WO2017096865A1 - 具有人脸的图像处理方法和装置 - Google Patents

具有人脸的图像处理方法和装置 Download PDF

Info

Publication number
WO2017096865A1
WO2017096865A1 PCT/CN2016/088995 CN2016088995W WO2017096865A1 WO 2017096865 A1 WO2017096865 A1 WO 2017096865A1 CN 2016088995 W CN2016088995 W CN 2016088995W WO 2017096865 A1 WO2017096865 A1 WO 2017096865A1
Authority
WO
WIPO (PCT)
Prior art keywords
face
ambient light
decision point
area
image
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2016/088995
Other languages
English (en)
French (fr)
Inventor
王文平
肖鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Le Holdings Beijing Co Ltd
Lemobile Information Technology (Beijing) Co Ltd
Original Assignee
Le Holdings Beijing Co Ltd
Lemobile Information Technology (Beijing) Co Ltd
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 Le Holdings Beijing Co Ltd, Lemobile Information Technology (Beijing) Co Ltd filed Critical Le Holdings Beijing Co Ltd
Priority to US15/243,447 priority Critical patent/US20170163953A1/en
Publication of WO2017096865A1 publication Critical patent/WO2017096865A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face

Definitions

  • the present application relates to the field of image processing technologies, for example, to an image processing method and apparatus having a human face.
  • the white balance of the smart terminal in different scenarios is obtained by judging the gray point position of the entire picture.
  • the face area in the self-timer image takes up a large proportion, and the face area in the image is warm light, and the pixel points of the part area fall in the warm light area, the face area
  • the pixel points are larger in the pixels of the entire image, and the white balance is misjudged as the low color temperature, which eventually leads to the overall blueness of the image after the white balance processing.
  • the application provides an image processing method and device with a human face, which effectively restores the essence of the scene and improves the image quality.
  • the present application discloses an image processing method with a human face, including:
  • the image with the face is adjusted according to the white balance parameter.
  • adjusting the white balance parameter according to the face determination point, the ambient light determination point, and the set distance threshold including:
  • the white balance parameter is adjusted according to the magnitude relationship between the decision point distance and the set distance threshold.
  • adjusting the white balance parameter according to the relationship between the determined point distance and the set distance threshold including:
  • the white balance parameter of the face area is adjusted according to the face determination point, and the environment is determined according to the ambient light decision point.
  • White balance parameter of the light region
  • the white balance parameter is adjusted according to the point at which the entire image falls into the gray band.
  • the face recognition is performed on the image with a face, and the face region and the ambient light region except the face region are obtained, including:
  • the face contour is used as the face region, and other regions in the image are used as ambient light regions.
  • determining a face determination point of the face area and an ambient light decision point of the ambient light area including:
  • the macroblock of the gray area is a gray area macroblock
  • the face determination point is calculated according to the red/green ratio and the blue/green ratio of the gray area macroblock of the face region
  • the ambient light decision point is calculated according to the red/green ratio and the blue/green ratio of the gray area macroblock of the ambient light area.
  • an image processing apparatus having a human face including:
  • At least one processor and,
  • the memory stores a program executable by the at least one processor, the program comprising:
  • An image acquisition module configured to acquire an image having a face in a current shooting scene
  • An area recognition module configured to perform face recognition on the image with a face to obtain a face area and an ambient light area other than the face area;
  • a decision point determining module configured to determine a face determination point of the face area and an ambient light decision point of the ambient light area
  • a white balance parameter adjustment module configured to adjust a white balance parameter according to the face determination point, the ambient light determination point, and the set distance threshold
  • the image adjustment module is configured to adjust the image with a face according to the white balance parameter.
  • the white balance parameter adjustment module includes:
  • a decision point distance calculation unit configured to calculate a decision point distance between the face decision point and the ambient light decision point
  • the white balance parameter adjustment unit is configured to adjust the white balance parameter according to a magnitude relationship between the decision point distance and the set distance threshold.
  • the white balance parameter adjustment unit is further configured to:
  • the white balance parameter of the face area is adjusted according to the face determination point, and the environment is determined according to the ambient light decision point.
  • White balance parameter of the light region
  • the white balance parameter is adjusted according to the point at which the entire image falls into the gray band.
  • the area identification module includes: a face rectangular frame determining unit, a face contour extracting unit, and an area dividing unit;
  • the face rectangle frame determining unit is configured to perform face recognition on the image having a face, and determine a rectangular frame corresponding to the face;
  • the face contour extraction unit is configured to extract a face contour in the rectangular frame
  • the area dividing unit is configured to use the face contour as the face area, and the other areas in the image as the ambient light area.
  • the decision point determining module includes: a color ratio calculating unit, a gray area macro block determining unit, and a decision point calculating unit;
  • the color ratio calculation unit is configured to divide the image having a face into 256 macroblocks, and calculate a red/green ratio and a blue/green ratio of each macroblock color;
  • the gray zone macroblock determining unit is configured to determine, according to a red/green ratio value and a blue/green ratio value of the macroblock, and a red/green ratio range and a blue/green ratio range of the light source, to determine that the gray block of the gray space is gray Macroblock
  • the decision point calculating unit is configured to calculate a face decision point according to a red/green ratio and a blue/green ratio of the gray area macroblock of the face region, and according to a red/green ratio of the gray region macroblock of the ambient light region and The blue/green ratio calculates the ambient light decision point.
  • the present application also discloses a non-volatile computer storage medium storing computer-executable instructions for performing an image processing method with a face of any of the above aspects.
  • the technical solution provided by the present application can adjust the white balance parameter of the face region by dividing the image with the face into the face region and the ambient light region, thereby effectively reducing the essence of the scene and improving the image quality.
  • FIG. 1 is a schematic flow chart of an image processing method with a human face according to Embodiment 1 of the present application;
  • FIG. 2 is a schematic flow chart of an image processing method with a human face according to Embodiment 2 of the present application;
  • FIG. 3 is a schematic flow chart of an image processing method with a human face according to Embodiment 3 of the present application;
  • FIG. 4 is a schematic structural diagram of an image processing apparatus with a human face according to Embodiment 4 of the present application;
  • FIG. 5 is a schematic diagram showing the hardware structure of an image processing apparatus with a human face according to Embodiment 6 of the present application.
  • FIG. 1 is a schematic flow chart of an image processing method with a human face according to Embodiment 1 of the present application.
  • the method is performed by an image processing apparatus having a face, which is generally integrated in a device having a photographing function, such as a smart mobile terminal or the like.
