameter can be lowered. The first quantity threshold may be a fixed value set; the first quantity threshold may also be determined according to a product of a preset percentage and a number of image blocks of the target image, such as a target image having 900 image blocks, If the percentage is set to 10%, the first number threshold is 90. Further, the color parameter may be reduced to a preset color parameter value, or the color parameter may be adjusted according to a preset rule by a certain value, which is not limited herein. After adjusting the color parameters, color adjustment is performed on each color pixel point after the color adjustment, and whether the number of the first pixel points of the strong color pixel with the feature saturation higher than the first saturation threshold is greater than or equal to the first A number threshold is determined, and the loop is repeated until the number of first pixels is less than the first number threshold.

Optionally, the image color adjusting device may divide the plurality of saturation ranges, and then perform histogram statistics on the number of feature saturations of the strong color pixels falling in the respective saturation ranges, thereby more intuitively obtaining the feature saturation is higher than The number of first pixels of the strong color pixel of the first saturation threshold. For example, in the strong saturation pixel histogram saturation histogram shown in FIG. 4a, the feature saturation S with a value range of 0 to 100 is divided into 100 saturation ranges, which are 0 ≤ S < 1, 1 ≤ S < 2...99≤S<100, wherein the abscissa of the histogram is the saturation range, and the ordinate is the number of strong color pixels. The statistical feature saturation statistics fall on the number of strong color pixels in each saturation range, which can form the strong saturation pixel point feature saturation histogram shown in Fig. 4a. Assuming that the first quantity threshold is 50 and the first saturation threshold is 98, using the strong color pixel point feature saturation histogram, it can be determined that the current strong color picture has 98 ≤ S < 99 and 99 ≤ S < 100. The number of strong color pixels corresponding to the saturation range is 65 (40+25), that is, the number of first pixels is 65.

In a second possible implementation manner of the design, the image color adjusting device adjusts the color parameter according to the feature saturation of the strong color pixel corresponding to each image block of the target image; and obtains the adjusted color parameter. In the color-adjusted color pixels, the corresponding feature saturations are respectively in the number of pixels of the high-saturation pixel points in the M high saturation range; the M high-saturation ranges are preset in the plurality of saturation ranges from High to low ranks the top M saturation ranges, M is a positive integer greater than 1; when at least one of the M high saturation ranges corresponds to a target high saturation range, the number of pixels is greater than or equal to the target high saturation range When the corresponding second quantity threshold is used, the color parameter of the color adjustment module is decreased until the number of pixel points corresponding to the M high saturation ranges are respectively smaller than the second quantity threshold corresponding to the M high saturation ranges.

In a second possible implementation manner, the image color adjustment device may divide a plurality of saturation ranges, and the saturation ranges in which the saturation ranges are ranked as the M high saturation ranges. For example, there are 100 saturation ranges, which are 0 ≤ S < 1, 1 ≤ S < 2 ... 99 ≤ S < 100. Assuming M is 3, the high saturation range is 97 ≤ S < 98, 98 ≤ Three saturation ranges of S<99 and 99≤S<100. Each high saturation range sets a corresponding second quantity threshold. For example, a second quantity threshold corresponding to 97≤S<98 is 35, and a second quantity threshold corresponding to 98≤S<99 is 30, 99≤S<100. The corresponding second number threshold is 25.

In a second possible implementation manner, the image color adjusting device performs color adjustment on each of the strong color pixel points (ie, the strong color image) obtained in S201, and then, according to the color characteristic values of the color pixels after the color adjustment, The characteristic saturation corresponding to each color pixel point after the color adjustment is determined. According to the characteristic saturation of each color pixel point after the color adjustment, the number of pixel points of the strong color pixel points whose feature saturation is respectively in the M high saturation range is obtained. When the number of pixel points corresponding to at least one target high saturation range of the M high saturation ranges is greater than or equal to the second number threshold corresponding to the target high saturation range, the feature saturation in the strong color map may be considered to be too high. If there are too many color pixels, the color parameters can be lowered. Wherein, the second quantity threshold is similar to the setting method of the first quantity threshold. After adjusting the color parameters, the color-adjusted color pixels are input into the adjusted color adjustment module for color adjustment, and then it is determined whether at least one of the M high-saturation ranges corresponds to at least one target high-saturation range. The number of points is greater than or equal to the second number threshold corresponding to the target high saturation range, and the loop is repeated until the number of pixels corresponding to the M high saturation ranges is less than the second number threshold corresponding to the M high saturation ranges, and the loop ends. .

Similarly, the image color adjustment device can also intuitively determine the number of pixels corresponding to the M high saturation ranges by performing histogram statistics on the feature saturation of the strong color pixel points.

In a third possible implementation manner of the design, the image color adjusting device adjusts the color parameter according to the feature saturation of the strong color pixel corresponding to each image block of the target image; and obtains the adjusted color parameter. In the color-adjusted color pixels, the corresponding feature saturations are respectively in the number of pixels of the strong color pixels in the M high saturation range and the weight parameters corresponding to the M high-saturation ranges respectively; M high saturation The degree range is a preset plurality of saturation ranges from high to low, and the top M saturation ranges, M is a positive integer greater than 1; the second pixel number is calculated, and the second pixel number is high saturation The sum of the number of pixels corresponding to the degree range and the weight parameter corresponding to each high saturation range; when the number of second pixels is greater than or equal to the third number threshold, the color parameter is lowered until the second pixel The number of points is less than the third number threshold.

