WO2019015477A1 - Procédé de correction d'image, support d'informations lisible par ordinateur et dispositif informatique - Google Patents

Procédé de correction d'image, support d'informations lisible par ordinateur et dispositif informatique Download PDF

Info

Publication number
WO2019015477A1
WO2019015477A1 PCT/CN2018/094471 CN2018094471W WO2019015477A1 WO 2019015477 A1 WO2019015477 A1 WO 2019015477A1 CN 2018094471 W CN2018094471 W CN 2018094471W WO 2019015477 A1 WO2019015477 A1 WO 2019015477A1
Authority
WO
WIPO (PCT)
Prior art keywords
deformation
face
profile
image
operator
Prior art date
Application number
PCT/CN2018/094471
Other languages
English (en)
Chinese (zh)
Inventor
曾元清
Original Assignee
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Publication of WO2019015477A1 publication Critical patent/WO2019015477A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G06V10/247—Aligning, centring, orientation detection or correction of the image by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids

Definitions

  • the present application relates to the field of image processing, and in particular to an image correction method, a non-transitory computer readable storage medium, and a computer device.
  • Photographing has gradually become a part of people's lives, and people can take pictures or portraits with mobile devices with cameras anytime, anywhere.
  • the number of people with visual impairment is very large, and the deformation caused by the lens during photographing affects the imaging effect of the photographed face.
  • an image correction method a non-transitory computer readable storage medium, and a computer device are provided.
  • An image correction method comprising:
  • the deformation profile is subjected to deformation processing using the updated deformation operator.
  • One or more non-transitory computer readable storage media containing computer executable instructions that, when executed by one or more processors, cause the processor to:
  • the deformation profile is subjected to deformation processing using the updated deformation operator.
  • a computer device comprising a memory and a processor, the memory storing computer readable instructions, wherein when executed by the processor, the processor causes the processor to:
  • the deformation profile is subjected to deformation processing using the updated deformation operator.
  • the image correcting method, the non-volatile computer readable storage medium, and the computer device in the embodiments of the present application improve the imaging effect of the face.
  • FIG. 1 is a diagram showing the internal structure of a computer device in an embodiment
  • FIG. 2 is a flow chart of an image correction method in one embodiment
  • FIG. 3 is a flow chart of an image correction method in another embodiment
  • FIG. 4 is a schematic diagram showing deformation of a photo taken by a user wearing glasses in an embodiment
  • FIG. 5 is a schematic diagram showing a fitting curve obtained by fitting a deformation region in the contour of the face in FIG. 4 in one embodiment
  • Figure 6 is an internal block diagram of an image correcting device in one embodiment
  • Figure 7 is a schematic illustration of an image processing circuit in one embodiment.
  • first may be referred to as a second client
  • second client may be referred to as a first client, without departing from the scope of the present application.
  • Both the first client and the second client are clients, but they are not the same client.
  • FIG. 1 is a schematic diagram showing the internal structure of a computer device in an embodiment.
  • the computer device includes a processor coupled through a system bus, a non-volatile storage medium, an internal memory, a network interface, a display screen, and an input device.
  • the non-volatile storage medium of the computer device stores an operating system and computer readable instructions.
  • the computer readable instructions are executed by the processor to implement an image correction method.
  • the processor is used to provide computing and control capabilities to support the operation of the entire computer device.
  • the internal memory in the computer device provides an environment for the operation of computer executable instructions in a non-volatile storage medium.
  • the network interface is used for network communication with servers or other devices.
  • the display screen of the computer device may be a liquid crystal display or an electronic ink display screen.
  • the input device may be a touch layer covered on the display screen, or may be a button, a trackball or a touchpad provided on a computer device casing, or may be An external keyboard, trackpad, or mouse.
  • the computer device can be a cell phone, a tablet or a personal digital assistant or a wearable device or the like. It will be understood by those skilled in the art that the structure shown in FIG. 1 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation of the computer device to which the solution of the present application is applied.
  • the specific computer device may It includes more or fewer components than those shown in the figures, or some components are combined, or have different component arrangements.
  • FIG. 2 is a flow chart of an image correction method in one embodiment. As shown in FIG. 2, an image correction method is run on a computer device, and the method may include the operation shown in FIG. 2.
  • Operation 202 detecting a deformation profile of the image including the face.
  • the image can be taken by an electronic device with a camera.
  • the image contains a human face.
  • the image can be an image stored in an album or on a network.
  • the deformation profile refers to a facial contour formed by deformation of a facial contour caused by refraction or the like of the face.
