CN110473156B - Image information processing method, device, storage medium and electronic device - Google Patents

Abstract

The embodiment of the application discloses a method for processing image information, which comprises the following steps: acquiring an image to be processed, and performing object recognition to obtain a first object area and a second object area which are related; determining corresponding first color adjustment information based on the first object area and the second object area; performing tone mapping processing on the first object region to generate a first target object region after the tone mapping processing; and calculating second color tone adjustment information of the first target object area and the first object area, and determining a color tone mapping processing strategy of the second object area according to the first color tone adjustment information and the second color tone adjustment information. Therefore, a tone mapping processing strategy suitable for the second object area is determined according to the first tone adjustment information of the associated first object area and the second object area before and after tone mapping processing and the second tone adjustment information of the first object area before and after tone mapping, so that the processing effect of the associated area is real, and the processing efficiency of the image information is greatly improved.

Description

Image information processing method, device, storage medium and electronic device

technical field

The present application relates to the technical field of image processing, and in particular, to a method, apparatus, storage medium and electronic device for processing image information.

Background technique

With the continuous development of electronic technology, the camera pixels and image processing functions of electronic devices such as mobile phones are becoming more and more powerful, and people's requirements for image processing effects are getting higher and higher, especially for high dynamic range (High Dynamic Range Imaging, HDR). ) of the image processing effect.

At present, the high dynamic range image is generally processed by tone mapping, which makes the overall visual effect of the image better. The processing effect is inconsistent, which affects the processing efficiency.

SUMMARY OF THE INVENTION

Embodiments of the present application provide an image information processing method, apparatus, storage medium, and electronic device, which can improve the processing efficiency of image information.

In a first aspect, an embodiment of the present application provides a method for processing image information, including:

acquiring an image to be processed, and performing object recognition on the image to be processed to obtain the associated first object area and second object area;

determining corresponding first tone adjustment information based on the first object area and the second object area;

Perform tone mapping processing on the first object area to generate the first target object area after tone mapping processing;

Calculate the second tone adjustment information of the first target object area and the first object area, and determine a tone mapping processing strategy for the second object area according to the first tone adjustment information and the second tone adjustment information.

In a second aspect, an embodiment of the present application provides an apparatus for processing image information, including:

an identification unit for acquiring an image to be processed, and performing object recognition on the image to be processed to obtain the associated first object area and second object area;

a determining unit, configured to determine corresponding first tone adjustment information based on the first object area and the second object area;

a processing unit, configured to perform tone mapping processing on the first object area, and generate the first target object area after tone mapping processing;

a calculation unit, configured to calculate the second tone adjustment information of the first target object area and the first object area, and determine the tone mapping of the second object area according to the first tone adjustment information and the second tone adjustment information processing strategy.

In a third aspect, a storage medium provided by an embodiment of the present application stores a computer program thereon, and when the computer program runs on a computer, the computer is made to execute the image information processing method provided by any embodiment of the present application. .

In a fourth aspect, an electronic device provided by an embodiment of the present application includes a processor and a memory, the memory has a computer program, and the processor is configured to execute the image provided by any embodiment of the present application by invoking the computer program. Information processing method.

The embodiment of the present application acquires the image to be processed for object recognition, and obtains the associated first object area and the second object area; determines the corresponding first color tone adjustment information based on the first object area and the second object area; Perform tone mapping processing to generate the first target object area after tone mapping processing; calculate the second tone adjustment information of the first target object area and the first object area, and determine the first tone adjustment information according to the first tone adjustment information and the second tone adjustment information. Tone-mapping processing strategy for two-object regions. In this way, a tone mapping suitable for the second object area is determined according to the combination of the first tone adjustment information of the associated first object area and the second object area before tone mapping processing and the second tone adjustment information of the first object area before and after tone mapping. The processing strategy makes the processing effect of the associated area real, and greatly improves the processing efficiency of image information.

Description of drawings

The technical solutions and other beneficial effects of the present application will be apparent through the detailed description of the specific embodiments of the present application in conjunction with the accompanying drawings.

FIG. 1 is a schematic flowchart of a method for processing image information provided by an embodiment of the present application.

FIG. 2 is another schematic flowchart of a method for processing image information provided by an embodiment of the present application.

FIG. 3 is a schematic scene diagram of a method for processing image information provided by an embodiment of the present application.

FIG. 4 is a schematic block diagram of an apparatus for processing image information according to an embodiment of the present application.

FIG. 5 is a schematic diagram of another module of the image information processing apparatus provided by the embodiment of the present application.

FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

FIG. 7 is another schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

Please refer to the drawings, wherein the same component symbols represent the same components, and the principles of the present application are exemplified by being implemented in a suitable computing environment. The following description is based on illustrated specific embodiments of the present application and should not be construed as limiting other specific embodiments of the present application not detailed herein.

As used herein, the term "module" can be thought of as a software object that executes on the computing system. The various components, modules, engines and services mentioned herein can be considered as implementation objects on the computing system. While the apparatus and method herein are preferably implemented in software, of course, they can also be implemented in hardware, which are all within the protection scope of the present application.

An embodiment of the present application provides a method for processing image information, and the execution body of the method for processing image information may be the image information processing apparatus provided in the embodiment of the present application, or an electronic device integrating the image information processing apparatus, wherein The image information processing apparatus can be implemented in hardware or software. The electronic device may be a smart phone, a tablet computer, a PDA (Personal Digital Assistant), and the like.

The specific analysis is described below.

An embodiment of the present application provides a method for processing image information, as shown in FIG. 1 , which is a schematic flowchart of the method for processing image information provided by an embodiment of the present application, and the method for processing image information may include the following steps:

In step S101, an image to be processed is acquired, and object recognition is performed on the image to be processed to obtain an associated first object area and a second object area.

Wherein, the format of the image to be processed may be a bitmap (BitMaP, BMP), a joint photographic expert group (Joint Photographic Expert Group, JPEG), etc., and the image to be recognized may be a high dynamic range image, the high dynamic range image, phase Compared with ordinary images, it can provide more dynamic range and image details, but due to the uneven grayscale distribution of high dynamic range images, some pixels are too bright, and some pixels are too dark, so it is necessary to use tone mapping. , map the color of the image, map the color value of the image from high dynamic range to low dynamic range, so that the color distribution is uniform, it looks more comfortable, and the overall rendering effect is better, and in the process of this operation, it will be brighter The most common operation is to darken the pixels.

However, in the tone mapping processing method of the image, the preset object area is protected, such as the protection mechanism of the face object area, so as to prevent the face object area from being darkened too much during the tone mapping process, resulting in the appearance of the face not appearing. Naturally, however, only protecting the face object area will cause the objects around the face object area to still be processed in the original tone-mapping way, such as human hair. When the hair is black, darkening the hair will not cause the same The face object area is too uncoordinated, but now with the diversification of life, more and more people like to dye their hair, and many of them dye their hair into bright colors that are not black, or Europeans and Americans are born with non-black hair. Here In this case, if the face object area is protected, but the associated hair object area is still processed according to the original tone mapping method, the protected face object area and the hair object processed by the normal tone mapping method will result. The regional differences are too large, making the entire portrait after tone processing unnatural.

Optionally, an image recognition algorithm, such as a convolutional neural network (Convolutional Neural Networks, CNN) algorithm, can be used to perform image recognition on the image to be processed, identify different objects in the image to be processed, and determine the interrelated objects from different objects. The first object region and the second object region, such as the face object region and the hair object region are strongly correlated, or the trunk object region and the leaf object region are strongly correlated, and the associated first object region and the second object region are in Reasonable processing is required in tone mapping processing to avoid unrealistic image processing.

In step S102, corresponding first color tone adjustment information is determined based on the first object area and the second object area.

Wherein, corresponding first tone adjustment information may be calculated based on the first object area and the second object area, where the first tone adjustment information is the expressiveness of the first object area and the second object area before tone mapping processing is performed The difference range, such as the difference in brightness and contrast between the first object area and the second object area, the corresponding difference range is determined according to the difference, and the difference range is the first tone adjustment information. The first tone adjustment The information reflects the difference in image representation between the first object area and the second object area in the original image. Even if tone mapping is performed subsequently, the difference in image representation needs to be preserved to preserve the authenticity value of the image.

In step S103, tone mapping processing is performed on the first target area to generate a first target target area after tone mapping processing.

Among them, the conventional tone mapping method is to adjust according to the brightness and contrast of the pixel itself, which easily leads to the adjustment of the brightness and contrast of objects in different areas of the entire image cannot meet the requirements at the same time. For example, in an image of a person, the background is brighter At this time, if you want to tone-map the image to a low dynamic image, you need to compress the pixels with high pixel values. Although the dynamic range of the sky can be reduced, it will also lead to higher pixel values in the portrait. The points will also be compressed at the same time, making the portrait unreal, and the contrast between parts will be poor. At this time, the face object area is generally protected to prevent the face object area from being darkened too much during the tone mapping process. Causes the face to display abnormally.

Optionally, a region similar to a face object region that needs a tone-mapping protection mechanism is determined as the first object region, and tone-mapping processing is performed according to the tone-mapping processing under the protection mechanism to generate the first target object region after tone-mapping. .

