WO2019011110A1 - 逆光场景的人脸区域处理方法和装置 - Google Patents

逆光场景的人脸区域处理方法和装置 Download PDF

Info

Publication number
WO2019011110A1
WO2019011110A1 PCT/CN2018/091883 CN2018091883W WO2019011110A1 WO 2019011110 A1 WO2019011110 A1 WO 2019011110A1 CN 2018091883 W CN2018091883 W CN 2018091883W WO 2019011110 A1 WO2019011110 A1 WO 2019011110A1
Authority
WO
WIPO (PCT)
Prior art keywords
foreground
face region
backlight
depth
saturation
Prior art date
Application number
PCT/CN2018/091883
Other languages
English (en)
French (fr)
Inventor
袁全
Original Assignee
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Publication of WO2019011110A1 publication Critical patent/WO2019011110A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70—Circuitry for compensating brightness variation in the scene
    • H04N23/71—Circuitry for evaluating the brightness variation

Definitions

  • the present invention relates to the field of image processing technologies, and in particular, to a method and apparatus for processing a face region of a backlight scene.
  • the exposed face of the user is insufficiently exposed, and the backlight is effective.
  • the brightness is very low, the user's face is dark, and the interview details are blurred.
  • the sensitivity ISO is pulled high to increase the brightness of the face region by enhancing the sensitivity to light.
  • the present invention provides a face area processing method and apparatus for backlit scenes, which solves the problem that in the prior art, in the backlight scene, only the brightness of the face area is increased, and the noise reduction intensity is increased, and the skin color of the face area is pale. technical problem.
  • An embodiment of the present disclosure provides a method for processing a face region of a backlight scene, including: when a backlight scene is detected, separating a foreground and a backlight background from the current captured image; performing brightness enhancement processing on the foreground, and determining the foreground The face area; the saturation corresponding to the face area in the HSV color model is increased.
  • a face region processing apparatus for a backlight scene, comprising: a separation module, configured to separate a foreground and a backlight background from a current shooting image when a backlight scene is detected; and a brightness enhancement module for The foreground is subjected to a brightness enhancement process; a determination module is configured to determine a face region in the foreground; and an adjustment module is configured to increase saturation in the HSV color model corresponding to the face region.
  • a further embodiment of the present application provides a terminal device including one or more components: a housing and a processor and a memory located in the housing, wherein the processor reads the memory stored in the memory by reading
  • the program code is executed to execute a program corresponding to the executable program code for performing a face region processing method of the backlighting scene as described in the first aspect of the present application.
  • a further embodiment of the present application provides a non-transitory computer readable storage medium having stored thereon a computer program, the computer program being executed by a processor to implement a face of a backlight scene as described in the first aspect of the present application.
  • Regional processing method
  • a further embodiment of the present application provides an image processing circuit, the image processing circuit comprising: a photographing unit and a processing unit, wherein the photographing unit is configured to output a photographing screen; and the processing unit is configured to detect when The backlight scene separates the foreground and the backlight background from the current captured image, performs brightness enhancement processing on the foreground, and determines a face region in the foreground to improve saturation in the HSV color model corresponding to the face region.
  • the technical solutions provided by the embodiments of the present application may include the following beneficial effects:
  • the foreground and backlight backgrounds are separated from the current shooting image, the foreground is brightness-raised, and the face region in the foreground is determined, and the saturation corresponding to the face region in the HSV color model is improved. Therefore, when the face region image in the case of backlighting is raised, the problem that the face color is lightened without blood color is avoided, and the visual effect of the image display is ensured while improving the image quality.
  • FIG. 1 is a flowchart of a face area processing method for a backlight scene according to an embodiment of the present application
  • FIG. 2 is a schematic diagram of a backlight shooting scene according to an embodiment of the present application.
  • FIG. 3( a ) is a schematic diagram of an effect before processing an image of a current shooting screen according to an embodiment of the present application
  • FIG. 3(b) is a schematic diagram showing the effect of improving the brightness of the face region of the current shooting picture according to an embodiment of the present application
  • FIG. 3(c) is a schematic diagram showing an effect of increasing saturation of a current photographing screen according to an embodiment of the present application
  • FIG. 4 is a flowchart of a face area processing method for a backlight scene according to another embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a face region processing apparatus for a backlight scene according to an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a face region processing apparatus for a backlight scene according to another embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a face region processing apparatus for a backlight scene according to still another embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of an image processing circuit according to an embodiment of the present application.
  • the present application proposes a face region processing method for the backlight scene, which can improve the brightness of the face region while improving the backlight scene, and avoid Sacrificing the details of the face makes the visual display of the image stronger.
  • FIG. 1 is a flowchart of a method for processing a face region of a backlight scene according to an embodiment of the present application. As shown in FIG. 1 , the method includes:
  • step 101 when the backlight scene is detected, the foreground and backlight backgrounds are separated from the current shooting image.
  • the position of the face region can be separated.
  • the range of clear imaging before the focus area is the foreground.
  • Depth of field the location of the face area is in the foreground depth of field.
  • the range of clear imaging after the focus area is the background depth of field, and the backlight background is in the background depth of field. Therefore, in this example, the foreground and backlight background are separated from the current shot according to the depth information. .
  • the first example is a first example:
  • the relevant parameters of the shooting can be acquired to calculate the depth information of the image area outside the focus area in the preview image according to the formula of the shooting camera.
  • the two rear cameras have a certain angular difference and a distance difference with respect to the captured target object, so the preview image data acquired by the two cameras is also There is a certain phase difference.
  • the pixel point coordinates corresponding to the point A are (30, 50), and in the preview image data of the camera 2, the point A corresponds.
