WO2019019870A1 - 图像的白平衡处理方法、装置和终端设备 - Google Patents

图像的白平衡处理方法、装置和终端设备 Download PDF

Info

Publication number
WO2019019870A1
WO2019019870A1 PCT/CN2018/094086 CN2018094086W WO2019019870A1 WO 2019019870 A1 WO2019019870 A1 WO 2019019870A1 CN 2018094086 W CN2018094086 W CN 2018094086W WO 2019019870 A1 WO2019019870 A1 WO 2019019870A1
Authority
WO
WIPO (PCT)
Prior art keywords
color
white balance
image
balance processing
face
Prior art date
Application number
PCT/CN2018/094086
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
Priority to EP18837675.0A priority Critical patent/EP3657785B1/en
Publication of WO2019019870A1 publication Critical patent/WO2019019870A1/zh
Priority to US16/747,289 priority patent/US11277595B2/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N9/00Details of colour television systems
    • H04N9/64Circuits for processing colour signals
    • H04N9/73Colour balance circuits, e.g. white balance circuits or colour temperature control
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80Camera processing pipelines; Components thereof
    • H04N23/84Camera processing pipelines; Components thereof for processing colour signals
    • H04N23/88Camera processing pipelines; Components thereof for processing colour signals for colour balance, e.g. white-balance circuits or colour temperature control
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/90Determination of colour characteristics
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30196Human being; Person
    • G06T2207/30201Face

