WO2023207381A1 - 图像处理方法、装置、电子设备和存储介质 - Google Patents

图像处理方法、装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2023207381A1
WO2023207381A1 PCT/CN2023/081335 CN2023081335W WO2023207381A1 WO 2023207381 A1 WO2023207381 A1 WO 2023207381A1 CN 2023081335 W CN2023081335 W CN 2023081335W WO 2023207381 A1 WO2023207381 A1 WO 2023207381A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
image
dyeing
configuration
target
Prior art date
Application number
PCT/CN2023/081335
Other languages
English (en)
French (fr)
Inventor
马佳欣
王雨佳
黄佳斌
陈沙利
Original Assignee
北京字跳网络技术有限公司
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 北京字跳网络技术有限公司 filed Critical 北京字跳网络技术有限公司
Publication of WO2023207381A1 publication Critical patent/WO2023207381A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/001—Texturing; Colouring; Generation of texture or colour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/451—Execution arrangements for user interfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence

Definitions

  • Embodiments of the present disclosure relate to image processing technology, for example, to an image processing method, device, electronic device, and storage medium.
  • Short video materials are generally generated from images or video clips to be displayed. In order to enrich the display effect of short videos, special effects are often superimposed on the images in the short video materials.
  • Embodiments of the present disclosure provide an image processing method, device, electronic device and storage medium to meet the personalized needs of hair dyeing.
  • an embodiment of the present disclosure provides an image processing method, including:
  • a highlight special effects configuration interface In response to the received special effects configuration triggering operation for configuring the hair highlight special effects, a highlight special effects configuration interface is displayed, wherein the highlight special effects configuration interface displays an image preview area and at least one highlight configuration item.
  • the dyeing configuration items at least include area configuration items used to configure the dyeing area;
  • embodiments of the present disclosure also provide an image processing device, including:
  • An interface display module configured to display a highlight special effects configuration interface in response to a received special effects configuration trigger operation for configuring hair highlight special effects, wherein the highlight special effects configuration interface displays an image preview area and at least one highlight Configuration items, the highlight configuration items at least include area configuration items for configuring the dyeing area;
  • the image display module to be processed is configured to display the image to be processed for configuring hair highlighting special effects in the image preview area;
  • the dyeing effect display module is configured to receive the dyeing area configuration parameters input based on the area configuration item, and display in the image preview area the dyed target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed. stain preview image.
  • embodiments of the present disclosure also provide an electronic device, including:
  • the processor When the program is executed by the processor, the processor is caused to implement the image processing method described in any embodiment of the present disclosure.
  • embodiments of the present disclosure also provide a computer-readable storage medium.
  • the computer-readable storage medium stores computer instructions.
  • the computer instructions are used to implement any embodiment of the disclosure when executed by a processor.
  • Figure 1 is a schematic flowchart of an image processing method provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic flowchart of another image processing method provided by an embodiment of the present disclosure.
  • FIG. 3 is a schematic flowchart of another image processing method provided by an embodiment of the present disclosure.
  • FIG. 4 is a schematic flowchart of another image processing method provided by an embodiment of the present disclosure.
  • Figure 5 is a schematic diagram of a highlight special effect configuration interface provided by an embodiment of the present disclosure.
  • Figure 6 is a structural block diagram of an image processing device provided by an embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of an electronic device that implements the image processing method according to an embodiment of the present disclosure.
  • the term “include” and its variations are open-ended, ie, “including but not limited to.”
  • the term “based on” means “based at least in part on.”
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; and the term “some embodiments” means “at least some embodiments”. Relevant definitions of other terms will be given in the description below.
  • Figure 1 is a schematic flowchart of an image processing method provided by an embodiment of the present disclosure.
  • the embodiment of the present disclosure is applicable to the situation of hair highlight processing.
  • the method can be executed by an image processing device, and the device can use software and/or hardware.
  • PC Personal Computer
  • the method of the embodiment of the present disclosure may include:
  • the special effects configuration triggering operation may be a triggering operation for enabling the function of configuring parameters for the hair highlight special effects.
  • the highlight special effect configuration interface may be a user interaction interface used to implement the operation logic of parameter configuration of the hair highlight special effect.
  • the highlight special effect configuration interface may display at least one highlight configuration item.
  • the highlight configuration items can be understood as various parameter configuration controls used to set the effects associated with hair highlights.
  • the highlight configuration items at least include area configuration items for configuring the dyeing area.
  • the area configuration item can be understood as providing the user with controls that can configure the dyeing area on the hair.
  • the highlight special effects configuration interface may also display an image preview area.
  • the image preview area may include an image display control and an image display area for obtaining the image to be processed.
  • the image display control may be an image capture control for enabling the capture device to capture images in real time and an image upload control for uploading images from a target image library.
  • the image display area can be used to display the image before the hair highlighting special effect and the image after configuring the hair highlighting special effect, so that users can view the effect of the hair highlighting.
  • the image preview area may also be provided with an original image viewing control for viewing the image before the hair highlight special effect is applied, or used to switch between displaying the image before the hair highlight special effect is configured and the image after the hair highlight special effect is configured.
  • Image toggle control That is, switch the control that displays the image to be processed and the stained preview image. This allows users to compare and view the image effects before and after configuring the hair highlight effects at any time.
  • the received special effect configuration triggering operation for configuring the hair highlighting special effect may include: receiving a control triggering operation acting on a preset special effects triggering control for enabling the hair highlighting special effect; or, by inputting The operation of the preset special effects enabling command to enable the hair highlight special effect; or, receiving the interface opening operation for opening the highlight special effect configuration interface, etc.
  • the special effects activation command may be a command in the form of machine language, or a command in the form of voice, or a command in the form of a preset action, or a command in the touch trajectory type, etc.
  • the image to be processed may be an image used to perform hair highlighting effects.
  • the image presentation control may include an image capture control for enabling the capture device to capture images in real time and/or an image upload control for uploading images from a target image library.
  • the image display area can be used to display images obtained through the image display control.
  • the image obtained through the image display control may be used as the image to be processed.
  • the image upload control may be an operation control provided in the image preview area for uploading images.
  • the image to be processed can be uploaded by clicking a preset image upload control.
  • the image to be processed can also be uploaded by dragging the image to be processed or the video including the image to be processed into the image preview area, so that the image to be processed for configuring the hair highlight special effect is displayed in the image preview area.
  • the image to be processed can be an independent image or an image in a video.
  • the method includes: receiving an image upload operation input based on an image upload control in the image preview area, displaying the uploaded image in the image preview area, and using the uploaded image as a to-be-processed image for configuring a hair highlight special effect.
  • the user uploads the image to be processed to the image preview area through the image upload operation in the image preview area of the highlight special effects configuration interface, and displays the image to be processed in the image preview area so that the user can confirm more intuitively.
  • Configuration object used to configure hair highlight effects is
  • displaying the image to be processed for configuring the hair highlight effect in the image preview area includes: receiving a video upload operation input based on the video upload control of the image preview area, and displaying the upload in the image preview area. of the video, and use the images in the uploaded video that meet the preset conditions as the images to be processed for configuring the hair highlight effects.
  • the video upload control may be an operation control provided in the video preview area for uploading videos.
  • the video upload operation may be an operation that triggers the video upload control to upload the video.
  • the video upload control can be triggered by clicking or pressing.
  • the user uploads the video to be uploaded to the image preview area by triggering the video upload operation of the video upload control in the video preview area of the highlight special effects configuration interface, and displays the uploaded video in the image preview area.
  • a video contains multiple frames of images.
  • images in uploaded videos that meet preset conditions can be used as images to be processed for configuring hair highlighting special effects.
  • the preset conditions can be set according to actual needs.
  • the preset condition may be all images in the video that contain the target processing object, or each frame of image in the video, or a preset number of images in the video or within a preset playback time range, etc.
  • the image to be processed for configuring the hair highlight effect may be all images in the video that contain the target processing object, or each frame of image in the video, or a preset number of images in the video or within a preset playback time range, etc.
  • the dyeing area configuration parameter may be an area determination parameter used to determine which area of the hair in the image to be processed is to be dyed.
  • the dyeing area parameters can be represented by area identifiers, such as the whole head area, the outer ear hanging area, the inner hanging ear area, the left hanging ear area, the right hanging ear area, etc.
  • the dyeing preview image may be an image to be processed after dyeing a region in the image to be processed corresponding to the dyeing region configuration parameter through the region configuration item.
  • the user can input the dyeing area configuration parameters through the area configuration item in the highlight special effect configuration interface, and then according to the dyeing area configuration parameters, the area corresponding to the image to be processed that matches the dyeing area configuration parameters is used as Carry out dyeing on the target dyeing area, and then display the dyed dyeing preview image in the image preview area so that users can view the dyeing effect.
  • the color dyed in the target dyeing area can be a default fixed color in the background, or a randomly matched color, or a color determined based on a preset color matching rule, etc.
  • the color determined based on the preset color matching rules may be the color determined based on the image background color, skin color, or the user's historical dyeing data in the image to be processed.
  • the highlight configuration items also include color configuration items and/or transparency configuration items. This allows users to personalize the color of the dyed area and the transparency of the dyed color.
  • the highlight configuration item may also include an object selection control for the processing object, allowing the user to select the target processing object in the image to be processed.