  • the relationship between the depth information and the phase difference may be established in advance according to the experimental data or the camera parameters, and then the corresponding depth information may be searched according to the phase difference in the preview image data acquired by the two cameras in the preview image. .
  • the depth information corresponding to the point A in the preview screen is 5 meters.
  • the depth of field information of each pixel in the current preview picture that is, the depth of field map of the image area outside the focus area is obtained.
  • the foreground depth information of the image area before the focus area and the background depth information after the focus area may be further determined, thereby determining the foreground before the focus area according to the depth map Depth of field and background depth of focus after the focus area, and separate foreground and backlit backgrounds based on foreground depth and background depth.
  • Step 102 Perform brightness enhancement processing on the foreground and determine a face area in the foreground.
  • the brightness of the face area and other areas in the foreground in the backlight scene are relatively low, and the boundary of the face area is blurred compared with other areas. Therefore, the brightness of the foreground is improved at this time.
  • the brightness of the face area is improved, the face is clearly visible, and the boundary of the face area is clearer than other areas, so that the face area can be extracted to further process the face area.
  • the first example is a first example:
  • the face area is the color of the human body such as the skin color
  • the other areas are the colors of other scenes different from the color of the face area. Therefore, the color channel detection algorithm can be adopted.
  • the area where the skin color is located is identified to determine the contour edge of the face area in the foreground according to the area covered by the skin color.
  • the image edge detection algorithm such as CANNY algorithm and wavelet transform algorithm is used to determine the contour edge of the face region in the foreground.
  • step 103 the saturation corresponding to the face region in the HSV color model is improved.
  • saturation Degree refers to the degree of vividness of color, also known as the purity of color.
  • the saturation of face area depends on the proportion of the color component and the achromatic component (gray) in the face area. The larger the color component, the greater the saturation. The larger the color component, the smaller the saturation.
  • the saturation of the face is increased, the color component of the face region is increased, so that the face region is rosy and shiny.
  • HSV Hue, Saturation, Value
  • S saturation
  • V brightness
  • the face region is extracted by using the depth information-based method, and the extraction accuracy of the face region is higher than that of the direct face recognition. Since the brightness of the face area is low and the features are not obvious in the backlight scene, it is very likely that the face recognition directly causes the recognition to fail.
  • the face region processing method of the backlight scene in the embodiment of the present application improves the color component of the face region based on the parameter value of the saturation in the HSV space after the face brightness is improved, so that the face is rosy. luster.
  • the foreground and the backlight background are separated from the current photographing screen, and then the foreground is brightness-enhanced, as shown in FIG. 3( b ), the processed human face is displayed.
  • the brightness of the part is increased, but the facial details are lost. Further, the saturation corresponding to the face area in the HSV color model is improved.
  • the face of the face is rosy and lustrous, and the brightness is improved.
  • the face region processing method of the backlight scene in the embodiment of the present application detects the backlight scene, separates the foreground and the backlight background from the current captured image, performs brightness enhancement processing on the foreground, and determines the face in the foreground.
  • the degree of darkening of the face region is different due to the difference in the intensity of the ambient light of the backlight, the stronger the ambient light, the darker the face region, and the more the ambient light is. Not strong, the brighter the face area, the darker the face area, the more facial details that are lost, the higher the saturation needs to be lifted. Therefore, in order to improve the processing effect on the saturation of the face area, according to the current environment The backlight intensity is adjusted for saturation.
  • the above step 103 includes:
  • Step 201 Detect the backlight intensity of the current scene.
  • the manner of detecting the backlight intensity of the current scene may be different according to the specific application scenario, for example, obtaining the backlight intensity sensed by the photosensitive element in the camera module, for example, calculating the backlight intensity according to the brightness of the foreground.
  • Step 202 Acquire an enhancement range corresponding to the backlight intensity.
  • the enhancement range corresponds to the saturation increase, and the higher the enhancement, the greater the increase of saturation. Conversely, the lower the enhancement, the smaller the increase of saturation.
  • a plurality of different implementation manners may be used to obtain an enhancement range corresponding to the backlight intensity.
  • the correspondence between the backlight intensity and the enhancement amplitude is pre-stored, thereby After obtaining the backlight intensity, query the corresponding relationship to obtain the corresponding enhancement range.
  • the conversion function is generated according to the relationship between the backlight intensity and the enhancement amplitude, so that after the backlight intensity is acquired, the corresponding enhancement amplitude is obtained by the conversion function.
  • Step 203 increasing the saturation corresponding to the face region in the HSV color model according to the enhancement range.
  • the saturation corresponding to the face region in the HSV color model is improved according to the enhancement amplitude consistent with the backlight intensity in the current scene, so that the super-saturation or under-saturation of the face region does not occur, and the processing effect is better.
  • the skin color of each part of the face is also different.
  • the face cheek is more rosy than the forehead, and thus, in order to further improve the processing effect, the face area may be different.
  • the locations determine different saturation coefficients to adjust different degrees of saturation for different parts of the face region according to different saturation coefficients.
  • a saturation adjustment coefficient corresponding to a different part of the face region is obtained, wherein the saturation coefficient of the more rosy part is higher in reality, and further, the calculation and the difference are performed according to the saturation adjustment coefficient and the enhancement range corresponding to different parts.
  • the corresponding lifting range of the part increases the saturation of the pixel position corresponding to the face area in the HSV color model according to the lifting range corresponding to the different parts.