  • Refraction refers to the refraction of the area of the lens due to myopia or farsighted lenses.
  • the image can be detected by a machine learning model to obtain a deformation profile containing the face in the image.
  • the computer device needs to collect normal facial contour samples and facial contour samples containing deformation contours as training samples for machine learning, and train machine learning models through training samples to obtain machine learning of facial contours. model.
  • the computer device can also recognize facial features in the image through a key feature point extraction algorithm for the face.
  • the facial features may include several features such as the eyes, mouth, nose, and eyebrows.
  • the face key feature points may include 2 eyeball center points, 4 eye corner points, 2 nozzle midpoints, and 2 mouth corner points.
  • the computer device can use the susan operator to extract the edge and corner features of the local region.
  • the principle of the Susan operator is to use a circular area with a radius of pixels as a mask to examine how the pixel values of all points in the region of the image coincide with the values of the current point.
  • the computer device can also detect the facial contour and the deformation contour of the face by using an edge detection operator such as sobel or canny.
  • a deformation trend of the deformation profile is determined, and a corresponding deformation operator is selected according to the deformation trend.
  • the shape of the deformation profile can be obtained.
  • the computer device compares the shape of the deformed contour with the shape of the reference facial contour, and whether the deformation trend of the deformed contour is reduced or expanded.
  • the reference face contour refers to a preset face contour as a standard.
  • the operation 204 includes: when determining that the deformation trend of the deformation profile is reduced, selecting a first deformation operator; and when determining that the deformation trend of the deformation profile is expanding, selecting a second deformation calculation child.
  • the computer device may pre-establish a correspondence relationship between the deformation trend and the deformation operator, and after detecting the deformation trend, obtain a corresponding deformation operator from the corresponding relationship between the deformation trend and the deformation operator according to the deformation trend.
  • a deformation operator is a parameter that performs a deformation operation on an image.
  • Operation 206 identifying a facial contour of the face in the image.
  • the computer device may employ a machine learning model to identify facial contours in the image.
  • the machine learning model is obtained by training the training samples in advance, or by extracting key feature points of the face.
  • Operation 208 curve fitting the deformed contour of the face according to the facial contour to obtain a fitting curve.
  • the computer device may fit the corresponding reference facial contour according to the remaining contours remaining in the facial contour except the deformed contour.
  • the computer device obtains a curve contoured face contour, that is, a fitting curve, according to the reference face contour and the detected facial contour in the image.
  • Curve fitting can use scatter points other than the deformed contour in the contour of the face, select the appropriate curve type for variable transformation, make the two variables after the transformation have a linear relationship, and find the linear equation and variance according to the least squares method, and straighten the line.
  • the equation is converted to a function expression about the original variable.
  • the deformation operator is adjusted according to the fitting curve and the deformation profile to obtain an updated deformation operator.
  • the computer device adjusts the deformation operator according to the difference between the fitting curve and the deformation profile to obtain the updated deformation operator.
  • the deformation operator can be an affine transformation matrix. Each affine transform corresponds to a multiplication of a rectangle and a vector. Affine transformations can be achieved through a series of atomic transformations, including translation, scaling, flipping, rotation, and miscutting.
  • the simulation transformation is represented by a 3 ⁇ 3 matrix, the last of which is (0, 0, 1).
  • the transformation matrix transforms the original coordinates (x 1 , y 1 ) into new coordinates (x 2 , y 2 ).
  • the original coordinates and the new coordinates are adjacent to the three-dimensional column of the last behavior (1), and the original column vector is multiplied by the transformation.
  • the matrix gets a new column vector, as in equation (1).
  • the deformation profile can be obtained by translational transformation.
  • the transformation matrix of the translation transformation can be
  • Operation 212 deforming the deformation profile by using the updated deformation operator.
  • the computer device deforms the deformation profile by the updated deformation operator to obtain the corrected contour.
  • the image correction method in the embodiment of the present application detects the deformation profile of the face in the image, selects a corresponding deformation operator according to the deformation trend of the deformation profile, detects the contour of the face, and formulates the deformation profile according to the contour of the face.
