WO2017092593A1 - 一种调整融合素材的方法、装置和设备 - Google Patents

一种调整融合素材的方法、装置和设备 Download PDF

Info

Publication number
WO2017092593A1
WO2017092593A1 PCT/CN2016/106878 CN2016106878W WO2017092593A1 WO 2017092593 A1 WO2017092593 A1 WO 2017092593A1 CN 2016106878 W CN2016106878 W CN 2016106878W WO 2017092593 A1 WO2017092593 A1 WO 2017092593A1
Authority
WO
WIPO (PCT)
Prior art keywords
fusion
pixel
fused material
image
fused
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/CN2016/106878
Other languages
English (en)
French (fr)
Inventor
秦文煜
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.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding 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 Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Publication of WO2017092593A1 publication Critical patent/WO2017092593A1/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
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/18—Image warping, e.g. rearranging pixels individually
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4023—Scaling of whole images or parts thereof, e.g. expanding or contracting based on decimating pixels or lines of pixels; based on inserting pixels or lines of pixels
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/77—Retouching; Inpainting; Scratch removal
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/44—Receiver circuitry for the reception of television signals according to analogue transmission standards
    • H04N5/57—Control of contrast or brightness
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging

Definitions

  • the present invention relates to the field of computer application technologies, and in particular, to a method, device and device for adjusting a fused material.
  • image fusion processing is often involved, such as blending the makeup material with a specific area in the face image. Due to the difference in face position and posture, the difference in the environment, etc., the brightness of the face area will change. This requires corresponding adjustment of the brightness of the makeup material, otherwise the image after fusion will be very abrupt. And not natural.
  • the present invention provides a method, apparatus and apparatus for adjusting a fused material such that the adjustment process does not require manual participation.
  • the present invention provides a method of adjusting a fused material, the method comprising:
  • the pixel value of the fused material is adjusted by using the adjustment parameter.
  • the method before determining the adjustment parameter for the fused material according to the brightness condition of the fused area and the brightness condition of the fused material, the method further includes:
  • adjusting the brightness status of the fused material according to the overall brightness condition includes:
  • the luminance values of the pixels of the fused material are respectively added to the difference values.
  • determining the adjustment parameters for the fused material according to the brightness condition of the fused region and the brightness condition of the fused material includes:
  • B p_i is a fusion of the i-th luminance value of pixels in the region, B m_i creative fusion i-th luminance value of the pixel point.
  • adjusting the pixel values of the fused material by using the adjustment parameter includes:
  • the A new_p_i is a pixel value of the ith pixel of the fused material
  • the A old_p_i is a pixel value of the ith pixel of the fused material before the adjustment, where ⁇ i is the fusion
  • the adjustment parameter of the ith pixel of the material is a pixel value of the ith pixel of the fused material.
  • the method further includes:
  • the fusion region in the image is subjected to fusion processing by using the fused material after adjusting the pixel value.
  • the merging the fusion region in the image by using the fused material after adjusting the pixel value comprises:
  • the image new_i is a pixel value of the i-th pixel of the fusion region after the fusion processing
  • the ⁇ i is a predetermined fusion weight
  • the image old_i is the ith pixel of the fusion region before the fusion processing.
  • the A new_p_i is a pixel value of the i-th pixel of the fused material after the pixel value is adjusted.
  • the method is applied to a beauty-like APP
  • the fusion area is a to-be-tested area, and the fusion material is a makeup material.
  • the present invention also provides an apparatus for adjusting a fused material, the apparatus comprising:
  • a region determining unit configured to determine a fusion region corresponding to the fused material in the image
  • a brightness acquiring unit configured to acquire a brightness status of the fusion area
  • a parameter determining unit configured to determine an adjustment parameter for the fused material according to a brightness condition of the fused area and a brightness condition of the fused material
  • a first adjusting unit configured to adjust a pixel value of the fused material by using the adjustment parameter.
  • the apparatus further includes a second adjustment unit
  • the brightness acquiring unit is further configured to acquire an overall brightness status of the image
  • the second adjusting unit is configured to adjust a brightness condition of the fused material according to the overall brightness condition, so that a brightness condition of the fused material is closer to the overall brightness condition.
  • the second adjusting unit is specifically configured to:
  • the luminance values of the pixels of the fused material are respectively added to the difference values.
  • the parameter determining unit is specifically configured to Fusion determined adjustment parameter beta] i i-th material point pixels, wherein, B p_i is a fusion of the i-th luminance value of pixels in the region, B m_i creative fusion i-th luminance value of the pixel point.
  • the A new_p_i is a pixel value of the ith pixel of the fused material
  • the A old_p_i is a pixel value of the ith pixel of the fused material before the adjustment, where ⁇ i is the fusion
  • the adjustment parameter of the ith pixel of the material is a pixel value of the ith pixel of the fused material.
  • the device further comprises:
  • the fusion processing unit is configured to perform fusion processing on the fused region in the image by using the fused material after adjusting the pixel value.
  • the image new_i is a pixel value of the i-th pixel of the fusion region after the fusion processing
  • the ⁇ i is a predetermined fusion weight
  • the image old_i is the ith pixel of the fusion region before the fusion processing.
  • the A new_p_i is a pixel value of the i-th pixel of the fused material after the pixel value is adjusted.
  • the device is applied to a beauty APP
  • the fusion area is a to-be-tested area, and the fusion material is a makeup material.
  • One or more processors are One or more processors;
  • One or more programs the one or more programs being stored in the memory, executed by the one or more processors to:
  • the pixel value of the fused material is adjusted by using the adjustment parameter.
  • the present invention can automatically adjust the pixel value of the fused material according to the brightness condition of the fused region in the image, without manual participation, and the implementation is simpler, and the adjustment effect is not limited by the user's understanding of art.
  • FIG. 1 is a flowchart of a main method according to an embodiment of the present invention
  • FIG. 3a is a schematic diagram of a face image according to an embodiment of the present invention.
  • Figure 3b is a schematic diagram of feature point location based on Figure 3a;
  • FIG. 4 is a structural diagram of a device according to an embodiment of the present invention.
  • FIG. 5 is a structural diagram of a device according to an embodiment of the present invention.
  • the word “if” as used herein may be interpreted as “when” or “when” or “in response to determining” or “in response to detecting.”
  • the phrase “if determined” or “if detected (conditions or events stated)” may be interpreted as “when determined” or “in response to determination” or “when detected (stated condition or event) “Time” or “in response to a test (condition or event stated)”.
  • the execution body of the method may be embodied in the form of an application, which may be an application running locally on the device (native APP) or a web page on the device browser.
  • a program webApp