  • the face region processing method of the backlight scene in the embodiment of the present application determines the enhancement range according to the backlight intensity of the current scene, and improves the saturation corresponding to the face region in the HSV color model according to the enhancement range. Therefore, an appropriate enhancement range is selected for the face region to be processed to improve the saturation, and the supersaturation or undersaturation of the face region is avoided, thereby further improving the visual effect of the image display.
  • FIG. 5 is a schematic structural diagram of a face area processing apparatus for a backlight scene according to an embodiment of the present application, as shown in FIG.
  • the face region processing device of the backlighting scene includes: a separation module 100, a brightness enhancement module 200, a determination module 300, and an adjustment module 400.
  • the separation module 100 is configured to separate the foreground and the backlight background from the current shooting image when the backlight scene is detected.
  • the separation module 100 includes a first acquisition unit 110, a determination unit 120, and a separation unit 130.
  • the first obtaining unit 110 is configured to determine a depth map of the image area outside the focus area according to the current captured picture data respectively acquired by the dual cameras.
  • the determining unit 120 is configured to determine a foreground depth of field before the focus area and a background depth of field after the focus area according to the depth of field map.
  • the separating unit 130 is configured to separate the foreground and the backlight background according to the foreground depth of field and the background depth of field.
  • the brightness enhancement module 200 is configured to perform brightness enhancement processing on the foreground.
  • the determining module 300 is configured to determine a face area in the foreground.
  • the adjustment module 400 is configured to improve the saturation corresponding to the face region in the HSV color model.
  • the face region processing device of the backlight scene of the embodiment of the present invention detects the backlight scene, separates the foreground and the backlight background from the current captured image, performs brightness enhancement processing on the foreground, and determines the face in the foreground.
  • FIG. 7 is a schematic structural diagram of a face region processing of a backlighting scene according to still another embodiment of the present application.
  • the adjustment module 400 includes a detecting unit 410 and a second acquiring unit, as shown in FIG. 420 and adjustment unit 430.
  • the detecting unit 410 is configured to detect the backlight intensity of the current scene.
  • the second obtaining unit 420 is configured to acquire an enhancement range corresponding to the backlight intensity.
  • the adjusting unit 430 is configured to increase the saturation corresponding to the face region in the HSV color model according to the enhancement range.
  • the face region processing apparatus of the backlight scene of the embodiment of the present application determines the enhancement range according to the backlight intensity of the current scene, and improves the saturation corresponding to the face region in the HSV color model according to the enhancement range. Therefore, an appropriate enhancement range is selected for the face region to be processed to improve the saturation, and the supersaturation or undersaturation of the face region is avoided, thereby further improving the visual effect of the image display.
  • FIG. 8 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
  • the terminal device 1000 includes a housing 1100 and a processor 1110 and a memory 1120 located in the housing 1100.
  • the processor 1110 is operable by reading executable program code stored in the memory 1120.
  • a program corresponding to the program code is executed for performing the face region processing method of the backlight scene described in the above embodiment.
  • FIG. 99 is a schematic diagram of an image processing circuit as a possible implementation. For ease of explanation, only the various aspects related to the embodiments of the present application are shown.
  • the image processing circuit specifically includes: a photographing unit 11 and a processing unit 12, wherein
  • the photographing unit 11 is configured to output a photographing screen.
  • the processing unit 12 is configured to: when the backlight scene is detected, separate the foreground and the backlight background from the current captured image, perform brightness enhancement processing on the foreground, and determine a face region in the foreground to improve the HSV color model. The saturation corresponding to the face area.
  • the photographing unit 11 includes an electrically connected dual camera 111
  • the processor 12 includes an image signal processing ISP processor 121, wherein
  • the dual camera 111 is configured to output a current shooting picture respectively acquired by the two cameras.
  • the ISP processor 121 is configured to determine a depth map of an image area outside the focus area according to the current captured picture data respectively acquired by the dual camera, and determine a foreground depth and the focus area before the focus area according to the depth map. Subsequent background depth of field separates the foreground and backlit background from the foreground depth of field and the background depth of field.
  • the processor 12 includes an electrically connected CPU 122, wherein the CPU 122 is configured to detect a backlight intensity of a current scene, and obtain an enhancement range corresponding to the backlight intensity.
  • the saturation corresponding to the face region in the HSV color model is increased according to the enhancement range.
  • the CPU 122 is further configured to acquire a saturation adjustment coefficient corresponding to a different portion of the face region, and calculate and describe the saturation adjustment coefficient and the enhancement amplitude according to the different portions.
  • the corresponding lifting range of different parts according to the lifting range corresponding to the different parts, the saturation of the pixel position corresponding to the face area in the HSV color model is improved.
  • the present application also proposes a non-transitory computer readable storage medium having stored thereon a computer program capable of realizing a backlighting scene as described in the foregoing embodiments when the computer program is executed by the processor Face area processing method.
  • first and second are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
  • features defining “first” and “second” may include at least one of the features, either explicitly or implicitly.
  • the meaning of "a plurality” is at least two, such as two, three, etc., unless specifically defined otherwise.
  • a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device.
  • computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
  • the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.
  • portions of the application can be implemented in hardware, software, firmware, or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware and in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: discrete with logic gates for implementing logic functions on data signals Logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.
  • each functional unit in each embodiment of the present application may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like. While the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are illustrative and are not to be construed as limiting the scope of the present application. The embodiments are subject to variations, modifications, substitutions and variations. Take the storage medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