  • the image processing method with a face includes:
  • the device with shooting function When the device with shooting function is turned on, an image with a face in the current scene is taken by the front camera or the rear camera in the device.
  • the device with shooting function can be a smart phone, a tablet computer, and a personal computer with a camera.
  • S120 Perform face recognition on an image with a human face to obtain a face region and an ambient light region other than the face region.
  • the image with the face is divided into regions, and the face region can be recognized by various face recognition algorithms, and the region other than the face region in the image is determined as the ambient light region.
  • the face recognition algorithm can adopt the Adaboost algorithm.
  • Adaboost is an iterative algorithm.
  • the core of Adaboost algorithm is to train different classifiers (weak classifiers) for the same training set, and then combine these weak classifiers to form a stronger final classifier (strong classifier).
  • the algorithm itself is implemented by changing the data distribution, which determines the weight of each sample based on whether the classification of each sample in each training set is correct and the accuracy of the last overall classification.
  • the new data set with the modified weight is sent to the lower classifier for training, and finally the classifier obtained by each training is finally merged as the final decision classifier.
  • dynamic thresholds can be used in the Adaboost algorithm to speed up face recognition.
  • the face recognition algorithm may also adopt other algorithms capable of quickly recognizing a face region, and the face recognition algorithm is not limited in this application.
  • performing face recognition on the image with the face, and obtaining the face region and the ambient light region other than the face region may include: performing face recognition on the image having the face, and determining a rectangle corresponding to the face a frame; a face contour is extracted in a rectangular frame; a face contour is used as the face region, and other regions in the image are used as ambient light regions.
  • extracting the face contour in the rectangular frame may adopt the active shape model or the active appearance model to extract the face contour.
  • the image of the face with the face is first divided into regions, and the red/green ratio and the blue/green ratio of each partial pixel are calculated according to the color of each part of the image, and the red/green ratio of all the pixels of each part is taken.
  • the average value is averaged for the blue/green ratio of all the pixels of each portion, and the average value is taken as the red/green ratio and the blue/green ratio of the portion.
  • the red/green ratio range and the blue/green ratio range of the light source determine the source of each part of the image.
  • the red/green ratio and the blue/green ratio in the image fall within the red/green ratio range and the blue/green ratio range of the source. Part outside Gray area.
  • the light source of nature includes a light source D75, a light source D65, a light source D50, a light source CW, a light source TL84, a light source A, and a light source H, each of which corresponds to a certain R/G and B/G.
  • the image having the face may not be divided into macroblocks, but the face determination point and the ambient light decision point are obtained according to the R, G, and B colors of all the pixel points of the face region and the ambient light region.
  • the method of calculating the face decision point and the ambient light decision point by the pixel point is suitable for an image having a face with a small number of pixels.
  • the face determines the corresponding light source, and the light source corresponding to the ambient light decision point is determined by the same method.
  • the white balance parameter can be adjusted by the light source.
  • the distance between the face decision point and the ambient light decision point can represent the distance between the mainstream light source of the face area and the mainstream light source of the ambient light area.
  • the distance between the face determination point and the ambient light decision point is greater than the set distance threshold, the distance between the mainstream light source of the face area and the mainstream light source of the ambient light area is larger, and accordingly, the face area is based on
  • the light source corresponding to the face determination point adjusts the white balance parameter
  • the ambient light area adjusts the white balance parameter according to the light source corresponding to the ambient light determination point.
  • the white balance parameters are adjusted for the face area and the ambient light area respectively, thereby avoiding the environment being reduced due to the adjustment of the face part.
  • adjusting the white balance parameter according to the face determination point, the ambient light determination point, and the set distance threshold may include: calculating a decision point distance between the face determination point and the ambient light determination point; Adjust the white balance parameter with the relationship between the set distance threshold and the threshold value.
  • the images of the face area and the ambient light area can be adjusted according to the white balance parameters of the face area and the ambient light area.
  • the technical solution provided by the embodiment of the present application by dividing an image with a face into a face region and an ambient light region, performs white balance parameter adjustment on the face region, thereby avoiding the face region and the ambient light region.
  • the mutual influence of the domain can effectively restore the essence of the scene and improve the image quality.
  • FIG. 2 is a schematic flow chart of an image processing method with a face according to Embodiment 2 of the present application.
  • the image processing method with a face includes.
  • S220 Perform face recognition on an image with a human face to obtain a face region and an ambient light region other than the face region.
  • step S250 Determine whether the distance between the face determination point and the ambient light determination point is greater than a set distance threshold. If yes, execute step S260; otherwise, execute step S270.
  • step S260 Adjust the white balance parameter of the face region according to the face determination point, and adjust the white balance parameter of the ambient light region according to the ambient light determination point, and execute step S280.
  • the face area adjusts the white balance parameter of the face area according to the face determination point
  • the ambient light area adjusts the ambient light area according to the ambient light decision point.
  • the mainstream light source of the ambient light area may be A light or H light, or There are a small number of TL85 light sources, so the light source in the ambient light area and the light source in the face area are warmer.
  • the global decision point is recalculated according to the part of the entire image with the face falling into the gray area, and the global decision point is passed. The decision point adjusts the white balance parameter of the entire image with the face.
  • the technical solution provided by the embodiment of the present invention divides the image with the face into the face region and the ambient light region, and adjusts the white balance parameter of the face region, thereby avoiding the mutual influence between the face region and the ambient light region, effectively Restore the essence of the scene and improve the image quality.
  • FIG. 3 is a schematic flow chart of an image processing method with a human face according to Embodiment 3 of the present application.
  • the image processing method with a face includes.
  • S320 Perform face recognition on the image with the face to obtain a face region and an ambient light region other than the face region.
  • the face image is divided into 16 rows and 16 columns, that is, 256 macroblocks, and each macroblock corresponds to one sub-image in a certain image, and the number of macroblocks can be set according to the situation.
  • the average of R/G and B/G of the pixel points included in the macroblock can be taken as R/G and B/G of the macroblock.
  • the macroblock of the gray space is a gray area macroblock.