  • object selection control for the processing object, allowing the user to select the target processing object in the image to be processed. It can be understood that when there are multiple processable objects in the image to be processed, the target processing object can be accurately selected. For example, when the image to be processed includes two hair areas that can be processed, you can select the object to be processed through the object selection control. It can be understood that the object selection control can be used to select one of the target processing objects or can be used to select multiple target processing objects.
  • the highlight special effect configuration interface may include multiple area configuration items, each area configuration item corresponds to a dyeing area parameter, and each dyeing area configuration parameter corresponds to a dyeing area.
  • the input dyeing area configuration parameters can be determined through the selection operation input for each area configuration item. In other words, receiving the dyeing area configuration parameters input based on the area configuration item can be receiving multiple areas displayed on the highlight special effect configuration interface.
  • the selection operation of the configuration item obtains the dyeing area configuration parameters corresponding to the selected area configuration item.
  • the method of displaying in the image preview area the dyeing preview image after dyeing the target dyeing area corresponding to the dyeing area configuration parameters in the image to be processed can be a dynamic display or a static display, wherein the dynamic display can be It is displayed after the dyeing preview image is superimposed with preset dynamic elements, or an animation is generated based on the dyeing preview image for display.
  • the technical solution of the embodiment of the present disclosure displays the highlight special effects configuration interface by responding to the received special effects configuration trigger operation for configuring the hair highlight special effects, because the highlight special effects configuration interface displays an image preview area and at least one highlight.
  • Configuration items, highlight configuration items at least include regional configuration items for configuring the dyeing area, which can provide users with the function of selecting hair dyeing areas, and can interact with users to more accurately obtain user needs.
  • the image to be processed for configuring the hair highlight special effect is displayed in the image preview area, so that the user can intuitively view the image to be processed in the highlight special effect configuration interface, and then receive the dyeing area configuration parameters based on the input of the area configuration item , in the image preview area, the dyeing preview image after dyeing the target dyeing area corresponding to the dyeing area configuration parameters in the image to be processed is displayed, and the dyeing preview image can be generated according to the user's configuration parameters of the dyeing area to display different Hair highlights.
  • the technical solution of the present disclosure only requires the user to input the dyeing area configuration parameters through the area configuration item to automatically dye the selected area of the hair.
  • the interaction method is simple and has strong universal applicability, saving the user's manual processing time and improving It improves the generation efficiency of hair highlighting special effects, solves the technical problems in related technologies such as the professional requirements for refining the local information of the image, the time-consuming and labor-intensive and the unstable processing effect, and realizes the simple and rapid hair highlighting.
  • ,Satisfied The user's personalized hair dyeing needs improve the user experience.
  • FIG. 2 is a schematic flowchart of another image processing method provided by an embodiment of the present disclosure.
  • the technical solution of this embodiment is based on any optional technical solution in the embodiment of the present disclosure, and adds a highlight configuration item.
  • the highlight configuration items also include color configuration items and/or transparency configuration items. In this way, the parameter configuration of hair dyeing can be made more diverse through the configuration of color configuration items and/or transparency configuration items.
  • the image processing method may further include: receiving a color configuration operation based on input of the color configuration item; correspondingly, displaying in the image preview area a comparison of the image to be processed and
  • the dyeing preview image after dyeing the target dyeing area corresponding to the dyeing area configuration parameter may include: in the image preview area, displaying the effect of the corresponding target color of the color configuration operation on the image to be processed and The staining preview image after the target staining area corresponding to the staining area configuration parameters.
  • the same or corresponding technical features as those in the previous embodiments will not be described again.
  • the image processing method according to the embodiment of the present disclosure may include:
  • the color configuration item is used to configure the color to be dyed in the target dyeing area, that is, the target color.
  • the color configuration items can be displayed in a variety of ways in the highlight special effect configuration interface, such as color identification input boxes, bar-shaped color cards, disk-shaped color selection cards, and color drop-down selection boxes.
  • color configuration operations can be multiple ways of receiving color configuration operations based on the color configuration item input. For example, it can be to receive colors for a bar-shaped color card, a disk-shaped color selection card, or a color drop-down selection box. Select the operation; or, receive the operation of inputting the color identification for the color identification input box, etc.
  • the color selection operation can be generated by clicking on the color, by scrolling the mouse after selecting the color configuration item, or by triggering the color switching control.
  • the target color corresponding to the color parameter of the color configuration item in the area configuration item is applied to the target dyeing area corresponding to the dyeing area configuration parameter. It can be understood that dyeing the target dyeing area corresponding to the dyeing area configuration parameter corresponds to the color configuration operation. target color.
  • the highlight special effects configuration interface can set Set the default color parameters and/or transparency parameters corresponding to the regional configuration items. The user can choose to adjust the color configuration items or transparency configuration items individually, or select both the color configuration items and the transparency configuration items at the same time.
  • the image processing method of the embodiment of the present disclosure may further include: receiving a transparency configuration operation based on the input of the transparency configuration item; accordingly, the Displaying in the image preview area a dyeing preview image after dyeing the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed includes: displaying the transparency configuration in the image preview area The target color transparency corresponding to the operation is applied to the dyeing preview image after the target color dyed in the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed.
  • the transparency configuration item is used to configure the color transparency of the color to be dyed in the target dyeing area, that is, the target color transparency.
  • the target transparency configured according to the transparency configuration item of the highlight special effect configuration interface is applied to the target color configured in the color configuration item, and then the target color is applied to the dyeing area corresponding to the configuration parameters. target dyeing area, thereby displaying the dyeing preview image after adjusting the transparency of the target dyeing area in the image preview area.
  • the user can perform highlight configuration on the color configuration item and the transparency configuration item at the same time.
  • a dyeing preview image after the target dyeing area of the image to be processed is dyed with the target color having the input color transparency is displayed.
  • the highlight special effects configuration interface can also provide the recommended color for configuring hair highlights in the regional configuration items and the recommended color transparency corresponding to the recommended color parameters, so that the user can choose Provide reference for more suitable hair highlighting effects.
  • the technical solution of the embodiment of the present disclosure can not only configure the hair highlight area, but also configure the color of the target dyeing area, which can better meet the personalized needs of users, and, on this basis, The color transparency can also be superimposed to adjust the target color of the hair, making the effect of hair highlights more natural and improving the user experience.
  • FIG. 3 is a schematic flowchart of another image processing method provided by an embodiment of the present disclosure.
  • the technical solution of this embodiment is based on any optional technical solution in the embodiment of the present disclosure, and refines how to quickly and accurately generate a dyeing preview image.
  • the staining area configuration parameters input based on the area configuration item, and displaying in the image preview area the images corresponding to the staining area configuration parameters in the image to be processed.
  • the method further includes: obtaining a region mask texture map corresponding to the dyeing region configuration parameters, and determining, according to the region mask texture map, the difference between the image to be processed and the The dyeing area configures a target dyeing area corresponding to the parameters, performs dyeing processing on the target dyeing area, and generates a dyeing preview image.
  • the same or corresponding technical features as those in the previous embodiments will not be described again.
  • the technical solution of this embodiment may include:
  • S330 Receive the dyeing area configuration parameters input based on the area configuration item, and obtain the area mask texture map corresponding to the dyeing area configuration parameters.
  • the regional mask texture map includes a mask texture map of the entire hair region and a mask texture map of at least one partial region of the hair.
  • obtaining the area mask texture corresponding to the staining area configuration parameters includes: identifying the image to be processed through a pre-trained neural network model corresponding to the staining area configuration parameters, and determining the area of the current image to be processed.
  • Mask texture map may include the mask texture map of the overall segmentation of the hair, the left outer ear hanging mask texture map, the right outer hanging ear mask texture map, the left inner hanging ear mask texture map, and the right inner hanging ear mask texture map.
  • a neural network model can be trained for each staining area configuration parameter to identify the staining area corresponding to the staining area configuration parameter in the image to be processed.
  • the pre-trained neural network model can be an image processing model, and the image processing model can be trained based on the neural network structure.
  • a convolutional neural network Convolutional Neural Network, CNN
  • CNN convolutional Neural Network
  • a large number of images containing faces and hair and regional mask texture maps after image processing are collected as training samples.
  • images containing faces and hair are input into the image processing model to be trained, and the image processing model to be trained outputs a trained area mask texture image.
  • the output area mask texture image is combined with the image processing
  • the resulting regional mask texture map is used to calculate the loss through the loss function, and the parameters in the image processing model to be trained are adjusted based on the calculated loss.
  • the loss function of the image processing model can include any one of the mean square error function, the mean absolute value error function and the cross-entropy error function.
  • S340 Determine the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed according to the area mask texture map.
  • the value in the R (red) or A (transparency) channel of the area mask texture map of the image to be processed can be obtained, and the area mask is determined based on the value in the R or A channel of the area mask texture map. Whether the pixels in the texture map belong to the target highlight area.
  • the value in the R or A channel can be [0, 1], where 0 indicates that it is not the target highlighted area, and 1 indicates that it is the target highlighted area.
  • the UV coordinates of each pixel point in the highlight area are used to determine each pixel point to be dyed in the image to be processed, and the area composed of each pixel point to be dyed in the image to be processed is determined as the target dyeing area corresponding to the dyeing area configuration parameters.