Definitions

  • the present disclosure relates to the field of mobile terminal technologies, and in particular, to a white balance processing method, apparatus, and terminal device for an image.
  • white balance adjustment is required to perform color reproduction.
  • various white balance algorithms in the prior art which can be used to calculate a gain value, and white balance processing is performed based on the gain value.
  • the user-set method is often adopted, and the user selects it.
  • such a user setting manner in the prior art may easily cause the white balance algorithm to not match the actual scene, resulting in a problem that the white balance processing effect is poor.
  • the present disclosure proposes a white balance processing method for an image, which is used to solve the technical problems in the prior art.
  • the present disclosure proposes an image white balance processing apparatus.
  • the present disclosure proposes a terminal device.
  • the present disclosure proposes a computer readable storage medium.
  • the first aspect of the present disclosure provides a white balance processing method for an image, where the content of the image includes a human face, including the following steps:
  • the face white balance algorithm is configured to adjust a face in the image to a skin color
  • the image is white balanced according to the face white balance algorithm.
  • the white balance processing method of the image of the embodiment of the present disclosure extracts a color feature by using a background region in the image, where the color feature is used to indicate the color distribution of the background region.
  • the applicable condition of the face white balance algorithm is matched. If the color feature matches the applicable condition, the image is white balanced according to the face white balance algorithm for adjusting the face in the image to the skin color.
  • the color feature of the image is matched with the applicable conditions of the algorithm to determine whether the image is suitable for the face white balance algorithm.
  • the embodiment of the second aspect of the present disclosure provides a white balance processing apparatus for an image, the content of the image includes a human face, and the apparatus includes:
  • An extraction module configured to extract a color feature for a background region in the image; wherein the color feature is used to indicate a color distribution of the background region;
  • a matching module configured to match an applicable condition of the face white balance algorithm according to the color feature;
  • the face white balance algorithm is configured to adjust a face in the image to a skin color;
  • a processing module configured to perform white balance processing on the image according to the face white balance algorithm if the color feature matches the applicable condition.
  • the white balance processing device for an image of the embodiment of the present disclosure extracts a color feature by using a background region in the image, where the color feature is used to indicate a color distribution of the background region.
  • the applicable condition of the face white balance algorithm is matched. If the color feature matches the applicable condition, the image is white balanced according to the face white balance algorithm for adjusting the face in the image to the skin color.
  • the color feature of the image is matched with the applicable conditions of the algorithm to determine whether the image is suitable for the face white balance algorithm.
  • a third aspect of the present disclosure provides a terminal device including one or more of the following components: a housing and a processor, a memory, and a camera located in the housing, wherein the memory stores executable program code.
  • the processor runs a program corresponding to the executable program code by reading executable program code stored in the memory for performing a white balance processing method of the image of the first aspect.
  • the terminal device of the embodiment of the present disclosure extracts a color feature by using a background region in the image, where the color feature is used to indicate the color distribution of the background region.
  • the applicable condition of the face white balance algorithm is matched. If the color feature matches the applicable condition, the image is white balanced according to the face white balance algorithm for adjusting the face in the image to the skin color.
  • the color feature of the image is matched with the applicable conditions of the algorithm to determine whether the image is suitable for the face white balance algorithm.
  • a fourth aspect of the present disclosure provides a computer readable storage medium having stored thereon a computer program, characterized in that the program implements a white balance processing method of an image according to the first aspect when executed by a processor.
  • a computer readable storage medium of an embodiment of the present disclosure extracts a color feature by using a background region in an image, where the color feature is used to indicate a color distribution of the background region.
  • the applicable condition of the face white balance algorithm is matched. If the color feature matches the applicable condition, the image is white balanced according to the face white balance algorithm for adjusting the face in the image to the skin color.
  • the color feature of the image is matched with the applicable conditions of the algorithm to determine whether the image is suitable for the face white balance algorithm.
  • FIG. 1 is a flowchart of a white balance processing method of an image provided according to an embodiment of the present disclosure
  • FIG. 2 is a flowchart of a white balance processing method of an image according to another embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of a white balance processing apparatus for an image according to an embodiment of the present disclosure
  • FIG. 4 is a schematic structural diagram of a white balance processing apparatus for an image according to another embodiment of the present disclosure.
  • FIG. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure.
  • FIG. 1 is a flowchart of a white balance processing method for an image according to an embodiment of the present disclosure.
  • the image in this embodiment includes a human face in the content of the image.
  • the method includes:
  • Step 101 Extract a color feature from a background area in the image.
  • the color feature is used to indicate the color distribution of the background area.
  • Color center and degree of color concentration are used as the color feature.
  • the position with the highest pixel density can be used as the color center, and the pixel density is lowered to a position where the pixel density is half of the color center.
  • the edge of the color concentration area the color center is measured from the edge. Distance, as a degree of concentration.
  • the color space is divided into a plurality of regions, and then, for the background regions in the image, the distribution positions of the pixel points in the background region in the preset color space are determined, for each The area performs statistics to determine the number of pixels contained in each area. For the area where the number of pixels is more than the threshold number, the color of the center of the area is taken as the center color. The number of pixels included in the area is concentrated.
  • Step 102 Match the applicable conditions of the face white balance algorithm according to the color feature.
  • the face white balance algorithm is used to adjust the face in the image to the skin color.
  • the face white balance algorithm can be applied to multiple scenarios.
  • corresponding applicable conditions can be separately established for each scenario. Match color features to each of the applicable conditions.
  • the face white balance algorithm is used to adjust the face in the image to the skin tone.
  • the color components of all the pixels in the face region are obtained, and the color of each pixel is represented by a (R, G, B) color vector, and the color vector of each pixel is averaged.
  • Calculate the color vector corresponding to the skin color of the face. Determine whether the R, G, and B values corresponding to the skin color of the face are within the range of R, G, and B values corresponding to the normal face color, and if not within the range of R, G, and B values corresponding to the normal face color, pass a gain.
  • the value adjusts the R, G, and B values corresponding to the skin color of the face so as to be within the range of R, G, and B values corresponding to the normal human skin color, and the gain value is the first gain value.
  • R, G, and B values for the normal face color matching can be confirmed according to the R, G, and B values provided in the color matrix CC, wherein the R, G, and B values in the color matrix CC can be according to the International Commission on Illumination.
  • the CIE color space provided by (Commission Internationale de L'Eclairage) is available.
  • the second gain value is calculated.
  • the second gain value calculated here is different from the first gain value.
  • the average value of the saturation of each color component tends to the same gray value, so that the mean values of the three components R, G, and B in the color vector of all the pixels tend to be balanced (1:1: 1)
  • the white balance gain value that is, the second gain value.
  • the portrait area is divided into a plurality of sub-blocks, and color vectors of all the pixels in each sub-block are obtained.
  • Each pixel is represented by a (R, G, B) color vector, and then R, G, B in each sub-block are calculated.
  • the mean and standard deviation of the three channels then weighting the standard deviation of each sub-block (discarding the sub-blocks with low correlation, retaining the sub-blocks with high correlation) to reduce the influence of the large single color, so that the image Colorful colors. Then, the average values of the three channels R, G, and B weighted by the standard deviation are calculated, and the gain coefficients of the three channels R, G, and B are finally calculated, that is, the second gain value is obtained.
  • the weights of the first gain value and the second gain value are determined.
  • the first gain value and the second gain value are weighted according to the calculated weights to obtain a final white balance gain value of the face gain algorithm. According to this, white balance processing is performed.
  • Step 103 If the color feature matches the applicable condition, perform white balance processing on the image according to the face white balance algorithm.
  • the image is applied to the face white balance algorithm.
  • the applicable condition is multiple. If the color feature matches at least one applicable condition, the image is applicable to the face white balance algorithm. Further, the image may be white balanced according to a face white balance algorithm for adjusting a face in the image to a skin color.
  • the white balance processing method of the image extracts a color feature by using a background region in the image, where the color feature is used to indicate the color distribution of the background region.
  • the applicable condition of the face white balance algorithm is matched. If the color feature matches the applicable condition, the image is white balanced according to the face white balance algorithm for adjusting the face in the image to the skin color.
  • the color feature of the image is matched with the applicable conditions of the algorithm to determine whether the image is suitable for the face white balance algorithm.
