CN105979236A - Image quality adjustment method and device - Google Patents

Abstract

Embodiments of the present invention provide a method and device for image quality adjustment, wherein the method specifically includes: collecting a user's facial image; extracting a corresponding facial feature image from the facial image; determining the color information of the facial feature image based on the color information Displays the color temperature parameters of the device. The embodiments of the present invention can improve the accuracy and rationality of the color temperature parameters, thereby satisfying the user's personalized requirements for the color temperature parameters.

Description

Image quality adjustment method and device

technical field

Embodiments of the present invention relate to the field of video technology, and in particular, to a method and device for adjusting image quality.

Background technique

With the development of TV technology and the advent of the smart TV era, there are more and more TV programs, and with the application of set-top boxes on TVs, and more and more smart TVs support online video playback, the content played on TV is becoming more and more More and more, such as TV program content, game content, etc. In order to watch a variety of broadcast content on the TV, users have higher and higher requirements for image quality adjustment.

Currently, there are two main ways to adjust the picture quality on the TV:

One is several standard modes adjusted by TV manufacturers, such as gorgeous mode for display in shopping malls, sports mode for watching pictures with strong movements, etc., but these modes are adjusted by TV manufacturers based on experience and comparison machines , but does not necessarily meet the user's individual needs for image quality adjustment;

The other is to provide users with an interface for adjusting image quality. For example, users can adjust image quality parameters such as brightness, contrast, and saturation through this interface; however, this method requires users to have considerable image quality knowledge. If you master the image quality knowledge, the adjusted image quality cannot meet the user's individual needs for image quality adjustment.

Contents of the invention

Embodiments of the present invention provide a method and device for image quality adjustment, which are used to solve the defect that the existing solutions cannot meet the user's individual needs for image quality adjustment, and can improve the accuracy and rationality of the color temperature parameters, thereby satisfying the user's requirements for image quality adjustment. Individual requirements for color temperature parameters.

An embodiment of the present invention provides a method for adjusting image quality, including:

Collect facial images of users;

extracting a corresponding facial feature image from the facial image;

Determine the color temperature parameter of the display device according to the color information of the facial feature image.

An embodiment of the present invention provides an image quality adjustment device, including:

The collection module is used to collect the facial image of the user;

An extraction module, configured to extract a corresponding facial feature image from the facial image; and

The determination module is configured to determine the color temperature parameter of the display device according to the color information of the facial feature image.

The image quality adjustment method and device provided by the embodiments of the present invention determine the color temperature parameter of the display device according to the color information of the facial feature image, and can automatically adjust to obtain the color temperature parameter that matches the color information of the facial feature image; because the above color temperature parameter can It is matched with the facial feature image of the current user, so the embodiments of the present invention can improve the accuracy and rationality of the color temperature parameters, thereby satisfying the user's personalized requirements for the color temperature parameters.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

FIG. 1 is a flow chart of the steps of Embodiment 1 of an image quality adjustment method of the present invention;

FIG. 2 is a flow chart of the steps of Embodiment 2 of an image quality adjustment method of the present invention;

FIG. 3 is a flow chart of the steps of Embodiment 3 of an image quality adjustment method of the present invention;

FIG. 4 is a flow chart of the steps of Embodiment 4 of an image quality adjustment method of the present invention;

Fig. 5 is a schematic diagram of eye positioning of the present invention; and

FIG. 6 is a structural block diagram of an embodiment of an image quality adjustment device of the present invention.

detailed description

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

Method embodiment one

Referring to FIG. 1 , it shows a flow chart of the steps of Embodiment 1 of an image quality adjustment method of the present invention, which may specifically include:

Step 101, collecting the facial image of the user;

The embodiments of the present invention can be applied to display devices such as ordinary TVs, smart TVs, monitors, mobile phones, etc., and are used to adjust PQ (Picture Quality, Picture Quality) on these display devices, and can automatically adjust to obtain the color information corresponding to the facial feature image. Matching color temperature parameters, so it can meet the user's individual needs for color temperature parameters.