In step S104, the first target object area and the second tone adjustment information of the first object area are calculated, and the tone mapping processing strategy of the second object area is determined according to the first tone adjustment information and the second tone adjustment information.

Wherein, based on the performance difference range of the first target object area after tone mapping processing under the protection mechanism and the first object area without tone mapping processing under the protection mechanism, such as the first target object area and the first object area In the difference between brightness and contrast, a corresponding difference range is determined according to the difference, and the difference range is the second adjustment information, and the second tone adjustment information reflects the first object area in the original image and the protection mechanism according to The difference in the image representation of the first target object area after the tone mapping processing in

Further, the corresponding tone mapping processing strategy of the second object area is determined in combination with the first tone adjustment information and the second tone adjustment information, so that after the second object area is subjected to tone mapping processing based on the tone mapping processing strategy, the obtained tone The expressiveness of the second target object area after the mapping processing conforms to the difference in expressiveness between the first object area and the second object area in the original to-be-processed image, and also conforms to the processing range of the tone mapping processing of the first object area, so that tone mapping is performed. The expressiveness of the processed first target object region and the second target object region meets the requirements of the real scene.

It can be seen from the above that, in a method for processing image information provided by this embodiment, object recognition is performed by acquiring an image to be processed, and the associated first object area and second object area are obtained; based on the first object area and the second object area, determine obtain the corresponding first tone adjustment information; perform tone mapping processing on the first object area to generate the first target object area after tone mapping processing; calculate the second tone adjustment information of the first target object area and the first object area, and A tone mapping processing strategy for the second object area is determined according to the first tone adjustment information and the second tone adjustment information. In this way, a tone mapping suitable for the second object area is determined according to the combination of the first tone adjustment information of the associated first object area and the second object area before tone mapping processing and the second tone adjustment information of the first object area before and after tone mapping. The processing strategy makes the processing effect of the associated area real, and greatly improves the processing efficiency of image information.

According to the methods described in the above embodiments, the following examples will be used for further detailed description.

Please refer to FIG. 2 , which is another schematic flowchart of a method for processing image information provided by an embodiment of the present application.

Specifically, the method includes:

In step S201, an image to be processed is acquired, and key feature point information in the image to be processed is extracted.

It should be noted that, in order to better illustrate the present application, the electronic device is exemplified by a mobile phone in the following.

Among them, the mobile phone obtains a high dynamic range image. As shown in Figure 3, the processed image 1 is the high dynamic range image. The processed image 1 may include the sky and people. Due to the problem of light refraction, the sky in the processed image 1 is captured Brightness and contrast are bound to be higher than the brightness and contrast of characters.

Optionally, the convolutional neural network can perform feature recognition on the pixels of the image to be processed one by one in a top-to-bottom order, and extract key feature point information in the image to be processed.

In step S202, the associated face object region and hair object region are determined according to the key feature point information.

Among them, the face object area can be determined according to the key feature point information. Since the features contained in the face object area are very rich and special, such as key feature points such as eyes, mouth, eyebrows, nose and hair, the key feature points are determined according to the key feature points. Out face object regions and associated hair object regions.

Since the current conventional tone mapping method is to simultaneously process the brightness and contrast of different object regions in the entire image to be processed, as shown in Figure 3, the conventional tone mapping method is to process the hair object region A, the face object region B and the sky. The object area C is subjected to tone-mapping processing together, and the background is a brighter sky. At this time, if you want to tone-map the processed image 1 to a low-dynamic image, you need to compress the pixels with high pixel values. The dynamic range is reduced, but at the same time, the pixel values in the portrait will be over-compressed like the sky processing degree, making the portrait unreal and the contrast between parts is relatively poor, so it is often necessary to protect the face of the image. The area is subjected to separate tone mapping processing, and other object areas such as the hair object area are still processed according to the same degree as the sky. Therefore, in the case of strong correlation between the face object area and the hair object area, it will cause the face after tone mapping processing. There is a large difference between the brightness and contrast of the object area and the hair object area, making the portrait appear unreal.

In step S203, a first brightness value and a first contrast value of the face object region are obtained, and a second brightness value and a second contrast value of the hair object region are obtained.

Among them, the first brightness value and the first contrast value of the face object area before tone mapping processing are obtained, and the second brightness value and the second contrast value of the hair object area before tone mapping processing are obtained. The brightness value, the first contrast value, and the second brightness value and the second contrast value represent the expressiveness difference range between the face object region and the hair object region in the original image, which are more realistic representations of portraits.

In step S204, a first brightness difference between the first brightness value and the second brightness value and a first contrast difference between the first contrast value and the second contrast value are calculated, and the first brightness difference and the first contrast difference are determined as the first Hue adjustment information.