  • FIG. 2 is a flowchart of a white balance processing method for an image according to another embodiment of the present disclosure. Compared with the previous embodiment, the present embodiment provides applicable conditions for various facial white balance algorithms.
  • the method includes:
  • Step 201 When the content of the image includes a human face, determine a distribution position of the pixel points in the background region in the preset color space for the background region in the image.
  • the color space can be varied, for example:
  • RGB red, green, blue
  • HSI color space which is derived from a human visual system, and describes colors by Hue, Saturation or Chroma, and Intensity or Brightness.
  • the HSI color space can be described by a conical space model.
  • Step 202 Perform statistics on the distribution position to obtain a color center and a color concentration degree in the distribution position, and use the color center and the corresponding concentration degree as color features.
  • the position with the highest pixel dot density can be used as the color center, and the pixel dot density is lowered to a position where the pixel dot density is half of the color center, and the color center distance is measured as the edge of the color concentration region. The distance of the edge as a degree of concentration.
  • Step 203 Acquire an applicable condition corresponding to the optical scene, an applicable condition corresponding to the green plant scene, and an applicable condition corresponding to the solid color background, so as to match the color feature with the plurality of applicable conditions.
  • the face white balance algorithm can be applied to multiple scenarios. For each scenario, corresponding applicable conditions are preset for describing the color features of the corresponding scene. If the color feature of the image matches the color feature of a scene, the image is suitable for the face white balance algorithm.
  • Step 204 Match the color features of the extracted image with the applicable conditions corresponding to the mixed light scene.
  • the applicable conditions corresponding to the mixed light scene are set, including:
  • the background area contains at least two color centers whose color concentration is above a threshold.
  • Step 205 Match the color features of the extracted image with the applicable conditions corresponding to the green plant scene.
  • the applicable conditions corresponding to the green plant scene are set, including:
  • the background area includes at least two color centers
  • At least one color center of the at least two color centers is located in a target area of the color space, and the degree of color concentration is lower than a threshold.
  • the target area here is the target area corresponding to green.
  • Step 206 Match the color features of the extracted image with the applicable conditions corresponding to the solid color background.
  • the applicable conditions corresponding to the solid scene are set, including:
  • the background area contains a single color center, and the color center is more concentrated than the threshold.
  • the solid color background may cause interference to the traditional gray space algorithm, the color reproduction degree is not high, and the white balance effect is not ideal. If the image contains a human face, it is more suitable to perform white balance processing on the image using the face white balance algorithm.
  • step 207 it is determined whether there is a matching applicable condition. If the step 208 is performed, otherwise step 209 is performed.
  • Step 208 Perform white balance processing on the image by using a face white balance algorithm.
  • Step 209 Perform white balance processing on the image according to a grayscale world algorithm.
  • the image is white balanced according to the gray world algorithm.
  • the human visual system has color constancy, and can obtain the invariant characteristics of the surface color of the object from the changing illumination environment and imaging conditions, but the imaging device does not have such an adjustment function, and different illumination environments may result in the color and reality of the captured image. There is a certain degree of deviation in color, and it is necessary to select an appropriate white balance algorithm to eliminate the influence of the illumination environment on color appearance.
  • the gray-scale world algorithm is based on the gray-scale world assumption. This assumption is that for an image with a large number of color variations, the average of the three components of RGB tends to the same gray value. In the physical sense, the gray world method assumes that the mean of the average reflection of the natural scene on the light is generally a fixed value, which is approximately "grey". The color balance algorithm enforces this assumption on the image to be processed, and the effect of ambient light can be removed from the image to obtain the original scene image.
  • the color feature is extracted by the background region in the image, where the color feature is used to indicate the color distribution of the background region.
  • the applicable condition of the face white balance algorithm is matched. If the color feature matches the applicable condition, the image is white balanced according to the face white balance algorithm for adjusting the face in the image to the skin color.
  • the color feature of the image is matched with the applicable conditions of the algorithm to determine whether the image is suitable for the face white balance algorithm.
  • FIG. 3 is a schematic structural diagram of a white balance processing device for an image according to an embodiment of the present disclosure.
  • the content of the image includes a human face, as shown in the figure.
  • the apparatus includes an extraction module 31, a matching module 32, and a processing module 33.
  • the extracting module 31 is configured to extract a color feature from a background region in the image.
  • the color feature is used to indicate a color distribution of the background region.
  • the matching module 32 is configured to match an applicable condition of the face white balance algorithm according to the color feature.
  • the face white balance algorithm is used to adjust the face in the image to the skin color.
  • the processing module 33 is configured to perform white balance processing on the image according to the face white balance algorithm if the color feature matches the applicable condition.
  • the applicable condition is multiple.
  • the color feature matches at least one applicable condition, determining that the image is applicable to the face white balance algorithm, and further, according to the face white balance algorithm, The image is white balanced.
  • processing module 33 is further configured to match the applicable condition of the face white balance algorithm, if the color feature does not match the applicable condition, the image is white balanced according to the gray world algorithm.
  • the white balance processing device of the image of the embodiment extracts a color feature by using a background region in the image, where the color feature is used to indicate the color distribution of the background region.
  • the applicable condition of the face white balance algorithm is matched. If the color feature matches the applicable condition, the image is white balanced according to the face white balance algorithm for adjusting the face in the image to the skin color. Because the color feature of the image is matched with the applicable condition of the algorithm, whether the image is suitable for the face white balance algorithm is determined, and the technical problem that the white balance processing effect caused by the artificial setting algorithm in the prior art is poor is solved.
  • the extraction module 31 is shown in FIG. Further, the method may further include: a determining unit 311, a counting unit 312, and a generating unit 313.
  • the determining unit 311 is configured to determine a distribution position of the pixel point in the background area in the preset color space for the background area in the image.
  • the statistic unit 312 is configured to perform statistics on the distribution locations to obtain a color center and a color concentration degree in the distribution location.
  • the statistics unit is further configured to:
  • the position of the highest pixel density is used as the color center in the preset color space, and then the pixel density is lowered to half of the highest pixel density as the edge of the color concentration area, and finally determined according to the distance from the edge of the color center.
  • the degree of color concentration in the center of the color is used as the color center in the preset color space, and then the pixel density is lowered to half of the highest pixel density as the edge of the color concentration area, and finally determined according to the distance from the edge of the color center. The degree of color concentration in the center of the color.
  • the statistics unit is further configured to:
  • the generating unit 313 is configured to use the color center and the corresponding concentration degree as the color feature.
  • the applicable conditions are at least one of: an applicable condition corresponding to the mixed light scene, an applicable condition corresponding to the green plant scene, and an applicable condition corresponding to the solid color background.
  • the applicable condition corresponding to the mixed light scene includes: the background area includes at least two color centers whose color concentration is higher than a threshold.
  • the applicable condition corresponding to the green plant scene includes: the background area includes at least two color centers; and at least one color center of the at least two color centers is located in the target area of the color space, and the color concentration is lower than Threshold.
  • the applicable conditions corresponding to the solid color background include: the background area includes a single color center, and the color center of the color center is higher than a threshold.
  • FIG. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure.
  • the terminal device 1000 includes: a housing 1100 and A camera 1113, a memory 1114, and a processor 1115 in the housing 1100.
  • the memory 1114 stores executable program code; the processor 1115 runs a program corresponding to the executable program code by reading the executable program code stored in the memory 1114 for performing the following steps:
  • the face white balance algorithm is configured to adjust a face in the image to a skin color
  • the image is white balanced according to the face white balance algorithm.
  • the white balance processing method of the image extracts a color feature by using a background region in the image, where the color feature is used to indicate the color distribution of the background region.
  • the applicable condition of the face white balance algorithm is matched. If the color feature matches the applicable condition, the image is white balanced according to the face white balance algorithm for adjusting the face in the image to the skin color.
  • the color feature of the image is matched with the applicable conditions of the algorithm to determine whether the image is suitable for the face white balance algorithm.
  • the present disclosure also proposes a computer readable storage medium having stored thereon a computer program that, when executed by a processor, implements white balance processing of an image as described in the first aspect of the embodiment. method.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Color Television Image Signal Generators (AREA)
  • Processing Of Color Television Signals (AREA)
  • Color Image Communication Systems (AREA)
  • Image Processing (AREA)