  • S350 Perform dyeing processing on the target dyeing area to generate a dyeing preview image.
  • the original color value of the pixel is fused with the color value to be dyed of the color to be dyed in the target dyeing area to obtain the target color value of the pixel.
  • fusing the original color value of the pixel with the to-be-dyed color value of the color to be dyed in the target dyeing area includes: fusing the original color value of the pixel with the target color according to a preset fusion operation rule.
  • the dyeing color values of the colors to be dyed in the dyeing area are fused, wherein the preset fusion operation rules include at least one of a summation operation, a weighted summation operation, a product operation and a weighted product operation.
  • the image processing method of the embodiment of the present disclosure may also include: adjusting the color of the target dyeing area to be dyed according to a preset color adjustment curve. Make adjustments; and/or adjust the color of the dyed target dyeing area according to the preset color adjustment curve. This setting can increase the contrast of the image, for example, making the bright areas brighter and the dark areas darker, thereby obtaining a better smoothing effect. Then, the target dyeing area is colored with the adjusted color to obtain a dyeing preview image.
  • the preset color adjustment curve can be understood as a curve used to adjust the brightness or saturation of a color.
  • it can be an adjustment curve generated based on a color look-up table (Look-Up-Table, LUT).
  • the color of the dyed target dyeing area can be adjusted according to the preset color adjustment curve.
  • the color of the target dyeing area to be dyed can be adjusted according to a preset color adjustment curve, and then, The target dyeing area is dyed based on the adjusted color to generate a dyeing preview image; or, after the target dyeing area corresponding to the dyeing area configuration parameters in the image to be processed is determined, the target dyeing area can be dyed based on the adjusted color.
  • the dyeing area is dyed, and then the color of the dyed target dyeing area is adjusted according to the preset color adjustment curve, and a dyeing preview image is generated based on the adjusted color; or, the image to be processed can be determined in After configuring the target dyeing area corresponding to the dyeing area parameters, the color to be dyed in the target dyeing area is adjusted according to the preset color adjustment curve, and then the target dyeing area is dyed based on the adjusted color. , and then adjust the color of the dyed target dyeing area according to the preset color adjustment curve, and generate a dyeing preview image based on the adjusted color.
  • S360 Display the dyeing preview image in the image preview area after dyeing the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed.
  • the dyeing preview image generated by performing the foregoing steps is the dyeing preview image after dyeing the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed.
  • the highlight special effects configuration interface is displayed.
  • the user can view the image to be processed with the hair highlighting effect in the image preview area of the highlight special effects configuration interface.
  • the user can intuitively select the hair area to be highlighted in the image to be processed, and then in the area Enter the dyeing area configuration parameters in the configuration item, enter the dyeing area configuration parameters in the area configuration item, and then obtain the corresponding area mask texture map through the pre-trained neural network model, and then determine the target corresponding to the dyeing area configuration parameters based on the area mask texture map.
  • the dyeing area in the hair is refined through the area mask texture map, and at the same time, the target dyeing area corresponding to the dyeing area configuration parameters is accurately located according to the area mask texture map, so that the target dyeing area is dyed and processed.
  • the image preview area displays the dyeing preview image of the target dyeing area corresponding to the dyeing area configuration parameters in the image to be processed, which improves the degree of refinement of the hair highlighting special effects and enables refined highlighting of each area of the hair. .
  • FIG. 4 is a schematic flowchart of another image processing method provided by Embodiment 3 of the present disclosure.
  • the technical solution of this embodiment is based on any optional technical solution in the embodiment of the present disclosure, and refines how to perform masking processing on the facial area to more accurately ensure the dyeing effect.
  • the step of dyeing the target dyed area includes: determining a face mask texture map of the facial area in the image to be processed, and performing the dyeing process on the target dyed area according to the face mask texture map. Dyeing treatment. Among them, the same or corresponding technical features as those in the previous embodiments will not be described again.
  • the technical solution of this embodiment may include:
  • S430 Receive the dyeing area configuration parameters input based on the area configuration item, and obtain the area mask texture map corresponding to the dyeing area configuration parameters.
  • S440 Determine the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed according to the area mask texture map.
  • S450 Determine the face mask texture map of the facial area in the image to be processed, perform dyeing processing on the target stained area according to the face mask texture map, and generate a stained preview image.
  • the facial area of the image to be processed is identified through a facial recognition algorithm, all the facial areas are regarded as non-stained areas, and the face mask texture map is obtained by setting the pixel values of the non-stained areas to 0 or 1.
  • the facial mask texture map at least includes the interface area between the facial area and the hair in the image to be processed. For example, forehead area or ear area, etc.
  • the embodiment of the present disclosure also uses a facial mask texture map to cover the facial area in the current image to be processed, thereby protecting the facial area and preventing the facial area from being dyed.
  • dyeing the target stained area according to the face mask texture map includes: determining an overlapping area between the target stained area and the face mask texture map, and removing the target stained area from the target stained area. The area outside the overlapping area is dyed.
  • the UV coordinates of the pixels in the target dyeing area in the image to be processed are obtained, and the UV coordinates of each pixel in the face mask texture map are also obtained.
  • the UV coordinates of the pixels determine the facial area in the image to be processed, and then match the UV coordinates of the target staining area with the facial area of the pixels in the image to be processed, and use the area corresponding to the successfully matched UV coordinates as the target staining
  • the overlapping area between the area and the face mask texture map, and the area of the target dyeing area except the overlapping area is dyed.
  • the target dyeing area is placed in the current to-be-processed image.
  • the UV coordinates of the pixels in the processed image are directly matched with the UV coordinates of each pixel in the facial mask texture map, and the area corresponding to the UV coordinates of the successfully matched pixel is used as the target dyeing area and the facial mask texture map. of the overlapping area, and perform dyeing processing on the area of the target dyeing area other than the overlapping area.
  • staining the area in the target staining area except the overlapping area includes: targeting each pixel in the area in the target staining area except the overlapping area. , fuse the original color value of the pixel with the to-be-dyed color value of the color to be dyed in the target dyeing area to obtain the target color value of the pixel.
  • the original color value may be the original color value of the pixel in the target dyeing area.
  • the color value to be dyed can be the color value that needs to be dyed for the hair. For example, it may be the color value of the target color corresponding to the color configuration operation.
  • fusing the original color value of the pixel with the to-be-dyed color value of the color to be dyed in the target dyeing area includes: fusing the original color value of the pixel with the target color according to a preset fusion operation rule.
  • the dyeing color values of the colors to be dyed in the dyeing area are fused, wherein the preset fusion operation rules include at least one of a summation operation, a weighted summation operation, a product operation and a weighted product operation.
  • the color value of the pixel to be dyed can be used as the target. color value.
  • S460 Receive the dyeing area configuration parameter input based on the area configuration item, and display the dyeing preview image in the image preview area after dyeing the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed.
  • the dyeing preview image generated by performing the previous steps is the dyeing preview image after dyeing the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed.
  • the highlight special effects configuration interface is displayed.
  • the user can view the image to be processed with the hair highlighting effect in the image preview area of the highlight special effects configuration interface.
  • the user can intuitively select the hair area to be highlighted in the image to be processed, and then in the area
  • the configuration item enters the dyeing area configuration parameters, and the dyeing area configuration parameters are entered in the area configuration item, and then when the corresponding area mask texture map is obtained through the pre-trained neural network model, the facial mask texture map is also obtained, and then the mask texture is based on the area.
  • the image and the facial mask texture map more accurately locate the dyeing area in the target dyeing area corresponding to the dyeing area configuration parameters except the overlapping area, thereby protecting the facial area, preventing the facial area from being dyed, and solving the problem of hair problems.
  • the problem of infecting the skin of the forehead may occur during dyeing. This improves the degree of refinement of the hair highlighting effects and achieves refined highlights of the target dyeing area of the hair.
  • Figure 5 is a schematic diagram of a highlight special effects configuration interface provided by an embodiment of the present disclosure.
  • the highlight special effects configuration interface includes area configuration items and an image preview area (ie, a preview window).
  • the preview window includes: image upload control, video upload control, image selection control, refresh control and image display area for displaying preview images.
  • the user can click the image upload control in the image preview window to select the image to upload, and then the image uploaded by the user can be displayed in the image display area; if the image uploaded by the user is a video, select the video button control to display the image uploaded by the user in the image display area.
  • videos users can select images in the video for processing or automatically identify images in the video for processing based on preset logic.
  • the user can click the refresh control to generate a preview dyeing preview image based on the user-configured target dyeing area, target color, and target color transparency, and Display the staining preview image in the image display area.
  • the highlight configuration items include: partial hair highlight area (outer ear highlight and inner ear highlight in Figure 5), color input field and transparency input field.
  • the user can select the target dyeing area through the configuration item of the local hair highlight area in the preview window, or can unselect the local hair highlight area corresponding to the selected dyeing position by selecting the dyeing position of the image to be processed displayed in the image display area.
  • configuration items The user can enter the color value to be dyed in the color input field, or select the color value to be dyed, that is, the target color, in the color selector provided in the highlight special effects configuration interface.
  • the user can enter the target color transparency in the transparency input field, or select the target color transparency using the transparency selector provided in the highlight effect configuration interface.