In a third possible implementation manner, the image color adjustment device may divide the plurality of saturation ranges, and the saturation ranges in which the saturation ranges are ranked as the M high saturation ranges. For example, there are 100 saturation ranges, which are 0 ≤ S < 1, 1 ≤ S < 2 ... 99 ≤ S < 100. Assuming M is 3, the high saturation range is 97 ≤ S < 98, 98 ≤ Three saturation ranges of S<99 and 99≤S<100. Each high saturation range sets a corresponding weight parameter. For example, the weight parameter corresponding to 97≤S<98 is 30%, the weight parameter corresponding to 98≤S<99 is 30%, and the weight parameter corresponding to 99≤S<100. It is 40%. The weight parameter may be preset, and the weight parameter has a corresponding relationship with the number of M, that is, the M high saturation ranges correspond to the M weight parameters, and the M weight parameters are followed by 1.

The image color adjusting device performs color adjustment on each of the strong color pixel points (ie, the strong color image) obtained in S201, and then determines the color-adjusted color pixels according to the color characteristic values of the color-adjusted color pixels. Corresponding feature saturation. The number of pixel points of the strong color pixel points with the feature saturations in the M high saturation ranges and the weight parameters corresponding to the M high saturation ranges respectively are obtained according to the feature saturation corresponding to the color-adjusted color pixels. The sum of the values obtained by multiplying the number of pixels corresponding to each high saturation range by the weight parameter corresponding to each high saturation range is calculated as the number of second pixel points. For example, the weight parameter corresponding to 97≤S<98 is 30%, the number of pixels of the strong color pixel falling within the range is 30; the weight parameter corresponding to 98≤S<99 is 30%, and the weight falling in the range is strong. The number of pixels of the color pixel is 40; the weight parameter corresponding to 99 ≤ S < 100 is 40%, and the number of pixels of the strong color pixel falling within the range is 25. Then the number of second pixels is 30*30%+40*30%+25*40%=31. When the number of second pixel points is greater than or equal to the third number threshold, it can be considered that there are too many strong color pixels with high feature saturation in the strong color map, and the color parameter can be reduced. Wherein, the third quantity threshold is similar to the setting method of the first quantity threshold. After adjusting the color parameters, color adjustment is performed on each color-adjusted pixel point after color adjustment, and then it is determined whether the number of second pixel points is greater than or equal to a third number threshold, and so on, until the number of second pixels is smaller than the third The number threshold, the end of the loop.

Similarly, the image color adjusting device can also determine the number of pixels corresponding to the high saturation range by performing histogram statistics on the feature saturation of the strong color pixel points, thereby determining the number of second pixel points.

It should be noted that the three possible implementations of the above-mentioned design are applicable to the three possible implementation scenarios of the above-mentioned design. In the manner implemented by the color adjustment module, the color adjustment module may include color. Any one, two or three of the correction module, the color enhancement module, and the three-dimensional look-up table module, or any implementation scenario in which the color adjustment module is a black box-like whole can follow the three possible implementations of the above design. The method adjusts the color parameters of the color adjustment module cyclically. Further, in the second or third possible implementation scenario of the design, for the different modules included in the color adjustment module, the values M and the respective thresholds involved in the above three possible implementation manners may be different. .

Optionally, the color parameter is adjusted according to the feature saturation of the strong color pixel corresponding to each image block of the target image, so that each image block of the target image respectively corresponds to the adjusted color of the strong color pixel. After the color adjustment of the parameter, before the characteristic saturation of the corresponding color pixel points of each image block of the target image is saturated, the method further includes:

S2021. The characteristic saturation of the strong color pixel corresponding to each image block of the target image is compared with the first saturation threshold to determine the third pixel number. If the third pixel number is determined to be greater than or equal to the fourth quantity threshold, Then, S2022 is performed; if it is determined that the number of third pixel points is less than the fourth number threshold, then S202 is performed.

The first saturation threshold may be a predetermined threshold for measuring whether the feature saturation is too low. The number of the third pixel points is the number of strong color pixel points in the corresponding strong color pixel points corresponding to the image blocks of the target image that are less than the first saturation threshold. A third pixel number is determined and it is determined whether the number is greater than or equal to a fourth number threshold. Wherein, the fourth quantity threshold is similar to the setting method of the first quantity threshold. If it is determined that the number of the third pixel points is greater than or equal to the fourth number threshold, it may be stated that the feature saturation of most of the pixels in the strong color image is too low, and the target image is considered to be a weak color picture, then S2022 is executed, according to the preset. The value greatly reduces the color parameters. If it is determined that the number of the third pixel points is not greater than or equal to the fourth number threshold, it may be considered that the target image is not a weak color picture, and then S202 is performed to perform cyclic adjustment on the color parameters.

Optionally, the strong saturation pixel histogram saturation histogram may also be used herein to determine the number of feature saturations that are less than the first saturation threshold. For example, as shown in FIG. 4b, the strong color pixel point feature saturation histogram assumes that the fourth number threshold is 800 and the first saturation threshold is 2, then the current saturation map can be determined using the strong color pixel point feature saturation histogram. In the strong color map, the number of strong color pixels corresponding to the two saturation ranges of 0≤S<1 and 1≤S<2 is 805 (400+405), that is, the strong color corresponding to each image block of the target image S2032 is performed when the number of feature saturations of the feature saturation of the pixel that is less than the first saturation threshold is greater than or equal to the fourth number threshold.

S2022, greatly reduce the color parameters according to the preset value.

Since it is determined in S2021 that the target image is a weak color picture, the color parameter of the color adjustment module can be reduced to a preset value of the color parameter corresponding to the weak color picture, for example, the color parameter can be reduced to the lowest value; The color parameter of the color adjustment module is adjusted according to a preset rule for the weak color picture, and is not limited herein.

It should be noted that, unlike S202, the color reduction parameter in S2022 is a large-scale and one-step adjustment method, and S202 is a cyclically fine-tuning and then judging until the required loop adjustment process is reached. Since it is determined that the target image is a weak color picture, it is not necessary to perform the step of continuously fine-tuning the color parameter as in S202, but directly adjust to the color parameter suitable for the weak color picture.