Abstract

本公开公开了一种图像的白平衡处理方法、装置和终端设备,涉及移动终端技术领域,其中,方法包括:图像的白平衡处理方法,通过对图像中的背景区域,提取色彩特征,这里的色彩特征用于指示背景区域色彩分布情况。根据色彩特征,匹配人脸白平衡算法的适用条件,若该色彩特征与适用条件匹配,则根据用于将图像中的人脸调整至肤色的人脸白平衡算法,对图像进行白平衡处理。由于采用了图像的色彩特征与算法适用条件匹配的方式,判断图像是否适用于人脸白平衡算法,解决了现有技术中人为设定算法导致的白平衡处理效果较差的技术问题。

Description

图像的白平衡处理方法、装置和终端设备
相关申请的交叉引用
本申请要求OPPO广东移动通信有限公司于2017年7月25日提交的、公开名称为“图像的白平衡处理方法、装置和终端设备”的、中国专利申请号“201710612885.4”的优先权。
技术领域
本公开涉及移动终端技术领域,尤其涉及一种图像的白平衡处理方法、装置和终端设备。
背景技术
用户在进行拍摄的时候,往往会遇到图像偏色的问题。比如,在日光灯的房间里拍摄的影像会显得发绿,在室内钨丝灯光下拍摄出来的景物就会偏黄,而在日光阴影处拍摄到的照片则可能偏蓝。
为了解决这种偏色问题,需要进行白平衡调整,从而进行色彩还原。现有技术中存在多种白平衡算法,均可用于计算出增益值,基于该增益值进行白平衡处理。但具体采用哪一种算法进行增益值的计算,现有技术中往往采用用户设定的方式,由用户进行选择。但现有技术中的这种用户设定方式,容易导致白平衡算法与实际场景不匹配,导致白平衡处理效果较差的问题。
公开内容
本公开提出一种图像的白平衡处理方法,该方法,用于解决现有技术中的技术问题。
本公开提出一种图像的白平衡处理装置。
本公开提出一种终端设备。
本公开提出一种计算机可读存储介质。
本公开第一方面实施例提出了一种图像的白平衡处理方法,图像的内容包括人脸,包括以下步骤:
对所述图像中的背景区域,提取色彩特征;其中,所述色彩特征用于指示所述背景区域色彩分布情况;
根据所述色彩特征,匹配人脸白平衡算法的适用条件;所述人脸白平衡算法用于将所 述图像中的人脸调整至肤色;
若所述色彩特征与所述适用条件匹配,根据所述人脸白平衡算法,对所述图像进行白平衡处理。
本公开实施例的图像的白平衡处理方法,通过对图像中的背景区域,提取色彩特征,这里的色彩特征用于指示背景区域色彩分布情况。根据色彩特征,匹配人脸白平衡算法的适用条件,若该色彩特征与适用条件匹配,则根据用于将图像中的人脸调整至肤色的人脸白平衡算法,对图像进行白平衡处理。采用了图像的色彩特征与算法适用条件匹配的方式,判断图像是否适用于人脸白平衡算法。
本公开第二方面实施例提出了一种图像的白平衡处理装置,图像的内容包括人脸,所述装置包括:
提取模块,用于对所述图像中的背景区域,提取色彩特征;其中,所述色彩特征用于指示所述背景区域色彩分布情况;
匹配模块,用于根据所述色彩特征,匹配人脸白平衡算法的适用条件;所述人脸白平衡算法用于将所述图像中的人脸调整至肤色;
处理模块,用于若所述色彩特征与所述适用条件匹配,根据所述人脸白平衡算法,对所述图像进行白平衡处理。
本公开实施例的图像的白平衡处理装置,图像的白平衡处理方法,通过对图像中的背景区域,提取色彩特征,这里的色彩特征用于指示背景区域色彩分布情况。根据色彩特征,匹配人脸白平衡算法的适用条件,若该色彩特征与适用条件匹配,则根据用于将图像中的人脸调整至肤色的人脸白平衡算法,对图像进行白平衡处理。采用了图像的色彩特征与算法适用条件匹配的方式,判断图像是否适用于人脸白平衡算法。
本公开第三方面实施例提出了一种终端设备,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、摄像头,其中,所述存储器存储有可执行程序代码,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,以用于执行第一方面所述的图像的白平衡处理方法。
本公开实施例的终端设备,通过对图像中的背景区域,提取色彩特征,这里的色彩特征用于指示背景区域色彩分布情况。根据色彩特征,匹配人脸白平衡算法的适用条件,若该色彩特征与适用条件匹配,则根据用于将图像中的人脸调整至肤色的人脸白平衡算法,对图像进行白平衡处理。采用了图像的色彩特征与算法适用条件匹配的方式,判断图像是否适用于人脸白平衡算法。
本公开第四方面实施例提出了一种计算机可读存储介质,其上存储有计算机程序,其特征在于,该程序被处理器执行时实现第一方面所述的图像的白平衡处理方法。
本公开实施例的计算机可读存储介质,通过对图像中的背景区域,提取色彩特征,这里的色彩特征用于指示背景区域色彩分布情况。根据色彩特征,匹配人脸白平衡算法的适用条件,若该色彩特征与适用条件匹配,则根据用于将图像中的人脸调整至肤色的人脸白平衡算法,对图像进行白平衡处理。采用了图像的色彩特征与算法适用条件匹配的方式,判断图像是否适用于人脸白平衡算法。
本公开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,或通过本公开的实践了解到。
附图说明
本公开上述的和/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是根据本公开一个实施例提供的图像的白平衡处理方法的流程图;
图2是根据本公开另一个实施例提供的图像的白平衡处理方法的流程图;
图3是根据本公开一个实施例提供的图像的白平衡处理装置的结构示意图;
图4是根据本公开另一个实施例提供的图像的白平衡处理装置的结构示意图;以及
图5是根据本公开一个实施例提供的终端设备的结构示意图。
具体实施方式
下面详细描述本公开的实施例,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,旨在用于解释本公开,而不能理解为对本公开的限制。
下面参考附图描述本公开实施例的图像的白平衡处理方法、装置和终端设备。
图1是根据本公开一个实施例提供的图像的白平衡处理方法的流程图,本实施例中的图像,该图像的内容中包括人脸,如图1所示,该方法包括:
步骤101,对图像中的背景区域,提取色彩特征。
其中,色彩特征用于指示所述背景区域色彩分布情况。
作为一种可能的实现方式,对所述图像中的背景区域,确定所述背景区域中的像素点在预设色彩空间中的分布位置,进而对所述分布位置进行统计,得到分布位置集中的色彩中心和色彩集中程度;将所述色彩中心和所述集中程度,作为所述色彩特征。具体在确定色彩中心时,可以将像素点密度最高的位置,作为色彩中心,将像素点密度下降至色彩中心处像素点密度一半的位置,作为色彩集中区的边缘,测量色彩中心距离该边缘的距离,作为集中程度。