  • the average or weighted average of the R/G and B/G of the gray area macroblock of the face region is calculated, and the R/G and B/G corresponding average or weighted average are determined as the face.
  • Point R/G and B/G is calculated, and the average or weighted average of the R/G and B/G of the gray area macroblock of the face region.
  • S360 Adjust the white balance parameter according to the face determination point, the ambient light determination point, and the set distance threshold.
  • the face determines the corresponding light source, and the light source corresponding to the ambient light decision point is determined by the same method.
  • the white balance parameter can be adjusted by the light source.
  • the distance between the face area light source and the ambient light area light source can be determined by the distance between the light sources respectively for the face area and the ambient light area. Adjust the white balance parameter or use a decision point to adjust the white balance parameter for the entire image with a face.
  • the technical solution provided by the embodiment of the present invention divides the image with the face into the face region and the ambient light region, and adjusts the white balance parameter of the face region, thereby avoiding the mutual influence between the face region and the ambient light region, effectively Restores the essence of the scene and improves image quality.
  • FIG. 4 is a schematic structural diagram of an image processing apparatus with a human face according to Embodiment 4 of the present application.
  • an image processing apparatus having a human face includes an image acquisition module 40, an area identification module 41, a decision point determination module 42, a white balance parameter adjustment module 43, and an image adjustment module 44.
  • the image acquisition module 40 is configured to acquire an image having a face in the current shooting scene; the area recognition module 41 is configured to perform face recognition on the image having the face, and obtain an ambient light and an ambient light other than the face area.
  • a determination point determining module 42 is configured to determine a face determination point of the face area and an ambient light decision point of the ambient light area;
  • the white balance parameter adjustment module 43 is configured to determine a point according to the face, an ambient light decision point, and a set distance The threshold adjusts the white balance parameter;
  • the image adjustment module 44 is configured to adjust the image having the face according to the white balance parameter.
  • the white balance parameter adjustment module 43 includes: a decision point distance calculation unit and a white balance parameter adjustment unit.
  • the decision point distance calculation unit is configured to calculate a decision point distance between the face decision point and the ambient light decision point;
  • the white balance parameter adjustment unit is configured to adjust the white balance according to the magnitude relationship between the decision point distance and the set distance threshold parameter.
  • the white balance parameter adjustment unit is further configured to:
  • the white balance parameter of the face area is adjusted according to the face determination point, and the environment is determined according to the ambient light decision point.
  • White balance parameter of the light region
  • the white balance parameter is adjusted according to the point at which the entire image falls into the gray band.
  • the area identifying module 41 includes: a face rectangular frame determining unit, a face contour extracting unit, and an area dividing unit.
  • the face rectangle frame determining unit is configured to perform face recognition on the image having the face, and determine a rectangular frame corresponding to the face; the face contour extraction unit is configured to extract the face contour in the rectangular frame; the area dividing unit is set to The face contour is used as the face area, and the other areas in the image are used as the ambient light area.
  • the decision point determining module 42 includes: a color ratio calculation, a gray zone macroblock determining unit, and a decision point calculating unit.
  • the color ratio calculation unit is configured to divide the image having a face into 256 macroblocks, and calculate a red/green ratio and a blue/green ratio value of each macroblock color;
  • the gray area macroblock determining unit is configured to a red/green ratio and a blue/green ratio of the macroblock and a red/green ratio range and a blue/green ratio range of the light source, determining that the macroblock of the gray area is a gray area macroblock; and determining the point calculation unit is set according to the person Gray area macroblock of face area
  • the red/green ratio and the blue/green ratio calculate the face decision point, and the ambient light decision point is calculated based on the red/green ratio and the blue/green ratio of the gray region macroblock of the ambient light region.
  • the technical solution provided by the embodiment of the present invention divides the image with the face into the face region and the ambient light region, and adjusts the white balance parameter of the face region, thereby effectively reducing the essence of the scene and improving the image quality.
  • the embodiment of the present application provides a non-volatile computer storage medium storing computer-executable instructions for performing an image processing method with a face in any of the above-described embodiments.
  • FIG. 5 is a schematic diagram showing the hardware structure of an image processing apparatus with a human face according to Embodiment 6 of the present application.
  • the apparatus includes:
  • One or more processors 50 and a memory 51, and one processor 50 is taken as an example in FIG. 5;
  • the apparatus may also include an input device 52 and an output device 53.
  • the processor 50, the memory 51, the input device 52, and the output device 53 in the device may be connected by a bus or other means, and the bus connection is taken as an example in FIG.
  • the memory 51 is a non-volatile computer readable storage medium, and is configured to store a non-volatile software program, a non-volatile computer-executable program, and a module, such as image processing with a face in the embodiment of the present application.
  • the program corresponds to a program instruction/module (for example, the image acquisition module 40, the region identification module 41, the decision point determination module 42, the white balance parameter adjustment module 43, and the image adjustment module 44 shown in FIG. 4).
  • the processor 50 executes the functional application of the server and the data processing by executing the software programs, the instructions, and the modules stored in the memory 51, that is, the image processing method with the face in the above method embodiment.
  • the memory 51 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to use of the terminal device, and the like. Further, the memory 51 may include a high speed random access memory, and may also include a nonvolatile memory such as at least one magnetic disk storage device, a flash memory device, or other nonvolatile solid state storage device. In some examples, memory 51 may include memory remotely located relative to processor 50, which may be connected to the terminal device over a network. Examples of the above networks include but not Limited to the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • Input device 52 can be arranged to receive input numeric or character information and to generate key signal inputs related to user settings and function control of the terminal.
  • the output device 53 may include a display device such as a display screen.
  • the one or more modules are stored in the memory 51, and when executed by the one or more processors 50, perform the steps of the method embodiment of any of the above-described image processing methods with faces.
  • the technical solution provided by the embodiment of the present invention divides the image with the face into the face region and the ambient light region, and adjusts the white balance parameter of the face region, thereby effectively reducing the essence of the scene and improving the image quality.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Color Image Communication Systems (AREA)
  • Color Television Image Signal Generators (AREA)
  • Image Processing (AREA)