S203: Perform color adjustment on the target image according to the adjusted color parameter.

In the manner implemented by the color adjustment module, S203 may perform color adjustment on the target image through the color adjustment module according to the adjusted color parameter.

S201-S202 completes the process of adapting the color parameters of the color adjustment module according to the strong color map of the target image. After that, the image color adjusting device can adjust the color of the target image according to the adjusted color parameter, thereby avoiding excessive color gain and causing over-saturation of the target image after color adjustment.

In the embodiment of the present application, by acquiring the color feature values of a strong color pixel corresponding to each image block of the target image, a small number of strong color pixels that best reflect the color characteristics of the image may be extracted from the target image including a plurality of pixel points. Point, adjust the color parameters based on the strong color pixels to output a target image with better color effect. It can greatly reduce the workload of the calculation. At the same time, it can also ensure the accuracy and adaptability of image color adjustment and improve the efficiency of image color adjustment.

Referring to FIG. 3, FIG. 3 is a schematic flowchart diagram of another image color adjustment method according to an embodiment of the present application. In the embodiment of the present application, the color parameter includes a color correction parameter, a color enhancement parameter, and a tone adjustment parameter, and the color adjustment module includes a color correction module, a color enhancement module, and a three-dimensional lookup table module. The method includes but is not limited to the following steps:

S301. Acquire scene information corresponding to the target image.

In the embodiment of the present application, the image color adjustment device may acquire the scene information corresponding to the target image. The scene information corresponding to the target image indicates what kind of scene is present in the target image, such as a blue sky scene, a green scene, a night scene, or a gourmet scene. The scene information corresponding to the first screen may be determined according to various characteristics such as the color, shape, and the like of the object in the image captured by the target image. Further, the scene information may be extracted from the target image by the image color adjustment device itself, or may be obtained by the other device after the other device recognizes the extracted scene information, and is not specifically limited herein.

S302. Determine, according to the scene information corresponding to the target image, a first hue range to be adjusted corresponding to the scene information.

The range of hue that requires color adjustment can also be different for different scenarios. For example, in a green scene, it is necessary to adjust the color of the pixel of the green hue range, and other pixels may not be concerned. Therefore, the correspondence between various scene information and the hue range can be set in advance, for example, it can be a scene hue range mapping table as shown in Table 2. Further, based on the scene information corresponding to the acquired target image, the image color adjustment device may determine a first hue range to be adjusted for the target image. Taking Table 2 as an example, if it is determined that the scene information corresponding to the target image is a blue sky scene, the first hue range to be adjusted is 34-53.

Scene information	Hue range
Blue sky scene	34-53
Night scene	78-89
Green plant scene	45-66
......	......

Table 2: Scene Hue Range Mapping Table (Example)

S303. Acquire, in each pixel block corresponding to each image block of the target image, a hue that matches a first hue range and at least one target pixel whose brightness is higher than the first brightness range.

For the specific implementation method of S303, refer to S2011, and details are not described herein again.

It should be noted that the difference between S303 and S2011 is that, in addition to the pixel points whose brightness corresponding to the pixel point is higher than the first brightness threshold, it is necessary to filter the pixel points whose hue conforms to the first hue range. That is to say, while filtering the pixel points whose brightness is too low, the pixel points in the first hue range to be adjusted corresponding to the scene information are also filtered out, so that the color adjustment is more targeted.

S304. Determine M high-saturation pixel points from the at least one target pixel.

S305. Determine color feature values of one strong color pixel point corresponding to each image block of the target image according to color values of M high-saturation pixel points in each image block of the target image.

For the specific implementation of S304-S305, refer to S2012-S2013, and details are not described here.

S306. Determine, according to the color feature value of the strong color pixel corresponding to each image block of the target image, the feature saturation of the strong color pixel corresponding to each image block.

S307: Compare a feature saturation of a strong color pixel corresponding to each image block of the target image with a first saturation threshold, and determine a third pixel number; if it is determined that the third pixel number is greater than or equal to a fourth quantity threshold, Then, S308 and S311 are performed, and if it is determined that the number of third pixel points is less than the fourth number threshold, S309-S312 is performed.

S308, the color parameter is greatly reduced according to the preset value.

For the specific implementation method of S307-S308, refer to S2021-S2022, and details are not described herein again.

S309, adjusting the color correction parameter according to the feature saturation of the strong color pixel corresponding to each image block of the target image, so that each image block of the target image respectively corresponds to the color correction parameter of the strong color pixel point After the color correction, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated.

The image color adjusting device inputs each strong color pixel into the color correction module to obtain the characteristic saturation of the output color corrected color pixels, and corrects the color according to the characteristic saturation of each color pixel after the color correction. The color correction parameters of the module are adjusted. Then, the color-corrected color pixels of the last output color are input into the color correction module adjusted by the color correction parameter, and the characteristic saturation of the color-corrected color pixels after the output color correction is obtained, and so on. The color correction parameter of the color correction module is cyclically adjusted until the characteristic saturation of each color pixel of the color correction module after the color correction parameter adjusted by the output is saturated.

S310, adjusting the color enhancement parameter according to the characteristic saturation of each color pixel point after the color correction of the adjusted color correction parameter, so that the color correction pixels after the color correction of the adjusted color correction parameter After the color enhancement of the adjusted color enhancement parameter, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated.