In practical applications, a row of PQ automatic adjustment drop-down menus may be added to the user interface of the display device, and the drop-down menus may include: selecting an option to automatically adjust PQ parameters through facial information recognition. In this way, when the user purchases the display device and places it in the use environment, he can click on the above option to enable the function of "selecting to automatically adjust PQ parameters through facial information", and then the image quality adjustment process of the embodiment of the present invention can be automatically executed.

In practical applications, the user's facial image can be collected through the camera. For example, the user's facial avatar may be collected through a camera equipped on a smart TV or a mobile phone, and the embodiment of the present invention does not limit the specific process of collecting the user's facial image.

Step 102, extracting a corresponding facial feature image from the facial image;

Step 103: Determine the color temperature parameter of the display device according to the color information of the facial feature image.

Color temperature is a concept derived from physics, which describes the color of luminous objects through temperature. The main frequency of the spectrum of a luminous object can be described by the blackbody radiation spectrum at a certain temperature, and this temperature is called the color temperature of the luminous object. The color temperature of the display device refers to the result in the pure white state. Common color temperatures are 5000K, 6500K, 9300K, etc. Generally speaking, a low color temperature light source is characterized by relatively more red radiation in the energy distribution, and a lower color temperature of red, about 2000K to 3000K, which is called "warm tone"; when the color temperature is increased, the blue radiation in the energy distribution The proportion of blue increases, and the color temperature of blue is higher, about 8000K to 10000K, which is called "cool tone".

In the embodiment of the present invention, facial features may be used to represent features such as eyes, nose, mouth, forehead, and skin color that are reflected in the facial image. Differences in facial features mainly depend on geographical location factors such as people's geographical location, living habits, genetic genes, etc. These geographical location factors are likely to cause differences in facial feature information. Taking geographical factors as an example, most people living in the warmer Asian plate have yellow skin, while most of the people living in the colder European plate have fair skin, and people living in the hotter African and North and South American plates have yellow skin. People who live mostly have black skin and so on. Taking genetics as an example, the eyes of Asians are mostly black, the eyes of Europeans are mostly blue, and the eyes of Africans are mostly brown.

After research, it can be found that the following rules of facial feature information and color temperature: the pigmentation of the pupil of the eye can affect the visual effect of color temperature. For example, a 9300K image looks white to a person with dark eyes, while a 9300K image appears bluish to a person with blue eyes. For another example, the picture quality of 6500K is white to people with blue eyes, while the picture quality of 6500K is yellowish to people with black eyes. For another example, the picture quality between 4700-5500K is white for people with brown eyes and so on.

The embodiment of the present invention utilizes the law of the eyes and determines the color temperature parameters of the display device according to the color information of the facial feature image, and can automatically adjust the color temperature parameters that match the color information of the facial feature image, thus satisfying the user's personalization of the color temperature parameters need.

In an application example of the present invention, Europeans go on a business trip to China, and the color temperature parameters of TVs in Chinese hotels are mostly around 9300K. The embodiment of the present invention can automatically adjust to match the color according to the facial feature information of Europeans. The color temperature parameter is about 6500K, so it can meet the individual needs of Europeans for color temperature parameters.

In another application example of the present invention, Chinese people go to study in Europe, and the color temperature parameters of European local TV sets are mostly around 6500K. The embodiment of the present invention can automatically adjust the color according to the facial feature information of Chinese people to obtain a corresponding Matching color temperature parameters, the color temperature parameters are about 9300K, so it can meet the individual needs of Chinese people for color temperature parameters.

To sum up, the embodiment of the present invention can determine the color temperature parameter of the display device according to the color information of the facial feature image.

Method embodiment two

Referring to FIG. 2 , it shows a flow chart of the steps of Embodiment 2 of an image quality adjustment method of the present invention, which may specifically include:

Step 201, collecting the facial image of the user;

Step 202, extracting a corresponding facial feature image from the facial image;

Step 203: Determine the color temperature parameter of the display device according to the color information of the facial feature image;

Wherein, the step 203 of determining the color temperature parameter of the display device according to the color information of the facial feature image may specifically include:

Step 231 , according to the color information of the facial feature image, search in the mapping relationship between facial color information and color temperature parameters, so as to obtain the color temperature parameters corresponding to the color information.