  • the fifth mask texture image is always the mask texture image of the overall segmentation of hair. mask4.
  • the value [0, 1] in the R channel of the area mask texture map is obtained. 0 means that it is not the target highlight area, and 1 means that it is the target highlight area.
  • the color value of the target color can be color adjusted to obtain a better smoothing effect.
  • the highlight area can be colored, and the input of color and transparency can be displayed in the image preview area.
  • the corresponding target color and target color transparency in the column are applied to the dyeing preview image after the target color dyed in the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed.
  • the technical solution of the embodiment of the present disclosure provides a layer of mask protection for the cheeks, using the face mask.
  • the mask texture pattern prevents the areas with skin from being colored, thereby ensuring the accuracy of the hair highlighting effects and achieving refined hair highlights.
  • FIG. 6 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure. As shown in Figure 6, the device may include: an interface display module 610, an image to be processed display module 620, and a dyeing effect display module 630.
  • the interface display module 610 is configured to display a highlight special effects configuration interface in response to a received special effects configuration trigger operation for configuring hair highlight special effects, wherein the highlight special effects configuration interface displays an image preview area and at least A highlight configuration item, the highlight configuration item at least includes a region configuration item for configuring the dyeing area; the image display module 620 to be processed is configured to display the to-be-processed image for configuring the hair highlight special effects in the image preview area Image; the dyeing effect display module 630 is configured to receive the dyeing area configuration parameters input based on the area configuration item, and display the target dyeing corresponding to the dyeing area configuration parameters in the image to be processed in the image preview area. Stain preview image after area staining.
  • the technical solution of the embodiment of the present disclosure displays the highlight special effects configuration interface by responding to the received special effects configuration trigger operation for configuring the hair highlight special effects, because the highlight special effects configuration interface displays an image preview area and at least one highlight.
  • Configuration items, highlight configuration items at least include regional configuration items for configuring the dyeing area, which can provide users with the function of selecting hair dyeing areas, and can interact with users to more accurately obtain user needs.
  • the image to be processed for configuring the hair highlight special effect is displayed in the image preview area, so that the user can intuitively view the image to be processed in the highlight special effect configuration interface, and then receive the dyeing area configuration parameters based on the input of the area configuration item , in the image preview area, the dyeing preview image after dyeing the target dyeing area corresponding to the dyeing area configuration parameters in the image to be processed is displayed, and the dyeing preview image can be generated according to the user's configuration parameters of the dyeing area to display different Hair highlights.
  • the technical solution of the present disclosure only requires the user to input the dyeing area configuration parameters through the area configuration item to automatically dye the selected area of the hair.
  • the interaction method is simple and has strong universal applicability, saving the user's manual processing time and improving It improves the generation efficiency of hair highlighting special effects, solves the technical problems in related technologies such as the professional requirements for refining the local information of the image, the time-consuming and labor-intensive and the unstable processing effect, and realizes the simple and rapid hair highlighting. , meets users’ personalized hair dyeing needs and improves user experience.
  • the image to be processed display module 620 is configured to determine the image to be processed for configuring the hair highlight special effect in the following manner:
  • the highlight configuration items also include color configuration items and/or transparency configuration items.
  • the device also includes:
  • a color configuration module configured to receive a color configuration operation based on the input of the color configuration item
  • the dyeing effect display module 630 is configured to display the dyeing preview image in the following manner:
  • a dyeing preview image after applying the corresponding target color of the color configuration operation to the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed is displayed.
  • the device also includes:
  • Transparency configuration module configured to receive transparency configuration operations based on the input of the transparency configuration item
  • the dyeing effect display module 630 is also configured to display the dyeing preview image in the following manner:
  • a dyeing preview image is displayed after applying the target color transparency corresponding to the transparency configuration operation to the target color dyed by the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed.
  • the device may also include:
  • a region mask module configured to display, in the image preview area, the configuration of the stained region in the image to be processed after receiving the stained region configuration parameters input based on the region configuration item.
  • the target mask texture map includes a mask texture map of the entire hair region and a mask texture map of at least one partial region of the hair.
  • the area mask module is configured to dye the target dyed area according to the facial mask texture map in the following manner:
  • a facial mask texture map of the facial area in the image to be processed is determined, and the target stained area is dyed according to the facial mask texture map.
  • the area mask module is configured to dye the target dyeing area except the overlapping area in the following manner:
  • An overlapping area between the target dyeing area and the face mask texture map is determined, and the area of the target dyeing area outside the overlapping area is dyed.
  • the area mask module is configured to perform color value fusion in the following manner:
  • the original color value of the pixel is fused with the to-be-dyed color value of the color to be dyed in the target dyeing area, Obtain the target color value of the pixel.
  • the area mask module is configured to perform color value fusion according to preset fusion operation rules in the following manner:
  • the original color value of the pixel is fused with the to-be-dyed color value of the color to be dyed in the target dyeing area according to the preset fusion operation rules, wherein the preset fusion operation rules include a summation operation, a weighted summation operation, At least one of the product operation and the weighted product operation.
  • the preset fusion operation rules include a summation operation, a weighted summation operation, At least one of the product operation and the weighted product operation.
  • the device also includes:
  • the color adjustment module is configured to adjust the color of the target dyeing area to be dyed according to a preset color adjustment curve; and/or adjust the color of the target dyeing area after dyeing according to the preset color adjustment curve.
  • the image processing device provided by the embodiments of the present disclosure can execute the image processing method provided by any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects for executing the image processing method.
  • the various units and modules included are only divided according to functional logic, but are not limited to the above divisions, as long as they can realize the corresponding functions; in addition, each unit and module is not limited to the above division.
  • the names of the functional units are also only for the purpose of distinguishing them from each other.
  • FIG. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • Terminal devices in embodiments of the present disclosure may include mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (Personal Digital Assistant, PDA), tablet computers (Portable Android Device, PAD), portable multimedia players (Portable Media Player, PMP), mobile terminals such as vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital televisions (that is, digital TVs), desktop computers, etc.
  • PDA Personal Digital Assistant
  • PAD Portable multimedia players
  • PMP portable multimedia players
  • mobile terminals such as vehicle-mounted terminals (such as vehicle-mounted navigation terminals)
  • fixed terminals such as digital televisions (that is, digital TVs), desktop computers, etc.
  • the electronic device shown in FIG. 7 is only an example.
  • the electronic device 700 may include a processing device (such as a central processing unit, a graphics processor, etc.) 701 , and the processing device 701 may process data stored in a read-only memory (Read Only Memory, ROM).
  • the program in 702 or the program loaded from the storage device 708 into the random access memory (Random Access Memory, RAM) 703 executes various appropriate actions and processes.
  • RAM 703 Random Access Memory
  • various programs and data required for the operation of the electronic device 700 are also stored.
  • the processing device 701, the ROM 702 and the RAM 703 are connected to each other via a bus 704.
  • An input/output (I/O) interface 705 is also connected to bus 704.
  • input devices 706 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a Liquid Crystal Display (LCD) , an output device 707 such as a speaker, a vibrator, etc.; a storage device 708 including a magnetic tape, a hard disk, etc.; and a communication device 709.
  • Communication device 709 may allow electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data.
  • FIG. 7 illustrates an electronic device 700 having various means, it should be understood that implementation or availability of all illustrated means is not required. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product including a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart diagram.
  • the computer program may be downloaded and installed from the network via communication device 709, or from storage device 708, or from ROM 702.
  • the processing device 701 the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.
  • the electronic device provided by the embodiments of the present disclosure and the image processing method provided by the above embodiments belong to the same inventive concept.
  • Technical details that are not described in detail in this embodiment can be referred to the above embodiments, and this embodiment has the same features as the above embodiments. beneficial effects.
  • Embodiments of the present disclosure provide a computer storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the image processing method provided by the above embodiments is implemented.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or a combination of the above two.
  • the computer-readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination thereof.
  • Examples of computer readable storage media may include: an electrical connection having at least one conductor, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (e.g., electronically removable memory).
  • a computer-readable storage medium may be a tangible medium that contains or stores a program that may be used by or in connection with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. This propagated data signal can be In various forms, including electromagnetic signals, optical signals, or a suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device .
  • Program codes contained on computer-readable media can be transmitted using appropriate media, including: wires, optical cables, radio frequency (Radio Frequency, RF), etc., or any suitable combination of the above.
  • the client and server can communicate using currently known or future developed network protocols such as HyperText Transfer Protocol (HTTP), and can communicate with digital data in any form or medium (e.g., communications network) interconnection.
  • HTTP HyperText Transfer Protocol
  • Examples of communication networks include local area networks (LAN), wide area networks (WAN), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as currently known or networks for future research and development.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; it may also exist independently without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries at least one program.
  • the electronic device executes the above-mentioned at least one program.
  • a highlight special effects configuration interface In response to the received special effects configuration triggering operation for configuring the hair highlight special effects, a highlight special effects configuration interface is displayed, wherein the highlight special effects configuration interface displays an image preview area and at least one highlight configuration item.
  • the dyeing configuration items at least include area configuration items used to configure the dyeing area;
  • Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedures, or a combination thereof. programming language such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through the Internet using an Internet service provider) .
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains at least one operable function for implementing the specified logical function.