作为另一种可能的实现方式,将色彩空间划分为多个区域,进而对所述图像中的背景区域,确定所述背景区域中的像素点在预设色彩空间中的分布位置,针对每一个区域进行统计,确定每一个区域内所含的像素点的个数。针对像素点个数多于阈值个数的区域,将该区域中心的色彩,作为中心色彩。将该区域所含的像素点的个数为集中程度。
步骤102,根据所述色彩特征,匹配人脸白平衡算法的适用条件。
其中,人脸白平衡算法用于将所述图像中的人脸调整至肤色。
具体地,人脸白平衡算法可以适用于多种场景,作为一种可能的实现方式,可以分别针对每一种场景建立对应的适用条件。将色彩特征与每一条适用条件进行匹配。
为了便于理解,下面对人脸白平衡算法进行简要介绍。
人脸白平衡算法用于将图像中的人脸调整至肤色。作为一种可能的实现方式,获取人脸区域的所有像素点的颜色分量,每个像素点的颜色由一个(R,G,B)颜色向量表示,对各像素点的颜色向量取平均,可计算得到人脸肤色对应的颜色向量。判断人脸肤色对应的R,G,B值是否在正常人脸肤色对应的R,G,B值范围内,如果不在正常人脸肤色对应的R,G,B值范围内,则通过一个增益值调整人脸肤色对应的R,G,B值,使其处于正常人脸肤色对应的R,G,B值范围内,该增益值即为第一增益值。
其中,正常人脸肤色对用的R,G,B值范围,可以根据色彩矩阵CC中提供的R,G,B值确认,其中,色彩矩阵CC中R,G,B值可以根据国际照明委员会(Commission Internationale de L'Eclairage)提供的CIE色彩空间得到。
进而采用灰度空间算法,计算得到第二增益值。一般来说,这里计算出的第二增益值不同于第一增益值。对于灰度空间算法,假设各颜色分量的饱和度的平均值趋于同一灰度值,从而所有像素点的颜色向量中的R,G,B三个分量的均值趋于平衡(1:1:1),基于此计算得到的白平衡增益值,即第二增益值。具体地,人像区域分成若干个子块,获取每个子块中所有像素点的颜色向量,每个像素点由一个(R,G,B)颜色向量表示,然后计算各子块中R,G,B三个通道的平均值和标准差,然后对每一个子块的标准差进行加权(舍弃相关性小的子块,保留相关性大的子块),以减少大块单一颜色的影响,使得图像颜色丰富多彩。进而计算通过标准差加权的R,G,B三个通道的平均值,最终计算得到R,G,B三个通道的增益系数,即得到第二增益值。
最后,根据人脸区域面积,确定第一增益值和第二增益值的权重,人脸区域面积越大,第一增益值的权重越大,人脸区域面积越小,第一增益值的权重越小。根据计算出的权重对第一增益值和第二增益值进行加权运算,得到该人脸增益算法最终的白平衡增益值。据此进行白平衡处理。
步骤103,若色彩特征与所述适用条件匹配,根据人脸白平衡算法,对所述图像进行 白平衡处理。
具体地,当色彩特征与所述适用条件匹配,说明图像适用于人脸白平衡算法。作为一种可能的实现方式,适用条件为多个,若色彩特征与至少一个适用条件匹配,则说明图像适用于人脸白平衡算法。进而可以根据用于将所述图像中的人脸调整至肤色的人脸白平衡算法,对所述图像进行白平衡处理。
本实施例中,图像的白平衡处理方法,通过对图像中的背景区域,提取色彩特征,这里的色彩特征用于指示背景区域色彩分布情况。根据色彩特征,匹配人脸白平衡算法的适用条件,若该色彩特征与适用条件匹配,则根据用于将图像中的人脸调整至肤色的人脸白平衡算法,对图像进行白平衡处理。采用了图像的色彩特征与算法适用条件匹配的方式,判断图像是否适用于人脸白平衡算法
图2是根据本公开另一个实施例提供的图像的白平衡处理方法的流程图,相较于上一实施例,本实施例提供了多种人脸白平衡算法的适用条件。
如图2所示,该方法包括:
步骤201,当图像的内容包括人脸时,对图像中的背景区域,确定背景区域中的像素点在预设色彩空间中的分布位置。
色彩空间可以由多种,例如:
RGB(red,green,blue)颜色空间,基于设备三基色的颜色空间。
另外,还可以是HSI色彩空间,该HSI色彩空间是从人的视觉系统出发,用色调(Hue)、色饱和度(Saturation或Chroma)和亮度(Intensity或Brightness)来描述色彩。HSI色彩空间可以用一个圆锥空间模型来描述。
当然,还可以采用其他色彩空间进行描述,本实施例中对此不再赘述。
步骤202,对该分布位置进行统计,得到分布位置集中的色彩中心和色彩集中程度,并将色彩中心和对应的集中程度,作为色彩特征。
具体地,在确定色彩中心时,可以将像素点密度最高的位置,作为色彩中心,将像素点密度下降至色彩中心处像素点密度一半的位置,作为色彩集中区的边缘,测量色彩中心距离该边缘的距离,作为集中程度。
步骤203,获取光场景对应的适用条件、绿植场景对应的适用条件和纯色背景对应的适用条件,以将色彩特征分别与多个适用条件匹配。
具体地,人脸白平衡算法可以应用于多种场景下,针对每一种场景,预设了相应的适用条件,以用于对相应场景的色彩特征进行描述。若图像的色彩特征与某一场景的色彩特征匹配,则说明该图像适用于人脸白平衡算法。
步骤204,将提取到的图像的色彩特征与混光场景对应的适用条件匹配。
针对混光场景,也就是至少两种不同色温光源照射下成像的图像,为了对这一场景进行识别,设置了混光场景对应的适用条件,包括:
背景区域包含至少两个色彩集中程度高于阈值的色彩中心。
这是由于不同色温光源照射,例如:白炽灯和钨丝灯的混光照射,导致出现不同的偏色情况。从而在色彩空间中,呈现出与光源对应的色彩中心。
步骤205,将提取到的图像的色彩特征与绿植场景对应的适用条件匹配。
针对绿植场景,也就是包含大面积绿植的图像,设置了绿植场景对应的适用条件,包括:
所述背景区域包含至少两个色彩中心;
所述至少两个色彩中心中存在至少一个色彩中心位于所述色彩空间的目标区域内,且色彩集中程度低于阈值。
这里的目标区域为绿色对应的目标区域。
步骤206,将提取到的图像的色彩特征与纯色背景对应的适用条件匹配。
针对纯色背景场景,也就是包含大面积单一颜色的图像,设置了纯色场景对应的适用条件,包括:
背景区域包含单一色彩中心,且所述色彩中心的色彩集中程度高于阈值。
由于纯色背景对于传统的灰度空间算法可能会造成干扰,导致色彩还原度不高,白平衡效果不理想。若在图像包含人脸的情况下,比较适合采用人脸白平衡算法对图像进行白平衡处理。
步骤207,判断是否存在匹配的适用条件,若是执行步骤208,否则执行步骤209。
步骤208,采用人脸白平衡算法对图像进行白平衡处理。
具体地,人脸白平衡算法可参见前述实施例的相关描述,本实施例中对此不再赘述。
步骤209,根据灰度世界算法,对所述图像进行白平衡处理。
具体地,若各条适用条件均与图像的色彩特征不匹配,根据灰度世界算法,对所述图像进行白平衡处理。