  • the device can be a client device or a server device.
  • SDK software development kit
  • a fusion region corresponding to the fused material in the image is located.
  • an image refers to an image that needs to be processed by using a fusion material.
  • the image may be an image uploaded by a user, or may be an image stored locally by the device, or may be a real-time image or a device.
  • the image obtained by other devices, etc., the present invention does not limit the form of image acquisition.
  • the fused material refers to a visual tool material used when the image is fused, and may include, but is not limited to, an image, an image segment, a graphic, a color, and the like.
  • a visual tool material used when the image is fused
  • the positioning method used in this step may be a manual designation manner, that is, obtaining a manually designated fusion region; or a combination of one or more of feature point positioning, template positioning, skin color model positioning, and the like. The details will be described in detail in the subsequent embodiments.
  • this step can be understood as the positioning of the specific fusion region, and the fine brightness adjustment is performed based on the fusion region.
  • the brightness condition of the fused material may be adjusted according to the overall brightness condition of the image, so that the brightness condition of the fused material is closer to the overall brightness state of the image. The details will also be described in detail in the subsequent embodiments.
  • the brightness value of each pixel in the fusion area may be counted, and the brightness average value of each pixel in the fusion area may also be counted.
  • the so-called brightness refers to the intensity of the image pixels, black is the darkest, white is the brightest, black is represented by 0, white Expressed by 255.
  • the pixel value of one pixel is basically represented by three color components of red, green and blue (RGB), and the range of R, G, and B is [0, 255]. Each pixel has a brightness value that has nothing to do with the hue, and is related to the intensity. There are many methods for calculating the brightness of a pixel, such as an averaging method, a weighting method, and the like.
  • the brightness L of the pixel is:
  • the brightness L of the pixel is:
  • a1, a2, and a3 are weighting coefficients, for example, a1, a2, and a3 may take 0.3, 0.5, and 0.2, respectively.
  • an adjustment parameter for the fused material is determined according to the brightness condition of the fused region and the brightness condition of the fused material.
  • the ratio of the brightness average of each pixel in the fusion region to the brightness average of each pixel in the fusion material may be roughly determined as the adjustment parameter of the fusion material.
  • this method is more extensive, and a preferred fine processing method is also provided in the embodiment of the present invention, that is, the ratio of the luminance value of each pixel in the fusion region to the luminance value of the corresponding pixel in the fusion material, As an adjustment parameter corresponding to each pixel point in the fused material.
  • a more accurate description can be used to determine the adjustment parameter ⁇ i of the i-th pixel of the fused material using the following formula:
  • B p_i is the i-th luminance value of pixels in the integration area
  • B m_i fusion of the i-th luminance value pixels clip.
  • the pixel values of the fused material are adjusted using the determined adjustment parameters.
  • the core of the invention is to adjust the pixel values of the pixels of the fusion material according to the state of the fusion region in the image.
  • the pixel values of each pixel in the fused material may be multiplied by the adjustment parameter as the pixel value of each pixel after the adjustment.
  • step 104 the pixel values of the pixels in the fused material are multiplied by the adjustment parameters of the corresponding pixel points as the pixel values of the adjusted pixels. That is, you can use the following formula to adjust the pixel value of the fused material:
  • a new_p_i ⁇ i *A old_p_i (4)
  • a new_p_i is the pixel value of the ith pixel of the adjusted fused material
  • a old_p_i is the pixel value of the ith pixel of the fused material before adjustment
  • ⁇ i is the adjustment parameter of the ith pixel of the fused material.
  • the adjusted fused material can be used to fuse the fused regions in the above image.
  • the method provided by the present invention can be applied to the fusion processing of still images, and can also be applied to the fusion processing of video images because it does not need to be manually involved in adjustment.
  • the execution body of the foregoing method provided by the present invention may be an application in a user terminal, or may be a plug-in in a user terminal application or a functional unit such as a Software Development Kit (SDK), or may be located in a server.
  • SDK Software Development Kit
  • the embodiment of the present invention does not specifically limit this.
  • the above applications may be, for example, image processing applications, beauty applications, and the like. The above method will be described in detail below by taking a lipstick test in a beauty application as an example in conjunction with FIG.
  • FIG. 2 is a flowchart of a detailed method according to an embodiment of the present invention.
  • a lipstick test is performed on a face of an image, that is, a lip in the image is fused with a lipstick material.
  • the process may specifically include the following steps:
  • feature point positioning is performed on the face region in the image to obtain a contour point of the face and a contour point of the lip.
  • the contour points of the lips need to be positioned in order to determine the fusion region when performing feature point positioning.
  • the contour point of the face is positioned to perform overall brightness adjustment on the lipstick material based on the overall brightness of the face.
  • the specific manner of the feature point positioning is not limited, and any feature point positioning manner such as positioning based on the SDM (Supervised Descent Method) model and id-exp model positioning may be adopted, and finally The position information of the above feature points is obtained.
  • SDM Supervised Descent Method
  • the feature points as shown in FIG. 3b that is, the contour points of the face and the contour points of the organ can be obtained (in the embodiment of the present invention, only the lip can be positioned only) Outline point of the section).
  • FIG. 3b it is only schematic. In order to facilitate the observation of the effect of exaggerating the feature points, the number and size of the feature points that are located may not be consistent with those in FIG. 3b when the actual feature points are located.
  • the average value of the brightness of each pixel in the face region can be counted and determined.
  • the luminance value of each pixel point can be calculated by a formula such as the above formula (1) or formula (2).
  • the brightness condition of the lipstick material is adjusted according to the obtained overall brightness condition.
  • This step is to bring the brightness of the lipstick material closer to the overall brightness of the face area. For example, it is possible to determine the difference between the mean value of the brightness of each pixel in the face region and the mean value of the brightness of each pixel of the lipstick material, and the lipstick will be The luminance values of the pixels of the material are respectively added to the difference. Of course, other adjustment methods can also be used, and will not be enumerated here.
  • the brightness condition of the lip region in the image is acquired.
  • the skin color model and the predefined lip template can be combined, wherein the skin color model limits the portion outside the lip region, and the lip template limits The basic shape of the lip, so that the lip region can be positioned more accurately, and the specific positioning manner is not limited in the present invention.
  • the brightness value of each pixel in the lip region can be counted.
  • the adjustment parameters for the lipstick material are determined based on the brightness condition of the lip region and the brightness condition of the lipstick material.
  • the adjustment parameter ⁇ i of each pixel of the lipstick material can be determined according to formula (3).