Compared with Embodiment 1, this embodiment embodies the process of determining the color temperature parameter of the display device according to the color information of the facial feature image, wherein the mapping relationship between the facial color information and the color temperature parameter can be searched, To obtain the color temperature parameter corresponding to the color information; in practical applications, the mapping relationship between the facial color information and the color temperature parameter can be stored in the memory of the display device, and obtain the color temperature parameter corresponding to the color information by searching the above memory, The efficiency of determining the color temperature parameter of the display device can be improved.

In an optional embodiment of the present invention, the mapping relationship between facial color information and color temperature parameters can be established through the following steps:

Step S11, determining the reference facial color information and the corresponding reference color temperature parameters;

Step S12: According to the mapping relationship between the facial color information offset and the color temperature parameter offset, adjust the reference facial color and the reference color temperature parameter to obtain facial color information adjusted according to the reference facial color information Corresponding color temperature parameters.

In an application example of the present invention, black RGB (0,0,0) and blue RGB (0,0,255) can be used as reference face color information respectively, and 9300K and 6500K can be used as black RGB (0,0 ,0), the reference color temperature parameters corresponding to blue RGB(0,0,255).

The facial color information offset and the reference color temperature parameter offset can be used to represent the facial color information, the reference color temperature parameter relative to the corresponding reference facial color information, the offset of the reference color temperature parameter, the facial color information offset and the color temperature parameter offset The mapping relationship between is used to indicate the amount of color temperature parameter shift caused by the face color information shift. Taking black RGB (0,0,0) as an example, the offset A1 of the R component can bring about the offset B1 of the color temperature parameter. For example, when A1 is 5, B1 is -2, and for example, when A1 is -5 When B1 is +2, etc., it can be understood that those skilled in the art can set the mapping relationship between facial color information offset and color temperature parameter offset according to the degree of influence of pupil pigmentation on the visual effect of color temperature. The embodiment does not limit the specific setting manner of the mapping relationship between the facial color information offset and the color temperature parameter offset.

Taking black RGB(0,0,0) as an example, the specific process of adjusting the reference face color and the reference color temperature parameter may be to adjust the R component of RGB(0,0,0), assuming that R The adjusted value of the component is A1, and the adjusted value of the color temperature parameter can be obtained by querying the mapping relationship between the face color information offset and the color temperature parameter offset. Therefore, the adjusted color temperature corresponding to RGB(A1,0,0) The parameter can be 9300K+B1. It can be understood that the foregoing is only an example, and the embodiment of the present invention does not limit the specific process of adjusting the reference face color and the reference color temperature parameter.

It should be noted that the above step 231 obtained by searching the color temperature parameter corresponding to the color information is only an optional embodiment, and it is not understood that the embodiment of the present invention determines the color temperature of the display device based on the color information of the facial feature image. Application limitations of the parameters. In fact, those skilled in the art may adopt other technical solutions for determining the color temperature parameters of the display device based on the color information of the facial feature image according to actual application requirements. For example, the reference color temperature parameter may be adjusted according to the difference between the color information and the reference facial color information, so as to obtain the color temperature parameter corresponding to the color information.

Method embodiment three

Referring to FIG. 3 , it shows a flow chart of the steps of Embodiment 3 of an image quality adjustment method of the present invention, which may specifically include:

Step 301, collecting the facial image of the user;

Step 302, extracting a corresponding facial feature image from the facial image;

Step 303. Determine the color temperature parameter of the display device according to the color information of the facial feature image;

Wherein, the step 303 of determining the color temperature parameter of the display device according to the color information of the facial feature image may specifically include:

Step 331, according to the eye color information of the facial feature image, search in the mapping relationship between eye and face color information and color temperature parameters to obtain the color temperature parameters corresponding to the eye color information;

Step 332: After finding the color temperature parameter corresponding to the eye color information, adjust the color temperature parameter according to the skin color information, and use the adjusted color temperature parameter as the color temperature parameter of the display device.