  • the fitting curve is obtained, and the deformation operator is adjusted according to the fitting curve and the deformation contour to obtain the updated deformation operator, and the deformed contour can be corrected according to the updated deformation operator to obtain the corrected facial contour and improved.
  • the imaging effect of the face is obtained, and the deformation operator is adjusted according to the fitting curve and the deformation contour to obtain the updated deformation operator, and the deformed contour can be corrected according to the updated deformation operator to obtain the corrected facial contour and improved.
  • identifying the facial contour in the image may precede the operation 202.
  • including the deformation profile of the face in the detection image comprises: acquiring the deformation profile including the face according to a color of the skin.
  • face detection based on skin color may include pre-processing, skin color segmentation based on skin color model; connected domain analysis, face region localization.
  • the preprocessing can use Gaussian filtering and histogram equalization.
  • the skin color model can adopt a color model of the YCbCr space, where Y refers to luminance information, and Cb and Cr are chrominance information.
  • the computer device establishes a Gaussian model of the skin color according to the mean and variance of the skin color, and obtains a face probability map through the Gaussian model of the skin color, and uses the binarization to obtain the face color binary image.
  • the computer device can perform connected domain analysis on the input image to obtain a minimum circumscribed rectangle of the binary image, that is, a face region.
  • the computer device first displays the pixels in the binary image that meet the preset connection rule by the same label, obtains the connected area contour of the binary image, and obtains the minimum circumscribed rectangle of the connected area.
  • Methods for connecting domain tags include pixel notation, line notation, and region growing.
  • the deforming contour of the detected image includes: determining whether there is glasses in the image, and when there is a human face in the image, detecting whether the area where the glasses is located includes a face, and when the glasses are located When the face is included, the facial contour of the area where the glasses are located is acquired, and the facial contour of the area where the glasses are located is used as the deformed contour including the face.
  • an image correction method includes:
  • operation 302 it is determined whether there is glasses in the image. When there are glasses in the image, operation 304 is performed, and when there is no glasses in the image, the process ends.
  • operation 304 it is detected whether the area where the glasses are located includes a facial contour.
  • operation 306 is performed, and when the area where the glasses is located does not include a facial contour, the processing ends.
  • operation 306 it is determined whether the deformation trend of the facial contour of the region where the glasses are located is reduced. When the deformation trend is reduced, operation 308 is performed, and when the deformation trend is not reduced, operation 310 is performed.
  • Operation 308 selecting the first deformation operator, and performing operation 312.
  • the first deformation operator is a myopia deformation operator.
  • Operation 310 selecting the second deformation operator, performs operation 312.
  • the second deformation operator is a far vision mirror deformation operator.
  • Operation 312 identifying a facial contour of the face in the image.
  • Operation 316 adjusting the deformation operator according to the fitting curve and the deformation profile to obtain an updated deformation operator.
  • Operation 318 deforming the deformation profile by using the updated deformation operator.
  • the corresponding deformation operator is selected according to the deformation trend of the facial contour in the region where the glasses are located, and the facial contour is detected according to the face.
  • the contour of the contour is fitted to the deformation profile to obtain a fitting curve.
  • the deformation operator is adjusted according to the fitting curve and the deformation contour to obtain the updated deformation operator.
  • the deformation deformation can be corrected according to the updated deformation operator.
  • the contour of the back face improves the imaging effect of the face, so that the user wearing the glasses gets a better portrait photo when shooting. When the area where the eye is located does not contain the face area, it ends, which reduces data processing.
  • FIG. 4 is a schematic diagram showing deformation of a photo taken by a user wearing glasses in an embodiment.
  • FIG. 4 the facial contour of the area in which the glasses are located is inwardly concave due to the refraction of the glasses, and if there is a fault in both the facial contour 42 and the facial contour 44, the facial contour 44 represents the deformed contour.
  • FIG. 5 is a schematic diagram showing a fitting curve obtained by fitting a deformation region in the contour of the face in FIG. 4 in one embodiment.
  • a fitted curve 46 is obtained by fitting a fault region between the facial contour 42 and the facial contour 44.
  • the selected deformation operator can be adjusted according to the fitting curve 46 and the face contour 44 to obtain an updated deformation operator.
  • the facial contour 44 is deformed according to the updated deformation operator to obtain a corrected facial contour.
  • the above image correction method can be applied to a photo editor.
  • the image correction method is used to correct the photo in the photo editor.