  • B p_i is the brightness value of the i-th pixel point in the lip region
  • B m_i is the brightness value of the i-th pixel point of the lipstick material
  • the lipstick material here is the lipstick material after the brightness adjustment in step 203.
  • the statistics of the brightness status may be in the form of a luminance histogram, and of course, the pixel-by-pixel point statistics may also be adopted in the form of a list.
  • the pixel value of each pixel of the lipstick material is adjusted by using the adjustment parameter of the lipstick material.
  • a new_p_i is the pixel value of the ith pixel of the adjusted lipstick material
  • a old_p_i is the ith pixel of the lipstick material before adjustment.
  • the pixel value, ⁇ i is the adjustment parameter of the i-th pixel point of the lipstick material.
  • each pixel of the lipstick material can be closer to the brightness of the lip region in the image. Under such conditions, it is more natural to use the lipstick material to fuse the lip region in the image.
  • 207 may be performed, that is, the lip region in the image is subjected to fusion processing by using the lipstick material after adjusting the pixel value.
  • the embodiment of the present invention may adopt a weighted fusion manner, and the pixel value of each pixel in the lip region obtained after the fusion may be determined by using the following formula:
  • Image new_i ⁇ i *Image old_i +(1- ⁇ i )*A new_p_i (5)
  • Image new_i is the pixel value of the i-th pixel of the lip region after fusion processing
  • ⁇ i is a predetermined fusion weight
  • Image old_i is the pixel value of the i-th pixel of the lip region before fusion processing
  • a new_p_i is adjusted The pixel value of the i-th pixel of the lipstick material after the pixel value.
  • the present invention does not limit the manner in which the fusion weights are determined, and only the predetermined fusion weights are utilized here.
  • the pixel values of the pixel points involved in the embodiment of the present invention relate to the values of the three channels R, G, and B.
  • the pixel value adjustment and the fusion processing of the fused material are performed, it is necessary to separately adjust and process the values of the three channels R, G, and B, respectively, which is a well-known content and will be briefly described herein.
  • the apparatus may include an area determining unit 01, a brightness obtaining unit 02, a parameter determining unit 03, and a first adjusting unit 04, and may further include a second adjusting unit 05 and a fusion processing unit 06.
  • the main functions of each component are as follows:
  • the region determining unit 01 is responsible for determining a fusion region in the image corresponding to the fused material.
  • the image refers to an image that needs to be processed by the fusion material, and the image may be an image uploaded by the user, or may be an image stored locally by the device, or may be an image obtained by the device from other devices.
  • the present invention does not limit the form of image acquisition.
  • the fused material refers to a visual tool material used when the image is fused, and may include, but is not limited to, an image, an image segment, a graphic, a color, and the like.
  • a visual tool material used when the image is fused
  • the brightness acquisition unit 02 is responsible for acquiring the brightness status of the fusion area.
  • the brightness value of each pixel in the fusion area can be counted, and the brightness average value of each pixel in the fusion area can also be counted.
  • the parameter determining unit 03 is responsible for determining an adjustment parameter for the fused material according to the brightness condition of the fused area and the brightness condition of the fused material.
  • the ratio of the brightness average of each pixel in the fusion region to the brightness average of each pixel in the fusion material may be roughly determined as the adjustment parameter of the fusion material.
  • this method is more extensive, and a preferred fine processing method is also provided in the embodiment of the present invention, that is, the ratio of the luminance value of each pixel in the fusion region to the luminance value of the corresponding pixel in the fusion material, As an adjustment parameter corresponding to each pixel point in the fused material.
  • the parameter determining unit 03 can be based on Fusion determined adjustment parameter beta] i i-th material point pixels, wherein, B p_i is the i-th luminance value of pixels in the integration area, B m_i fusion i-th point of the source pixel luminance value.
  • the first adjusting unit 04 is responsible for adjusting the pixel value of the fused material by using the adjustment parameter. If the parameter determining unit 03 determines the adjustment parameter in an extensive manner, the first adjusting unit 04 may multiply the pixel values of the pixels in the fused material by the adjustment parameter as the pixel value of each pixel after the adjustment.
  • the brightness acquiring unit 02 can also acquire the overall brightness condition of the image.
  • the second adjusting unit 05 Before the parameter determining unit 03 performs the operation, the second adjusting unit 05 first adjusts the brightness state of the fused material according to the overall brightness condition, so that the brightness state of the fused material is closer to the whole. Brightness condition.
  • the second adjusting unit 05 may first determine a difference between a brightness mean value of each pixel point of the image and a brightness average value of each pixel point of the fused material; and add a difference value to each of the brightness values of the pixels of the fused material.
  • the subsequent parameter determining unit 03 determines the brightness condition of the fused material after being processed by the second adjusting unit 05.
  • the fusion processing unit 06 is responsible for performing fusion processing on the fused regions in the image by using the fused material after adjusting the pixel values.
  • the device can be applied to an image processing type APP, and can also be applied to a beauty type APP or the like.
  • the device can be embodied in the form of an application, which can be an application running native to the device (native APP) or a web application (webApp) on the device browser.
  • it can also be embodied in the form of a plug-in or SDK in the application.
  • the present invention can also be applied to other image fusion scenes, such as incorporating a building material into a landscape image.
  • the above method and apparatus provided by the embodiments of the present invention may be embodied by a computer program that is set up and operates in a device.
  • the device may include one or more processors, and also includes a memory and one or more programs, as shown in FIG.
  • the one or more programs are stored in a memory and executed by the one or more processors to implement the method flow and/or device operations illustrated in the above-described embodiments of the present invention.
  • the method flow executed by one or more of the above processors may include:
  • the pixel value of the fused material is adjusted by using the adjustment parameter.
  • the method and apparatus provided by the present invention can have the following advantages:
  • the invention can automatically adjust the pixel value of the fused material according to the brightness condition of the fused area in the image, without manual participation, and the implementation is simpler, and the adjustment effect is not limited by the user's understanding of art.
  • This method of automatically adjusting the fused material can guarantee the real-time performance to a certain extent, and can be applied not only to the fusion processing of the still image but also to the fusion processing of the video image.
  • the method for adjusting the fused material provided by the invention has a small amount of calculation, on the one hand, it satisfies the real-time requirement, on the other hand, the pressure on the system performance is small, and the resource consumption is small.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division, and the actual implementation may have another division manner.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the above software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present invention. Part of the steps.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