The image color adjusting device inputs the strong color pixels adjusted by S309 into the color enhancement module, and obtains the characteristic saturation of the color pixels after the color enhancement of the output, and saturates according to the characteristics of the color pixels after the color enhancement. Degree, adjust the color enhancement parameters of the color enhancement module. Then, the color pixels that have been enhanced by the last output are input into the color enhancement module adjusted by the color enhancement parameter, and the characteristic saturation of each color pixel after the color enhancement is obtained, and so on. The color enhancement parameters of the color enhancement module are cyclically adjusted until the color saturation of the color enhancement module adjusted by the color enhancement parameter is respectively saturated with the characteristic saturation of each of the strong color pixels.

S311: Adjust the tone adjustment parameter according to the characteristic saturation of each of the strong color pixels after the color enhancement parameter of the adjusted color enhancement parameter, so that the color pixels of the adjusted color enhancement parameter are enhanced. After the tone adjustment of the adjusted tone adjustment parameter, the feature saturation of the strong color pixel corresponding to each image block of the target image is not saturated.

The image color adjusting device inputs the strong color pixels adjusted by S310 into the three-dimensional lookup table module, and obtains the characteristic saturation of the color tone pixels after the color tone adjustment, and the characteristics of the strong color pixels according to the color tone adjustment. Saturation, adjusts the tonal adjustment parameters of the 3D lookup table module. Then, the strong color pixels after the last color tone adjustment are input into the three-dimensional lookup table module adjusted by the tone adjustment parameter, and the characteristic saturation of each color pixel point after the tone adjustment is obtained, and so on. The loop adjustment parameter of the three-dimensional look-up table module is cyclically adjusted until the characteristic saturation of each of the strong color pixels after the tone adjustment of the output three-dimensional look-up table module adjusted by the tone adjustment parameter is not saturated.

It should be noted that, in the foregoing S309-S311, for a specific measurement manner of not saturating, refer to the description of the three possible implementation manners in S202.

Optionally, before S311, the image color adjustment device may further adjust the color enhanced pixel points by the brightness alignment module. For example, the brightness in FIG. 1 is aligned with the Gamma module 1024. The brightness alignment module can first adjust the brightness of each color pixel after the color enhancement, and then adjust the tone adjustment parameters of the three-dimensional lookup table module according to the intensity of the highlighted color pixels, so that the three-dimensional search is performed. The adjustment of the table module can be more accurate.

S312, performing color adjustment on the target image according to the adjusted color parameter.

In the embodiment of the present application, the color adjustment module includes a color correction module, a color enhancement module, and a three-dimensional lookup table module. After the color parameter adjustment corresponding to the color correction module, the color enhancement module and the three-dimensional lookup table module is completed, the color parameter of the adjusted color adjustment module can be used to adjust the color of the target image through the color adjustment module, that is, the target image Input the above-mentioned adjusted color correction module, color enhancement module and three-dimensional look-up table module for color adjustment, so as to avoid over-saturation of the target image after color adjustment caused by excessive color gain.

In the embodiment of the present application, by acquiring the color feature values of a strong color pixel corresponding to each image block of the target image, a small number of strong color pixels that best reflect the color characteristics of the image may be extracted from the target image including a plurality of pixel points. Point, adjust the color parameters based on the strong color pixels to output a target image with better color effect. It can greatly reduce the workload of the calculation. At the same time, it can also ensure the accuracy and adaptability of image color adjustment and improve the efficiency of image color adjustment.

The solution provided by the embodiment of the present application is mainly introduced from the perspective of interaction between different network elements. It can be understood that the image color adjustment device includes hardware structures and/or software modules corresponding to the execution of the respective functions in order to implement the above functions. The embodiments of the present application can be implemented in a combination of hardware or hardware and computer software in combination with the elements of the examples and algorithm steps described in the embodiments disclosed in the application. Whether a function is implemented in hardware or computer software to drive hardware depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the technical solutions of the embodiments of the present application.

The embodiment of the present application may perform the division of the function module or the function unit on the image color adjustment device according to the above method example. For example, each function module or function unit may be divided according to each function, or two or more functions may be integrated in the In a processing module or processing unit. The above integrated modules or units can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules or units in the embodiments of the present application is schematic, and is only a logical function division. In actual implementation, there may be another division manner. Please see the specifics below.

Please refer to FIG. 5. FIG. 5 is a schematic structural diagram of an image color adjustment apparatus according to an embodiment of the present application. The apparatus can be used to implement the image color adjustment apparatus of the embodiment shown in Fig. 2 or Fig. 3 described above. As shown in Figure 5, the device includes:

The obtaining module 501 is configured to obtain a color feature value of a strong color pixel point for each image block of the target image, where the target image is an image after automatic white balance correction, and the strong color pixel point is used to represent the image The pixel point of the color characteristic of the block;

The parameter adjustment module 502 is configured to adjust a color parameter according to a color feature value of a strong color pixel corresponding to each image block of the target image;

The color adjustment module 503 is configured to perform color adjustment on the target image according to the adjusted color parameter.

Optionally, the parameter adjustment module 502 is specifically configured to:

Determining, according to a color feature value of the strong color pixel corresponding to each image block of the target image, a feature saturation of the strong color pixel corresponding to each image block;

Adjusting the color parameter according to the feature saturation of the strong color pixel corresponding to each image block of the target image, so that each image block of the target image respectively corresponds to the adjusted color of the strong color pixel point After the parameter is color-adjusted, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated.

Optionally, the color parameter includes a color correction parameter or a tone adjustment parameter.