Abstract

一种具有人脸的图像处理方法，包括：获取当前拍摄场景中具有人脸的图像；对所述具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域；确定人脸区域的人脸决定点以及环境光区域的环境光决定点；根据所述人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数；根据所述白平衡参数对所述具有人脸的图像进行调整。

Description

具有人脸的图像处理方法和装置
本申请要求在2015年12月8日提交中国专利局、申请号为2015108965498、申请名称为“一种具有人脸的图像处理方法和装置”的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及图像处理技术领域，例如涉及一种具有人脸的图像处理方法和装置。
背景技术
相关技术中，不同场景下智能终端的白平衡是通过判断整张图片的灰点位置得到的。当采用智能终端中的前置摄像头进行自拍时，自拍图像中人脸区域占用了较大的比重，图像中人脸区域为暖光，该部分区域的像素点落在暖光区，人脸区域的像素点在整张图像的像素点中比例较大，白平衡误判为低色温，通过白平衡处理后最终导致图像整体偏蓝。
另外，多数人都喜欢在颜色比较鲜艳的环境下取景，通过后置摄像头拍摄的图像背景的饱和度较高，经过白平衡调试之后，导致人脸区域偏红。相关技术中，在对图像中偏红的人脸区域进行处理时，一般采用降低整张图像饱和度的方法调整人脸区域的偏红程度。
可见，相关技术在处理具有人脸的图像时，不能较好的进行白平衡调试，图像质量不佳。
发明内容
本申请提供了一种具有人脸的图像处理方法和装置，有效地还原了景色本质，提高了图像质量。
一方面，本申请公开了一种具有人脸的图像处理方法，包括：
获取当前拍摄场景中具有人脸的图像；
对所述具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域；
确定人脸区域的人脸决定点以及环境光区域的环境光决定点；
根据所述人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数；以及
根据所述白平衡参数对所述具有人脸的图像进行调整。
可选的，根据所述人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数，包括：
计算所述人脸决定点和环境光决定点之间的决定点距离；
根据所述决定点距离与所述设定距离阀值的大小关系，调整所述白平衡参数。
可选的，根据所述决定点距离与所述设定距离阀值的大小关系，调整所述白平衡参数，包括：
当所述人脸决定点和所述环境光决定点之间的距离大于所述设定距离阀值时，根据人脸决定点调整人脸区域的白平衡参数，并且根据环境光决定点调整环境光区域的白平衡参数；
当所述人脸决定点以及所述环境光决定点之间的距离小于所述设定距离阀值时，根据整张图像落入灰带的点调整白平衡参数。
可选的，对所述具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域，包括：
对所述具有人脸的图像进行人脸识别，确定人脸对应的矩形框；
在所述矩形框中提取人脸轮廓；以及
将所述人脸轮廓作为所述人脸区域，图像中的其他区域作为环境光区域。
可选的，确定人脸区域的人脸决定点以及环境光区域的环境光决定点，包括：
将所述具有人脸的图像划分为256个宏块，并计算每个宏块色彩的红/绿比值和蓝/绿比值；
根据所述宏块的红/绿比值和蓝/绿比值以及光源的红/绿比值范围和蓝/绿比值范围，确定落灰区的宏块为灰区宏块；以及
根据人脸区域的灰区宏块的红/绿比值和蓝/绿比值计算人脸决定点，并且根据环境光区域的灰区宏块的红/绿比值和蓝/绿比值计算环境光决定点。
另一方面，本申请还公开了一种具有人脸的图像处理装置，包括：
至少一个处理器；以及，
存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的程序，所述程序包括：
图像获取模块，设置为获取当前拍摄场景中具有人脸的图像；
区域识别模块，设置为对所述具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域；
决定点确定模块，设置为确定人脸区域的人脸决定点以及环境光区域的环境光决定点；
白平衡参数调整模块，设置为根据所述人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数；以及
图像调整模块，设置为根据所述白平衡参数对所述具有人脸的图像进行调整。
可选的，所述白平衡参数调整模块，包括：
决定点距离计算单元，设置为计算所述人脸决定点和环境光决定点之间的决定点距离；
白平衡参数调整单元，设置为根据所述决定点距离与所述设定距离阀值的大小关系，调整所述白平衡参数。
可选的，所述白平衡参数调整单元，还设置为：
当所述人脸决定点和所述环境光决定点之间的距离大于所述设定距离阀值时，根据人脸决定点调整人脸区域的白平衡参数，并且根据环境光决定点调整环境光区域的白平衡参数；
当所述人脸决定点以及所述环境光决定点之间的距离小于所述设定距离阀值时，根据整张图像落入灰带的点调整白平衡参数。
可选的，所述区域识别模块，包括：人脸矩形框确定单元、人脸轮廓提取单元以及区域划分单元；
所述人脸矩形框确定单元，设置为对所述具有人脸的图像进行人脸识别，确定人脸对应的矩形框；
所述人脸轮廓提取单元，设置为在所述矩形框中提取人脸轮廓；
所述区域划分单元，设置为将所述人脸轮廓作为所述人脸区域，图像中的其他区域作为环境光区域。
可选的，所述决定点确定模块，包括：色彩比值计算单元、灰区宏块确定单元以及决定点计算单元；
所述色彩比值计算单元，设置为将所述具有人脸的图像划分为256个宏块，并计算每个宏块色彩的红/绿比值和蓝/绿比值；
所述灰区宏块确定单元，设置为根据所述宏块的红/绿比值和蓝/绿比值以及光源的红/绿比值范围和蓝/绿比值范围，确定落灰区的宏块为灰区宏块；
所述决定点计算单元，设置为根据人脸区域的灰区宏块的红/绿比值和蓝/绿比值计算人脸决定点，并且根据环境光区域的灰区宏块的红/绿比值和蓝/绿比值计算环境光决定点。
本申请还公开了一种非易失性计算机存储介质，存储有计算机可执行指令，所述计算机可执行指令用于执行上述任一方面的具有人脸的图像处理方法。
本申请提供的技术方案，通过将具有人脸的图像划分为人脸区域以及环境光区域，对人脸区域进行白平衡参数调整，有效地还原了景色本质，提高了图像质量。
附图说明
图1是本申请实施例一提供的一种具有人脸的图像处理方法的流程示意图；
图2是本申请实施例二提供的一种具有人脸的图像处理方法的流程示意图；
图3是本申请实施例三提供的一种具有人脸的图像处理方法的流程示意图；
图4是本申请实施例四提供的一种具有人脸的图像处理装置的结构示意图；
图5是本申请实施例六提供的一种具有人脸的图像处理装置的硬件结构示意图。