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

Abstract

本发明提供了一种调整融合素材的方法、装置和设备，其中方法包括：确定图像中与融合素材对应的融合区域；获取所述融合区域的亮度状况；依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数；利用所述调整参数，调整所述融合素材的像素值。本发明能够依据图像中融合区域的亮度状况，实现自动调整融合素材的像素值，不需要人工参与，实现更加简单，调节效果不必受限于用户对艺术的理解。

Description

一种调整融合素材的方法、装置和设备
本申请要求2015年12月03日递交的申请号为201510873329.3、发明名称为“一种调整融合素材的方法、装置和设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及计算机应用技术领域，特别涉及一种调整融合素材的方法、装置和设备。
背景技术
随着智能终端的不断普及，人们利用智能终端进行图像处理的需求越来越高，各类美颜类APP受到爱美人士的广泛青睐。在这类APP中，常常会涉及到图像融合处理，例如将试妆素材与人脸图像中的特定区域进行融合等。由于人脸位置、姿态的不同，所处环境的不同等，造成面部区域的明暗程度会发生变化，这就需要相应地对试妆素材进行相应的亮度调整，否则会使得融合后的图像非常突兀和不自然。
现有依据图像亮度对试妆素材进行调整时，基本依靠用户手工调节。需要人工参与，比较麻烦，且调节效果也完全依靠用户对艺术的理解。
发明内容
有鉴于此，本发明提供了一种调整融合素材的方法、装置和设备，使得调节过程无需人工参与。
具体技术方案如下：
本发明提供了一种调整融合素材的方法，该方法包括：
确定图像中与融合素材对应的融合区域；
获取所述融合区域的亮度状况；
依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数；
利用所述调整参数，调整所述融合素材的像素值。
根据本发明一优选实施方式，在依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数之前，该方法还包括：
获取所述图像的整体亮度状况；
依据所述整体亮度状况，调整所述融合素材的亮度状况，使所述融合素材的亮度状况更接近所述整体亮度状况。
根据本发明一优选实施方式，依据所述整体亮度状况，调整所述融合素材的亮度状况包括：
确定所述图像各像素点的亮度均值与所述融合素材各像素点的亮度均值的差值；
将所述融合素材各像素点的亮度值分别加上所述差值。
根据本发明一优选实施方式，依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数包括：
依据
Figure PCTCN2016106878-appb-000001
确定融合素材第i个像素点的调整参数βi，其中，Bp_i为所述融合区域中第i个像素点的亮度值，Bm_i为融合素材第i个像素点的亮度值。
根据本发明一优选实施方式，利用所述调整参数，调整所述融合素材的像素值包括：
依据Anew_p_i＝βi*Aold_p_i，调整所述融合素材的像素值；
其中所述Anew_p_i为调整后的所述融合素材第i个像素点的像素值，所述Aold_p_i为调整前所述融合素材第i个像素点的像素值，所述βi为所述融合素材第i个像素点的调整参数。
根据本发明一优选实施方式，该方法还包括：
利用调整像素值后的融合素材，对所述图像中的融合区域进行融合处理。
根据本发明一优选实施方式，所述利用调整像素值后的融合素材，对所述图像中的融合区域进行融合处理包括：
利用Imagenew_i＝αi*Imageold_i+(1-αi)*Anew_p_i，对所述图像中的融合区域进行融合处理；
其中所述Imagenew_i为融合处理后所述融合区域第i个像素点的像素值，所述αi为预先确定的融合权重，所述Imageold_i为融合处理前所述融合区域第i个像素点的像素值，所述Anew_p_i为调整像素值后的融合素材第i个像素点的像素值。
根据本发明一优选实施方式，该方法应用于美颜类APP；
所述融合区域为待试妆区域，所述融合素材为试妆素材。
本发明还提供了一种调整融合素材的装置，该装置包括：
区域确定单元，用于确定图像中与融合素材对应的融合区域；
亮度获取单元，用于获取所述融合区域的亮度状况；
参数确定单元，用于依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数；
第一调整单元，用于利用所述调整参数，调整所述融合素材的像素值。
根据本发明一优选实施方式，该装置还包括第二调整单元；
所述亮度获取单元，还用于获取所述图像的整体亮度状况；
所述第二调整单元，用于依据所述整体亮度状况，调整所述融合素材的亮度状况，使所述融合素材的亮度状况更接近所述整体亮度状况。
根据本发明一优选实施方式，所述第二调整单元，具体用于：
确定所述图像各像素点的亮度均值与所述融合素材各像素点的亮度均值的差值；
将所述融合素材各像素点的亮度值分别加上所述差值。
根据本发明一优选实施方式，所述参数确定单元，具体用于依据
Figure PCTCN2016106878-appb-000002
确定融合素材第i个像素点的调整参数βi，其中，Bp_i为所述融合区域中第i个像素点的亮度值，Bm_i为融合素材第i个像素点的亮度值。
根据本发明一优选实施方式，所述第一调整单元，具体用于依据Anew_p_i＝βi*Aold_p_i，调整所述融合素材的像素值；
其中所述Anew_p_i为调整后的所述融合素材第i个像素点的像素值，所述Aold_p_i为调整前所述融合素材第i个像素点的像素值，所述βi为所述融合素材第i个像素点的调整参数。
根据本发明一优选实施方式，该装置还包括：
融合处理单元，用于利用调整像素值后的融合素材，对所述图像中的融合区域进行融合处理。
根据本发明一优选实施方式，所述融合处理单元，具体用于利用Imagenew_i＝αi*Imageold_i+(1-αi)*Anew_p_i，对所述图像中的融合区域进行融合处理；
其中所述Imagenew_i为融合处理后所述融合区域第i个像素点的像素值，所述αi为预先确定的融合权重，所述Imageold_i为融合处理前所述融合区域第i个像素点的像素值，所述Anew_p_i为调整像素值后的融合素材第i个像素点的像素值。
根据本发明一优选实施方式，该装置应用于美颜类APP；
所述融合区域为待试妆区域，所述融合素材为试妆素材。
一种设备，包括
一个或者多个处理器；
存储器；
一个或者多个程序，所述一个或者多个程序存储在所述存储器中，被所述一个或者多个处理器执行以实现如下操作：
确定图像中与融合素材对应的融合区域；
获取所述融合区域的亮度状况；
依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数；
利用所述调整参数，调整所述融合素材的像素值。
由以上技术方案可以看出，本发明能够依据图像中融合区域的亮度状况，实现自动调整融合素材的像素值，不需要人工参与，实现更加简单，调节效果不必受限于用户对艺术的理解。
附图说明
图1为本发明实施例提供的主要方法流程图；
图2为本发明实施例提供的一种详细方法流程图；
图3a为本发明实施例提供的一副人脸图像示意图；
图3b为基于图3a进行特征点定位的示意图；
图4为本发明实施例提供的装置结构图；