本申请公开了一种逆光场景的人脸区域处理方法和装置，其中，方法包括：当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景；对前景进行亮度提升处理，并确定前景中的人脸区域；提高HSV色彩模型中与人脸区域对应的饱和度。由此，在调高处于逆光情况下的人脸区域图像时，避免了人脸肤色变淡而没有血色的问题，在提升图像质量的同时，保证了图像显示的视觉效果。

Description

逆光场景的人脸区域处理方法和装置
相关申请的交叉引用
本申请要求广东欧拍移动通信有限公司于2017年07月10日提交的、发明名称为“逆光场景的人脸区域处理方法和装置”的、中国专利申请号“201710558406.5”的优先权。
技术领域
本发明涉及图像处理技术领域，尤其涉及一种逆光场景的人脸区域处理方法和装置。
背景技术
通常，在拍照时，如果用户人脸位于光源和摄像头之间，会导致被摄用户人脸曝光不充分，出现逆光的效果。而在该逆光场景下拍摄的用户的人脸图像中，亮度非常低，用户人脸较黑暗，面试细节较为模糊。
相关技术中，为了提高逆光场景下的人脸亮度，把感光度ISO拉得很高，以通过增强对光灵敏度来提高人脸区域亮度。
申请内容
本申请提供一种逆光场景的人脸区域处理方法和装置，以解决现有技术中，在逆光场景下，仅仅提高人脸区域的亮度，导致降噪强度增加而造成的人脸区域肤色惨白的技术问题。
本申请实施例提供一种逆光场景的人脸区域处理方法，包括：当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景；对所述前景进行亮度提升处理，并确定所述前景中的人脸区域；提高HSV色彩模型中与所述人脸区域对应的饱和度。
本申请另一实施例提供一种逆光场景的人脸区域处理装置，包括：分离模块，用于当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景；亮度提升模块，用于对所述前景进行亮度提升处理；确定模块，用于确定所述前景中的人脸区域；调整模块，用于提高HSV色彩模型中与所述人脸区域对应的饱和度。
本申请又一实施例提供一种终端设备，包括以下一个或多个组件：壳体和位于所述壳体内的处理器、存储器，其中，所述处理器通过读取所述存储器中存储的可执行程序代码来运行与所述可执行程序代码对应的程序，以用于执行如本申请第一方面实施例所述的逆光场景的人脸区域处理方法。
本申请还一实施例提供一种非临时性计算机可读存储介质，其上存储有计算机程序， 该计算机程序被处理器执行时实现如本申请第一方面实施例所述的逆光场景的人脸区域处理方法。
本申请再一实施例提供一种图像处理电路，所述的图像处理电路包括：拍摄单元和处理单元，其中，所述拍摄单元，用于输出拍摄画面；所述处理单元，用于当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景，对所述前景进行亮度提升处理，并确定所述前景中的人脸区域，提高HSV色彩模型中与所述人脸区域对应的饱和度。本申请实施例提供的技术方案可以包括以下有益效果：
当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景，对前景进行亮度提升处理，并确定前景中的人脸区域，提高HSV色彩模型中与人脸区域对应的饱和度。由此，在调高处于逆光情况下的人脸区域图像时，避免了人脸肤色变淡而没有血色的问题，在提升图像质量的同时，保证了图像显示的视觉效果。
本申请附加的方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本申请的实践了解到。
附图说明
本申请上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中，
图1是根据本申请一个实施例的逆光场景的人脸区域处理方法的流程图；
图2是根据本申请一个实施例的逆光拍摄场景示意图；
图3(a)是根据本申请一个实施例的对当前拍摄画面图像处理前效果示意图；
图3(b)是根据本申请一个实施例的对当前拍摄画面人脸区域亮度提升后效果示意图；
图3(c)是根据本申请一个实施例的对当前拍摄画面饱和度提高后的效果示意图；
图4是根据本申请另一个实施例的逆光场景的人脸区域处理方法的流程图；
图5是根据本申请一个实施例的逆光场景的人脸区域处理装置的结构示意图；
图6是根据本申请另一个实施例的逆光场景的人脸区域处理装置的结构示意图；
图7是根据本申请又一个实施例的逆光场景的人脸区域处理装置的结构示意图；
图8是根据本申请一个实施例的终端设备的结构示意图；以及
图9是根据本申请一个实施例的图像处理电路的结构示意图。
具体实施方式
下面详细描述本申请的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描 述的实施例是示例性的，旨在用于解释本申请，而不能理解为对本申请的限制。
基于以上分析，可以理解的是，相关技术中，如果提高ISO感光度，则图像传感器对光线的敏感度得到提高，在对光线的敏感度一旦提高，那么受到环境干扰而产生的噪声也会增大，为了减小图像中由于噪声而产生的一些无关像素点，针对图像的降噪力度会增加，但是随着降噪力度的增加，会导致图像的一些细节丢失，使得人脸区域面部颜色变淡、没有血色，视觉效果较差。
为了解决提高人脸亮度与失去面部细节之间的矛盾的技术问题，本申请提出了一种逆光场景的人脸区域处理方法，可以在提高逆光场景下，提升人脸区域的亮度的同时，避免牺牲脸部的细节，使得图像的视觉显示效果较强。
下面参考附图描述本申请实施例的逆光场景的人脸区域处理方法和装置。
图1是根据本申请一个实施例的逆光场景的人脸区域处理方法的流程图，如图1所示，该方法包括：
步骤101，当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景。
可以理解的是，如图2所示，当被摄人物处于光源和摄像头之间时，由于光是沿直线传播的，因此，被摄人物的背面有较强的光线照射而正面光线不足，用户人脸区域较为模糊，用户对画面呈现效果并不满意。
因而，在本实施例中，如果用户不希望改变拍摄方向，则为了针对性的提高人脸区域亮度，可以分离出人脸区域所在位置。
具体而言，由于在对拍摄的目标物体聚焦后，在目标物体所在的焦点区域之前和之后一段人眼容许的清晰成像的空间深度范围为景深，其中，在焦点区域之前清晰成像的范围为前景景深，人脸区域所在位置处于前景景深中，在焦点区域之后清晰成像的范围为背景景深，逆光背景处于背景景深中，因而在本实例中，根据景深信息对当前拍摄画面分离出前景和逆光背景。
需要说明的是，根据具体应用场景的不同，对当前拍摄画面分离出前景和逆光背景的方式不同，举例说明如下：
第一种示例：
可获取拍摄的相关参数，以根据拍摄摄像头的公式计算预览画面中焦点区域之外的图像区域的景深信息。