The first brightness difference between the first brightness value and the second brightness value and the first contrast difference between the first contrast value and the second contrast are calculated, and the first brightness difference and the first contrast difference are positive numbers, such as the first brightness If the difference and the first contrast difference are negative numbers, absolute value processing needs to be performed accordingly.

Optionally, the first brightness difference range may be determined according to the first brightness difference and the first contrast difference range may be determined according to the first contrast difference, and the size of the range fluctuates up and down according to the actual situation. 5 and so on, the corresponding first tone adjustment information is determined based on the first brightness difference range and the first contrast difference range, and the first tone adjustment information reflects the image representation of the face object area and the hair object area in the original image degree difference range.

In step S205, tone mapping processing is performed on the face object region to generate a first target face object region after tone mapping processing.

Wherein, as shown in FIG. 3 , a tone mapping process with a face protection mechanism is performed on the face object region B, and a first target face object region after tone mapping processing is generated.

In step S206, a third brightness value and a third contrast value of the first target face object region are obtained.

Wherein, the third brightness value and the third contrast value of the first target face object region after the tone mapping process with the face protection mechanism is performed are acquired.

In step S207, the second brightness difference between the third brightness value and the first brightness value and the second contrast difference between the third contrast value and the first contrast value are calculated, and the second brightness difference and the second contrast difference are determined as the second brightness difference Hue adjustment information.

Among them, no matter how the tone-mapping process is performed on the high-dynamic image, the final rendering effect should conform to the rendering law of the original dynamic image. Therefore, the third step of calculating the target face object area after tone-mapping processing with the face protection mechanism is calculated. The second luminance difference between the luminance value and the first luminance value of the face object region of the original image and the third contrast value of the target face object region after tone-mapping processing with the face protection mechanism and the face object region of the original image The second contrast difference of the first contrast value, the second brightness difference and the second contrast difference are positive numbers, if the second brightness difference and the second contrast difference are negative numbers, then the absolute value processing needs to be performed accordingly.

Optionally, the second brightness difference range may be determined according to the second brightness difference and the second contrast difference range may be determined according to the second contrast difference. The size of the range fluctuates up and down according to the actual situation. 5 and so on, based on the second brightness difference range and the second contrast difference range to determine the corresponding second tone adjustment information, the second tone adjustment information, the second tone adjustment information that reflects the face object area and The image representation degree of the target face object region after the tone mapping processing according to the face protection mechanism is in the range.

In step S208, the regional tone contrast range is determined according to the first brightness difference and the first contrast difference, the face tone adjustment range is determined according to the second brightness difference and the second contrast difference, and the regional tone contrast range and the face tone adjustment are combined. The range determines the corresponding tone-mapping processing strategy for the hair object area.

Wherein, according to the first brightness difference range corresponding to the first brightness difference and the first contrast difference range corresponding to the first contrast, the regional tone contrast range between the face object region and the hair object region in the original to-be-processed image is determined. The regional tone contrast range is the contrast range between the face object area and the hair object area of the original image to be processed. The target face object area and the target hair object area after subsequent tone mapping processing need to meet this contrast range, so that the face and hair Keep the original presentation, keep it authentic.

Further, according to the second brightness difference range corresponding to the second brightness difference and the second contrast difference range corresponding to the second contrast, determine the target face object area after tone mapping processing with the face protection mechanism and the original image to be processed. The face tone adjustment range between the face object regions, the face adjustment range is the adjustment range of the target face object region and the face object of the original to-be-processed image after the tone mapping process of the face protection mechanism is performed, The hair object region in the subsequent original to-be-processed image and the target hair head object region after tone-mapping processing need to satisfy this adjustment range, so that the tone-mapping processing effect of the hair object region is the same as the processing effect of tone-mapping processing with a face protection mechanism near.

Therefore, the tone mapping processing strategy of the hair object area is determined in combination with the tone contrast range of the area and the face tone adjustment range, so that after the hair object area is subjected to tone mapping processing according to the tone mapping processing strategy, the obtained target hair object area meets the requirements to be The difference between the original appearance of the face object area and the hair object area in the image and the adjustment processing effect after the tone mapping processing of the face protection mechanism are processed, so that the expression degree of the target face object area and the target hair object area after tone mapping are consistent with each other. Authenticity, which avoids the large difference in the rendering effect of the associated hair object area under the tone mapping processing of face protection under the face object area, which makes the portrait appear unreal.