实施方式
下面结合附图和实施例对本申请作详细说明。可以理解的是，此处所描述的实施例仅仅用于解释本申请，而非对本申请的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与本申请相关的部分而非全部结构。
实施例一
图1是本申请实施例一提供的一种具有人脸的图像处理方法的流程示意图。该方法由具有人脸的图像处理装置来执行，该装置一般集成于具有拍摄功能的设备中，例如智能移动终端等。参见图1，所述具有人脸的图像处理方法，包括：
S110、获取当前拍摄场景中具有人脸的图像。
当开启具有拍摄功能的设备后，通过设备中的前置摄像头或者后置摄像头拍摄一幅当前场景下具有人脸的图像。其中，具有拍摄功能的设备可以是智能手机、平板电脑以及带有摄像头的个人计算机。
S120、对具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域。
将具有人脸的图像进行区域划分，可以通过多种人脸识别算法识别人脸区域，图像中人脸区域以外的区域判定为环境光区域。
人脸识别算法可以采用Adaboost算法。Adaboost是一种迭代算法，Adaboost算法的核心是针对同一个训练集训练不同的分类器(弱分类器)，然后把这些弱分类器集合起来，构成一个更强的最终分类器(强分类器)，该算法本身是通过改变数据分布来实现的，它根据每次训练集之中每个样本的分类是否正确，以及上次的总体分类的准确率，来确定每个样本的权值，并将修改过权值的新数据集送给下层分类器进行训练，最后将每次训练得到的分类器最后融合起来，作为最后的决策分类器。可选的，在Adaboost算法中可以采用动态阀值，加速人脸识别的速度。人脸识别算法还可以采用其他能够快速识别人脸区域的算法，本申请中对人脸识别算法不作限定。
可选地，对具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域可以包括：对具有人脸的图像进行人脸识别，确定人脸对应的矩形框；在矩形框中提取人脸轮廓；将人脸轮廓作为所述人脸区域，图像中的其他区域作为环境光区域。
其中，在矩形框中提取人脸轮廓可以采用主动形状模型或者主动外观模型对人脸轮廓进行提取。
S130、确定人脸区域的人脸决定点以及环境光区域的环境光决定点。
将具有人脸的图像的首先进行区域划分，根据图像每个部分的色彩，计算每个部分像素点的红/绿比值和蓝/绿比值，对每个部分所有像素点的红/绿比值取平均值，并对每个部分所有像素点的蓝/绿比值取平均值，将该平均值作为该部分的红/绿比值和蓝/绿比值。结合由红/绿(R/G)作为横坐标和蓝/绿(B/G)作为纵坐标的R/G-B/G直方图，根据图像中每个部分的红/绿比值和蓝/绿比值以及光源的红/绿比值范围和蓝/绿比值范围，确定图像中每个部分的光源，图像中红/绿比值和蓝/绿比值落在光源的红/绿比值范围和蓝/绿比值范围之外的部分属于 灰区。自然界的光源包括光源D75、光源D65、光源D50、光源CW、光源TL84、光源A以及光源H，每个光源分别对应一定的R/G和B/G。
计算图像中人脸区域落在灰区部分的R/G和B/G的平均值，将R/G的平均值和B/G的平均值作为人脸决定点，并通过同样的计算得到环境光决定点。
另外，对具有人脸的图像还可以不划分宏块，而是根据人脸区域和环境光区域所有像素点的R、G、B色彩，求取人脸决定点和环境光决定点。通过像素点计算人脸决定点和环境光决定点的方法适用于像素点较少的具有人脸的图像。
S140、根据人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数。
将人脸决定点的R/G和B/G的值映射到R/G-B/G直方图中，该人脸决定点落在一光源对应的R/G和B/G范围内，从而确定人脸决定点对应的光源，并通过同样的方法确定环境光决定点对应的光源。通过光源可以对白平衡参数进行调整。
人脸决定点和环境光决定点之间的距离能够表示人脸区域的主流光源与环境光区域主流光源之间的距离。当人脸决定点和环境光决定点之间的距离大于设定距离阀值时，说明人脸区域的主流光源与环境光区域的主流光源之间的距离较大，相应地，人脸区域依据人脸决定点对应的光源调整白平衡参数，环境光区域依据环境光决定点对应的光源调整白平衡参数。
通过人脸决定点和环境光决定点之间的距离与设定距离阀值的比较，分别对人脸区域和环境光区域进行白平衡参数的调整，避免了由于调整人脸部分而降低了环境光区域的显示效果或者由于调整环境光区域而降低人脸区域显示效果的弊端。
可选地，根据人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数，可以包括：计算人脸决定点和环境光决定点之间的决定点距离；根据决定点距离与设定距离阀值的大小关系，调整白平衡参数。
S150、根据白平衡参数对具有人脸的图像进行调整。
在调整白平衡参数之后，可以根据人脸区域和环境光区域的白平衡参数对人脸区域和环境光区域的图像进行调整。
本申请实施例提供的技术方案，通过将具有人脸的图像划分为人脸区域以及环境光区域，对人脸区域进行白平衡参数调整，避免了人脸区域与环境光区 域的相互影响，可以有效地还原景色本质，提高了图像质量。
实施例二
图2是本申请实施例二提供的一种具有人脸的图像处理方法的流程示意图。参见图2，所述具有人脸的图像处理方法包括。
S210、获取当前拍摄场景中具有人脸的图像。
S220、对具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域。
S230、确定人脸区域的人脸决定点以及环境光区域的环境光决定点。
S240、计算人脸决定点和环境光决定点之间的决定点距离。
S250、判断人脸决定点和环境光决定点之间的距离是否大于设定距离阀值时，若是，则执行步骤S260，否则，执行步骤S270。
S260、根据人脸决定点调整人脸区域的白平衡参数，并且根据环境光决定点调整环境光区域的白平衡参数，执行步骤S280。
人脸决定点和环境光决定点之间的距离大于设定距离阀值时，人脸区域根据人脸决定点调整人脸区域的白平衡参数，环境光区域根据环境光决定点调整环境光区域的白平衡参数。
S270、根据整张图像落入灰带的点调整白平衡参数。
由于人脸区域一般是暖光源即A光源，人脸决定点和环境光决定点之间的距离小于设定距离阀值时，环境光区域的主流光源可能应该是A光或者H光，也可能有少部分的TL85光源，所以环境光区域的光源和人脸区域的光源都偏暖光，此时，根据整张具有人脸的图像落入灰区的部分重新计算全局决定点，并通过全局决定点调整整张具有人脸的图像的白平衡参数。
S280、根据白平衡参数对具有人脸的图像进行调整。
本申请实施例提供的技术方案，通过将具有人脸的图像划分为人脸区域以及环境光区域，对人脸区域进行白平衡参数调整，避免了人脸区域与环境光区域的相互影响，有效地还原景色本质，提高图像质量。
实施例三
图3是本申请实施例三提供的一种具有人脸的图像处理方法的流程示意图。参见图3，所述具有人脸的图像处理方法包括。