为了便于理解,下面将对灰度世界算法进行简要介绍。
人的视觉系统具有颜色恒常性,能从变化的光照环境和成像条件下获取物体表面颜色的不变特性,但成像设备不具有这样的调节功能,不同的光照环境会导致采集的图像颜色与真实颜色存在一定程度的偏差,需要选择合适的白平衡算法,消除光照环境对颜色显现的影响。灰度世界算法以灰度世界假设为基础,该假设认为:对于一幅有着大量色彩变化的图像,RGB,三个分量的平均值趋于同一灰度值。从物理意义上讲,灰色世界法假设自然界景物对于光线的平均反射的均值在总体上是个定值,这个定值近似地为“灰色”。颜色平 衡算法将这一假设强制应用于待处理图像,可以从图像中消除环境光的影响,获得原始场景图像。
本实施例中,通过对图像中的背景区域,提取色彩特征,这里的色彩特征用于指示背景区域色彩分布情况。根据色彩特征,匹配人脸白平衡算法的适用条件,若该色彩特征与适用条件匹配,则根据用于将图像中的人脸调整至肤色的人脸白平衡算法,对图像进行白平衡处理。采用了图像的色彩特征与算法适用条件匹配的方式,判断图像是否适用于人脸白平衡算法。
为了实现上述实施例,本公开还提出了一种图像的白平衡处理装置,图3是根据本公开一个实施例提供的图像的白平衡处理装置的结构示意图,图像的内容包括人脸,如图3所示,装置包括:提取模块31、匹配模块32和处理模块33。
提取模块31,用于对所述图像中的背景区域,提取色彩特征。
其中,所述色彩特征用于指示所述背景区域色彩分布情况。
匹配模块32,用于根据所述色彩特征,匹配人脸白平衡算法的适用条件。
其中,人脸白平衡算法用于将所述图像中的人脸调整至肤色。
处理模块33,用于若所述色彩特征与所述适用条件匹配,根据所述人脸白平衡算法,对所述图像进行白平衡处理。
在本实施例一种可能的实现方式中,适用条件为多个,当色彩特征与至少一个适用条件匹配时,确定图像适用于所述人脸白平衡算法,进而根据人脸白平衡算法,对图像进行白平衡处理。
进一步地,处理模块33还用于匹配人脸白平衡算法的适用条件之后,若所述色彩特征与所述适用条件不匹配,根据灰度世界算法,对所述图像进行白平衡处理。
本实施例的图像的白平衡处理装置,通过对图像中的背景区域,提取色彩特征,这里的色彩特征用于指示背景区域色彩分布情况。根据色彩特征,匹配人脸白平衡算法的适用条件,若该色彩特征与适用条件匹配,则根据用于将图像中的人脸调整至肤色的人脸白平衡算法,对图像进行白平衡处理。由于采用了图像的色彩特征与算法适用条件匹配的方式,判断图像是否适用于人脸白平衡算法,解决了现有技术中人为设定算法导致的白平衡处理效果较差的技术问题。
需要说明的是,前述对方法实施例的描述,也适用于本公开实施例的装置,其实现原理类似,在此不再赘述。
进而,图4是根据本公开另一个实施例提供的图像的白平衡处理装置的结构示意图,如图4所示,在如图3所示的基础上,该白平衡处理装置中,提取模块31进一步还可包括: 确定单元311、统计单元312和生成单元313。
确定单元311,用于对所述图像中的背景区域,确定所述背景区域中的像素点在预设色彩空间中的分布位置。
统计单元312,用于对所述分布位置进行统计,得到分布位置集中的色彩中心和色彩集中程度。
在本实施例一种可能的实现方式中,统计单元还用于:
首先在预设色彩空间中将最高像素点密度的位置作为色彩中心,然后将像素点密度下降至最高像素点密度一半的位置,作为色彩集中区的边缘,最后根据色彩中心距离边缘的距离,确定色彩中心的色彩集中程度。
在本实施例另一种可能的实现方式中,统计单元还用于:
在预设色彩空间中确定划分得到的多个区域,然后针对每一个区域进行统计,以确定每一个区域所含的像素点个数,若区域所含像素点个数多于阈值个数,将对应区域的中心位置作为色彩中心,将对应区域所含像素点的个数作为色彩中心的色彩集中程度。
生成单元313,用于将所述色彩中心和对应的集中程度,作为所述色彩特征。
进一步地,本实施例中,适用条件为多个,包括:混光场景对应的适用条件、绿植场景对应的适用条件和纯色背景对应的适用条件中的至少一个。
其中,混光场景对应的适用条件,包括:所述背景区域包含至少两个色彩集中程度高于阈值的色彩中心。
绿植场景对应的适用条件,包括:所述背景区域包含至少两个色彩中心;所述至少两个色彩中心中存在至少一个色彩中心位于所述色彩空间的目标区域内,且色彩集中程度低于阈值。
纯色背景对应的适用条件,包括:所述背景区域包含单一色彩中心,且所述色彩中心的色彩集中程度高于阈值。
需要说明的是,前述对方法实施例的描述,也适用于本公开实施例的装置,其实现原理类似,在此不再赘述。
为了实现上述实施例,本公开还提出了一种终端设备,图5是根据本公开一个实施例提供的终端设备的结构示意图,如图5所示,该终端设备1000包括:壳体1100和位于壳体1100内的摄像头1113、存储器1114和处理器1115。
其中,存储器1114存储有可执行程序代码;处理器1115通过读取存储器1114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,以用于执行以下步骤:
对所述图像中的背景区域,提取色彩特征;其中,所述色彩特征用于指示所述背景区 域色彩分布情况;
根据所述色彩特征,匹配人脸白平衡算法的适用条件;所述人脸白平衡算法用于将所述图像中的人脸调整至肤色;
若所述色彩特征与所述适用条件匹配,根据所述人脸白平衡算法,对所述图像进行白平衡处理。
需要说明的是,前述对方法实施例的描述,也适用于本公开实施例的终端设备1000,其实现原理类似,在此不再赘述。
综上所述,本公开实施例的终端设备,图像的白平衡处理方法,通过对图像中的背景区域,提取色彩特征,这里的色彩特征用于指示背景区域色彩分布情况。根据色彩特征,匹配人脸白平衡算法的适用条件,若该色彩特征与适用条件匹配,则根据用于将图像中的人脸调整至肤色的人脸白平衡算法,对图像进行白平衡处理。采用了图像的色彩特征与算法适用条件匹配的方式,判断图像是否适用于人脸白平衡算法。
为了实现上述实施例,本公开还提出了提出了一种计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现如第一方面实施例所述的图像的白平衡处理方法。
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公开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。
尽管上面已经示出和描述了本公开的实施例,可以理解的是,上述实施例是示例性的,不能理解为对本公开的限制,本领域的普通技术人员在本公开的范围内可以对上述实施例进行变化、修改、替换和变型