  • the operations in the flowchart of the method of the embodiment of the present application are sequentially displayed in accordance with the indication of the arrows, but the operations are not necessarily performed in the order indicated by the arrows. Except as explicitly stated herein, the execution of these operations is not strictly limited, and may be performed in other sequences. Moreover, at least a part of the operations in the method flowchart of the embodiment of the present application may include multiple sub-operations or multiple stages, which are not necessarily performed at the same time, but may be executed at different times. The order of execution is not necessarily performed sequentially, but may be performed alternately or alternately with at least a portion of the sub-operations or phases of other operations or other operations.
  • FIG. 6 is an internal block diagram of an image correcting device in one embodiment.
  • an image correction device 600 includes a detection module 602 , a selection module 604 , an identification module 606 , a fitting module 608 , an adjustment module 610 , and a correction module 612 . among them:
  • the detection module 602 detects a deformation profile that includes a face in the image.
  • the selecting module 604 is configured to determine a deformation trend of the deformation profile, and select a corresponding deformation operator according to the deformation trend.
  • the identification module 606 is for identifying a facial contour of the face in the image.
  • the fitting module 608 is configured to perform curve fitting on the deformation profile of the face according to the facial contour to obtain a fitting curve.
  • the adjustment module 610 is configured to adjust the deformation operator according to the fitting curve and the deformation profile to obtain an updated deformation operator.
  • the correction module 612 is configured to deform the deformation profile by using the updated deformation operator.
  • the image correcting device in the embodiment of the present application detects the deformation profile of the face in the image, selects a corresponding deformation operator according to the deformation trend of the deformation profile, detects the contour of the face, and formulates the deformation profile according to the contour of the face.
  • the fitting curve is obtained, and the deformation operator is adjusted according to the fitting curve and the deformation contour to obtain the updated deformation operator, and the deformed contour can be corrected according to the updated deformation operator to obtain the corrected facial contour and improved.
  • the imaging effect of the face is obtained, and the deformation operator is adjusted according to the fitting curve and the deformation contour to obtain the updated deformation operator, and the deformed contour can be corrected according to the updated deformation operator to obtain the corrected facial contour and improved.
  • the detection module 602 is further configured to acquire the deformation profile including the face according to the color of the skin.
  • the detecting module 602 is further configured to determine whether there is glasses in the image, and when there is glasses in the image, detecting whether the area where the glasses is located includes a face, and when the area where the glasses is located includes a face, acquiring the The facial contour of the region where the glasses are located, and the facial contour of the region where the glasses are located is used as the deformed contour including the face.
  • the selecting module 604 is further configured to: when determining that the deformation trend of the deformation contour is reduced, selecting a first deformation operator; and when determining that the deformation trend of the deformation contour is expanding, selecting the second Deformation operator.
  • the detection module 602 is further configured to identify a deformation profile of the image that includes the face using a machine learning model.
  • each module in the image correcting device described above is for illustrative purposes only. In other embodiments, the image correcting device may be divided into different modules as needed to perform all or part of the functions of the image correcting device.
  • the various modules in the image correcting device described above may be implemented in whole or in part by software, hardware, and combinations thereof.
  • the above modules may be embedded in the hardware in the processor or in the memory in the server, or may be stored in the memory in the server, so that the processor calls the corresponding operations of the above modules.
  • the terms "component”, “module” and “system” and the like are intended to mean a computer-related entity, which may be hardware, a combination of hardware and software, software, or software in execution.
  • a component can be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer.
  • both the application running on the server and the server can be components.
  • One or more components can reside within a process and/or executed thread, and the components can be located within one computer and/or distributed between two or more computers.
  • the embodiment of the present application also provides a non-transitory computer readable storage medium.
  • One or more non-transitory computer readable storage media containing computer executable instructions that, when executed by one or more processors, cause the processor to perform an image correction method as described above.
  • the embodiment of the present application further provides a computer device.
  • the above computer device includes an image processing circuit, and the image processing circuit may be implemented by hardware and/or software components, and may include various processing units defining an ISP (Image Signal Processing) pipeline.