In the embodiment of the present invention, the skin color information can be used as auxiliary information for identifying the geographical position information of the user and determining the color temperature parameter. For example, two users with the same blue eyes, user A's skin color is fair, and user B's skin color is yellowish. It can be considered that user A lives in a colder region, while user B lives in a warmer region. Suppose The reference skin color corresponding to the reference eye blue is RGB(238,233,233), and the reference color temperature parameter corresponding to the reference eye blue is 6500K. The reference color temperature parameter can be adjusted according to the difference between the reference skin color and the current skin color; For people with yellowish skin tone, the color temperature parameters can be adjusted downwards based on 6500K; for people with yellowish skin, the color temperature parameters can be adjusted upwards based on 6500K, so more accurate color temperature parameters can be obtained.

Method Embodiment Four

Referring to FIG. 4 , it shows a flow chart of the steps of Embodiment 4 of an image quality adjustment method of the present invention, which may specifically include:

Step 401, collecting the facial image of the user;

Step 402, extracting a corresponding facial feature image from the facial image;

Step 403: Determine the color temperature parameter of the display device according to the color information of the facial feature image;

Wherein, the step 402 of extracting a corresponding facial feature image from the facial image may specifically include:

Step 421, perform eye positioning on the facial image to obtain the eye position;

Step 422 , extract facial feature images from the facial image according to the eye positions.

Compared with the first embodiment, this embodiment describes the specific process of extracting the corresponding facial feature image from the facial image through steps 421-422.

Step 421

In a specific implementation, a statistical pattern recognition method may be used, and binocular region images and non-binocular region images in the collected and segmented facial images may be used as training samples to train a binocular region detector. For example, an adaptive boosting (Adaboost, adaptive boosting) algorithm is used to train 10,000 24×16 binocular region images and non-binocular region images to obtain a binocular region detector.

When performing eye positioning, the binocular area detector can be used to search for binocular area positions in the facial image, and after the binocular area positions are determined, the left eye position and the right eye position are located within the binocular area positions. Referring to FIG. 5 , a schematic diagram of eye positioning according to the present invention is shown, in which 5a is the position of the rectangular eye area searched by the binocular area detector, and the center of the rectangle shown in 5b is the eye position.

Step 422

Step 422 may extract images of facial features such as eyes, face, and nose from the facial image according to the position of the eyes.

In an optional embodiment of the present invention, the above extraction process may specifically include: cutting an eye image and/or a face image of a preset size from the face image according to the position of the eyes. Taking an eye image as an example, the cutting process may include: dividing two rectangular regions according to the center of the pupil. The preset size here can be determined according to the actual situation, for example, the eye image is also 24×16. Taking a face image as an example, the cropping process may include: cropping a face image of a first preset size at a position at a preset distance from the lower side of the eye image, and so on.

Method Embodiment Five

In this embodiment, on the basis of determining the color temperature parameters of the display device, the contrast and/or sharpness of the display device may be adjusted according to the color information of the facial feature image, so as to best match the color information of the facial feature image Color temperature parameters, contrast and/or sharpness, to achieve the best display effect of the monitor.

In an application example of the present invention, the contrast and/or sharpness of the display device can be adjusted according to the difference between the color information of the facial feature image and the reference color information corresponding to the color temperature parameter. Assuming that the determined color temperature parameter is 6500K, and the reference skin color corresponding to 6500K is the reference white, then if the current user's skin color is lighter than the reference white, the contrast and sharpness can be appropriately increased to achieve a clear transition of color; on the contrary, the current user's skin color If the color is darker than the reference white, the contrast and sharpness parameters can be appropriately reduced to ensure a slow transition of the color. It can be understood that the embodiment of the present invention does not limit the specific process of adjusting the contrast and/or sharpness of the display device according to the color information of the facial feature image.

Device embodiment

Referring to FIG. 6 , it shows a structural block diagram of an embodiment of an image quality adjustment device according to the present invention, which may specifically include:

Acquisition module 601, for collecting the facial image of the user;

An extraction module 602, configured to extract a corresponding facial feature image from the facial image; and

The determination module 603 is configured to determine the color temperature parameter of the display device according to the color information of the facial feature image.

In an optional embodiment of the present invention, the determining module 603 may specifically include:

The search sub-module is configured to search the mapping relationship between facial color information and color temperature parameters according to the color information of the facial feature image, so as to obtain the color temperature parameters corresponding to the color information.