Claims (20)

  1. 一种图像的白平衡处理方法,其特征在于,图像的内容包括人脸,所述方法包括以下步骤:
    对所述图像中的背景区域,提取色彩特征;其中,所述色彩特征用于指示所述背景区域色彩分布情况;
    根据所述色彩特征,匹配人脸白平衡算法的适用条件;所述人脸白平衡算法用于将所述图像中的人脸调整至肤色;
    若所述色彩特征与所述适用条件匹配,根据所述人脸白平衡算法,对所述图像进行白平衡处理。
  2. 根据权利要求1所述的图像的白平衡处理方法,其特征在于,所述对所述图像中的背景区域,提取色彩特征,包括:
    对所述图像中的背景区域,确定所述背景区域中的像素点在预设色彩空间中的分布位置;
    对所述分布位置进行统计,得到分布位置集中的色彩中心和对应的色彩集中程度;
    将所述色彩中心和所述集中程度,作为所述色彩特征。
  3. 根据权利要求2所述的图像的白平衡处理方法,其特征在于,所述对所述分布位置进行统计,得到分布位置集中的色彩中心和对应的色彩集中程度,包括:
    在所述预设色彩空间中将最高像素点密度的位置作为所述色彩中心;
    将所述像素点密度下降至所述最高像素点密度一半的位置,作为色彩集中区的边缘;
    根据所述色彩中心距离所述边缘的距离,确定所述色彩中心的色彩集中程度。
  4. 根据权利要求2所述的图像的白平衡处理方法,其特征在于,所述对所述分布位置进行统计,得到分布位置集中的色彩中心和对应的色彩集中程度,包括:
    在所述预设色彩空间中确定划分得到的多个区域;
    针对每一个区域进行统计,以确定每一个区域所含的像素点个数;
    若区域所含像素点个数多于阈值个数,将对应区域的中心位置作为所述色彩中心,将对应区域所含像素点的个数作为所述色彩中心的色彩集中程度。
  5. 根据权利要求2-4任一项所述的图像的白平衡处理方法,其特征在于,所述适用条件,包括混光场景对应的适用条件;
    所述混光场景对应的适用条件,包括:
    所述背景区域包含至少两个色彩集中程度高于阈值的色彩中心。
  6. 根据权利要求2-4任一项所述的图像的白平衡处理方法,其特征在于,所述适用条 件,包括绿植场景对应的适用条件;
    所述绿植场景对应的适用条件,包括:
    所述背景区域包含至少两个色彩中心;
    所述至少两个色彩中心中存在至少一个色彩中心位于所述色彩空间的目标区域内,且色彩集中程度低于阈值。
  7. 根据权利要求2-4任一项所述的图像的白平衡处理方法,其特征在于,所述适用条件,包括纯色背景对应的适用条件;
    所述纯色背景对应的适用条件,包括:
    所述背景区域包含单一色彩中心,且所述色彩中心的色彩集中程度高于阈值。
  8. 根据权利要求1-7任一项所述的图像的白平衡处理方法,其特征在于,所述匹配人脸白平衡算法的适用条件之后,还包括:
    若所述色彩特征与所述适用条件不匹配,根据灰度世界算法,对所述图像进行白平衡处理。
  9. 根据权利要求1-8任一项所述的图像的白平衡处理方法,其特征在于,所述适用条件为多个,所述若所述色彩特征与所述适用条件匹配,根据所述人脸白平衡算法,对所述图像进行白平衡处理,包括:
    若所述色彩特征与至少一个适用条件匹配,确定所述图像适用于所述人脸白平衡算法;
    根据所述人脸白平衡算法,对所述图像进行白平衡处理。
  10. 一种图像的白平衡处理装置,其特征在于,图像的内容包括人脸,所述装置包括:
    提取模块,用于对所述图像中的背景区域,提取色彩特征;其中,所述色彩特征用于指示所述背景区域色彩分布情况;
    匹配模块,用于根据所述色彩特征,匹配人脸白平衡算法的适用条件;所述人脸白平衡算法用于将所述图像中的人脸调整至肤色;
    处理模块,用于若所述色彩特征与所述适用条件匹配,根据所述人脸白平衡算法,对所述图像进行白平衡处理。
  11. 根据权利要求10所述的图像的白平衡处理装置,其特征在于,所述提取模块,包括:
    确定单元,用于对所述图像中的背景区域,确定所述背景区域中的像素点在预设色彩空间中的分布位置;
    统计单元,用于对所述分布位置进行统计,得到分布位置集中的色彩中心和色彩集中程度;
    生成单元,用于将所述色彩中心和对应的集中程度,作为所述色彩特征。
  12. 根据权利要求11所述的图像的白平衡处理装置,其特征在于,所述统计单元对所述分布位置进行统计,得到分布位置集中的色彩中心和对应的色彩集中程度,包括:
    在所述预设色彩空间中将最高像素点密度的位置作为所述色彩中心;
    将所述像素点密度下降至所述最高像素点密度一半的位置,作为色彩集中区的边缘;
    根据所述色彩中心距离所述边缘的距离,确定所述色彩中心的色彩集中程度。
  13. 根据权利要求11所述的图像的白平衡处理装置,其特征在于,所述统计单元对所述分布位置进行统计,得到分布位置集中的色彩中心和对应的色彩集中程度,包括:
    在所述预设色彩空间中确定划分得到的多个区域;
    针对每一个区域进行统计,以确定每一个区域所含的像素点个数;
    若区域所含像素点个数多于阈值个数,将对应区域的中心位置作为所述色彩中心,将对应区域所含像素点的个数作为所述色彩中心的色彩集中程度。
  14. 根据权利要求11-13任一项所述的图像的白平衡处理装置,其特征在于,所述适用条件,包括混光场景对应的适用条件;
    所述混光场景对应的适用条件,包括:
    所述背景区域包含至少两个色彩集中程度高于阈值的色彩中心。
  15. 根据权利要求11-13任一项所述的图像的白平衡处理装置,其特征在于,所述适用条件,包括绿植场景对应的适用条件;
    所述绿植场景对应的适用条件,包括:
    所述背景区域包含至少两个色彩中心;
    所述至少两个色彩中心中存在至少一个色彩中心位于所述色彩空间的目标区域内,且色彩集中程度低于阈值。
  16. 根据权利要求11-13任一项所述的图像的白平衡处理装置,其特征在于,所述适用条件,包括纯色背景对应的适用条件;
    所述纯色背景对应的适用条件,包括:
    所述背景区域包含单一色彩中心,且所述色彩中心的色彩集中程度高于阈值。
  17. 根据权利要求10-16任一项所述的图像的白平衡处理装置,其特征在于,所述匹配模块匹配人脸白平衡算法的适用条件之后,还包括:
    若所述色彩特征与所述适用条件不匹配,根据灰度世界算法,对所述图像进行白平衡处理。
  18. 根据权利要求10-17任一项所述的图像的白平衡处理装置,其特征在于,所述处理模块适用条件为多个,所述若所述色彩特征与所述适用条件匹配,根据所述人脸白平衡算法,对所述图像进行白平衡处理,包括:
    若所述色彩特征与至少一个适用条件匹配,确定所述图像适用于所述人脸白平衡算法;
    根据所述人脸白平衡算法,对所述图像进行白平衡处理。
  19. 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、摄像头,其中,所述存储器存储有可执行程序代码,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1-9任一项所述的图像的白平衡处理方法。
  20. 一种计算机可读存储介质,其上存储有计算机程序,其特征在于,该程序被处理器执行时实现如权利要求1-9任一项所述的图像的白平衡处理方法。
PCT/CN2018/094086 2017-07-25 2018-07-02 图像的白平衡处理方法、装置和终端设备 WO2019019870A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP18837675.0A EP3657785B1 (en) 2017-07-25 2018-07-02 Image white balance processing method and apparatus, and terminal device
US16/747,289 US11277595B2 (en) 2017-07-25 2020-01-20 White balance method for image and terminal device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710612885.4A CN107483906B (zh) 2017-07-25 2017-07-25 图像的白平衡处理方法、装置和终端设备
CN201710612885.4 2017-07-25

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/747,289 Continuation US11277595B2 (en) 2017-07-25 2020-01-20 White balance method for image and terminal device

Publications (1)

Publication Number Publication Date
WO2019019870A1 true WO2019019870A1 (zh) 2019-01-31

Family

ID=60595959

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/094086 WO2019019870A1 (zh) 2017-07-25 2018-07-02 图像的白平衡处理方法、装置和终端设备

Country Status (4)