  • Figure 7 is a schematic illustration of an image processing circuit in one embodiment. As shown in FIG. 7, for convenience of explanation, only various aspects of the image processing technique related to the embodiment of the present application are shown.
  • the image processing circuit includes an ISP processor 740 and a control logic 750.
  • the image data captured by imaging device 710 is first processed by ISP processor 740, which analyzes the image data to capture image statistical information that may be used to determine and/or control one or more control parameters of imaging device 710.
  • Imaging device 710 can include a camera having one or more lenses 712 and image sensors 714.
  • Image sensor 714 can include a color filter array (such as a Bayer filter) that can capture light intensity and wavelength information captured with each imaging pixel of image sensor 714 and provide a set of primitives that can be processed by ISP processor 740 Image data.
  • Sensor 720 can provide raw image data to ISP processor 740 based on sensor 720 interface type.
  • the sensor 720 interface may utilize a SMIA (Standard Mobile Imaging Architecture) interface, other serial or parallel camera interfaces, or a combination of the above.
  • SMIA Serial Mobile Imaging Architecture
  • the ISP processor 740 processes the raw image data pixel by pixel in a variety of formats.
  • each image pixel can have a bit depth of 8, 10, 12, or 14 bits, and the ISP processor 740 can perform one or more image processing operations on the raw image data, collecting statistical information about the image data. Among them, image processing operations can be performed with the same or different bit depth precision.
  • ISP processor 740 can also receive pixel data from image memory 730. For example, raw pixel data is sent from the sensor 720 interface to image memory 730, which is then provided to ISP processor 740 for processing.
  • Image memory 730 can be part of a memory device, a storage device, or a separate dedicated memory within an electronic device, and can include DMA (Direct Memory Access) features.
  • DMA Direct Memory Access
  • ISP processor 740 can perform one or more image processing operations, such as time domain filtering.
  • the processed image data can be sent to image memory 730 for additional processing before being displayed.
  • the "front end” processing data may also be received directly from the ISP processor 740, or the "front end” processing data may be received from the image memory 730, and the "front end” processing data may be processed in the original domain and in the RGB and YCbCr color spaces.
  • the processed image data can be output to display 770 for viewing by a user and/or further processed by a graphics engine or GPU (Graphics Processing Unit).
  • graphics engine or GPU Graphics Processing Unit
  • the output of ISP processor 740 can also be sent to image memory 730, and display 770 can read image data from image memory 730.
  • image memory 730 can be configured to implement one or more frame buffers.
  • the output of ISP processor 740 can be sent to encoder/decoder 760 to encode/decode image data. The encoded image data can be saved and decompressed before being displayed on the display 770 device.
  • the ISP processor 740 processes the image data by performing VFE (Video Front End) processing and CPP (Camera Post Processing) processing on the image data.
  • VFE processing of the image data may include correcting the contrast or brightness of the image data, modifying the digitally recorded illumination state data, performing compensation processing on the image data (such as white balance, automatic gain control, gamma correction, etc.), and performing image data.
  • CPP processing of image data may include scaling the image, providing a preview frame and a recording frame to each path. Among them, CPP can use different codecs to process preview frames and record frames.
  • the image data processed by the ISP processor 740 can be sent to the beauty module 760 for aesthetic processing of the image prior to being displayed.
  • the beauty treatment of the image data by the beauty module 760 may include: whitening, freckle, dermabrasion, face-lifting, acne, eye enlargement, and the like.
  • the beauty module 760 can be a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) in a computer device.
  • the processed data of the beauty module 760 can be sent to the encoder/decoder 770 to encode/decode the image data.
  • the encoded image data can be saved and decompressed before being displayed on the display 780 device.
  • the statistics determined by the ISP processor 740 can be sent to the control logic 750 unit.
  • the statistics may include image sensor 714 statistics such as auto exposure, auto white balance, auto focus, flicker detection, black level compensation, lens 712 shading correction, and the like.
  • Control logic 750 can include a processor and/or a microcontroller that executes one or more routines, such as firmware, and one or more routines can determine control parameters and control of imaging device 710 based on received statistical data.
  • the control parameters may include sensor 720 control parameters (eg, gain, integration time for exposure control), camera flash control parameters, lens 712 control parameters (eg, focus or zoom focal length), or a combination of these parameters.
  • the ISP control parameters may include gain levels and color correction matrices for automatic white balance and color adjustment (eg, during RGB processing), and lens 712 shading correction parameters.
  • the image correction method described above is implemented by a processor in the image processing technique of FIG.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or the like.