Optionally, the color parameter includes a color correction parameter, a color enhancement parameter, and a tone adjustment parameter;

The parameter adjustment module 502 is specifically configured to:

Adjusting the color correction parameters according to the feature saturation of the strong color pixel points corresponding to the image blocks of the target image, so that the respective color image pixels corresponding to the image blocks of the target image are adjusted After the color correction of the color correction parameter, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated;

Adjusting the color enhancement parameter according to the characteristic saturation of each color pixel point after the color correction of the adjusted color correction parameter, so that the color correction of the adjusted color correction parameter is performed after each After the color enhancement of the adjusted color enhancement parameter of the strong color pixel is performed, the characteristic saturation of the corresponding strong color pixel point of each image block of the target image is not saturated;

Adjusting the tone adjustment parameter according to the feature saturation of each of the strong color pixels after the color enhancement of the adjusted color enhancement parameter, so that the color of the adjusted color enhancement parameter is enhanced After the color tone adjustment of the adjusted color tone adjustment parameter of the strong color pixel is performed, the feature saturation of the strong color pixel corresponding to each image block of the target image is not saturated.

Optionally, the parameter adjustment module 502 is specifically configured to:

Adjusting the color parameter according to a feature saturation of a strong color pixel corresponding to each image block of the target image;

Obtaining, in each of the strong color pixels after the color adjustment of the adjusted color parameter, the corresponding number of first pixels of the strong color pixel whose feature saturation is higher than the first saturation threshold;

When the number of the first pixel points is greater than or equal to the first number threshold, the color parameter is decreased until the number of the first pixel points is less than the first number threshold.

Optionally, the parameter adjustment module 502 is specifically configured to:

Adjusting the color parameter according to a feature saturation of a strong color pixel corresponding to each image block of the target image;

Obtaining, in each of the strong color pixels after the color adjustment of the adjusted color parameter, the corresponding feature saturation is respectively in the number of pixels of the strong color pixel points of the M high saturation range; the M high saturation The degree range is a preset plurality of saturation ranges from high to low ranked after the top M saturation ranges, and M is a positive integer greater than one;

When the number of pixel points corresponding to at least one target high saturation range of the M high saturation ranges is greater than or equal to a second quantity threshold corresponding to the target high saturation range, the color parameter is lowered until the M The number of pixels corresponding to each of the high saturation ranges is smaller than the second number threshold corresponding to the M high saturation ranges respectively.

Optionally, the parameter adjustment module 502 is specifically configured to:

Adjusting the color parameter according to a feature saturation of a strong color pixel corresponding to each image block of the target image;

Obtaining, in each of the strong color pixels after the color adjustment of the adjusted color parameter, the corresponding feature saturation is in the number of pixels of the high color saturation pixel of the M high saturation range and the M high saturation The weight ranges respectively correspond to the weight ranges; the M high saturation ranges are preset saturation ranges of the top M after the plurality of saturation ranges are sorted from high to low, and M is a positive integer greater than 1;

Calculating a number of second pixel points, wherein the number of the second pixel points is a sum of values obtained by multiplying the number of pixels corresponding to each high saturation range by a weight parameter corresponding to each high saturation range;

When the number of the second pixel points is greater than or equal to the third number threshold, the color parameter is decreased until the number of the second pixel points is less than the third number threshold.

Optionally, the acquiring module 501 is further configured to: compare a feature saturation of a strong color pixel corresponding to each image block of the target image with a first saturation threshold, and determine a third pixel number, The number of the third pixel points is the number of the strong color pixel points corresponding to the feature saturation of the strong color pixel corresponding to each image block of the target image that is smaller than the first saturation threshold;

The device also includes:

The comparing module 504 is configured to determine that the number of the third pixel points is less than a fourth number threshold.

Optionally, the obtaining module 501 is specifically configured to:

Acquiring at least one target pixel point of the pixel corresponding to each image block of the target image that is higher in brightness than the first brightness threshold;

Determining N high-saturation pixel points from the at least one target pixel point, wherein the N high-saturation pixel points are the top N target after the reference saturation is sorted from high to low in the at least one target pixel point a pixel, where N is a positive integer greater than or equal to 1;

Determining, according to color values of the N high-saturation pixel points in each image block of the target image, color feature values of a strong color pixel corresponding to each image block of the target image.

Optionally, the obtaining module 501 is specifically configured to:

Obtaining, in each pixel block corresponding to each image block of the target image, the hue conforms to the first hue range and the at least one target pixel whose brightness is higher than the first brightness threshold.

Optionally, the obtaining module 501 is further configured to:

Obtaining scene information corresponding to the target image;

Determining, according to the scene information corresponding to the target image, the first hue range to be adjusted corresponding to the scene information.

Optionally, the reference saturation is saturation; or the reference saturation is a comprehensive value determined by the saturation and the brightness.

Optionally, the acquiring 501 module is specifically configured to:

When N is equal to 1, determining that a color value of a high-saturation pixel corresponding to each image block of the target image is a color feature value of a strong color pixel corresponding to each image block of the target image;

When N is greater than 1, respectively, calculating an average value of color values of N high-saturation pixel points corresponding to each image block of the target image; determining color of N high-saturation pixel points corresponding to each image block of the target image The average value of the values is a color feature value of one strong color pixel corresponding to each image block of the target image.

The image color adjusting device in the embodiment shown in FIG. 5 described above can be implemented by the image color adjusting device 600 shown in FIG. 6. FIG. 6 is a schematic structural diagram of another image color adjustment apparatus according to an embodiment of the present application. The image color adjustment apparatus 600 shown in FIG. 6 includes a processor 601, and the processor 601 is configured to implement the acquisition module in FIG. 501. An action performed by any one of the parameter adjustment module 502, the color adjustment module 503, and the comparison module 504. The processor 601 and the transceiver 603 are communicatively coupled, such as by a bus. The image color adjustment device 600 may also include a memory 602. The memory 602 is configured to store program code and data for execution by the image color adjustment device 600, and the processor 601 is configured to execute the application code stored in the memory 602 to implement the image color adjustment device provided by the embodiment shown in FIG. Actions. The image color adjustment device 600 may further include a transceiver 603 for supporting information transmission between the image color adjustment device 600 and other terminal devices.