Country Link
US (1) US11277595B2 (zh)
EP (1) EP3657785B1 (zh)
CN (2) CN109688396B (zh)
WO (1) WO2019019870A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107277480B (zh) * 2017-07-10 2019-03-29 Oppo广东移动通信有限公司 白平衡同步方法、装置和终端设备
CN109688396B (zh) 2017-07-25 2021-02-02 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
CN108063934B (zh) * 2017-12-25 2020-01-10 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
CN108769634B (zh) * 2018-07-06 2020-03-17 Oppo(重庆)智能科技有限公司 一种图像处理方法、图像处理装置及终端设备
CN108965846A (zh) * 2018-09-07 2018-12-07 晶晨半导体(上海)股份有限公司 调节白平衡的方法、系统及显示器
WO2022032564A1 (zh) * 2020-08-13 2022-02-17 华为技术有限公司 白平衡处理的方法与装置
CN112858268B (zh) * 2020-09-18 2022-06-14 武汉大学 基于化学成像-校正分析的土壤水和溶质迁移全域性测量方法
CN113012640B (zh) * 2021-03-08 2022-07-12 京东方科技集团股份有限公司 显示面板及显示装置
CN113727085B (zh) * 2021-05-31 2022-09-16 荣耀终端有限公司 一种白平衡处理方法、电子设备、芯片系统和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101262617A (zh) * 2007-03-02 2008-09-10 富士胶片株式会社 白平衡校正设备和方法
JP2011188186A (ja) * 2010-03-08 2011-09-22 Aof Imaging Technology Ltd ホワイトバランスゲイン算出装置
CN105187810A (zh) * 2014-11-11 2015-12-23 怀效宁 一种基于人脸色彩特征的自动白平衡方法及电子媒体装置
CN105894458A (zh) * 2015-12-08 2016-08-24 乐视移动智能信息技术(北京)有限公司 一种具有人脸的图像处理方法和装置
CN107483906A (zh) * 2017-07-25 2017-12-15 广东欧珀移动通信有限公司 图像的白平衡处理方法、装置和终端设备

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1977542B (zh) * 2004-06-30 2010-09-29 皇家飞利浦电子股份有限公司 利用感知规律提取主色以产生来自视频内容的环境光
US20070031060A1 (en) * 2005-08-04 2007-02-08 Canon Kabushiki Kaisha Image processing apparatus, method for calculating white balance evaluation value, program including program code for realizing the method for calculating white balance evaluation value, and storage medium for storing the program
JP2008042616A (ja) * 2006-08-08 2008-02-21 Eastman Kodak Co 撮像装置
CN101420594A (zh) * 2007-10-26 2009-04-29 三星电子株式会社 将视频图像划分为构成区域的设备和方法
JP5178170B2 (ja) * 2007-12-11 2013-04-10 オリンパス株式会社 ホワイトバランス調整装置及びホワイトバランス調整方法
JP5113514B2 (ja) * 2007-12-27 2013-01-09 キヤノン株式会社 ホワイトバランス制御装置およびホワイトバランス制御方法
JP5398156B2 (ja) 2008-03-04 2014-01-29 キヤノン株式会社 ホワイトバランス制御装置およびその制御方法並びに撮像装置
TWI360353B (en) * 2008-06-11 2012-03-11 Vatics Inc Method for auto-white-balance control
JP2010035048A (ja) * 2008-07-30 2010-02-12 Fujifilm Corp 撮像装置及び撮像方法
CN102446347B (zh) * 2010-10-09 2014-10-01 株式会社理光 图像白平衡方法和装置
JP5804856B2 (ja) * 2011-09-07 2015-11-04 キヤノン株式会社 画像処理装置、画像処理方法及びプログラム
US9420248B2 (en) * 2014-09-19 2016-08-16 Qualcomm Incorporated Multi-LED camera flash for color temperature matching
CN104735362B (zh) 2015-03-11 2017-11-07 广东欧珀移动通信有限公司 拍照方法和装置
US20170163953A1 (en) * 2015-12-08 2017-06-08 Le Holdings (Beijing) Co., Ltd. Method and electronic device for processing image containing human face
CN105430367B (zh) * 2015-12-30 2017-11-03 浙江宇视科技有限公司 一种自动白平衡的方法和装置
US9883155B2 (en) * 2016-06-14 2018-01-30 Personify, Inc. Methods and systems for combining foreground video and background video using chromatic matching
CN106878695A (zh) * 2017-02-13 2017-06-20 广东欧珀移动通信有限公司 白平衡处理的方法、装置和计算机设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101262617A (zh) * 2007-03-02 2008-09-10 富士胶片株式会社 白平衡校正设备和方法
JP2011188186A (ja) * 2010-03-08 2011-09-22 Aof Imaging Technology Ltd ホワイトバランスゲイン算出装置
CN105187810A (zh) * 2014-11-11 2015-12-23 怀效宁 一种基于人脸色彩特征的自动白平衡方法及电子媒体装置
CN105894458A (zh) * 2015-12-08 2016-08-24 乐视移动智能信息技术(北京)有限公司 一种具有人脸的图像处理方法和装置
CN107483906A (zh) * 2017-07-25 2017-12-15 广东欧珀移动通信有限公司 图像的白平衡处理方法、装置和终端设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3657785A4 *

Also Published As

Publication number Publication date
EP3657785A1 (en) 2020-05-27
CN109688396B (zh) 2021-02-02
CN107483906A (zh) 2017-12-15
CN109688396A (zh) 2019-04-26
EP3657785A4 (en) 2020-07-29
US20200154086A1 (en) 2020-05-14
EP3657785B1 (en) 2021-08-04
US11277595B2 (en) 2022-03-15
CN107483906B (zh) 2019-03-19

Similar Documents

Publication Publication Date Title
WO2019019870A1 (zh) 图像的白平衡处理方法、装置和终端设备
US10397486B2 (en) Image capture apparatus and method executed by image capture apparatus
CN104796683B (zh) 一种校准图像色彩的方法和系统
EP2426928B1 (en) Image processing apparatus, image processing method and program
US7184080B2 (en) Automatic white balancing via illuminant scoring
US11323676B2 (en) Image white balance processing system and method
US7576797B2 (en) Automatic white balancing via illuminant scoring autoexposure by neural network mapping
CN110381303B (zh) 基于皮肤颜色统计的人像自动曝光白平衡矫正方法及系统
CN106878695A (zh) 白平衡处理的方法、装置和计算机设备
JP3018914B2 (ja) 階調補正装置
US20190108628A1 (en) Image processing apparatus, image processing method, and recording medium
WO2004032524A1 (ja) 画像処理装置
JPWO2006059573A1 (ja) 色彩調整装置及び方法
KR101349968B1 (ko) 자동 영상보정을 위한 영상 처리 장치 및 방법
JP2012510201A (ja) デジタル画像における記憶色の修正
CN105631812B (zh) 一种对显示图像进行色彩增强的控制方法及控制装置
TW201738841A (zh) 動態調整混色光源白平衡的方法
Lukac Refined automatic white balancing
Kehtarnavaz et al. New approach to auto-white-balancing and auto-exposure for digital still cameras
WO2022271161A1 (en) Light compensations for virtual backgrounds
JP2001057680A (ja) ホワイトバランス調整方法および装置並びに記録媒体
Kang et al. Surrounding adaptive color image enhancement based on CIECAM02
Wang et al. Improve Image White Balance by Facial Skin Color
Jiang et al. Color correction of smartphone photos with prior knowledge
Quan et al. Memory color based preferred color reproduction with psychophysical evaluation

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: 18837675

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018837675

Country of ref document: EP

Effective date: 20200221