It can be seen from the above that, in a method for processing image information provided by this embodiment, object recognition is performed by acquiring an image to be processed, and the associated first object area and second object area are obtained; based on the first object area and the second object area, determine obtain the corresponding first tone adjustment information; perform tone mapping processing on the first object area to generate the first target object area after tone mapping processing; calculate the second tone adjustment information of the first target object area and the first object area, and A tone mapping processing strategy for the second object area is determined according to the first tone adjustment information and the second tone adjustment information. In this way, a tone mapping suitable for the second object area is determined according to the combination of the first tone adjustment information of the associated first object area and the second object area before tone mapping processing and the second tone adjustment information of the first object area before and after tone mapping. The processing strategy makes the processing effect of the associated area real, and greatly improves the processing efficiency of image information.

In order to facilitate better implementation of the image information processing method provided by the embodiment of the present application, the embodiment of the present application further provides a device based on the above-mentioned image information processing method. The meanings of the nouns are the same as those in the above-mentioned image information processing method, and the specific implementation details can refer to the description in the method embodiment.

Please refer to FIG. 4 , which is a schematic block diagram of an apparatus for processing image information according to an embodiment of the present application. Specifically, the image information processing apparatus 300 includes: an identification unit 31 , a determination unit 32 , a processing unit 33 and a calculation unit 34 .

The identification unit 31 is configured to acquire an image to be processed, and perform object recognition on the image to be processed to obtain the associated first object area and second object area.

The recognition unit 31 can perform image recognition on the image to be processed through an image recognition algorithm, such as a convolutional neural network algorithm, identify different objects in the image to be processed, and determine the interrelated first object area and The second object region, such as the face object region and the hair object region are strongly correlated, or the trunk object region and the leaf object region are strongly correlated, the associated first object region and the second object region need in the tone mapping process Carry out reasonable processing to avoid unrealistic image processing.

In some embodiments, as shown in FIG. 5 , the identification unit 31 includes:

The extraction subunit 311 is used for acquiring the image to be processed, and extracting the key feature point information in the image to be processed;

The determining subunit 312 is configured to determine the associated face object region and hair object region according to the key feature point information.

The determining unit 32 is configured to determine corresponding first tone adjustment information based on the first object area and the second object area.

Wherein, the determining unit 32 may calculate corresponding first tone adjustment information based on the first object area and the second object area, and the first tone adjustment information is the first object area and the second object area before tone mapping processing is performed For example, the difference between the brightness and contrast of the first object area and the second object area, the corresponding difference range is determined according to the difference, and the difference range is the first tone adjustment information. The tone adjustment information reflects the difference in image representation between the first object area and the second object area in the original image. Even if tone mapping processing is performed subsequently, the image representation difference needs to be preserved to preserve the authenticity value of the image.

In some embodiments, the determining unit 32 is specifically configured to obtain the first brightness value and the first contrast value of the face object region; obtain the second brightness value and the second contrast value of the hair object region; calculate the first brightness value and the second contrast value of the hair object region; The first brightness difference between the brightness value and the second brightness value and the first contrast difference between the first contrast value and the second contrast value; the first brightness difference and the first contrast difference are determined as the first tone adjustment information.

The processing unit 33 is configured to perform tone mapping processing on the first object area to generate a first target object area after tone mapping processing.

Wherein, the processing unit 33 determines the area similar to the face object area that needs to be subjected to the tone mapping protection mechanism as the first object area, and performs tone mapping processing according to the tone mapping processing under the protection mechanism to generate the first target object after tone mapping area.

In some embodiments, the processing unit 33 is specifically configured to: perform tone mapping processing on the face object region, and generate a first target face object region after tone mapping processing.

A calculation unit 34, configured to calculate the second tone adjustment information of the first target object area and the first object area, and determine the tone of the second object area according to the first tone adjustment information and the second tone adjustment information Map processing strategies.

Wherein, the calculation unit 34 is based on the expression difference range of the first target object area processed according to the tone mapping under the protection mechanism and the first object area not processed according to the tone mapping under the protection mechanism, such as the first target object area and the first target area. The difference between the brightness and contrast of an object area, and the corresponding difference range is determined according to the difference. The difference range is the second adjustment information, and the second tone adjustment information reflects the difference between the first object area and the original image. According to the difference in image representation of the first target object area after tone mapping processing under the protection mechanism, subsequent tone mapping processing on the second object area needs to follow the difference in processing degree of the tone mapping processing on the first object area.

Further, the calculation unit 34 determines the corresponding tone mapping processing strategy of the second object area in combination with the first tone adjustment information and the second tone adjustment information, so that after the second object area performs tone mapping processing based on the tone mapping processing strategy, The obtained expressivity of the second target object area after tone mapping processing conforms to the difference in expressivity between the first object area and the second object area in the original to-be-processed image, and also conforms to the processing range of the tone mapping processing of the first object area, The expressiveness of the first target object region and the second target object region after tone mapping processing is made to meet the requirements of the real scene.