  • Execute instructions may also be noted that in some alternative implementations, the functionality noted in the box may also be represented in a different form than The sequence noted in the drawing occurs. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block in the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure can be implemented in software or hardware.
  • the name of the unit does not constitute a limitation on the unit itself under certain circumstances.
  • the first acquisition unit can also be described as "the unit that acquires at least two Internet Protocol addresses.”
  • exemplary types of hardware logic components include: Field-Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP) ), System on Chip (SOC), Complex Programmable Logic Device (CPLD), etc.
  • FPGA Field-Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Parts
  • SOC System on Chip
  • CPLD Complex Programmable Logic Device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or suitable combinations of the foregoing. Examples of machine-readable storage media may include an electrical connection based on at least one wire, a portable computer disk, a hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory). flash memory), fiber optics, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or a suitable combination of the above.
  • Example 1 provides an image processing method, which includes:
  • a highlight special effects configuration interface In response to the received special effects configuration triggering operation for configuring the hair highlight special effects, a highlight special effects configuration interface is displayed, wherein the highlight special effects configuration interface displays an image preview area and at least one highlight configuration item.
  • the dyeing configuration items at least include area configuration items used to configure the dyeing area;
  • Example 2 provides an image processing method, which includes:
  • the image preview area displays the image to be processed for configuring the hair highlighting effect.
  • the image preview area displays the image to be processed for configuring the hair highlighting effect.
  • Example 3 provides an image processing method, which includes:
  • the highlight configuration items also include color configuration items and/or transparency configuration items.
  • Example 4 provides an image processing method, which includes:
  • Displaying in the image preview area a dyeing preview image after dyeing the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed includes:
  • a dyeing preview image after applying the corresponding target color of the color configuration operation to the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed is displayed.
  • Example 5 provides an image processing method, which includes:
  • Displaying in the image preview area a dyeing preview image after dyeing the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed includes:
  • a dyeing preview image is displayed after applying the target color transparency corresponding to the transparency configuration operation to the target color dyed by the target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed.
  • Example 6 provides an image processing method, which includes:
  • the staining preview image after staining the target staining area also includes:
  • Obtain a region mask texture map corresponding to the dyeing region configuration parameters determine a target dyeing region in the image to be processed corresponding to the dyeing region configuration parameters according to the region mask texture map, and dye the target The area is stained and a stained preview image is generated.
  • Example 7 provides an image processing method, which includes:
  • the target mask texture map includes a mask texture map of the entire hair region and a mask texture map of at least one partial region of the hair.
  • Example 8 provides an image processing method, which includes:
  • staining the target stained area includes:
  • a facial mask texture map of the facial area in the image to be processed is determined, and the target stained area is dyed according to the facial mask texture map.
  • Example 9 provides an image processing method, which includes:
  • dyeing the target dyeing area according to the face mask texture map includes:
  • An overlapping area between the target dyeing area and the face mask texture map is determined, and the area of the target dyeing area except the overlapping area is dyed.
  • Example 10 provides an image processing method, which method includes:
  • staining the area in the target staining area except the overlapping area includes:
  • the original color value of the pixel is fused with the to-be-dyed color value of the color to be dyed in the target dyeing area, Obtain the target color value of the pixel.
  • Example 11 provides an image processing method, which method includes:
  • fusing the original color value of the pixel with the color value to be dyed of the color to be dyed in the target dyeing area includes:
  • the original color value of the pixel is fused with the to-be-dyed color value of the color to be dyed in the target dyeing area according to the preset fusion operation rules, wherein the preset fusion operation rules include a summation operation, a weighted summation operation, At least one of the product operation and the weighted product operation.