在本示例中，可获取拍摄摄像头的容许弥散圆直径、光圈值、焦距、对焦距离等参数，从而根据公式：前景景深＝(光圈值*容许弥散圆直径*对焦距离的平方)/(焦距的平方+光圈值*容许弥散圆直径*对焦距离)计算出前景景深，已根据前景景深分离出前景，并根据公式背景景深＝(光圈值*容许弥散圆直径*对焦距离的平方)/(焦距的平方-光圈值*容许弥散 圆直径*对焦距离)计算出逆光背景的景深，进而根据逆光背景的景深分离出逆光背景。
第二种示例:
根据双摄像头分别获取的当前拍摄画面数据确定焦点区域之外的图像区域的景深地图,根据景深地图确定焦点区域之前的前景景深和焦点区域之后的背景景深,并根据前景景深和背景景深分离出前景和逆光背景。
具体而言，在本示例中，由于两个摄像头的位置并不相同，因而，两个后置摄像头相对与拍摄的目标物体具有一定的角度差和距离差，因此二者获取的预览图像数据也存在一定的相位差。
举例而言，对于拍摄目标物体上的A点，在摄像头1的预览图像数据中，A点对应的像素点坐标为(30，50)，而在摄像头2的预览图像数据中，A点对应的像素点坐标为(30，48)，A点在两个预览图像数据中对应的像素点的相位差为50-48＝2。
在本示例中，可预先根据实验数据或者摄像头参数建立景深信息与相位差的关系，进而，可根据预览图像中各图像点在两个摄像头获取的预览图像数据中的相位差查找对应的景深信息。
举例来说，对于上述A点对应的相位差2，如果根据预设的对应关系查询到对应的景深为5米，则预览画面中A点对应的景深信息为5米。由此，可得到当前预览画面中每个像素点的景深信息，即获取焦点区域之外的图像区域的景深地图。
进而，在得到焦点区域之外的图像区域的景深地图后，可进一步确定焦点区域之前的图像区域的前景景深信息，以及焦点区域之后的背景景深信息，从而，根据景深地图确定焦点区域之前的前景景深和焦点区域之后的背景景深,并根据前景景深和背景景深分离出前景和逆光背景。
步骤102，对前景进行亮度提升处理，并确定前景中的人脸区域。
可以理解的是，逆光场景下的人脸区域和前景中的其他区域亮度均较低，人脸区域相比于其他区域的界限较为模糊，因而，此时对前景进行亮度提升处理，此时不但提高了人脸区域的亮度，使得人脸清晰可见，而且使得人脸区域相比于其他区域的界限较为清晰，便于提取出人脸区域，以针对人脸区域进行进一步处理。
其中，在不同的应用场景下，可采用不同的实现方式实现对前景中的人脸区域的确定，举例说明如下：
第一种示例：
前景中人脸区域和其他区域的颜色是不一样的，人脸区域为肤色等人体颜色，而其他区域为其他与人脸区域的颜色不同的其他景物的颜色，因此，可以通过颜色通道检测算法，识别出肤色所在区域以根据肤色所涵盖的区域确定前景中人脸区域的轮廓边缘。
第二种示例：
由于图像边缘具有不连续性，比如灰度级的突变，颜色的突变以及纹理结构的突变等，这种边缘存在于物体与背景之间，因此，在本示例中，利用图像边缘的这种特性，通过CANNY算法、小波变换算法等图像边缘检测算法确定前景中人脸区域的轮廓边缘。
步骤103，提高HSV色彩模型中与人脸区域对应的饱和度。
正如以上分析的，当提高人脸区域的亮度时，人脸区域的面部细会丢失从而使得面部苍白失去血色，而面部苍白丢失血色实际上体现在人脸区域饱和度不高上，其中，饱和度是指色彩的鲜艳程度，也称色彩的纯度，人脸区域饱和度取决于人脸区域中含色成分和消色成分(灰色)的比例，含色成分越大，饱和度越大，消色成分越大，饱和度越小。
由此，如果提高面部的饱和度则会提高人脸区域的含色成分，从而使得人脸区域红润有光泽。
具体而言，HSV(Hue,Saturation,Value)是根据颜色的直观特性创建的一种颜色空间,这个模型中颜色的参数分别是：色调(H)，饱和度(S)，明度(V),从而，在本实施例中，可在HSV空间中通过提高饱和度的参数值而提高人脸区域的饱和度，人脸区域的饱和度提高了人脸区域的含色成分变高。
需要强调的是，在本申请的实例中，在逆光场景下，采用基于深度信息的方式进行人脸区域的提取，相对于直接人脸识别以获取人脸区域的提取精确度更高，这是由于在逆光场景下，人脸区域的亮度较低，特征不明显，很有可能直接进行面部识别导致识别失败。
由此，本申请实施例的逆光场景的人脸区域处理方法，在提高人脸面部亮度后，基于HSV空间中提高饱和度的参数值，提高人脸区域的含色成分，使得人脸红润有光泽。
为了更加清楚的体现逆光场景的人脸区域处理流程，下面举例说明：
当检测到如图3(a)所示的逆光场景时，对当前拍摄画面分离出前景和逆光背景，进而，对前景进行亮度提升处理，如图3(b)所示，处理后的人脸面部亮度提高，但是面部细节丢失，进而，提高HSV色彩模型中与人脸区域对应的饱和度，则如图3(c)所示，人脸的面部红润后光泽，且亮度得到了提升。
综上所述，本申请实施例的逆光场景的人脸区域处理方法，当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景，对前景进行亮度提升处理，并确定前景中的人脸区域，提高HSV色彩模型中与人脸区域对应的饱和度。由此，在调高处于逆光情况下的人脸区域图像时，避免了人脸肤色变淡而没有血色的问题，在提升图像质量的同时，保证了图像显示的视觉效果。
基于以上实施例，应当理解的是，在不同的应用场景下，由于逆光的环境光线的 强度的不同，人脸区域的暗化程度不同，环境光线越强烈，人脸区域越暗，环境光线越不强烈，人脸区域越明亮，人脸区域越暗，失去的面部细节越多，需要提升饱和度程度更高，因此，为了提升提高对人脸区域的饱和度时的处理效果，根据当前环境的逆光强度进行饱和度的调整。
如图4所示，上述步骤103包括：
步骤201，检测当前场景的逆光强度。
应当理解的是，在拍照时用户背部的光线强度越高，当前场景的逆光强度越高，用户的面部区域所在前景越暗。
检测当前场景的逆光强度的方式，可根据具体应用场景的不同而不同，比如，获取摄像头模组中感光元件感应到的逆光强度，比如，根据前景的亮度计算逆光强度等。
步骤202，获取与逆光强度对应的增强幅度。
其中，增强幅度对应与饱和度提高幅度，增强幅度越高，饱和度的提高幅度越大，反之，增强幅度越低，饱和度的提高幅度越小。
需要说明的是，根据应用场景的不同，可采用多种不同的实现方式获取与逆光强度对应的增强幅度，作为一种可能的实现方式，预先存储逆光强度与增强幅度的对应关系，从而，在获取逆光强度后，查询上述对应关系，获取对应的增强幅度。作为另一种可能的实现方式，根据逆光强度与增强幅度的关系生成转换函数，从而，在获取逆光强度后，通过该转换函数获取对应的增强幅度。
步骤203，根据增强幅度提高HSV色彩模型中与人脸区域对应的饱和度。
具体地，根据与当前场景下的逆光强度相一致的增强幅度提高HSV色彩模型中与人脸区域对应的饱和度，使得人脸区域的不会出现过饱和或者欠饱和的情况，处理效果较好。
当然，在实际应用中，人脸每个部位的肤色也是不同的，比如，通常情况下，人脸脸颊相对于额头较为红润一些等，因而，为了进一步提高处理效果，还可以对人脸区域不同部位确定不同的饱和度系数，以根据不同的饱和系数对人脸区域不同部位实施不同程度的饱和度的调整。
具体而言，获取与人脸区域不同部位对应的饱和度调整系数，其中，现实中越红润的部位的饱和度系数越高，进而，根据不同部位对应的饱和度调整系数和增强幅度，计算与不同部位对应的提升幅度，根据与不同部位对应的提升幅度，提高HSV色彩模型中与人脸区域对应像素位置的饱和度。