图5为本发明实施例提供的设备结构图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面结合附图和具体实施例对本发明进行详细描述。
在本发明实施例中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本发明。在本发明实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。
应当理解，本文中使用的术语“和/或”仅仅是一种描述关联对象的关联关系，表示 可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是“或”的关系。
取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”或“响应于检测”。类似地，取决于语境，短语“如果确定”或“如果检测(陈述的条件或事件)”可以被解释成为“当确定时”或“响应于确定”或“当检测(陈述的条件或事件)时”或“响应于检测(陈述的条件或事件)”。
图1为本发明实施例提供的主要方法流程图，该方法的执行主体可以体现为一个应用的形式，可以是运行于设备本地的应用程序(nativeAPP)，也可以是设备浏览器上的一个网页程序(webApp)，其中设备可以是用户端设备，也可以是服务器端设备。除此之外，也可以体现为应用中的插件或软件开发包(SDK)的形式。如图1中所示，该方法主要包括以下步骤：
在101中，定位图像中与融合素材对应的融合区域。
本发明实施例中，图像指的是需要利用融合素材进行融合处理的图像，该图像可以是用户上传的图像，也可以是设备本地存储的图像，也可以是实时拍摄的图像，也可以是设备从其他设备获取的图像等，本发明对于图像的获取形式并不加以限制。
在本发明实施例中，融合素材指的是对图像进行融合处理时采用的视觉工具材料，可以包括但不限于：图像、图像片段、图形、色彩等等。在进行融合处理时，通常需要将融合素材融合至图像中对应的融合区域，该对应关系可以是用户指定，也可以是系统默认。
本步骤中采用的定位方式可以是人工指定的方式，即获取人工指定的融合区域；也可以是通过特征点定位、模板定位、肤色模型定位等中的一种或多种相结合的方式。具体将在后续实施例中详细描述。
需要说明的是，本步骤可以理解为具体融合区域的定位，基于融合区域进行精细的亮度调整。另外，在本步骤之前，还可以首先依据图像的整体亮度状况，对融合素材的亮度状况进行调整，使融合素材的亮度状况更接近图像的整体亮度状况。具体也将在后续实施例中详细描述。
在102中，获取融合区域的亮度状况。
在本步骤中可以统计融合区域中各像素点的亮度值，也可以统计融合区域中各像素点的亮度均值。
所谓亮度指的是图像像素的强度,黑色为最暗,白色为最亮,黑色用0来表示,白色 用255来表示。一个像素点的像素值基本上是用红绿蓝(RGB)三个颜色分量来表示的，R、G、B的取值区间均为[0,255]。每个像素点都有亮度值，该亮度值与色相是没有关系的，与强度有关。计算像素点的亮度存在很多方法，例如平均法、加权法等等。
若采用平均法计算像素点的亮度，那么该像素点的亮度L为：
Figure PCTCN2016106878-appb-000003
若采用加权法计算像素点的亮度，那么该像素点的亮度L为：
L＝a1*R+a2*G+a3*B            (2)
其中，a1、a2、a3为加权系数，例如a1、a2和a3可以分别取0.3、0.5和0.2。
在103中，依据融合区域的亮度状况以及融合素材的亮度状况，确定对融合素材的调整参数。
在本步骤中，在确定调整参数时，可以粗略的将融合区域中各像素点的亮度均值与融合素材中各像素点的亮度均值的比值，确定为融合素材的调整参数。但这种方式较为粗放，在本发明实施例中还提供了一种优选的精细处理方式，即分别将融合区域中各像素点的亮度值与在融合素材中对应像素点的亮度值的比值，作为融合素材中对应各像素点的调整参数。更加准确的描述可以采用如下公式确定融合素材第i个像素点的调整参数βi：
Figure PCTCN2016106878-appb-000004
其中，Bp_i为融合区域中第i个像素点的亮度值，Bm_i为融合素材第i个像素点的亮度值。
在104中，利用确定出的调整参数，调整融合素材的像素值。
本发明的核心就是依据图像中融合区域的状况，对融合素材各像素点的像素值进行相应调整。
若步骤103中采用粗放的方式确定调整参数，那么在本步骤中可以将融合素材中各像素点的像素值均乘以该调整参数作为调整后各像素点的像素值。
若步骤104中采用精细的方式确定调整参数，那么在本步骤重可以将融合素材中各像素点的像素值分别乘以对应像素点的调整参数作为调整后各像素点的像素值。即可以采用以下公式调整融合素材的像素值：
Anew_p_i＝βi*Aold_p_i          (4)
其中Anew_p_i为调整后的融合素材第i个像素点的像素值，Aold_p_i为调整前融合素材第i个像素点的像素值，βi为融合素材第i个像素点的调整参数。
调整后的融合素材就可以用于对上述图像中的融合区域进行融合处理。
本发明所提供的方法可以应用于对静态图像的融合处理，由于无需人工参与调节，因此也可以应用于对视频图像的融合处理。另外，本发明提供的上述方法的执行主体可以为用户终端中的应用，也可以为用户终端应用中的插件或软件开发工具包(Software Development Kit，SDK)等功能单元，或者，还可以位于服务器端，本发明实施例对此不进行特别限定。上述应用可以是诸如图像处理类应用、美颜类应用等等。下面结合图2，以美颜类应用中进行口红试妆为例，对上述方法进行详细描述。
图2为本发明实施例提供的一种详细方法流程图，在本实施例中实现对图像的人脸进行口红试妆，即将图像中的唇部与口红素材进行融合。如图2中所示，该流程可以具体包括以下步骤：
在201中，对图像中的人脸区域进行特征点定位，得到人脸的轮廓点以及唇部的轮廓点。
由于在本实施例中是进行口红试妆，因此在进行特征点定位时，至少需要定位出唇部的轮廓点，以便确定融合区域。另外，在本实施例中，定位出人脸的轮廓点可以用于基于面部的整体亮度，对口红素材进行整体的亮度调整。
在本发明实施例中，并不对特征点定位的具体方式进行限制，可以采用诸如基于SDM(Supervised Descent Method，监督下降方法)模型的定位、id-exp模型定位等任意特征点定位方式，最终可以得到上述特征点的位置信息。
假设对图3a中的人脸区域进行特征点定位，可以得到如图3b中所示的特征点，即人脸的轮廓点以及器官的轮廓点(在本发明实施例中也可以仅定位出唇部的轮廓点)。需要说明的是，图3b中仅仅是示意性的，为了方便查看夸大了特征点的效果，在实际的特征点定位时，定位出的特征点数量和粒度可能与图3b中不一致。
在202中，获取人脸区域的整体亮度状况。
在本实施例中，可以统计并确定人脸区域中各像素点的亮度均值。各像素点的亮度值可以采用诸如上述公式(1)或公式(2)等的计算方式。
在203中，依据获取的整体亮度状况，调整口红素材的亮度状况。
本步骤的目的是使口红素材的亮度状况更接近人脸区域的整体亮度状况。例如，可以确定人脸区域各像素点的亮度均值与口红素材各像素点的亮度均值的差值，将口红素 材各像素点的亮度值分别加上该差值。当然，也可以采用其他调整方式，在此不再一一列举。
在204中，获取图像中唇部区域的亮度状况。