In some embodiments, the calculation unit 34 is specifically configured to: obtain a third brightness value and a third contrast value of the first target face object region; calculate the third brightness value and the second brightness of the first brightness value difference and a second contrast difference between the third contrast value and the first contrast value; determining the second brightness difference and the second contrast difference as second tone adjustment information; according to the first brightness difference and the first contrast The difference determines the regional tone contrast range; determines the face tone adjustment range according to the second brightness difference and the second contrast difference; combines the regional tone contrast range and the face tone adjustment range to determine the corresponding tone of the hair object area Map processing strategies.

It can be seen from the above that the image information processing device provided in this embodiment obtains the image to be processed through the identification unit 31 for object identification, and obtains the associated first object area and the second object area; the determination unit 32 is based on the first object area. Determine the corresponding first tone adjustment information with the second object area; the processing unit 33 performs tone mapping processing on the first object area to generate the first target object area after tone mapping processing; the computing unit 34 calculates the first target object area and the second color tone adjustment information of the first object area, and the tone mapping processing strategy of the second object area is determined according to the first color tone adjustment information and the second tone adjustment information. In this way, a tone mapping suitable for the second object area is determined according to the combination of the first tone adjustment information of the associated first object area and the second object area before tone mapping processing and the second tone adjustment information of the first object area before and after tone mapping. The processing strategy makes the processing effect of the associated area real, and greatly improves the processing efficiency of image information.

The embodiments of the present application also provide an electronic device. Referring to FIG. 6 , the electronic device 500 includes a processor 501 and a memory 502 . The processor 501 is electrically connected to the memory 502 .

The processor 500 is the control center of the electronic device 500, and uses various interfaces and lines to connect various parts of the entire electronic device, execute or load the computer program stored in the memory 502, and call the data stored in the memory 502 to execute Various functions of the electronic device 500 and processing data, so as to monitor the electronic device 500 as a whole.

The memory 502 can be used to store software programs and modules, and the processor 501 executes various functional applications and image information processing by running the computer programs and modules stored in the memory 502 . The memory 502 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, a computer program (such as a sound playback function, an image playback function, etc.) required for at least one function, and the like; Data created by the use of electronic equipment, etc. Additionally, memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 502 may also include a memory controller to provide processor 501 access to memory 502 .

In this embodiment of the present application, the processor 501 in the electronic device 500 loads the instructions corresponding to the processes of one or more computer programs into the memory 502 according to the following steps, and is executed by the processor 501 and stored in the memory 502 The computer program in , so as to realize various functions, as follows:

acquiring an image to be processed, and performing object recognition on the image to be processed to obtain the associated first object area and second object area;

determining corresponding first tone adjustment information based on the first object area and the second object area;

Perform tone mapping processing on the first object area to generate the first target object area after tone mapping processing;

Calculate the second tone adjustment information of the first target object area and the first object area, and determine a tone mapping processing strategy for the second object area according to the first tone adjustment information and the second tone adjustment information.

In some embodiments, the first object region is a face object region, and the second object region is a hair object region, and the associated first object region and second object region are obtained by performing object recognition on the to-be-processed image. When the object area is selected, the processor 501 may specifically perform the following steps:

extracting key feature point information in the to-be-processed image;

The associated face object region and hair object region are determined according to the key feature point information.

In some embodiments, when the corresponding first color tone adjustment information is determined based on the first object area and the second object area, the processor 501 may specifically perform the following steps:

obtaining the first brightness value and the first contrast value of the face object area;

obtaining the second brightness value and the second contrast value of the hair object area;

calculating a first brightness difference between the first brightness value and the second brightness value and a first contrast difference between the first contrast value and the second contrast value;

The first brightness difference and the first contrast difference are determined as first tone adjustment information.

In some embodiments, when calculating the second color tone adjustment information of the first target object area and the first object area, the processor 501 may specifically perform the following steps:

obtaining the third brightness value and the third contrast value of the first target face object area;

calculating a second brightness difference between the third brightness value and the first brightness value and a second contrast difference between the third contrast value and the first contrast value;

The second luminance difference and the second contrast difference are determined as second hue adjustment information.

In some embodiments, when determining the tone mapping processing strategy of the second object area according to the first tone adjustment information and the second tone adjustment information, the processor 501 may specifically perform the following steps:

determining a regional hue contrast range according to the first brightness difference and the first contrast difference;

determining a face tone adjustment range according to the second brightness difference and the second contrast difference;

The corresponding tone mapping processing strategy for the hair object area is determined in combination with the regional tone contrast range and the face tone adjustment range.