综上所述，本申请实施例的逆光场景的人脸区域处理方法，根据当前场景的逆光强度确定增强幅度，根据增强幅度提高HSV色彩模型中与人脸区域对应的饱和度。由此，为待处理的人脸区域选择合适的增强幅度进行饱和度的提高，避免人脸区域的过饱和或欠饱和， 进一步提升了图像显示的视觉效果。
为了实现上述实施例，本申请还提出了一种逆光场景的人脸区域处理装置，图5是根据本申请一个实施例的逆光场景的人脸区域处理装置的结构示意图，如图5所示，该逆光场景的人脸区域处理装置包括：分离模块100、亮度提升模块200、确定模块300和调整模块400。
其中，分离模块100，用于当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景。
在本申请的一个实施例中，如图6所示，分离模块100包括第一获取单元110、确定单元120和分离单元130。
其中，第一获取单元110，用于根据双摄像头分别获取的当前拍摄画面数据确定焦点区域之外的图像区域的景深地图。
确定单元120，用于根据所述景深地图确定所述焦点区域之前的前景景深和所述焦点区域之后的背景景深。
分离单元130，用于根据所述前景景深和所述背景景深分离出前景和逆光背景。
亮度提升模块200，用于对前景进行亮度提升处理。
确定模块300，用于确定前景中的人脸区域。
调整模块400，用于提高HSV色彩模型中与人脸区域对应的饱和度。
需要说明的是，前述对逆光场景的人脸区域处理方法的解释说明，也适用于本申请实施例的逆光场景的人脸区域处理装置，其实现原理类似，在此不再赘述。
综上所述，本申请实施例的逆光场景的人脸区域处理装置，当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景，对前景进行亮度提升处理，并确定前景中的人脸区域，提高HSV色彩模型中与人脸区域对应的饱和度。由此，在调高处于逆光情况下的人脸区域图像时，避免了人脸肤色变淡而没有血色的问题，在提升图像质量的同时，保证了图像显示的视觉效果。
图7是根据本申请又一个实施例的逆光场景的人脸区域处理的结构示意图，如图7所示，在如图5所示的基础上，调整模块400包括检测单元410、第二获取单元420和调整单元430。
其中，检测单元410，用于检测当前场景的逆光强度。
第二获取单元420，用于获取与逆光强度对应的增强幅度。
调整单元430，用于根据增强幅度提高HSV色彩模型中与人脸区域对应的饱和度。
需要说明的是，前述对逆光场景的人脸区域处理方法的解释说明，也适用于本申请实施例的逆光场景的人脸区域处理装置，其实现原理类似，在此不再赘述。
综上所述，本申请实施例的逆光场景的人脸区域处理装置，根据当前场景的逆光强度确定增强幅度，根据增强幅度提高HSV色彩模型中与人脸区域对应的饱和度。由此，为待处理的人脸区域选择合适的增强幅度进行饱和度的提高，避免人脸区域的过饱和或欠饱和，进一步提升了图像显示的视觉效果。
为了实现上述实施例，本申请还提出了一种终端设备，图8是根据本申请一个实施例的终端设备的结构示意图。如图8所示，该终端设备1000包括：壳体1100和位于壳体1100内的处理器1110、存储器1120，其中，处理器1110通过读取存储器1120中存储的可执行程序代码来运行与可执行程序代码对应的程序，以用于执行上述实施例描述的逆光场景的人脸区域处理方法。
为了更加清楚地说明本申请实施例的终端设备，图99为作为一种可能的实现方式的图像处理电路的示意图。为便于说明，仅示出与本申请实施例相关的各个方面。
如图9所示，该图像处理电路具体包括：拍摄单元11和处理单元12，其中，
拍摄单元11，用于输出拍摄画面。
所述处理单元12，用于当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景，对所述前景进行亮度提升处理，并确定所述前景中的人脸区域，提高HSV色彩模型中与所述人脸区域对应的饱和度。
继续参照图9，在本申请的一个实施例中，拍摄单元11包括电性连接的双摄像头111，所述处理器12包括图像信号处理ISP处理器121，其中，
双摄像头111，用于输出两个摄像头分别获取的当前拍摄画面。
所述ISP处理器121，用于根据双摄像头分别获取的当前拍摄画面数据确定焦点区域之外的图像区域的景深地图，根据所述景深地图确定所述焦点区域之前的前景景深和所述焦点区域之后的背景景深，根据所述前景景深和所述背景景深分离出前景和逆光背景。
继续参照图9，在本申请的一个实施例中，处理器12包括电性连接的CPU122，其中，所述CPU122，用于检测当前场景的逆光强度，获取与所述逆光强度对应的增强幅度，根据所述增强幅度提高HSV色彩模型中与所述人脸区域对应的饱和度。
在本申请的一个实施例中，所述CPU122还用于获取与人脸区域不同部位对应的饱和度调整系数；根据所述不同部位对应的饱和度调整系数和所述增强幅度，计算与所述不同部位对应的提升幅度；根据与所述不同部位对应的提升幅度，提高HSV色彩模型中与所述人脸区域对应像素位置的饱和度。
需要说明的是，本申请实施例中，图像处理电路在实施方法流程的实现细节，参照上 述实施例中逆光场景的人脸区域处理方法的描述，在此不再赘述。
为了实现上述实施例，本申请还提出一种非临时性计算机可读存储介质，其上存储有计算机程序，当该计算机程序被处理器执行时能够实现如前述实施例所述的逆光场景的人脸区域处理方法。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本申请的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本申请的描述中，“多个”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本申请的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本申请的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述 程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。
应当理解，本申请的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。如，如果用硬件来实现和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本申请各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器，磁盘或光盘等。尽管上面已经示出和描述了本申请的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本申请的限制，本领域的普通技术人员在本申请的范围内可以对上述实施例进行变化、修改、替换和变型。取存储介质中。