  • the preset fusion operation rules include a summation operation, a weighted summation operation, At least one of the product operation and the weighted product operation.
  • Example 12 provides an image processing method
  • the method further includes: adjusting the color to be dyed in the target dyeing area according to a preset color adjustment curve; and/or,
  • Example 13 provides an image processing device, The device includes:
  • An interface display module configured to display a highlight special effects configuration interface in response to a received special effects configuration trigger operation for configuring hair highlight special effects, wherein the highlight special effects configuration interface displays an image preview area and at least one highlight Configuration items, the highlight configuration items at least include area configuration items for configuring the dyeing area;
  • the image display module to be processed is configured to display the image to be processed for configuring hair highlighting special effects in the image preview area;
  • the dyeing effect display module is configured to receive the dyeing area configuration parameters input based on the area configuration item, and display in the image preview area the dyed target dyeing area corresponding to the dyeing area configuration parameter in the image to be processed. stain preview image.

Abstract

本公开实施例提供了一种图像处理方法、装置、电子设备和存储介质。该方法包括：响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，挑染配置项至少包括用于配置染色区域的区域配置项；于图像预览区域内展示用于配置头发挑染特效的待处理图像；接收基于区域配置项输入的染色区域配置参数，于图像预览区域内展示对待处理图像中与染色区域配置参数对应的目标染色区域染色后的染色预览图像。

Description

图像处理方法、装置、电子设备和存储介质
本公开要求在2022年4月29日提交中国专利局、申请号为202210476183.9的中国专利申请的优先权，以上申请的全部内容通过引用结合在本公开中。
技术领域
本公开实施例涉及图像处理技术，例如涉及一种图像处理方法、装置、电子设备和存储介质。
背景技术
在当今社会，随着移动终端普及和网络的提速，短视频作为一种短平快的互联网内容传播方式，逐渐获得各大平台和视频创作者的青睐。短视频素材一般由待展示的图像或者视频片段生成。为了丰富短视频的展示效果，往往会对短视频素材中的图像进行特效叠加的处理。
相关的图像处理方式在针对图像中的局部信息进行处理时，往往无法进行精细化的处理。例如，对图像中精细处理往往需要通过手动处理的方式针对单张图像中的局部信息进行处理，整个处理过程十分繁琐且需要大量的人力成本，效率较低，而且由于手动处理对处理人员的专业性有一定的要求，导致图像处理的效果也因人而异，而且这种手动处理方式也难以满足日益增多的图像精细化处理需求。
发明内容
本公开实施例提供一种图像处理方法、装置、电子设备和存储介质，以满足头发染色的个性化需求。
第一方面，本公开实施例提供了一种图像处理方法，包括：
响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项；
于所述图像预览区域内展示用于配置头发挑染特效的待处理图像；
接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色 后的染色预览图像。
第二方面，本公开实施例还提供了一种图像处理装置，包括：
界面展示模块，设置为响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项；
待处理图像展示模块，设置为于所述图像预览区域内展示用于配置头发挑染特效的待处理图像；
染色效果展示模块，设置为接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
第三方面，本公开实施例还提供了一种电子设备，包括：
处理器；
存储装置，设置为存储程序，
当所述程序被所述处理器执行，使得所述处理器实现本公开任一实施例所述的的图像处理方法。
第四方面，本公开实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，所述计算机指令用于使处理器执行时实现本公开任一实施例所述的图像处理方法。
附图说明
贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1是本公开实施例所提供的一种图像处理方法的流程示意图；
图2是本公开实施例所提供的另一种图像处理方法的流程示意图；
图3是本公开实施例所提供的另一种图像处理方法的流程示意图；
图4是本公开实施例所提供的另一种图像处理方法的流程示意图；
图5是本公开实施例所提供的一种挑染特效配置界面的示意图；
图6是本公开实施例所提供的一种图像处理装置的结构框图；
图7是实现本公开实施例的图像处理方法的电子设备的结构示意图。
具体实施方式
下面将参照附图描述本公开的实施例。虽然附图中显示了本公开的一些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。应当理解的是，本公开的附图及实施例仅用于示例性作用。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
图1为本公开实施例所提供的一种图像处理方法流程示意图，本公开实施例适用于头发挑染处理的情形，该方法可以由图像处理装置来执行，该装置可以通过软件和/或硬件的形式实现，可选的，通过电子设备来实现，该电子设备可以是移动终端、个人计算机(PersonalComputer，PC)端或服务器等。
如图1所示，本公开实施例的方法可包括：
S110、响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面。
其中，特效配置触发操作可以是用于启用对头发挑染特效进行参数配置这一功能的触发操作。挑染特效配置界面可以是用于实现头发挑染特效的参数配置的操作逻辑的用户交互界面。
可选的，所述挑染特效配置界面可以展示有至少一个挑染配置项。其中，挑染配置项可以理解为用于设置关联头发挑染的效果的各个参数配置控件。为了实现对头发指定区域进行染色的功能，在本公开实施例中，挑染配置项至少包括用于配置染色区域的区域配置项。其中，区域配置项可以理解为用户提供能够配置头发上的染色区域的控件。
可选的，所述挑染特效配置界面还可以展示有图像预览区域。图像预览区域可以包括用于获取待处理图像的图像展示控件和图像展示区域。示例性地，图像展示控件可以是用于启用拍摄装置来实时拍摄图像的图像拍摄控件和用于从目标图像库中上传图像的图像上传控件。图像展示区域可以用于展示头发挑染特效前的图像和配置头发挑染特效后的图像，以供用户查看头发挑染的效果。
在一实施例中，图像预览区域还可以设置有查看应用头发挑染特效前的图像的原图查看控件，或者，用于切换展示配置头发挑染特效前的图像和配置头发挑染特效后的图像的切换控件。即，切换展示待处理图像和染色预览图像的控件。以便用户能够随时对比查看配置头发挑染特效前和配置头发挑染特效后的图像效果。
本公开实施例中，特效配置触发操作的生成方式有多种，只要在触发后能够启用对头发挑染特效进行参数配置这一功能的操作都在本公开实施例的保护范围内。
示例性地，接收到的用于配置头发挑染特效的特效配置触发操作，可以包括：接收到作用于预先设置的用于启用头发挑染特效的特效触发控件的控件触发操作；或者，通过输入预设的启用头发挑染特效的特效启用命令的操作；或者，接收到用于打开挑染特效配置界面的界面打开操作等。其中，特效启用命令可以是机器语言形式的命令，或者，语音形式的命令，或者，预设动作形式的命令，也可是触控轨迹式的命令等。
S120、于所述图像预览区域展示用于配置头发挑染特效的待处理图像。
其中，待处理图像可以是用于进行头发挑染特效的图像。如前所述，图像展示控件可以包括用于启用拍摄装置来实时拍摄图像的图像拍摄控件和/或用于从目标图像库中上传图像的图像上传控件。图像展示区域可以用于展示通过图像展示控件获取到的图像。在本公开实施例中，可以将该通过图像展示控件获取到的图像作为待处理图像。其中，图像上传控件可以是图像预览区域提供的用于上传的图像的操作控件。示例性的，可以点击预设的图像上传控件的方式上传待处理图像。可选地，也可以通过将待处理图像或者包括待处理图像的视频拖入图像预览区域的方式上传待处理图像，以于所述图像预览区域展示用于配置头发挑染特效的待处理图像。
需要说明的是，待处理图像可以是独立的一张图像，也可以是视频中的图像。
可选的，于所述图像预览区域展示用于配置头发挑染特效的待处理图像， 包括：接收基于所述图像预览区域的图像上传控件输入的图像上传操作，于所述图像预览区域展示上传的图像，将上传的图像作为用于配置头发挑染特效的待处理图像。
本公开实施例中，用户在挑染特效配置界面的图像预览区域中通过图像上传操作将待处理图像上传至图像预览区域，并在图像预览区域接展示待处理图像，以便用户更为直观地确认用于配置头发挑染特效的配置对象。
可选的，于所述图像预览区域展示用于配置头发挑染特效的待处理图像，包括：接收基于所述图像预览区域的视频上传控件输入的视频上传操作，于所述图像预览区域展示上传的视频，将上传的视频中的符合预设条件的图像作为用于配置头发挑染特效的待处理图像。
其中，视频上传控件可以是视频预览区域提供用于上传的视频的操作控件。视频上传操作可以是触发视频上传控件进行视频上传的操作。示例性的，可以点击或按压触发视频上传控件。
本公开实施例中，用户在挑染特效配置界面的视频预览区域中通过触发视频上传控件的视频上传操作将待上传的视频上传至图像预览区域，并在图像预览区域展示上传的视频。
一般地，视频中包含有多帧图像。在本公开实施例中，可以将上传的视频中的符合预设条件的图像作为用于配置头发挑染特效的待处理图像。其中，预设条件可以根据实际需求进行设置。示例性地，预设条件可以是视频中所有包含目标处理对象的图像，或者，视频中的每一帧图像，又或者，视频中预设数量或者处于预设播放时间范围内的图像等。示例性地，可以通过视频预览区域对上传的视频中的每一帧图像进行图像识别，确定上传的视频中的符合预设条件的图像，将上传的视频中的符合预设条件的图像作为用于配置头发挑染特效的待处理图像。
S130、接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
其中，染色区域配置参数可以是用于确定待处理图像中头发的哪个区域进行染色的区域确定参数。示例性地，染色区域参数可以通过区域标识来表示，如全头区域、外挂耳区域、内挂耳区域、左挂耳区域及以右挂耳区域等。染色预览图像可以是通过区域配置项将待处理图像中与染色区域配置参数对应的区域染色后的待处理图像。