S310、获取当前拍摄场景中具有人脸的图像。
S320、对具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域。
S330、将具有人脸的图像划分为256个宏块，并计算每个宏块色彩的红/绿比值和蓝/绿比值。
其中，具有人脸图像被划分为16行16列，即256个宏块，每个宏块对应着一定的图像中的一个子图像，宏块的个数可以根据情况进行设置。可以将宏块包含的像素点的R/G和B/G的平均值作为该宏块的R/G和B/G。
S340、根据所述宏块的红/绿比值和蓝/绿比值以及光源的红/绿比值范围和蓝/绿比值范围，确定落灰区的宏块为灰区宏块。
S350、根据人脸区域的灰区宏块的红/绿比值和蓝/绿比值计算人脸决定点，并且根据环境光区域的灰区宏块的红/绿比值和蓝/绿比值计算环境光决定点。
示例性的，分别计算人脸区域的灰区宏块的R/G和B/G的平均值或者加权平均值，并将R/G和B/G对应平均值或者加权平均值作为人脸决定点的R/G和B/G。
S360、根据人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数。
将人脸决定点的R/G和B/G的值映射到R/G-B/G直方图中，该人脸决定点落在一光源对应的R/G和B/G范围内，从而确定人脸决定点对应的光源，并通过同样的方法确定环境光决定点对应的光源。通过光源可以对白平衡参数进行调整。
根据人脸决定点、环境光决定点以及设定距离阀值的关系可以得知，人脸区域光源和环境光区域光源的距离，通过光源之间的距离确定对人脸区域和环境光区域分别进行白平衡参数的调整或者对整张具有人脸的图像采用一个决定点进行白平衡参数的调整。
S370、根据白平衡参数对具有人脸的图像进行调整。
本申请实施例提供的技术方案，通过将具有人脸的图像划分为人脸区域以及环境光区域，对人脸区域进行白平衡参数调整，避免了人脸区域与环境光区域的相互影响，有效地还原了景色本质，提高了图像质量。
实施例四
图4是本申请实施例四提供的一种具有人脸的图像处理装置的结构示意图。参见图4，具有人脸的图像处理装置，包括：图像获取模块40、区域识别模块41、决定点确定模块42、白平衡参数调整模块43以及图像调整模块44。
其中，图像获取模块40设置为获取当前拍摄场景中具有人脸的图像；区域识别模块41设置为对具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域；决定点确定模块42设置为确定人脸区域的人脸决定点以及环境光区域的环境光决定点；白平衡参数调整模块43设置为根据人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数；图像调整模块44设置为根据白平衡参数对所述具有人脸的图像进行调整。
可选地，白平衡参数调整模块43，包括：决定点距离计算单元和白平衡参数调整单元。
其中，决定点距离计算单元设置为计算人脸决定点和环境光决定点之间的决定点距离；白平衡参数调整单元设置为根据决定点距离与设定距离阀值的大小关系，调整白平衡参数。
可选地，白平衡参数调整单元，还设置为：
当所述人脸决定点和所述环境光决定点之间的距离大于所述设定距离阀值时，根据人脸决定点调整人脸区域的白平衡参数，并且根据环境光决定点调整环境光区域的白平衡参数；
当所述人脸决定点以及所述环境光决定点之间的距离小于所述设定距离阀值时，根据整张图像落入灰带的点调整白平衡参数。
可选地，区域识别模块41，包括：人脸矩形框确定单元、人脸轮廓提取单元以及区域划分单元。
其中，人脸矩形框确定单元设置为对具有人脸的图像进行人脸识别，确定人脸对应的矩形框；人脸轮廓提取单元设置为在矩形框中提取人脸轮廓；区域划分单元设置为将人脸轮廓作为人脸区域，图像中的其他区域作为环境光区域。
可选地，决定点确定模块42，包括：色彩比值计算、灰区宏块确定单元以及决定点计算单元。
其中，色彩比值计算单元设置为将所述具有人脸的图像划分为256个宏块，并计算每个宏块色彩的红/绿比值和蓝/绿比值；灰区宏块确定单元设置为根据所述宏块的红/绿比值和蓝/绿比值以及光源的红/绿比值范围和蓝/绿比值范围，确定落灰区的宏块为灰区宏块；决定点计算单元设置为根据人脸区域的灰区宏块 的红/绿比值和蓝/绿比值计算人脸决定点，并且根据环境光区域的灰区宏块的红/绿比值和蓝/绿比值计算环境光决定点。
本申请实施例提供的技术方案，通过将具有人脸的图像划分为人脸区域以及环境光区域，对人脸区域进行白平衡参数调整，有效地还原了景色本质，提高了图像质量。
实施例五
本申请实施例提供了一种非易失性计算机存储介质，存储有计算机可执行指令，所述计算机可执行指令用于执行上述任意方法实施例中的具有人脸的图像处理方法。
实施例六
图5是本申请实施例六提供的一种具有人脸的图像处理装置的硬件结构示意图，参见图5，该装置包括：
一个或者多个处理器50以及存储器51，图5中以一个处理器50为例；
所述装置还可以包括：输入装置52和输出装置53。所述装置中的处理器50、存储器51、输入装置52和输出装置53可以通过总线或其他方式连接，图5中以通过总线连接为例。
存储器51作为一种非易失性计算机可读存储介质，可设置为存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请实施例中的具有人脸的图像处理方法对应的程序指令/模块(例如，附图4所示的图像获取模块40、区域识别模块41、决定点确定模块42、白平衡参数调整模块43以及图像调整模块44)。处理器50通过运行存储在存储器51中的软件程序、指令以及模块，从而执行服务器的功能应用以及数据处理，即实现上述方法实施例中的具有人脸的图像处理方法。
存储器51可包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据终端设备的使用所创建的数据等。此外，存储器51可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中，存储器51可包括相对于处理器50远程设置的存储器，这些远程存储器可以通过网络连接至终端设备。上述网络的实例包括但不 限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置52可设置为接收输入的数字或字符信息，以及产生与终端的用户设置以及功能控制有关的键信号输入。输出装置53可包括显示屏等显示设备。
所述一个或者多个模块存储在所述存储器51中，当被所述一个或者多个处理器50执行时，执行上述任意具有人脸的图像处理方法的方法实施例的步骤。
上述产品可执行本申请实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本申请实施例所提供的方法。
工业实用性
本申请实施例提供的技术方案，通过将具有人脸的图像划分为人脸区域以及环境光区域，对人脸区域进行白平衡参数调整，有效地还原了景色本质，提高了图像质量。