另外，做一点说明：在本实施例中，对唇部进行定位时，可以结合肤色模型和预定义的唇部模板，其中肤色模型限制了唇部区域的之外的部分，唇部模板限制了唇部的基本形状，这样就可以较为精确的定位出唇部区域，具体定位方式本发明不加以限制。
本步骤中，可以统计唇部区域各像素点的亮度值。
在205中，依据唇部区域的亮度状况以及口红素材的亮度状况，确定对口红素材的调整参数。
本步骤中可以按照公式(3)，确定口红素材各像素的调整参数βi。其中，Bp_i为唇部区域中第i个像素点的亮度值，Bm_i为口红素材第i个像素点的亮度值，这里的口红素材是经过步骤203的亮度调整后的口红素材。
在本发明实施例中，对于亮度状况的统计可以采用亮度直方图的形式，当然也可以采用列表的形式逐像素点统计。
在206中，利用口红素材的调整参数，调整口红素材各像素点的像素值。
对口红素材各像素点的像素值的调整，可以采用上述公式(4)，其中Anew_p_i为调整后的口红素材第i个像素点的像素值，Aold_p_i为调整前口红素材第i个像素点的像素值，βi为口红素材第i个像素点的调整参数。
经过上述调整后，口红素材的各像素点能够更接近图像中唇部区域的亮度状况，这种条件下利用口红素材对图像中的唇部区域进行融合时，能够更加自然。在进行融合时，可以执行207，即利用调整像素值后的口红素材，对图像中的唇部区域进行融合处理。
在进行融合处理时，本发明实施例可以采用加权融合的方式，可以利用如下公式确定融合后得到的唇部区域各像素点的像素值：
Imagenew_i＝αi*Imageold_i+(1-αi)*Anew_p_i       (5)
其中Imagenew_i为融合处理后唇部区域第i个像素点的像素值，αi为预先确定的融合权重，Imageold_i为融合处理前唇部区域第i个像素点的像素值，Anew_p_i为调整像素值后的口红素材第i个像素点的像素值。本发明对融合权重的确定方式并不加以限制，在此仅利用预先确定好的融合权重。
本发明实施例中涉及的像素点的像素值涉及到R、G、B三个通道的值，在进行上述 融合素材的像素值调整以及融合处理时，需要分别对各像素点R、G、B三个通道的值分别进行调整和处理，这是较为公知的内容，在此仅作简单说明。
以上是对本发明所提供方法进行的描述，下面结合图4对本发明实施例提供的装置进行详细描述。如图4中所示，该装置可以包括：区域确定单元01、亮度获取单元02、参数确定单元03和第一调整单元04，还可以包括第二调整单元05和融合处理单元06。各组成单元的主要功能如下：
区域确定单元01负责确定图像中与融合素材对应的融合区域。本发明实施例中，图像指的是需要利用融合素材进行融合处理的图像，该图像可以是用户上传的图像，也可以是设备本地存储的图像，也可以是设备从其他设备获取的图像等，本发明对于图像的获取形式并不加以限制。
在本发明实施例中，融合素材指的是对图像进行融合处理时采用的视觉工具材料，可以包括但不限于：图像、图像片段、图形、色彩等等。在进行融合处理时，通常需要将融合素材融合至图像中对应的融合区域，该对应关系可以是用户指定，也可以是系统默认。
亮度获取单元02负责获取融合区域的亮度状况。可以统计融合区域中各像素点的亮度值，也可以统计融合区域中各像素点的亮度均值。
参数确定单元03负责依据融合区域的亮度状况以及融合素材的亮度状况，确定对融合素材的调整参数。在确定调整参数时，可以粗略的将融合区域中各像素点的亮度均值与融合素材中各像素点的亮度均值的比值，确定为融合素材的调整参数。但这种方式较为粗放，在本发明实施例中还提供了一种优选的精细处理方式，即分别将融合区域中各像素点的亮度值与在融合素材中对应像素点的亮度值的比值，作为融合素材中对应各像素点的调整参数。即参数确定单元03可以依据
Figure PCTCN2016106878-appb-000005
确定融合素材第i个像素点的调整参数βi，其中，Bp_i为融合区域中第i个像素点的亮度值，Bm_i为融合素材第i个像素点的亮度值。
第一调整单元04负责利用调整参数，调整融合素材的像素值。若参数确定单元03采用粗放的方式确定调整参数，那么第一调整单元04可以将融合素材中各像素点的像素值均乘以该调整参数作为调整后各像素点的像素值。若参数确定单元03采用精细的方式确定调整参数，那么第一调整单元04可以依据Anew_p_i＝βi*Aold_p_i，调整融合素材的像 素值；其中Anew_p_i为调整后的融合素材第i个像素点的像素值，Aold_p_i为调整前融合素材第i个像素点的像素值，βi为融合素材第i个像素点的调整参数。
亮度获取单元02还可以获取图像的整体亮度状况，在参数确定单元03执行操作之前，首先由第二调整单元05依据整体亮度状况，调整融合素材的亮度状况，使融合素材的亮度状况更接近整体亮度状况。
具体地，第二调整单元05可以首先确定图像各像素点的亮度均值与融合素材各像素点的亮度均值的差值；将融合素材各像素点的亮度值分别加上差值。
后续参数确定单元03在确定对融合素材的调整参数时，所依据的融合素材的亮度状况为经过第二调整单元05处理后融合素材的亮度状况。
融合处理单元06负责利用调整像素值后的融合素材，对图像中的融合区域进行融合处理。
具体地，融合处理单元06可以利用Imagenew_i＝αi*Imageold_i+(1-αi)*Anew_p_i，对图像中的融合区域进行融合处理；其中Imagenew_i为融合处理后融合区域第i个像素点的像素值，αi为预先确定的融合权重，Imageold_i为融合处理前融合区域第i个像素点的像素值，Anew_p_i为调整像素值后的融合素材第i个像素点的像素值。
该装置可以应用于图像处理类APP，也可以应用于美颜类APP等。该装置可以体现为一个应用的形式，可以是运行于设备本地的应用程序(nativeAPP)，也可以是设备浏览器上的一个网页程序(webApp)。除此之外，也可以体现为应用中的插件或SDK的形式。
除了应用于上述美颜类APP中诸如口红试妆、眼影试妆等的场景之外，本发明还可以应用于其他图像融合的场景，例如将一个建筑素材融合入风景图像中。
本发明实施例提供的上述方法和装置可以以设置并运行于设备中的计算机程序体现。该设备可以包括一个或多个处理器，还包括存储器和一个或多个程序，如图5中所示。其中该一个或多个程序存储于存储器中，被上述一个或多个处理器执行以实现本发明上述实施例中所示的方法流程和/或装置操作。例如，被上述一个或多个处理器执行的方法流程，可以包括：
确定图像中与融合素材对应的融合区域；
获取所述融合区域的亮度状况；
依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材 的调整参数；
利用所述调整参数，调整所述融合素材的像素值。
由以上描述可以看出，本发明提供的方法和装置可以具备以下优点：
1)本发明能够依据图像中融合区域的亮度状况，实现自动调整融合素材的像素值，不需要人工参与，实现更加简单，调节效果不必受限于用户对艺术的理解。
2)这种自动调整融合素材的方式，能够在一定程度上保证实时性，不仅可以应用于静态图像的融合处理，也可以应用于视频图像的融合处理。
3)本发明提供的调整融合素材的方式，带来的计算量较小，一方面满足实时性要求，另一方面对系统性能的压力小，资源消耗少。
4)当应用于美颜类APP时，首先基于面部整体亮度对试妆素材进行全局性调整，再基于具体融合区域的亮度状况对试妆素材进行精确调整，使得调整后的试妆素材能够与图像的亮度状况更加匹配，看起来更加自然，不突兀。
在本发明所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明保护的范围之内。