Claims (14)

  1. 一种逆光场景的人脸区域处理方法，其特征在于，包括：
    当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景；
    对所述前景进行亮度提升处理，并确定所述前景中的人脸区域；
    提高HSV色彩模型中与所述人脸区域对应的饱和度。
  2. 如权利要求1所述的方法，其特征在于，所述对当前拍摄画面分离出前景和逆光背景，包括：
    根据双摄像头分别获取的当前拍摄画面数据确定焦点区域之外的图像区域的景深地图；
    根据所述景深地图确定所述焦点区域之前的前景景深和所述焦点区域之后的背景景深；
    根据所述前景景深和所述背景景深分离出前景和逆光背景。
  3. 如权利要求1或2所述的方法，其特征在于，所述确定所述前景中的人脸区域，包括：
    通过颜色通道检测算法，和/或，图像边缘检测算法，确定所述前景中人脸区域的轮廓边缘。
  4. 如权利要求1-3任一所述的方法，其特征在于，所述提高HSV色彩模型中与所述人脸区域对应的饱和度，包括：
    检测当前场景的逆光强度；
    获取与所述逆光强度对应的增强幅度；
    根据所述增强幅度提高HSV色彩模型中与所述人脸区域对应的饱和度。
  5. 如权利要求4所述的方法，其特征在于，所述根据所述增强幅度提高HSV色彩模型中与所述人脸区域对应的饱和度，包括：
    获取与人脸区域不同部位对应的饱和度调整系数；
    根据所述不同部位对应的饱和度调整系数和所述增强幅度，计算与所述不同部位对应的提升幅度；
    根据与所述不同部位对应的提升幅度，提高HSV色彩模型中与所述人脸区域对应像素位置的饱和度。
  6. 一种逆光场景的人脸区域处理装置，其特征在于，包括：
    分离模块，用于当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景；
    亮度提升模块，用于对所述前景进行亮度提升处理；
    确定模块，用于确定所述前景中的人脸区域；
    调整模块，用于提高HSV色彩模型中与所述人脸区域对应的饱和度。
  7. 如权利要求6所述的装置，其特征在于，所述分离模块包括：
    第一获取单元，用于根据双摄像头分别获取的当前拍摄画面数据确定焦点区域之外的图像区域的景深地图；
    确定单元，用于根据所述景深地图确定所述焦点区域之前的前景景深和所述焦点区域之后的背景景深；
    分离单元，用于根据所述前景景深和所述背景景深分离出前景和逆光背景。
  8. 如权利要求6或7所述的装置，其特征在于，所述调整模块包括：
    检测单元，用于检测当前场景的逆光强度；
    第二获取单元，用于获取与所述逆光强度对应的增强幅度；
    调整单元，用于根据所述增强幅度提高HSV色彩模型中与所述人脸区域对应的饱和度。
  9. 一种终端设备，其特征在于，包括以下一个或多个组件：壳体和位于所述壳体内的处理器、存储器，其中，所述处理器通过读取所述存储器中存储的可执行程序代码来运行与所述可执行程序代码对应的程序，以用于执行如权利要求1-5任一所述的逆光场景的人脸区域处理方法。
  10. 一种非临时性计算机可读存储介质，其上存储有计算机程序，其特征在于，该计算机程序被处理器执行时实现如权利要求1-5任一所述的逆光场景的人脸区域处理方法。
  11. 一种图像处理电路，其特征在于，所述的图像处理电路包括：拍摄单元和处理单元，其中，
    所述拍摄单元，用于输出拍摄画面；
    所述处理单元，用于当检测到逆光场景，对当前拍摄画面分离出前景和逆光背景，对所述前景进行亮度提升处理，并确定所述前景中的人脸区域，提高HSV色彩模型中与所述人脸区域对应的饱和度。
  12. 如权利要求11所述的图像处理电路，其特征在于，所述拍摄单元包括电性连接的双摄像头，所述处理器包括图像信号处理ISP处理器，其中，
    所述双摄像头，用于输出两个摄像头分别获取的当前拍摄画面；
    所述ISP处理器，用于根据双摄像头分别获取的当前拍摄画面数据确定焦点区域之外的图像区域的景深地图，根据所述景深地图确定所述焦点区域之前的前景景深和所述焦点区域之后的背景景深，根据所述前景景深和所述背景景深分离出前景和逆光背景。
  13. 如权利要求11或12所述的图像处理电路，其特征在于，
    所述处理单元，包括电性连接的CPU；
    其中，所述CPU，用于检测当前场景的逆光强度，获取与所述逆光强度对应的增强幅度，根据所述增强幅度提高HSV色彩模型中与所述人脸区域对应的饱和度。
  14. 如权利要求13所述的图像处理电路，其特征在于，所述CPU还用于：
    获取与人脸区域不同部位对应的饱和度调整系数；
    根据所述不同部位对应的饱和度调整系数和所述增强幅度，计算与所述不同部位对应的提升幅度；
    根据与所述不同部位对应的提升幅度，提高HSV色彩模型中与所述人脸区域对应像素位置的饱和度。
PCT/CN2018/091883 2017-07-10 2018-06-19 逆光场景的人脸区域处理方法和装置 WO2019011110A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710558406.5 2017-07-10
CN201710558406.5A CN107454315B (zh) 2017-07-10 2017-07-10 逆光场景的人脸区域处理方法和装置