本公开实施例中，用户可通过挑染特效配置界面中的区域配置项输入染色区域配置参数，进而在根据染色区域配置参数将待处理图像对应的区域中与染色区域配置参数相匹配的区域作为目标染色区域进行染色，然后在图像预览区域内展示染色后的染色预览图像，以便用户查看染色后的效果。
在一些实施例中，目标染色区域所染的颜色可以后台默认的固定颜色，或者，随机匹配的颜色，又或者，基于预设的颜色匹配规则确定的颜色等。其中，基于预设的颜色匹配规则确定的颜色可以是根据待处理图像中的图像背景颜色、皮肤颜色或者用户的历史染色数据等确定的颜色。
为了更好地适配用户需求，可选的，在本公开另一实施例中，所述挑染配置项还包括颜色配置项和/或透明度配置项等。以便于用户对标染色区域所染的颜色以及所染的颜色的透明度进行个性化配置。
另外，挑染配置项还可以包括处理对象的对象选择控件，以供用户选择待处理图像中的目标处理对象。可以理解的是，当待处理图像中存在多个可处理对象时，能够精准选择目标处理对象。例如，当待处理图像中包括两个可处理的头发区域时，可以通过对象选择控件，选择要处理的对象。可以理解的是，对象选择控件可以用于选择其中一个目标处理对象也可以用于选择多个目标处理对象。
在本公开实施例中，可选地，挑染特效配置界面中可以包括多个区域配置项，每个区域配置项对应一个染色区域参数，每个染色区域配置参数对应一个染色区域。可通过针对各个区域配置项输入的选中操作，确定输入的染色区域配置参数，换言之，接收基于所述区域配置项输入的染色区域配置参数，可以是接收针对挑染特效配置界面展示的多个区域配置项的选择操作，获取选中的区域配置项对应的染色区域配置参数。
于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像的方式可以是动态展示也可以是静态展示，其中，动态展示可以是在染色预览图像叠加预设的动态元素后展示，或者，基于所述染色预览图像生成动图来展示。
本公开实施例的技术方案，通过响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，由于挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，挑染配置项至少包括用于配置染色区域的区域配置项，能够为用户提供选择头发染色区域的功能，能够与用户进行交互，以便更为精准地获取用户需求。于所述图像预览区域展示用于配置头发挑染特效的待处理图像，使得用户能够在挑染特效配置界面中直观地查看待处理图像，进而接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像，能够根据用户对染色区域配置参数生成染色预览图像，展示不同的头发挑染效果。本公开的技术方案，只需要用户通过区域配置项输入的染色区域配置参数，即可自动对头发的选定区域进行染色，交互方式简单，普适性强，节省了用户的手动处理时间，提高了头发挑染特效的生成效率，解决了相关技术中对图像的局部信息进行精细化处理的专业性要求、时费时费力以及处理效果不稳定的技术问题，实现了简单快速地对头发进行挑染，满足了 用户的个性化的头发染色需求，提升了用户体验。
图2为本公开实施例所提供的另一种图像处理方法的流程示意图。本实施例的技术方案在本公开实施例中任一可选技术方案的基础上，增加了挑染配置项。可选地，所述挑染配置项还包括颜色配置项和/或透明度配置项。这样通过颜色配置项和/或透明度配置项的配置可以使头发染色的参数配置更加多样化。
可选地，本公开实施例的图像处理方法还可以包括：接收基于所述颜色配置项输入的颜色配置操作；相应地，所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像，可包括：于所述图像预览区域内，展示将所述颜色配置操作的对应的目标颜色作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域后的染色预览图像。其中，与前述实施例中相同或相应的技术特征不再赘述。
如图2所示，本公开实施例的图像处理方法可包括：
S210、响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项。
S220、于所述图像预览区域展示用于配置头发挑染特效的待处理图像。
S230、接收基于所述区域配置项输入的染色区域配置参数。
S240、接收基于所述颜色配置项输入的颜色配置操作。
其中，颜色配置项用于配置目标染色区域待染的颜色，即目标颜色。
在本公开实施例中，颜色配置项在挑染特效配置界面中的展示方式可以有多种，例如，颜色标识输入框、条状色卡、圆盘状颜色选择卡以及颜色下拉选择框等。示例性地，接收基于所述颜色配置项输入的颜色配置操作的方式也可以有多种，示例性地，可以是接收针对条状色卡、圆盘状颜色选择卡或者颜色下拉选择框的颜色选择操作；或者，接收针对颜色标识输入框输入颜色标识的操作等。其中，颜色选择操作的生成方式可以是通过针对颜色的点击操作生成，也可以是通过选中颜色配置项后滚动鼠标的方式生成，还可以是通过触发颜色切换控件的方式生成等。
S250、于所述图像预览区域内，展示将所述颜色配置操作的对应的目标颜色作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域后的染色预览图像。
其中，将区域配置项中颜色配置项的颜色参数对应的目标颜色作用在染色区域配置参数对应的目标染色区域，可以理解为，在染色区域配置参数对应的目标染色区域染上与颜色配置操作对应的目标颜色。
用户在挑染特效配置界面配置头发挑染特效时，挑染特效配置界面可以设 置与区域配置项对应的默认颜色参数和/或透明度参数，用户可以选择单独调整颜色配置项或透明度配置项，也可以选择同时颜色配置项和透明度配置项。
当所述挑染配置项包括透明度配置项时，作为一可选实施方式，本公开实施例的图像处理方法还可以包括：接收基于所述透明度配置项输入的透明度配置操作；相应地，所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像，包括：于所述图像预览区域内，展示将所述透明度配置操作对应的目标颜色透明度作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域所染的目标颜色后的染色预览图像。
其中，透明度配置项用于配置目标染色区域待染的颜色的颜色透明度，即，目标颜色透明度。
可选地，本公开实施例中，根据用户在挑染特效配置界面的透明度配置项配置的目标透明度作用于颜色配置项中配置的目标颜色上，进而将该目标颜色作用在染色区域配置参数对应的目标染色区域，从而在图像预览区域内展示目标染色区域透明度调整后的染色预览图像。
需要说明的是，在本公开实施例中，用户可以同时对颜色配置项和透明度配置项进行挑染配置。根据用户基于颜色配置项输入的目标颜色和基于透明度配置项输入的颜色透明度，展示对待处理图像的目标染色区域染上具有输入的颜色透明度的目标颜色后的染色预览图像。
可选的，用户在挑染特效配置界面进行挑染配置时，挑染特效配置界面还可以提供区域配置项中配置头发挑染的推荐颜色和与推荐颜色参数对应的推荐颜色透明度，为用户选择更适宜的头发挑染特效提供参考。
本公开实施例的技术方案，除了可以对头发挑染的区域进行配置，还可以对目标染色区域所染的颜色进行配置，能够更好地满足用户的个性化需求，而且，在此基础上，还可以叠加颜色透明度对所染的目标颜色的调整，使得头发挑染的效果更加自然，提升了用户体验。
图3为本公开实施例所提供的另一种图像处理方法的流程示意图。本实施例的技术方案在本公开实施例中任一可选技术方案的基础上，对如何快速精准地生成染色预览图像进行细化。可选地，在所述接收基于所述区域配置项输入的染色区域配置参数之后，以及在所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像之前，该方法还包括：获取与所述染色区域配置参数对应的区域遮罩纹理图，根据所述区域遮罩纹理图确定所述待处理图像中与所述染色区域配置参数对应的目标染色区域，并对所述目标染色区域进行染色处理，生成染色预览图像。其中，与前述实施例中相同或相应的技术特征不再赘述。
如图3所示，本实施例的技术方案可包括：
S310、响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项。
S320、于所述图像预览区域展示用于配置头发挑染特效的待处理图像。
S330、接收基于所述区域配置项输入的染色区域配置参数，获取与所述染色区域配置参数对应的区域遮罩纹理图。
其中，所述区域遮罩纹理图包括头发全部区域的遮罩纹理图以及至少一个头发局部区域的遮罩纹理图。
可选的，获取与所述染色区域配置参数对应的区域遮罩纹理，包括：通过预先训练的与所述染色区域配置参数对应的神经网络模型对待处理图像进行识别，确定当前待处理图像的区域遮罩纹理图。示例性的，区域遮罩纹理图可以包括头发整体分割的遮罩纹理图、左外挂耳遮罩纹理图、右外挂耳遮罩纹理图、左内挂耳遮罩纹理图和右内挂耳遮罩纹理图。
在本公开实施例中，可以针对每个染色区域配置参数训练一个神经网络模型，以识别待处理图像中与染色区域配置参数对应的染色区域。示例性地，预先训练的神经网络模型可以是图像处理模型，图像处理模型可以基于神经网络结构训练得出，例如可以采用卷积神经网络(ConvolutionalNeuralNetwork，CNN)对图像处理模型进行训练。
在训练图像处理模型之前，先收集大量的包含人脸和头发的图像和经过图像处理后的区域遮罩纹理图作为训练样本。在训练过程中，将包含人脸和头发的图像输入至待训练的图像处理模型中，得到待训练图像处理模型输出训练后的区域遮罩纹理图像，将输出的区域遮罩纹理图像与图像处理后的区域遮罩纹理图通过损失函数进行损失计算，根据计算的损失对待训练图像处理模型中的参数进行调整。当检测到待训练图像处理模型中损失函数收敛时，则待训练图像处理模型训练完成，获得图像处理模型。
其中，图像处理模型的损失函数可以包括：均方误差函数、平均绝对值误差函数和交叉熵误差函数中任意一种。
S340、根据所述区域遮罩纹理图确定所述待处理图像中与所述染色区域配置参数对应的目标染色区域。
本公开实施例中，可以获取待处理图像的区域遮罩纹理图的R(红色)或A(透明度)通道中的数值，根据区域遮罩纹理图的R或A通道中的数值确定区域遮罩纹理图中的像素点是否属于目标挑染区域。示例性的，R或A通道中的数值可以为[0，1]，其中，0表示不是目标挑染区域，1表示是目标挑染区域。
可选地，根据所述区域遮罩纹理图确定所述待处理图像中与所述染色区域配置参数对应的目标染色区域，例如可以是，根据区域遮罩纹理图中属于目标 挑染区域的各个像素点的UV坐标，确定出待处理图像中各个待染色像素点，将待处理图像中各个待染色像素点组成的区域确定为染色区域配置参数对应的目标染色区域。
S350、对所述目标染色区域进行染色处理，生成染色预览图像。
针对所述目标染色区域中的每个像素点，将所述像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，得到所述像素点的目标颜色值。可选地，将所述像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，包括：根据预设融合运算规则将像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，其中，所述预设融合运算规则包括求和运算、加权求和运算、乘积运算以及加权求乘积运算中的至少一项。
在对所述目标染色区域进行染色处理，生成染色预览图像时，可选地，本公开实施例的图像处理方法还可以包括：根据预设的颜色调整曲线对所述目标染色区域待染的颜色进行调整；和/或，根据预设的颜色调整曲线对染色后的目标染色区域的颜色进行调整。这样设置能够增加图像对比度，例如使得亮的地方更亮，暗的地方更暗，从而得到更好的平滑效果，然后在通过调整后的颜色对目标染区域进行上色处理，得到染色预览图像。
示例性地，预设的颜色调整曲线可以理解为用于调整颜色的亮度或者饱和度的曲线。例如可以是，基于颜色查找表(Look-Up-Table，LUT)生成的调整曲线。
示例性地，在对所述目标染色区域进行染色处理之前，根据预设的颜色调整曲线对所述目标染色区域待染的颜色进行调整，和/或，在对所述目标染色区域进行染色处理之后，可以根据预设的颜色调整曲线对染色后的目标染色区域的颜色进行调整。