Claims (11)

  1. 一种具有人脸的图像处理方法，包括：
    获取当前拍摄场景中具有人脸的图像；
    对所述具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域；
    确定人脸区域的人脸决定点以及环境光区域的环境光决定点；
    根据所述人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数；以及
    根据所述白平衡参数对所述具有人脸的图像进行调整。
  2. 根据权利要求1所述的方法，其中，根据所述人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数，包括：
    计算所述人脸决定点和环境光决定点之间的决定点距离；
    根据所述决定点距离与所述设定距离阀值的大小关系，调整所述白平衡参数。
  3. 根据权利要求2所述的方法，其中，根据所述决定点距离与所述设定距离阀值的大小关系，调整所述白平衡参数，包括：
    当所述人脸决定点和所述环境光决定点之间的距离大于所述设定距离阀值时，根据人脸决定点调整人脸区域的白平衡参数，并且根据环境光决定点调整环境光区域的白平衡参数；
    当所述人脸决定点以及所述环境光决定点之间的距离小于所述设定距离阀值时，根据整张图像落入灰带的点调整白平衡参数。
  4. 根据权利要求1所述的方法，其中，对所述具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域，包括：
    对所述具有人脸的图像进行人脸识别，确定人脸对应的矩形框；
    在所述矩形框中提取人脸轮廓；以及
    将所述人脸轮廓作为所述人脸区域，图像中的其他区域作为环境光区域。
  5. 根据权利要求1所述的方法，其中，确定人脸区域的人脸决定点以及环境光区域的环境光决定点，包括：
    将所述具有人脸的图像划分为256个宏块，并计算每个宏块色彩的红/绿比值和蓝/绿比值；
    根据所述宏块的红/绿比值和蓝/绿比值以及光源的红/绿比值范围和蓝/绿比值范围，确定落灰区的宏块为灰区宏块；以及
    根据人脸区域的灰区宏块的红/绿比值和蓝/绿比值计算人脸决定点，并且根据环境光区域的灰区宏块的红/绿比值和蓝/绿比值计算环境光决定点。
  6. 一种具有人脸的图像处理装置，包括：
    至少一个处理器；以及，
    存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的程序，所述程序包括：
    图像获取模块，设置为获取当前拍摄场景中具有人脸的图像；
    区域识别模块，设置为对所述具有人脸的图像进行人脸识别，得到人脸区域以及除人脸区域之外的环境光区域；
    决定点确定模块，设置为确定人脸区域的人脸决定点以及环境光区域的环境光决定点；
    白平衡参数调整模块，设置为根据所述人脸决定点、环境光决定点以及设定距离阀值，调整白平衡参数；以及
    图像调整模块，设置为根据所述白平衡参数对所述具有人脸的图像进行调整。
  7. 根据权利要求6所述的装置，其中，所述白平衡参数调整模块，包括：
    决定点距离计算单元，设置为计算所述人脸决定点和环境光决定点之间的决定点距离；
    白平衡参数调整单元，设置为根据所述决定点距离与所述设定距离阀值的大小关系，调整所述白平衡参数。
  8. 根据权利要求7所述的装置，其中，所述白平衡参数调整单元，还设置为：
    当所述人脸决定点和所述环境光决定点之间的距离大于所述设定距离阀值时，根据人脸决定点调整人脸区域的白平衡参数，并且根据环境光决定点调整环境光区域的白平衡参数；
    当所述人脸决定点以及所述环境光决定点之间的距离小于所述设定距离阀值时，根据整张图像落入灰带的点调整白平衡参数。
  9. 根据权利要求6所述的装置，其中，所述区域识别模块，包括：人脸矩形框确定单元、人脸轮廓提取单元以及区域划分单元；
    所述人脸矩形框确定单元，设置为对所述具有人脸的图像进行人脸识别，确定人脸对应的矩形框；
    所述人脸轮廓提取单元，设置为在所述矩形框中提取人脸轮廓；
    所述区域划分单元，设置为将所述人脸轮廓作为所述人脸区域，图像中的其他区域作为环境光区域。
  10. 根据权利要求6所述的装置，其中，所述决定点确定模块，包括：色彩比值计算单元、灰区宏块确定单元以及决定点计算单元；
    所述色彩比值计算单元，设置为将所述具有人脸的图像划分为256个宏块，并计算每个宏块色彩的红/绿比值和蓝/绿比值；
    所述灰区宏块确定单元，设置为根据所述宏块的红/绿比值和蓝/绿比值以及光源的红/绿比值范围和蓝/绿比值范围，确定落灰区的宏块为灰区宏块；
    所述决定点计算单元，设置为根据人脸区域的灰区宏块的红/绿比值和蓝/绿比值计算人脸决定点，并且根据环境光区域的灰区宏块的红/绿比值和蓝/绿比值计算环境光决定点。
  11. 一种非易失性计算机存储介质，存储有计算机可执行指令，所述计算机可执行指令用于执行权利要求1-5任一项的具有人脸的图像处理方法。
PCT/CN2016/088995 2015-12-08 2016-07-06 具有人脸的图像处理方法和装置 Ceased WO2017096865A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/243,447 US20170163953A1 (en) 2015-12-08 2016-08-22 Method and electronic device for processing image containing human face

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510896549.8 2015-12-08
CN201510896549.8A CN105894458A (zh) 2015-12-08 2015-12-08 一种具有人脸的图像处理方法和装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/243,447 Continuation US20170163953A1 (en) 2015-12-08 2016-08-22 Method and electronic device for processing image containing human face

Publications (1)

Publication Number Publication Date
WO2017096865A1 true WO2017096865A1 (zh) 2017-06-15

Family

ID=57002584

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/088995 Ceased WO2017096865A1 (zh) 2015-12-08 2016-07-06 具有人脸的图像处理方法和装置

Country Status (2)

Country Link
CN (1) CN105894458A (zh)
WO (1) WO2017096865A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109118427A (zh) * 2018-09-07 2019-01-01 Oppo广东移动通信有限公司 图像光效处理方法和装置、电子设备、存储介质
CN114092383A (zh) * 2020-08-24 2022-02-25 珠海全志科技股份有限公司 基于人脸图像的isp自适应调整控制方法以及装置
CN115035572A (zh) * 2022-05-27 2022-09-09 汤姆逊(广东)智能科技有限公司 人脸识别方法及装置
CN115118947A (zh) * 2021-03-23 2022-09-27 北京小米移动软件有限公司 图像的处理方法、装置、电子设备及存储介质
CN116962619A (zh) * 2022-04-12 2023-10-27 广州视源电子科技股份有限公司 图像显示效果的处理方法、装置、设备和存储介质