In another optional embodiment of the present invention, the device may further include: an establishment module for establishing a mapping relationship between facial color information and color temperature parameters;

The building module may specifically include:

A determination sub-module is used to determine the reference facial color information and the corresponding reference color temperature parameters; and

The first adjustment sub-module is configured to adjust the reference facial color and the reference color temperature parameter according to the mapping relationship between the facial color information offset and the color temperature parameter offset, so as to obtain the adjustment based on the reference facial color information The color temperature parameter corresponding to the obtained facial color information.

In yet another optional embodiment of the present invention, the color information includes eye color information and skin color information, then the determining module 603 may also include:

The second adjustment sub-module is configured to adjust the color temperature parameter according to the skin color information after finding the color temperature parameter corresponding to the eye color information, and use the adjusted color temperature parameter as the color temperature parameter of the display device .

In yet another optional embodiment of the present invention, the extraction module 602 may specifically include:

The positioning sub-module is used to perform eye positioning on the facial image to obtain the position of the eyes; and

The post-location extraction submodule is used to extract facial feature images from the facial image according to the eye position.

In an optional embodiment of the present invention, the extraction submodule after positioning may specifically include:

The extracting unit is configured to cut out an eye image and/or a face image of a preset size from the face image according to the position of the eyes.

In another optional embodiment of the present invention, the device may also include:

An adjustment module, configured to adjust the contrast and/or sharpness of the display device according to the color information of the facial feature image.

As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.

The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative effort.

Through the above description of the implementations, those skilled in the art can clearly understand that each implementation can be implemented by means of software plus a necessary general hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims (10)

1. an image quality adjustment method, it is characterised in that including:

Gather the face-image of user；

The facial feature image of correspondence is extracted from described face-image；

According to the colouring information of described facial feature image, determine the color temperature parameters of display device.

Method the most according to claim 1, it is characterised in that described according to described facial characteristics figure The colouring information of picture, determines the step of the color temperature parameters of display device, including:

According to the colouring information of described facial feature image, between face colouring information and color temperature parameters Mapping relations make a look up, the color temperature parameters corresponding to obtain described colouring information.

Method the most according to claim 2, it is characterised in that set up face face as follows Mapping relations between color information and color temperature parameters:

Determine the benchmark color temperature parameters of benchmark face colouring information and correspondence；

According to the mapping relations between face colouring information skew and color temperature parameters skew, to described datum level Portion's color and described benchmark color temperature parameters are adjusted, to obtain adjusting according to described benchmark face colouring information The color temperature parameters that the whole facial colouring information obtained is corresponding.

Method the most according to claim 2, it is characterised in that described colouring information includes eyes face Color information and Skin Color Information, the most described colouring information according to described facial feature image, determine that display sets The step of standby color temperature parameters, also includes:

After lookup obtains the color temperature parameters that described eye-color information is corresponding, according to described Skin Color Information pair Described color temperature parameters is adjusted, and will adjust after color temperature parameters as described display device colour temperature join Number.

5. according to described method arbitrary in Claims 1-4, it is characterised in that described from described Portion's image extracts the step of the facial feature image of correspondence, including:

Described face-image is carried out eye location, obtains eye position；

According to described eye position, from described face-image, extract facial feature image.

Method the most according to claim 5, it is characterised in that described according to described eye position, The step of facial feature image is extracted from described face-image, including:

According to described eye position, from described face-image, extract eye image and/or the face of default size Portion's image.

7. according to described method arbitrary in Claims 1-4, it is characterised in that described method is also wrapped Include:

According to the colouring information of described facial feature image, contrast and/or acutance to display device are carried out Adjust.

8. a quality adjustment device, it is characterised in that including:

Acquisition module, for gathering the face-image of user；

Extraction module, for extracting the facial feature image of correspondence from described face-image；And

Determine module, for the colouring information according to described facial feature image, determine the color of display device Temperature parameter.

Device the most according to claim 8, it is characterised in that described determine module, including:

Search submodule, for the colouring information according to described facial feature image, at face colouring information And the mapping relations between color temperature parameters make a look up, the colour temperature ginseng corresponding to obtain described colouring information Number.

Device the most according to claim 8 or claim 9, it is characterised in that described device also includes:

Adjusting module, for the colouring information according to described facial feature image, the contrast to display device Degree and/or acutance are adjusted.