It should be noted that, in actual application, the image color adjustment device 600 may include one or more processors, and the structure of the image color adjustment device 600 does not constitute a limitation on the embodiment of the present invention.

The processor 601 can be a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a general array logic (GAL), or any combination thereof.

The memory 602 may include a volatile memory such as a random access memory (RAM); the memory 602 may also include a non-volatile memory such as a read-only memory (read- Only memory, ROM), flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 602 may also include a combination of the above types of memories.

Also provided in the embodiment of the present application is a computer storage medium, which can be used to store computer software instructions used in the image color adjustment device in the embodiment shown in FIG. 2 to FIG. 3, and includes an image for performing the above embodiment. The program designed by the color adjustment device. The storage medium includes, but is not limited to, a flash memory, a hard disk, a solid state disk.

In the embodiment of the present application, a computer program product is also provided. When the computer product is operated by the computing device, the image color adjustment method designed for the image color adjusting device in the embodiment of FIG. 2 to FIG. 3 may be executed.

The terms "first", "second", "third", and "fourth" and the like in the specification and claims of the present invention are used to distinguish different objects, and are not intended to describe a specific order. . Furthermore, the terms "comprises" and "comprising" and "comprising" are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or device that comprises a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units not listed, or alternatively includes Other steps or units inherent to these processes, methods, products or equipment.

It will be understood by those skilled in the art that in various embodiments of the present invention, the size of the sequence numbers of the above processes does not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic, without The implementation of the embodiments of the present invention should be construed as being limited in any way.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with embodiments of the present invention are generated in whole or in part. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be from a website site, computer, server or data center Transfer to another website site, computer, server, or data center by wire (eg, coaxial cable, fiber optic, digital subscriber line (DSL), or wireless (eg, infrared, wireless, microwave, etc.). The computer readable storage medium can be any available media that can be accessed by a computer or a data storage device such as a server, data center, or the like that includes one or more available media. The usable medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

One of ordinary skill in the art can understand that all or part of the process of implementing the foregoing embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, the flow of an embodiment of the methods as described above may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The above is only the preferred embodiment of the present invention, and the scope of the present invention is not limited thereto, and thus equivalent changes made in the claims of the present invention are still within the scope of the present invention.

Claims (28)

1. An image color adjustment method, comprising:

   Obtaining a color feature value of a strong color pixel for each image block of the target image, the target image being an image after automatic white balance correction, wherein the strong color pixel is a pixel for characterizing a color characteristic of the image block point;

   Adjusting a color parameter according to a color feature value of a strong color pixel corresponding to each image block of the target image;

   Color adjustment is performed on the target image according to the adjusted color parameter.
2. The method according to claim 1, wherein the adjusting the color parameter according to the color feature value of the strong color pixel corresponding to each image block of the target image comprises:

   Determining, according to a color feature value of the strong color pixel corresponding to each image block of the target image, a feature saturation of the strong color pixel corresponding to each image block;

   Adjusting the color parameter according to the feature saturation of the strong color pixel corresponding to each image block of the target image, so that each image block of the target image respectively corresponds to the adjusted color of the strong color pixel point After the parameter is color-adjusted, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated.
3. The method of claim 2 wherein said color parameters comprise color correction parameters, color enhancement parameters or tone adjustment parameters.
4. The method of claim 2 wherein said color parameters comprise color correction parameters, color enhancement parameters, and tone adjustment parameters;

   The color parameter is adjusted according to the feature saturation of the strong color pixel corresponding to each image block of the target image, so that the corresponding strong color pixel points of each image block of the target image are adjusted. After the color parameter is color-adjusted, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is saturated but includes:

   Adjusting the color correction parameters according to the feature saturation of the strong color pixel points corresponding to the image blocks of the target image, so that the respective color image pixels corresponding to the image blocks of the target image are adjusted After the color correction of the color correction parameter, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated;

   Adjusting the color enhancement parameter according to the characteristic saturation of each color pixel point after the color correction of the adjusted color correction parameter, so that the color correction of the adjusted color correction parameter is performed after each After the color enhancement of the adjusted color enhancement parameter of the strong color pixel is performed, the characteristic saturation of the corresponding strong color pixel point of each image block of the target image is not saturated;

   Adjusting the tone adjustment parameter according to the feature saturation of each of the strong color pixels after the color enhancement of the adjusted color enhancement parameter, so that the color of the adjusted color enhancement parameter is enhanced After the color tone adjustment of the adjusted color tone adjustment parameter of the strong color pixel is performed, the feature saturation of the strong color pixel corresponding to each image block of the target image is not saturated.
5. The method according to claim 2 or 3, wherein the color parameter is adjusted according to a feature saturation of a strong color pixel corresponding to each image block of the target image, so that the target After the color parameters of the image pixels of the image are adjusted by the adjusted color parameters, the characteristic saturations of the corresponding strong color pixels of each image block of the target image are saturated but include:

   Adjusting the color parameter according to a feature saturation of a strong color pixel corresponding to each image block of the target image;

   Obtaining, in each of the strong color pixels after the color adjustment of the adjusted color parameter, the corresponding number of first pixels of the strong color pixel whose feature saturation is higher than the first saturation threshold;

   When the number of the first pixel points is greater than or equal to the first number threshold, the color parameter is decreased until the number of the first pixel points is less than the first number threshold.
6. The method according to claim 2 or 3, wherein the color parameter is adjusted according to a feature saturation of a strong color pixel corresponding to each image block of the target image, so that the target After the color parameters of the image pixels of the image are adjusted by the adjusted color parameters, the characteristic saturations of the corresponding strong color pixels of each image block of the target image are saturated but include:

   Adjusting the color parameter according to a feature saturation of a strong color pixel corresponding to each image block of the target image;