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106303250A (zh) * 2016-08-26 2017-01-04 维沃移动通信有限公司 一种图像处理方法及移动终端
CN106686308B (zh) * 2016-12-28 2018-02-16 平安科技（深圳）有限公司 图像焦距检测方法和装置
CN107295324A (zh) * 2017-06-16 2017-10-24 广东欧珀移动通信有限公司 白平衡处理方法、装置和终端设备
CN107343189B (zh) * 2017-07-10 2019-06-21 Oppo广东移动通信有限公司 白平衡处理方法和装置
CN107483906B (zh) * 2017-07-25 2019-03-19 Oppo广东移动通信有限公司 图像的白平衡处理方法、装置和终端设备
CN107396079B (zh) * 2017-08-31 2019-06-07 Oppo广东移动通信有限公司 白平衡调整方法和装置
CN107580205B (zh) * 2017-08-31 2019-06-07 Oppo广东移动通信有限公司 白平衡调整方法和装置
CN108012135B (zh) * 2017-12-25 2019-09-06 Oppo广东移动通信有限公司 图像处理方法及装置、计算机可读存储介质和计算机设备
CN108182667B (zh) * 2017-12-29 2020-07-17 珠海大横琴科技发展有限公司 一种图像优化方法、终端及计算机可读存储介质
CN108200347A (zh) * 2018-01-30 2018-06-22 努比亚技术有限公司 一种图像处理方法、终端和计算机可读存储介质
CN108364254B (zh) * 2018-03-20 2021-07-23 北京奇虎科技有限公司 图像处理方法、装置及电子设备
CN109446945B (zh) * 2018-10-15 2021-03-02 Oppo广东移动通信有限公司 三维模型处理方法和装置、电子设备、计算机可读存储介质
CN110012277B (zh) * 2019-04-09 2021-06-25 成都品果科技有限公司 一种针对人像图像的自动白平衡方法及装置
CN110647178A (zh) * 2019-10-12 2020-01-03 鑫喆喆 医院消毒直饮水实时水量调节系统及方法
CN111447354B (zh) * 2019-10-23 2020-10-27 岳阳县辉通物联网科技有限公司 智能调整式摄像平台
CN111445439B (zh) * 2020-02-26 2024-05-07 北京大米未来科技有限公司 图像分析方法、装置、电子设备及介质
CN112488933B (zh) * 2020-11-26 2024-06-18 有半岛(北京)信息科技有限公司 一种视频的细节增强方法、装置、移动终端和存储介质
CN113676715B (zh) * 2021-08-23 2022-12-06 展讯半导体(南京)有限公司 图像处理方法及装置
CN119342360B (zh) * 2024-12-20 2025-04-29 深圳市维海德技术股份有限公司 白平衡处理方法、装置、设备、存储介质及程序产品

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101350883A (zh) * 2007-07-17 2009-01-21 富士胶片株式会社 自动白平衡校正值计算装置、方法、程序以及摄像装置
CN101448085A (zh) * 2008-12-26 2009-06-03 北京中星微电子有限公司 一种支持人脸检测的摄像处理方法和系统
CN103310214A (zh) * 2012-03-12 2013-09-18 联想(北京)有限公司 图像处理方法和设备
CN104796683A (zh) * 2014-01-22 2015-07-22 中兴通讯股份有限公司 一种校准图像色彩的方法和系统
CN104994362A (zh) * 2015-07-02 2015-10-21 广东欧珀移动通信有限公司 白平衡处理的方法及装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7728880B2 (en) * 2004-06-25 2010-06-01 Qualcomm Incorporated Automatic white balance method and apparatus
KR101092539B1 (ko) * 2005-02-18 2011-12-14 삼성전자주식회사 화이트 밸런스를 자동 조정하는 영상장치 및 그의 화이트밸런스 조정 방법
KR100693412B1 (ko) * 2005-05-16 2007-03-09 주식회사 아이디테크 영상에서 감시대상의 눈을 검출하는 방법
JP5021338B2 (ja) * 2007-03-02 2012-09-05 富士フイルム株式会社 ホワイトバランス補正装置および方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101350883A (zh) * 2007-07-17 2009-01-21 富士胶片株式会社 自动白平衡校正值计算装置、方法、程序以及摄像装置
CN101448085A (zh) * 2008-12-26 2009-06-03 北京中星微电子有限公司 一种支持人脸检测的摄像处理方法和系统
CN103310214A (zh) * 2012-03-12 2013-09-18 联想(北京)有限公司 图像处理方法和设备
CN104796683A (zh) * 2014-01-22 2015-07-22 中兴通讯股份有限公司 一种校准图像色彩的方法和系统
CN104994362A (zh) * 2015-07-02 2015-10-21 广东欧珀移动通信有限公司 白平衡处理的方法及装置

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109118427A (zh) * 2018-09-07 2019-01-01 Oppo广东移动通信有限公司 图像光效处理方法和装置、电子设备、存储介质
CN109118427B (zh) * 2018-09-07 2023-05-05 Oppo广东移动通信有限公司 图像光效处理方法和装置、电子设备、存储介质
CN114092383A (zh) * 2020-08-24 2022-02-25 珠海全志科技股份有限公司 基于人脸图像的isp自适应调整控制方法以及装置
CN115118947A (zh) * 2021-03-23 2022-09-27 北京小米移动软件有限公司 图像的处理方法、装置、电子设备及存储介质
CN115118947B (zh) * 2021-03-23 2023-11-24 北京小米移动软件有限公司 图像的处理方法、装置、电子设备及存储介质
CN116962619A (zh) * 2022-04-12 2023-10-27 广州视源电子科技股份有限公司 图像显示效果的处理方法、装置、设备和存储介质
CN115035572A (zh) * 2022-05-27 2022-09-09 汤姆逊(广东)智能科技有限公司 人脸识别方法及装置

Also Published As

Publication number Publication date
CN105894458A (zh) 2016-08-24

Similar Documents

Publication Publication Date Title
WO2017096865A1 (zh) 具有人脸的图像处理方法和装置
US20170163953A1 (en) Method and electronic device for processing image containing human face
CN111402135B (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
US11030481B2 (en) Method and apparatus for occlusion detection on target object, electronic device, and storage medium
US10783354B2 (en) Facial image processing method and apparatus, and storage medium
CN107730445B (zh) 图像处理方法、装置、存储介质和电子设备
JP6961797B2 (ja) プレビュー写真をぼかすための方法および装置ならびにストレージ媒体
CN108537155B (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
CN108875619B (zh) 视频处理方法和装置、电子设备、计算机可读存储介质
US20190147598A1 (en) Image processing apparatus, image processing method, and computer-readable storage medium
US9135726B2 (en) Image generation apparatus, image generation method, and recording medium
CN106878695A (zh) 白平衡处理的方法、装置和计算机设备
WO2018103244A1 (zh) 直播视频处理方法、装置及电子设备
CN107808137A (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
CN104978710A (zh) 一种基于拍照识别调节人脸亮度的方法和装置
WO2020227945A1 (en) Photographing method and apparatus
CN104883504A (zh) 开启智能终端上高动态范围hdr功能的方法及装置
CN107871309A (zh) 检测方法以及检测装置
CN110710194A (zh) 一种曝光方法、装置及摄像模组、电子设备
CN110580435A (zh) 脸部识别系统以及加强脸部识别方法
CN108810406A (zh) 人像光效处理方法、装置、终端及计算机可读存储介质
CN111222506A (zh) 颜色识别方法、设备及计算机可读存储介质
CN108063891A (zh) 图像处理方法、装置、计算机可读存储介质和计算机设备
WO2015145917A1 (ja) 画像補正装置、画像補正方法およびプログラム記録媒体
CN106331661A (zh) 白平衡处理方法及装置

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: 16872066

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: 16872066

Country of ref document: EP

Kind code of ref document: A1