Abstract

L'invention a trait à un procédé de correction d'image, qui comprend les étapes consistant : à détecter un contour déformé contenant un visage dans une image ; à déterminer une tendance de déformation du contour déformé, et à sélectionner un opérateur de déformation correspondant à la tendance de déformation ; à identifier un contour facial du visage dans l'image ; à effectuer un ajustement de courbe sur le contour déformé du visage selon le contour facial pour obtenir une courbe ajustée ; à modifier l'opérateur de déformation en fonction de la courbe ajustée et du contour déformé pour obtenir un opérateur de déformation mis à jour ; et à effectuer un traitement de déformation sur le contour déformé au moyen de l'opérateur de déformation mis à jour.
PCT/CN2018/094471 2017-07-18 2018-07-04 Procédé de correction d'image, support d'informations lisible par ordinateur et dispositif informatique WO2019015477A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710587813.9 2017-07-18
CN201710587813.9A CN107368806B (zh) 2017-07-18 2017-07-18 图像矫正方法、装置、计算机可读存储介质和计算机设备

Publications (1)

Publication Number Publication Date
WO2019015477A1 true WO2019015477A1 (fr) 2019-01-24

Family

ID=60306903

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/094471 WO2019015477A1 (fr) 2017-07-18 2018-07-04 Procédé de correction d'image, support d'informations lisible par ordinateur et dispositif informatique

Country Status (2)

Country Link
CN (1) CN107368806B (fr)
WO (1) WO2019015477A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112529927A (zh) * 2020-12-11 2021-03-19 西安电子科技大学 基于fpga形态学算子的自适应轮廓提取系统及方法
CN112767359A (zh) * 2021-01-21 2021-05-07 中南大学 复杂背景下的钢板角点检测方法及系统
CN115063607A (zh) * 2022-08-17 2022-09-16 腾讯科技（深圳）有限公司 切割轮廓的确定方法、装置、设备、存储介质及程序产品

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107368806B (zh) * 2017-07-18 2020-01-10 Oppo广东移动通信有限公司 图像矫正方法、装置、计算机可读存储介质和计算机设备
CN109447911B (zh) * 2018-10-18 2020-06-09 百度在线网络技术（北京）有限公司 图像复原的方法、装置、存储介质和终端设备
CN111444856A (zh) * 2020-03-27 2020-07-24 广东博智林机器人有限公司 图像的分析方法、模型的训练方法、装置、设备及存储介质
CN113486714B (zh) * 2021-06-03 2022-09-02 荣耀终端有限公司 一种图像的处理方法及电子设备
CN113435445A (zh) * 2021-07-05 2021-09-24 深圳市鹰硕技术有限公司 图像过优化自动纠正方法以及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103824253A (zh) * 2014-02-19 2014-05-28 中山大学 一种基于图像局部精确变形的人物五官变形方法
JP2014146215A (ja) * 2013-01-30 2014-08-14 Nec Corp 画像補正装置、画像補正方法および画像補正プログラム
CN105678251A (zh) * 2015-12-31 2016-06-15 Tcl海外电子（惠州）有限公司 人脸图像处理方法及装置
CN107368806A (zh) * 2017-07-18 2017-11-21 广东欧珀移动通信有限公司 图像矫正方法、装置、计算机可读存储介质和计算机设备