   Obtaining, in each of the strong color pixels after the color adjustment of the adjusted color parameter, the corresponding feature saturation is respectively in the number of pixels of the strong color pixel points of the M high saturation range; the M high saturation The degree range is a preset plurality of saturation ranges from high to low ranked after the top M saturation ranges, and M is a positive integer greater than one;

   When the number of pixel points corresponding to at least one target high saturation range of the M high saturation ranges is greater than or equal to a second quantity threshold corresponding to the target high saturation range, the color parameter is lowered until the M The number of pixels corresponding to each of the high saturation ranges is smaller than the second number threshold corresponding to the M high saturation ranges respectively.
7. The method according to claim 2 or 3, wherein the color parameter is adjusted according to a feature saturation of a strong color pixel corresponding to each image block of the target image, so that the target After the color parameters of the image pixels of the image are adjusted by the adjusted color parameters, the characteristic saturations of the corresponding strong color pixels of each image block of the target image are saturated but include:

   Adjusting the color parameter according to a feature saturation of a strong color pixel corresponding to each image block of the target image;

   Obtaining, in each of the strong color pixels after the color adjustment of the adjusted color parameter, the corresponding feature saturation is in the number of pixels of the high color saturation pixel of the M high saturation range and the M high saturation The weight ranges respectively correspond to the weight ranges; the M high saturation ranges are preset saturation ranges of the top M after the plurality of saturation ranges are sorted from high to low, and M is a positive integer greater than 1;

   Calculating a number of second pixel points, wherein the number of the second pixel points is a sum of values obtained by multiplying the number of pixels corresponding to each high saturation range by a weight parameter corresponding to each high saturation range;

   When the number of the second pixel points is greater than or equal to the third number threshold, the color parameter is decreased until the number of the second pixel points is less than the third number threshold.
8. The method according to any one of claims 2 to 7, wherein the color parameter is adjusted according to a feature saturation of a strong color pixel corresponding to each image block of the target image, such that After each of the image blocks of the target image is color-adjusted by the adjusted color parameter of each of the image pixels, the characteristic saturation of the corresponding color pixel points of each image block of the target image is saturated before being saturated. include:

   Comparing the feature saturation of the strong color pixel corresponding to each image block of the target image with the first saturation threshold to determine the third pixel number, wherein the third pixel number is each image of the target image a corresponding number of strong color pixels in the strong color pixel corresponding to the block having a characteristic saturation greater than the first saturation threshold;

   It is determined that the number of the third pixel points is less than a fourth number threshold.
9. The method according to any one of claims 1 to 8, wherein the obtaining a color feature value of a strong color pixel for each image block of the target image comprises:

   Acquiring at least one target pixel point of the pixel corresponding to each image block of the target image that is higher in brightness than the first brightness threshold;

   Determining N high-saturation pixel points from the at least one target pixel point, wherein the N high-saturation pixel points are the top N target after the reference saturation is sorted from high to low in the at least one target pixel point a pixel, where N is a positive integer greater than or equal to 1;

   And determining, according to the color values of the N high-saturation pixel points in each image block of the target image, color feature values of a strong color pixel point corresponding to each image block of the target image.
10. The method according to claim 9, wherein the acquiring at least one target pixel of the pixel corresponding to each of the image blocks of the target image having a brightness higher than the first brightness threshold comprises:

    Obtaining, in each pixel block corresponding to each image block of the target image, the hue conforms to the first hue range and the at least one target pixel whose brightness is higher than the first brightness threshold.
11. The method of claim 10, further comprising: before: obtaining, in the image block of the target image, the hue of the first hue and the at least one target pixel having a brightness higher than the first brightness threshold, the method further comprising:

    Obtaining scene information corresponding to the target image;

    Determining, according to the scene information corresponding to the target image, the first hue range to be adjusted corresponding to the scene information.
12. The method according to any one of claims 9 to 11, wherein the reference saturation is saturation; or the reference saturation is a combined value determined by saturation and luminance.
13. The method according to any one of claims 9 to 12, wherein said determining each of said target images based on color values of said N highly saturated pixel points in each image block of said target image The color feature values of a strong color pixel corresponding to the image block respectively include:

    When N is equal to 1, determining that a color value of a high-saturation pixel corresponding to each image block of the target image is a color feature value of a strong color pixel corresponding to each image block of the target image;

    When N is greater than 1, an average value of color values of N high-saturation pixel points corresponding to each image block of the target image is respectively calculated; and N high-saturation pixel points corresponding to each image block of the target image are determined. The average value of the color values is a color feature value of one strong color pixel corresponding to each image block of the target image.
14. An image color adjustment device, comprising:

    And an obtaining module, configured to acquire, for each image block of the target image, a color feature value of a strong color pixel, wherein the target image is an image after automatic white balance correction, and the strong color pixel is used to represent the image block Pixels of color characteristics;

    a parameter adjustment module, configured to adjust a color parameter according to a color feature value of a strong color pixel corresponding to each image block of the target image;

    a color adjustment module, configured to perform color adjustment on the target image according to the adjusted color parameter.
15. The device according to claim 14, wherein the parameter adjustment module is specifically configured to:

    Determining, according to a color feature value of the strong color pixel corresponding to each image block of the target image, a feature saturation of the strong color pixel corresponding to each image block;

    Adjusting the color parameter according to the feature saturation of the strong color pixel corresponding to each image block of the target image, so that each image block of the target image respectively corresponds to the adjusted color of the strong color pixel point After the parameter is color-adjusted, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated.
16. The apparatus of claim 15 wherein said color parameters comprise color correction parameters, color enhancement parameters, or tone adjustment parameters.
17. The apparatus according to claim 15, wherein said color parameters comprise color correction parameters, color enhancement parameters, and tone adjustment parameters;