Publications (1)

Publication Number Publication Date
WO2019011110A1 true WO2019011110A1 (zh) 2019-01-17

Family

ID=60487938

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/091883 WO2019011110A1 (zh) 2017-07-10 2018-06-19 逆光场景的人脸区域处理方法和装置

Country Status (2)

Country Link
CN (1) CN107454315B (zh)
WO (1) WO2019011110A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117152819A (zh) * 2023-09-04 2023-12-01 广州市鹏驰信息科技有限公司 一种人脸识别方法和装置

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107454315B (zh) * 2017-07-10 2019-08-02 Oppo广东移动通信有限公司 逆光场景的人脸区域处理方法和装置
CN108335271B (zh) * 2018-01-26 2022-03-18 努比亚技术有限公司 一种图像处理的方法、设备及计算机可读存储介质
CN108810407B (zh) * 2018-05-30 2021-03-02 Oppo广东移动通信有限公司 一种图像处理方法、移动终端及计算机可读存储介质
CN111275648B (zh) * 2020-01-21 2024-02-09 腾讯科技（深圳）有限公司 人脸图像处理方法、装置、设备及计算机可读存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005250725A (ja) * 2004-03-03 2005-09-15 Seiko Epson Corp 逆光画像の判定
CN102447815A (zh) * 2010-10-09 2012-05-09 中兴通讯股份有限公司 视频图像的处理方法及装置
CN106791471A (zh) * 2016-12-29 2017-05-31 宇龙计算机通信科技(深圳)有限公司 图像优化方法、图像优化装置和终端
CN106937049A (zh) * 2017-03-09 2017-07-07 广东欧珀移动通信有限公司 基于景深的人像色彩的处理方法、处理装置和电子装置
CN107277356A (zh) * 2017-07-10 2017-10-20 广东欧珀移动通信有限公司 逆光场景的人脸区域处理方法和装置
CN107454315A (zh) * 2017-07-10 2017-12-08 广东欧珀移动通信有限公司 逆光场景的人脸区域处理方法和装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005250725A (ja) * 2004-03-03 2005-09-15 Seiko Epson Corp 逆光画像の判定
CN102447815A (zh) * 2010-10-09 2012-05-09 中兴通讯股份有限公司 视频图像的处理方法及装置
CN106791471A (zh) * 2016-12-29 2017-05-31 宇龙计算机通信科技(深圳)有限公司 图像优化方法、图像优化装置和终端
CN106937049A (zh) * 2017-03-09 2017-07-07 广东欧珀移动通信有限公司 基于景深的人像色彩的处理方法、处理装置和电子装置
CN107277356A (zh) * 2017-07-10 2017-10-20 广东欧珀移动通信有限公司 逆光场景的人脸区域处理方法和装置
CN107454315A (zh) * 2017-07-10 2017-12-08 广东欧珀移动通信有限公司 逆光场景的人脸区域处理方法和装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117152819A (zh) * 2023-09-04 2023-12-01 广州市鹏驰信息科技有限公司 一种人脸识别方法和装置
CN117152819B (zh) * 2023-09-04 2024-04-19 广州市鹏驰信息科技有限公司 一种人脸识别方法和装置

Also Published As

Publication number Publication date
CN107454315B (zh) 2019-08-02
CN107454315A (zh) 2017-12-08

Similar Documents

Publication Publication Date Title
CN107277356B (zh) 逆光场景的人脸区域处理方法和装置
US11145038B2 (en) Image processing method and device for adjusting saturation based on depth of field information
CN107977940B (zh) 背景虚化处理方法、装置及设备
JP7027537B2 (ja) 画像処理方法および装置、電子機器、ならびにコンピュータ可読記憶媒体
US10997696B2 (en) Image processing method, apparatus and device
WO2019011110A1 (zh) 逆光场景的人脸区域处理方法和装置
US20200043225A1 (en) Image processing apparatus and control method thereof
WO2018228467A1 (zh) 图像曝光方法、装置、摄像设备及存储介质
US10304164B2 (en) Image processing apparatus, image processing method, and storage medium for performing lighting processing for image data
EP3480784B1 (en) Image processing method, and device
WO2019109805A1 (zh) 图像处理方法和装置
US8150188B2 (en) Imaging apparatus
US8094964B2 (en) Methods and systems for estimating illumination source characteristics from a single image
KR20200023651A (ko) 미리보기 사진 블러링 방법 및 장치 및 저장 매체
WO2019105254A1 (zh) 背景虚化处理方法、装置及设备
EP2962278A1 (en) Multi-spectral imaging system for shadow detection and attenuation
EP3644599A1 (en) Video processing method and apparatus, electronic device, and storage medium
KR20110124965A (ko) 아웃 포커싱 촬영에서 빛망울 효과를 생성하기 위한 장치 및 방법
WO2019011148A1 (zh) 白平衡处理方法和装置
US11710343B2 (en) Image processing device, image processing method, and storage medium for correcting brightness
JP2007312206A (ja) 撮像装置及び、画像再生装置
CN109961422B (zh) 数字图像的对比度值的确定
US11842467B2 (en) Image processing apparatus, image processing method and storage medium
JP2019129469A (ja) 画像処理装置
US20230005296A1 (en) Object recognition method and apparatus, electronic device and readable storage medium

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18831654

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18831654

Country of ref document: EP

Kind code of ref document: A1