In some embodiments, when performing tone mapping processing on the first object area to generate the first target object area after tone mapping processing, the processor 501 may specifically perform the following steps:

Tone-mapping processing is performed on the face object region to generate a first target face object region after tone-mapping processing.

It can be seen from the above that the electronic device according to the embodiment of the present application performs object recognition by acquiring the image to be processed to obtain the associated first object area and the second object area; based on the first object area and the second object area, the corresponding first object area is determined. tone adjustment information; perform tone mapping processing on the first object area to generate the first target object area after tone mapping processing; calculate the second tone adjustment information of the first target object area and the first object area, and adjust the tone according to the first tone The information and the second tone adjustment information determine a tone mapping processing strategy for the second object area. In this way, a tone mapping suitable for the second object area is determined according to the combination of the first tone adjustment information of the associated first object area and the second object area before tone mapping processing and the second tone adjustment information of the first object area before and after tone mapping. The processing strategy makes the processing effect of the associated area real, and greatly improves the processing efficiency of image information.

Please also refer to FIG. 7 , in some embodiments, the electronic device 500 may further include: a display 503 , a radio frequency circuit 504 , an audio circuit 505 and a power supply 506 . Among them, the display 503 , the radio frequency circuit 504 , the audio circuit 505 and the power supply 506 are respectively electrically connected to the processor 501 .

The display 503 may be used to display information input by the user or information provided to the user and various graphical user interfaces, which may be composed of graphics, text, icons, video, and any combination thereof. The display 503 may include a display panel, and in some embodiments, the display panel may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), or an organic light-emitting diode (Organic Light-Emitting Diode, OLED).

The radio frequency circuit 504 can be used to send and receive radio frequency signals, so as to establish wireless communication with network devices or other terminals through wireless communication, and to send and receive signals with network devices or other terminals.

The audio circuit 505 can be used to provide an audio interface between a user and an electronic device through a speaker or a microphone.

The power supply 506 may be used to power various components of the electronic device 500 . In some embodiments, the power supply 506 may be logically connected to the processor 501 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption through the power management system.

Embodiments of the present application further provide a storage medium, where a computer program is stored in the storage medium, and when the computer program runs on a computer, the computer is made to execute the image information processing method in any of the above-mentioned embodiments, such as: processing the image, and performing object recognition on the to-be-processed image to obtain the associated first object region and second object region; determining corresponding first tone adjustment information based on the first object region and the second object region; The first object area is subjected to tone mapping processing to generate the first target object area after tone mapping processing; the second tone adjustment information of the first target object area and the first object area is calculated, and the The adjustment information and the second tone adjustment information determine a tone mapping processing strategy for the second object area.

In this embodiment of the present application, the storage medium may be a magnetic disk, an optical disk, a read only memory (Read Only Memory, ROM,), or a random access memory (Random Access Memory, RAM), or the like.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

It should be noted that, for the image information processing method of the embodiment of the present application, ordinary testers in the art can understand that all or part of the process of realizing the image information processing method of the embodiment of the present application can be controlled by a computer program. The computer program can be stored in a computer-readable storage medium, such as a memory of an electronic device, and executed by at least one processor in the electronic device, and the execution process can include images such as images Flow of an embodiment of a method for processing information. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, or the like.

For the image information processing apparatus according to the embodiment of the present application, each functional module may be integrated in one processing chip, or each module may exist physically alone, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk or an optical disk.

The image information processing method, device, storage medium, and electronic device provided by the embodiments of the present application have been described in detail above. The principles and implementations of the present application are described with specific examples. The description is only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, there will be changes in the specific embodiment and the scope of application. In summary, The contents of this specification should not be construed as limiting the application.

Claims (10)