    The parameter adjustment module is specifically configured to:

    Adjusting the color correction parameters according to the feature saturation of the strong color pixel points corresponding to the image blocks of the target image, so that the respective color image pixels corresponding to the image blocks of the target image are adjusted After the color correction of the color correction parameter, the characteristic saturation of the corresponding strong color pixel points of each image block of the target image is not saturated;

    Adjusting the color enhancement parameter according to the characteristic saturation of each color pixel point after the color correction of the adjusted color correction parameter, so that the color correction of the adjusted color correction parameter is performed after each After the color enhancement of the adjusted color enhancement parameter of the strong color pixel is performed, the characteristic saturation of the corresponding strong color pixel point of each image block of the target image is not saturated;

    Adjusting the tone adjustment parameter according to the feature saturation of each of the strong color pixels after the color enhancement of the adjusted color enhancement parameter, so that the color of the adjusted color enhancement parameter is enhanced After the color tone adjustment of the adjusted color tone adjustment parameter of the strong color pixel is performed, the feature saturation of the strong color pixel corresponding to each image block of the target image is not saturated.
18. The device according to claim 15 or 16, wherein the parameter adjustment module is specifically configured to:

    Adjusting the color parameter according to a feature saturation of a strong color pixel corresponding to each image block of the target image;

    Obtaining, in each of the strong color pixels after the color adjustment of the adjusted color parameter, the corresponding number of first pixels of the strong color pixel whose feature saturation is higher than the first saturation threshold;

    When the number of the first pixel points is greater than or equal to the first number threshold, the color parameter is decreased until the number of the first pixel points is less than the first number threshold.
19. The device according to claim 15 or 16, wherein the parameter adjustment module is specifically configured to:

    Adjusting the color parameter according to a feature saturation of a strong color pixel corresponding to each image block of the target image;

    Obtaining, in each of the strong color pixels after the color adjustment of the adjusted color parameter, the corresponding feature saturation is respectively in the number of pixels of the strong color pixel points of the M high saturation range; the M high saturation The degree range is a preset plurality of saturation ranges from high to low ranked after the top M saturation ranges, and M is a positive integer greater than one;

    When the number of pixel points corresponding to at least one target high saturation range of the M high saturation ranges is greater than or equal to a second quantity threshold corresponding to the target high saturation range, the color parameter is lowered until the M The number of pixels corresponding to each of the high saturation ranges is smaller than the second number threshold corresponding to the M high saturation ranges respectively.
20. The device according to claim 15 or 16, wherein the parameter adjustment module is specifically configured to:

    Adjusting the color parameter according to a feature saturation of a strong color pixel corresponding to each image block of the target image;

    Obtaining, in each of the strong color pixels after the color adjustment of the adjusted color parameter, the corresponding feature saturation is in the number of pixels of the high color saturation pixel of the M high saturation range and the M high saturation The weight ranges respectively correspond to the weight ranges; the M high saturation ranges are preset saturation ranges of the top M after the plurality of saturation ranges are sorted from high to low, and M is a positive integer greater than 1;

    Calculating a number of second pixel points, wherein the number of the second pixel points is a sum of values obtained by multiplying the number of pixels corresponding to each high saturation range by a weight parameter corresponding to each high saturation range;

    When the number of the second pixel points is greater than or equal to the third number threshold, the color parameter is decreased until the number of the second pixel points is less than the third number threshold.
21. A device according to any of claims 15-20, wherein

    The acquiring module is further configured to: compare a feature saturation of a strong color pixel corresponding to each image block of the target image with a first saturation threshold, and determine a third pixel number, the third pixel number And a number of strong color pixel points corresponding to the first saturation threshold in the strong color pixel corresponding to each image block of the target image;

    The device also includes:

    And a comparing module, configured to determine that the number of the third pixel points is less than a fourth number threshold.
22. The device according to any one of claims 14 to 21, wherein the obtaining module is specifically configured to:

    Acquiring at least one target pixel point of the pixel corresponding to each image block of the target image that is higher in brightness than the first brightness threshold;

    Determining N high-saturation pixel points from the at least one target pixel point, wherein the N high-saturation pixel points are the top N target after the reference saturation is sorted from high to low in the at least one target pixel point a pixel, where N is a positive integer greater than or equal to 1;

    Determining, according to color values of the N high-saturation pixel points in each image block of the target image, color feature values of a strong color pixel corresponding to each image block of the target image.
23. The device of claim 22, wherein the obtaining module is specifically configured to:

    Obtaining, in each pixel block corresponding to each image block of the target image, the hue conforms to the first hue range and the at least one target pixel whose brightness is higher than the first brightness threshold.
24. The device of claim 23, wherein the obtaining module is further configured to:

    Obtaining scene information corresponding to the target image;

    Determining, according to the scene information corresponding to the target image, the first hue range to be adjusted corresponding to the scene information.
25. The apparatus according to any one of claims 11 to 24, wherein the reference saturation is saturation; or the reference saturation is a combined value determined by saturation and luminance.
26. The device according to any one of claims 11 to 25, wherein the obtaining module is specifically configured to:

    When N is equal to 1, determining that a color value of a high-saturation pixel corresponding to each image block of the target image is a color feature value of a strong color pixel corresponding to each image block of the target image;

    When N is greater than 1, respectively, calculating an average value of color values of N high-saturation pixel points corresponding to each image block of the target image; determining color of N high-saturation pixel points corresponding to each image block of the target image The average value of the values is a color feature value of one strong color pixel corresponding to each image block of the target image.
27. An image color adjustment device, comprising:

    Memory for storing programs;

    A processor for executing the program stored by the memory, the processor for performing the steps of any of claims 1-13 when the program is executed.
28. A computer readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any of claims 1-13.

Images