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100464346C (zh) * 2006-04-29 2009-02-25 北大方正集团有限公司 一种表格图像几何畸变的数字校正方法
CN102034079B (zh) * 2009-09-24 2012-11-28 汉王科技股份有限公司 眼镜遮挡下的人脸识别方法和系统
CN102542534B (zh) * 2010-12-31 2015-01-14 北京海思威科技有限公司 基于图像轮廓的图像畸变校正方法和装置
CN104811602A (zh) * 2014-01-24 2015-07-29 维科技术有限公司 移动终端的自拍方法及其装置
CN104408426B (zh) * 2014-11-27 2018-07-24 小米科技有限责任公司 人脸图像眼镜去除方法及装置
CN104537630A (zh) * 2015-01-22 2015-04-22 厦门美图之家科技有限公司 一种基于年龄估计的图像美颜方法和装置
US9514524B2 (en) * 2015-02-27 2016-12-06 Sony Corporation Optical distortion compensation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014146215A (ja) * 2013-01-30 2014-08-14 Nec Corp 画像補正装置、画像補正方法および画像補正プログラム
CN103824253A (zh) * 2014-02-19 2014-05-28 中山大学 一种基于图像局部精确变形的人物五官变形方法
CN105678251A (zh) * 2015-12-31 2016-06-15 Tcl海外电子（惠州）有限公司 人脸图像处理方法及装置
CN107368806A (zh) * 2017-07-18 2017-11-21 广东欧珀移动通信有限公司 图像矫正方法、装置、计算机可读存储介质和计算机设备

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112529927A (zh) * 2020-12-11 2021-03-19 西安电子科技大学 基于fpga形态学算子的自适应轮廓提取系统及方法
CN112767359A (zh) * 2021-01-21 2021-05-07 中南大学 复杂背景下的钢板角点检测方法及系统
CN112767359B (zh) * 2021-01-21 2023-10-24 中南大学 复杂背景下的钢板角点检测方法及系统
CN115063607A (zh) * 2022-08-17 2022-09-16 腾讯科技（深圳）有限公司 切割轮廓的确定方法、装置、设备、存储介质及程序产品

Also Published As

Publication number Publication date
CN107368806A (zh) 2017-11-21
CN107368806B (zh) 2020-01-10

Similar Documents

Publication Publication Date Title
US10929646B2 (en) Method and apparatus for image processing, and computer-readable storage medium
WO2019015477A1 (fr) Procédé de correction d'image, support d'informations lisible par ordinateur et dispositif informatique
EP3477931B1 (fr) Procédé et dispositif de traitement d'images, support d'informations lisible et dispositif électronique
JP7027537B2 (ja) 画像処理方法および装置、電子機器、ならびにコンピュータ可読記憶媒体
US11250571B2 (en) Robust use of semantic segmentation in shallow depth of field rendering
WO2021017811A1 (fr) Procédé et appareil de traitement d'image, dispositif électronique et support d'informations lisible par ordinateur
WO2017101626A1 (fr) Procédé et appareil pour mettre en œuvre un traitement d'image
CN108537155B (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
CN107766831B (zh) 图像处理方法、装置、移动终端和计算机可读存储介质
US11854243B2 (en) Gaze correction of multi-view images
CN107509031B (zh) 图像处理方法、装置、移动终端及计算机可读存储介质
WO2021022983A1 (fr) Appareil et procédé de traitement d'images, dispositif électronique et support d'enregistrement lisible par ordinateur
EP3480784B1 (fr) Procédé et dispositif de traitement d'images
CN108846807B (zh) 光效处理方法、装置、终端及计算机可读存储介质
CN107993209B (zh) 图像处理方法、装置、计算机可读存储介质和电子设备
CN107862658B (zh) 图像处理方法、装置、计算机可读存储介质和电子设备
US11538175B2 (en) Method and apparatus for detecting subject, electronic device, and computer readable storage medium
CN109242794B (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
WO2019105304A1 (fr) Procédé de traitement d'équilibrage des blancs d'une image, support de d'informations lisible par ordinateur, et dispositif électronique
WO2019061659A1 (fr) Procédé et dispositif permettant de supprimer des lunettes d'une image de visage, et support d'informations
CN107578372B (zh) 图像处理方法、装置、计算机可读存储介质和电子设备
CN107392870B (zh) 图像处理方法、装置、移动终端及计算机可读存储介质
CN107770446B (zh) 图像处理方法、装置、计算机可读存储介质和电子设备
JP2002269545A (ja) 顔画像処理方法及び顔画像処理装置
CN109118427B (zh) 图像光效处理方法和装置、电子设备、存储介质

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: 18835776

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: 18835776

Country of ref document: EP

Kind code of ref document: A1