1. a processing method of image information, is characterized in that, comprises: acquiring an image to be processed, and performing object recognition on the image to be processed to obtain the associated first object area and second object area; Determining the corresponding first hue adjustment information based on the first object area and the second object area includes: acquiring a first brightness value and a first contrast value of the first object area; acquiring a second brightness value of the second object area and the second contrast value; calculate the first brightness difference between the first brightness value and the second brightness value and the first contrast difference between the first contrast value and the second contrast value; A contrast difference is determined as the first tone adjustment information; wherein, the first tone adjustment information is the range of expression difference between the first object area and the second object area before tone mapping processing is performed; Perform tone-mapping processing on the first object area based on tone-mapping processing under the protection mechanism, to generate a first target object area after tone-mapping processing; Calculate the second tone adjustment information of the first target object area and the first object area, and determine the tone mapping processing strategy of the second object area according to the first tone adjustment information and the second tone adjustment information, including: acquiring a third brightness value and a third contrast value of the first target object area; calculating a second brightness difference between the third brightness value and the first brightness value and a second contrast difference between the third contrast value and the first contrast value; Determine the second brightness difference and the second contrast difference as the second tone adjustment information; determine the regional tone contrast range according to the first brightness difference and the first contrast difference; The second contrast difference determines the tone adjustment range of the first object area; the tone mapping processing strategy corresponding to the second object area is determined by combining the area tone contrast range and the tone adjustment range of the first object area; wherein, the second tone adjustment The information is based on the expressiveness difference range of the first target object area processed according to tone mapping under the protection mechanism and the first object area not processed according to tone mapping under the protection mechanism. 2 . The method for processing image information according to claim 1 , wherein the first object area is a face object area, the second object area is a hair object area, and the image to be processed is processed. 3 . Object identification, the steps of obtaining the associated first object area and the second object area include: extracting key feature point information in the to-be-processed image; The associated face object region and hair object region are determined according to the key feature point information. 3. The method for processing image information according to claim 2, wherein the acquiring the first brightness value and the first contrast value of the first object area; acquiring the second brightness value and the second brightness value of the second object area Contrast value steps, including: obtaining the first brightness value and the first contrast value of the face object area; A second brightness value and a second contrast value of the hair object region are obtained. 4. The method for processing image information according to claim 3, wherein the step of acquiring the third brightness value and the third contrast value of the first target object region comprises: Obtain a third brightness value and a third contrast value of the first target face object region. 5 . The image information processing method according to claim 4 , wherein, determining the tone adjustment range of the first object area according to the second brightness difference and the second contrast difference; combining the area tone contrast range The step of determining a tone mapping processing strategy corresponding to the second object area with the tone adjustment range of the first object area includes: determining a face tone adjustment range according to the second brightness difference and the second contrast difference; The corresponding tone mapping processing strategy for the hair object area is determined in combination with the regional tone contrast range and the face tone adjustment range. 6. The method for processing image information according to any one of claims 2 to 5, wherein the tone mapping processing is performed on the first target area to generate a tone-mapped image of the first target target area. steps, including: Tone-mapping processing is performed on the face object region to generate a first target face object region after tone-mapping processing. 7. An apparatus for processing image information, comprising: an identification unit for acquiring an image to be processed, and performing object recognition on the image to be processed to obtain the associated first object area and second object area; a determining unit, configured to determine corresponding first tone adjustment information based on the first object area and the second object area, including: acquiring a first brightness value and a first contrast value of the first object area; acquiring the second object area the second brightness value and the second contrast value; calculate the first brightness difference between the first brightness value and the second brightness value and the first contrast difference between the first contrast value and the second contrast value; The difference and the first contrast difference are determined as the first tone adjustment information; wherein, the first tone adjustment information is the expressiveness difference range between the first object area and the second object area before tone mapping processing is performed; a processing unit, configured to perform tone-mapping processing on the first object area based on tone-mapping processing under the protection mechanism, to generate the first target object area after tone-mapping processing; a calculation unit, configured to calculate the second tone adjustment information of the first target object area and the first object area, and determine the tone mapping of the second object area according to the first tone adjustment information and the second tone adjustment information The processing strategy includes: acquiring the third brightness value and the third contrast value of the first target object area; calculating the second brightness difference between the third brightness value and the first brightness value and the difference between the third contrast value and the first contrast value second contrast difference; determining the second brightness difference and the second contrast difference as second tone adjustment information; determining a regional tone contrast range according to the first brightness difference and the first contrast difference; The second brightness difference and the second contrast difference determine the tone adjustment range of the first object area; the tone mapping processing strategy corresponding to the second object area is determined in combination with the area tone contrast range and the tone adjustment range of the first object area; wherein, the The second tone adjustment information is based on the expressiveness difference range of the first target object area processed according to tone mapping under the protection mechanism and the first object area not processed according to tone mapping under the protection mechanism. 8. The image information processing device according to claim 7, wherein the first object region is a face object region, the second object region is a hair object region, and the identifying unit comprises: an extraction subunit, used for acquiring an image to be processed, and extracting key feature point information in the image to be processed; A determination subunit, configured to determine the associated face object region and hair object region according to the key feature point information. 9. A storage medium on which a computer program is stored, characterized in that, when the computer program is run on a computer, the computer is made to execute the processing of image information according to any one of claims 1 to 6 method. 10. An electronic device, comprising a processor and a memory, wherein the memory has a computer program, wherein the processor is used to execute the computer program according to any one of claims 1 to 6 by invoking the computer program. The processing method of image information.

Images