Claims (17)

  1. 一种调整融合素材的方法，其特征在于，该方法包括：
    确定图像中与融合素材对应的融合区域；
    获取所述融合区域的亮度状况；
    依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数；
    利用所述调整参数，调整所述融合素材的像素值。
  2. 根据权利要求1所述的方法，其特征在于，在依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数之前，该方法还包括：
    获取所述图像的整体亮度状况；
    依据所述整体亮度状况，调整所述融合素材的亮度状况，使所述融合素材的亮度状况更接近所述整体亮度状况。
  3. 根据权利要求2所述的方法，其特征在于，依据所述整体亮度状况，调整所述融合素材的亮度状况包括：
    确定所述图像各像素点的亮度均值与所述融合素材各像素点的亮度均值的差值；
    将所述融合素材各像素点的亮度值分别加上所述差值。
  4. 根据权利要求1所述的方法，其特征在于，依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数包括：
    依据
    Figure PCTCN2016106878-appb-100001
    确定融合素材第i个像素点的调整参数βi，其中，Bp_i为所述融合区域中第i个像素点的亮度值，Bm_i为融合素材第i个像素点的亮度值。
  5. 根据权利要求1所述的方法，其特征在于，利用所述调整参数，调整所述融合素材的像素值包括：
    依据Anew_p_i＝βi*Aold_p_i，调整所述融合素材的像素值；
    其中所述Anew_p_i为调整后的所述融合素材第i个像素点的像素值，所述Aold_p_i为调整前所述融合素材第i个像素点的像素值，所述βi为所述融合素材第i个像素点的调整参数。
  6. 根据权利要求1所述的方法，其特征在于，该方法还包括：
    利用调整像素值后的融合素材，对所述图像中的融合区域进行融合处理。
  7. 根据权利要求6所述的方法，其特征在于，所述利用调整像素值后的融合素材，对所述图像中的融合区域进行融合处理包括：
    利用Imagenew_i＝αi*Imageold_i+(1-αi)*Anew_p_i，对所述图像中的融合区域进行融合处理；
    其中所述Imagenew_i为融合处理后所述融合区域第i个像素点的像素值，所述αi为预先确定的融合权重，所述Imageold_i为融合处理前所述融合区域第i个像素点的像素值，所述Anew_p_i为调整像素值后的融合素材第i个像素点的像素值。
  8. 根据权利要求1至7任一权项所述的方法，其特征在于，该方法应用于美颜类APP；
    所述融合区域为待试妆区域，所述融合素材为试妆素材。
  9. 一种调整融合素材的装置，其特征在于，该装置包括：
    区域确定单元，用于确定图像中与融合素材对应的融合区域；
    亮度获取单元，用于获取所述融合区域的亮度状况；
    参数确定单元，用于依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数；
    第一调整单元，用于利用所述调整参数，调整所述融合素材的像素值。
  10. 根据权利要求9所述的装置，其特征在于，该装置还包括第二调整单元；
    所述亮度获取单元，还用于获取所述图像的整体亮度状况；
    所述第二调整单元，用于依据所述整体亮度状况，调整所述融合素材的亮度状况，使所述融合素材的亮度状况更接近所述整体亮度状况。
  11. 根据权利要求10所述的装置，其特征在于，所述第二调整单元，具体用于：
    确定所述图像各像素点的亮度均值与所述融合素材各像素点的亮度均值的差值；
    将所述融合素材各像素点的亮度值分别加上所述差值。
  12. 根据权利要求9所述的装置，其特征在于，所述参数确定单元，具体用于依据
    Figure PCTCN2016106878-appb-100002
    确定融合素材第i个像素点的调整参数βi，其中，Bp_i为所述融合区域中第i个像素点的亮度值，Bm_i为融合素材第i个像素点的亮度值。
  13. 根据权利要求9所述的装置，其特征在于，所述第一调整单元，具体用于依据Anew_p_i＝βi*Aold_p_i，调整所述融合素材的像素值；
    其中所述Anew_p_i为调整后的所述融合素材第i个像素点的像素值，所述Aold_p_i为调整前所述融合素材第i个像素点的像素值，所述βi为所述融合素材第i个像素点的调整参数。
  14. 根据权利要求9所述的装置，其特征在于，该装置还包括：
    融合处理单元，用于利用调整像素值后的融合素材，对所述图像中的融合区域进行融合处理。
  15. 根据权利要求14所述的装置，其特征在于，所述融合处理单元，具体用于利用Imagenew_i＝αi*Imageold_i+(1-αi)*Anew_p_i，对所述图像中的融合区域进行融合处理；
    其中所述Imagenew_i为融合处理后所述融合区域第i个像素点的像素值，所述αi为预先确定的融合权重，所述Imageold_i为融合处理前所述融合区域第i个像素点的像素值，所述Anew_p_i为调整像素值后的融合素材第i个像素点的像素值。
  16. 根据权利要求9至15任一权项所述的装置，其特征在于，该装置应用于美颜类APP；
    所述融合区域为待试妆区域，所述融合素材为试妆素材。
  17. 一种设备，包括
    一个或者多个处理器；
    存储器；
    一个或者多个程序，所述一个或者多个程序存储在所述存储器中，被所述一个或者多个处理器执行以实现如下操作：
    确定图像中与融合素材对应的融合区域；
    获取所述融合区域的亮度状况；
    依据所述融合区域的亮度状况以及所述融合素材的亮度状况，确定对所述融合素材的调整参数；
    利用所述调整参数，调整所述融合素材的像素值。
PCT/CN2016/106878 2015-12-03 2016-11-23 一种调整融合素材的方法、装置和设备 Ceased WO2017092593A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510873329.3 2015-12-03
CN201510873329.3A CN106846240B (zh) 2015-12-03 2015-12-03 一种调整融合素材的方法、装置和设备

Publications (1)

Publication Number Publication Date
WO2017092593A1 true WO2017092593A1 (zh) 2017-06-08

Family

ID=58796276

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/106878 Ceased WO2017092593A1 (zh) 2015-12-03 2016-11-23 一种调整融合素材的方法、装置和设备

Country Status (2)

Country Link
CN (1) CN106846240B (zh)
WO (1) WO2017092593A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107395958B (zh) * 2017-06-30 2019-11-15 北京金山安全软件有限公司 一种图像处理方法、装置、电子设备及存储介质
CN110728618B (zh) * 2018-07-17 2023-06-27 淘宝（中国）软件有限公司 虚拟试妆的方法、装置、设备及图像处理方法
CN109102484B (zh) * 2018-08-03 2021-08-10 北京字节跳动网络技术有限公司 用于处理图像的方法和装置
CN109584180A (zh) * 2018-11-30 2019-04-05 深圳市脸萌科技有限公司 人脸图像处理方法、装置、电子设备及计算机存储介质
CN109584153A (zh) * 2018-12-06 2019-04-05 北京旷视科技有限公司 修饰眼部的方法、装置和系统
CN113763287B (zh) * 2021-09-27 2024-09-17 北京市商汤科技开发有限公司 图像处理方法及装置、电子设备和存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103180872A (zh) * 2010-10-29 2013-06-26 欧姆龙株式会社 图像处理装置、图像处理方法及控制程序
CN103236066A (zh) * 2013-05-10 2013-08-07 苏州华漫信息服务有限公司 一种基于人脸特征分析的虚拟试妆方法
CN104537608A (zh) * 2014-12-31 2015-04-22 深圳市中兴移动通信有限公司 一种图像处理的方法及其装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3878541B2 (ja) * 2002-11-28 2007-02-07 富士フイルムホールディングス株式会社 画像通信システム
JP6396890B2 (ja) * 2013-04-08 2018-09-26 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ メイクアップ塗材が塗布された状態を仮想的に再現することができる画像処理装置、画像処理方法、プログラム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103180872A (zh) * 2010-10-29 2013-06-26 欧姆龙株式会社 图像处理装置、图像处理方法及控制程序
CN103236066A (zh) * 2013-05-10 2013-08-07 苏州华漫信息服务有限公司 一种基于人脸特征分析的虚拟试妆方法
CN104537608A (zh) * 2014-12-31 2015-04-22 深圳市中兴移动通信有限公司 一种图像处理的方法及其装置

Also Published As

Publication number Publication date
CN106846240A (zh) 2017-06-13
CN106846240B (zh) 2021-05-07

Similar Documents

Publication Publication Date Title
US11265523B2 (en) Illuminant estimation referencing facial color features
WO2017092593A1 (zh) 一种调整融合素材的方法、装置和设备
US11070717B2 (en) Context-aware image filtering
CN110163810B (zh) 一种图像处理方法、装置以及终端
US9565410B2 (en) Automatic white balance with facial color features as reference color surfaces
WO2022160701A1 (zh) 特效生成方法、装置、设备及存储介质
US9864901B2 (en) Feature detection and masking in images based on color distributions
CN110390632B (zh) 基于妆容模板的图像处理方法、装置、存储介质及终端
WO2021169307A1 (zh) 人脸图像的试妆处理方法、装置、计算机设备和存储介质
WO2017092592A1 (zh) 一种图像融合的方法、装置和设备
CN114429476B (zh) 图像处理方法、装置、计算机设备以及存储介质
CN106709886A (zh) 自动修图方法及装置
CN108198155A (zh) 一种自适用色调映射方法及系统
CN104994363B (zh) 一种基于服饰的美颜方法、装置及智能终端
CN110827218A (zh) 基于图像hsv透射率加权校正的机载图像去雾方法
CN111127367B (zh) 人脸图像处理的方法、装置及系统
CN105704395B (zh) 拍照方法和拍照装置
CN109584145A (zh) 卡通化方法和装置、电子设备和计算机存储介质
CN112752031A (zh) 图像采集检测方法、装置、电子设备及存储介质
CN106097261B (zh) 图像处理方法、装置、存储介质及终端设备
CN107730442A (zh) 一种人脸美颜方法及装置
CN108447026A (zh) 美颜参数特征值的获取方法、终端及计算机可读存储介质
CN118396857A (zh) 一种图像处理方法及电子设备
CN107705279A (zh) 实现双重曝光的图像数据实时处理方法及装置、计算设备
US10645357B2 (en) Selectively applying color to an image

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: 16869903

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: 16869903

Country of ref document: EP

Kind code of ref document: A1