示例性地，可以在确定出所述待处理图像中与所述染色区域配置参数对应的目标染色区域之后，根据预设的颜色调整曲线对所述目标染色区域待染的颜色进行调整，然后，基于调整后的颜色对所述目标染色区域进行染色处理，生成染色预览图像；或者，可以在确定出所述待处理图像中与所述染色区域配置参数对应的目标染色区域之后，对所述目标染色区域进行染色处理，然后，根据预设的颜色调整曲线对染色后的目标染色区域的颜色进行调整，基于调整后的颜色生成染色预览图像；又或者，可以在确定出所述待处理图像中与所述染色区域配置参数对应的目标染色区域之后，根据预设的颜色调整曲线对所述目标染色区域待染的颜色进行调整，然后，基于调整后的颜色对所述目标染色区域进行染色处理，再根据预设的颜色调整曲线对染色后的目标染色区域的颜色进行调整，基于调整后的颜色生成染色预览图像。
S360、于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
可以理解的是，通过执行前述步骤生成的染色预览图像即为对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
本公开实施例中，在接收到配置头发挑染特效的特效配置触发操作，响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面。用户在挑染特效配置界面中的图像预览区域查看头发挑染特效的待处理图像，通过挑染特效配置界面的图像预览区域可以直观选择待处理图像中想要挑染的头发区域，进而在区域配置项输入染色区域配置参数，在区域配置项中输入染色区域配置参数，进而通过预先训练的神经网络模型获取相应区域遮罩纹理图，进而根据区域遮罩纹理图确定染色区域配置参数对应的目标染色区域，通过区域遮罩纹理图，精细化区分头发中染色区域，同时根据区域遮罩纹理图精准定位染色区域配置参数对应的目标染色区域，从而对所述目标染色区域进行染色处理，并在图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像，提高了头发挑染特效精细化程度，实现对头发各个区域精细化挑染。
图4为本公开实施例三所提供的另一种图像处理方法流程示意图。本实施例的技术方案在本公开实施例中任一可选技术方案的基础上，对如何针对面部区域进行遮罩处理，以更加精准地保证染色效果进行细化。可选地，所述对所述目标染色区域进行染色处理，包括：确定所述待处理图像中的面部区域的面部遮罩纹理图，根据所述面部遮罩纹理图对所述目标染色区域进行染色处理。其中，与前述实施例中相同或相应的技术特征不再赘述。
如图4所示，本实施例的技术方案可包括：
S410、响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项。
S420、于所述图像预览区域展示用于配置头发挑染特效的待处理图像。
S430、接收基于所述区域配置项输入的染色区域配置参数，获取与所述染色区域配置参数对应的区域遮罩纹理图。
S440、根据所述区域遮罩纹理图确定所述待处理图像中与所述染色区域配置参数对应的目标染色区域。
S450、确定所述待处理图像中的面部区域的面部遮罩纹理图，根据所述面部遮罩纹理图对所述目标染色区域进行染色处理，生成染色预览图像。
可选的，通过预先训练的神经网络模型对待处理图像进行识别，确定当前待处理图像的区域遮罩纹理图。或者，通过面部识别算法识别出待处理图像的面部区域，将所述面部区域均作为非染色区域，通过将非染色区域的像素值均设置为0或1的方式得到面部遮罩纹理图。
其中，面部遮罩纹理图至少包括待处理图像中的面部区域与头发的交界区域。如，额头区域或耳朵区域等。本公开实施例在对目标染色区域进行染色区域时，还使用面部遮罩纹理图覆盖当前待处理图像中的面部区域，进而保护面部区域，防止对面部区域进行染色。
可选地，根据所述面部遮罩纹理图对所述目标染色区域进行染色处理，包括：确定所述目标染色区域与所述面部遮罩纹理图的重叠区域，对所述目标染色区域除所述重叠区域之外的区域进行染色处理。
可选的，根据本公开上述实施例获取目标染色区域在待处理图像中像素点的UV坐标，同时也获取面部遮罩纹理图每个像素点的UV坐标，通过面部遮罩纹理图中每个像素点的UV坐标确定待处理图像中的面部区域，进而，将目标染色区域在待处理图像中像素点的UV坐标和面部区域进行匹配，将匹配成功的UV坐标对应的区域作为所述目标染色区域与所述面部遮罩纹理图的重叠区域，对所述目标染色区域除所述重叠区域之外的区域进行染色处理。
可选的，在本公开另一实施例中，获取面部遮罩纹理图中每个像素点的UV坐标和目标染色区域在待处理图像中像素点的UV坐标后，将目标染色区域在当前待处理图像中像素点的UV坐标和面部遮罩纹理图每个像素点的UV坐标直接进行匹配，将匹配成功的像素点UV坐标对应的区域作为所述目标染色区域与所述面部遮罩纹理图的重叠区域，对所述目标染色区域除所述重叠区域之外的区域进行染色处理。
可选地，所述对所述目标染色区域中除所述重叠区域之外的区域进行染色处理，包括：针对所述目标染色区域中除所述重叠区域之外的区域中的每个像素点，将所述像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，得到所述像素点的目标颜色值。
其中，原始颜色值可以是目标染色区域中像素点的原本的颜色值。待染颜色值可以是需要给头发染上的颜色值。例如可以是，与颜色配置操作对应的目标颜色的颜色值。
可选的，将所述像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，包括：根据预设融合运算规则将像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，其中，所述预设融合运算规则包括求和运算、加权求和运算、乘积运算以及加权求乘积运算中的至少一项。
可选的，在本公开另一种实施例中，针对所述目标染色区域中除所述重叠区域之外的区域中的每个像素点，可以采用所述像素点的待染颜色值作为目标颜色值。
S460、接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
如前所述，通过执行前述步骤生成的染色预览图像即为对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
本公开实施例中，在接收到配置头发挑染特效的特效配置触发操作，响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面。用户在挑染特效配置界面中的图像预览区域查看头发挑染特效的待处理图像，通过挑染特效配置界面的图像预览区域可以直观选择待处理图像中想要挑染的头发区域，进而在区域配置项输入染色区域配置参数，在区域配置项中输入染色区域配置参数，进而通过预先训练的神经网络模型获取相应区域遮罩纹理图时，还获取面部遮罩纹理图，进而根据区域遮罩纹理图和面部遮罩纹理图更精准的定位染色区域配置参数对应的目标染色区域中除所述重叠区域之外的染色区域，进而保护面部区域，防止对面部区域进行染色，解决了对头发进行挑染时可能出现对额头的皮肤产生侵染的问题，提高了头发挑染特效精细化程度，实现对头发的目标染色区域的精细化挑染。
图5为本公开实施例所提供的一种挑染特效配置界面的示意图，如图5所示，挑染特效配置界面包括区域配置项和图像预览区域(即预览窗口)。
其中，预览窗口包括：图像上传控件、视频上传控件、图像选择控件、刷新控件和用于展示预览图像的图像展示区域。用户可以在图像预览窗口中点击图像上传控件选择图像上传图像，进而可以在图像展示区域显示用户上传的图像；如果用户上传的图像为视频时，选择视频按钮控件，在图像展示区域中显示用户上传的视频，用户可以在视频中选择图像进行处理或者基于预设逻辑自动识别视频中的图像进行处理。用户在挑染配置项中配置相应的目标染色区域、目标颜色和目标颜色透明度后，可以通过点击刷新控件，根据用户配置的目标染色区域、目标颜色和目标颜色透明度生成预览的染色预览图像，并在图像展示区域中展示染色预览图像。
其中，挑染配置项包括：局部头发挑染区域(如图5中的外挂耳挑染和内挂耳挑染)、颜色输入栏和透明度输入栏。用户可以在预览窗口中通过局部头发挑染区域的配置项选择目标染色区域，也可以通过选中图像展示区域中展示的待处理图像的染色位置反选中与选中的染色位置对应的局部头发挑染区域的配置项。用户可以在颜色输入栏中输入待染颜色值，也可以在挑染特效配置界面提供的颜色选择器选择待染颜色值，即目标颜色。用户可以在透明度输入栏中输入目标颜色透明度，也可以在挑染特效配置界面提供的透明度选择器选择目标颜色透明度。
举例而言，假设根据算法模型的"hp_ger_channel_ids"配置，能返回与待处理图像的头发区域对应的五张单独的区域遮罩纹理图，分别为左外挂耳遮罩纹理图mask0、右外挂耳遮罩纹理图mask1、左内挂耳遮罩纹理图mask2、右内挂耳遮罩纹理图mask3。其中，第5张遮罩纹理图始终为头发整体分割的遮罩纹理图 mask4。进而，在着色器shader中采样时，拿到区域遮罩纹理图的R通道中的数值[0，1]，0表示不是目标挑染区域，1表示是目标挑染区域。进一步地，可以将该目标颜色的颜色值做颜色调整处理，以得到更好的平滑效果，最后再对挑染区域进行上色处理，并于所述图像预览区域内，展示将颜色和透明度输入栏中对应的目标颜色和目标颜色透明度作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域所染的目标颜色后的染色预览图像。
由于区域遮罩纹理图返回的区域可能会覆盖到额头部分，使额头部分也带上颜色，为了处理这种情况，本公开实施例的技术方案给脸颊做了一层遮罩保护，使用面部遮罩纹理图使得有皮肤的地方就不上色，从而保证头发挑染特效的精准性，实现对头发的精细化挑染。
图6为本公开实施例所提供的一种图像处理装置的结构示意图。如图6所示，该装置可包括：界面展示模块610、待处理图像展示模块620和染色效果展示模块630。
其中，界面展示模块610，设置为响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项；待处理图像展示模块620，设置为于所述图像预览区域展示用于配置头发挑染特效的待处理图像；染色效果展示模块630，设置为接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
本公开实施例的技术方案，通过响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，由于挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，挑染配置项至少包括用于配置染色区域的区域配置项，能够为用户提供选择头发染色区域的功能，能够与用户进行交互，以便更为精准地获取用户需求。于所述图像预览区域展示用于配置头发挑染特效的待处理图像，使得用户能够在挑染特效配置界面中直观地查看待处理图像，进而接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像，能够根据用户对染色区域配置参数生成染色预览图像，展示不同的头发挑染效果。本公开的技术方案，只需要用户通过区域配置项输入的染色区域配置参数，即可自动对头发的选定区域进行染色，交互方式简单，普适性强，节省了用户的手动处理时间，提高了头发挑染特效的生成效率，解决了相关技术中对图像的局部信息进行精细化处理的专业性要求、时费时费力以及处理效果不稳定的技术问题，实现了简单快速地对头发进行挑染，满足了用户的个性化的头发染色需求，提升了用户体验。
可选的，待处理图像展示模块620设置为通过以下方式确定用于配置头发挑染特效的待处理图像：
接收基于所述图像预览区域的图像上传控件输入的图像上传操作，于所述图像预览区域展示上传的图像，将上传的图像作为用于配置头发挑染特效的待处理图像；或者，
接收基于所述图像预览区域的视频上传控件输入的视频上传操作，于所述图像预览区域展示上传的视频，将上传的视频中的符合预设条件的图像作为用于配置头发挑染特效的待处理图像。
可选的，所述挑染配置项还包括颜色配置项和/或透明度配置项。
可选的，所述装置还包括：
颜色配置模块，设置为接收基于所述颜色配置项输入的颜色配置操作；
相应地，所述染色效果展示模块630设置为通过以下方式展示染色预览图像：
于所述图像预览区域内，展示将所述颜色配置操作的对应的目标颜色作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域后的染色预览图像。
可选的，所述装置还包括：
透明度配置模块，设置为接收基于所述透明度配置项输入的透明度配置操作；
相应地，所述染色效果展示模块630还设置为通过以下方式展示染色预览图像：
于所述图像预览区域内，展示将所述透明度配置操作对应的目标颜色透明度作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域所染的目标颜色后的染色预览图像。
可选的，所述装置还可以包括：
区域遮罩模块，设置为在所述接收基于所述区域配置项输入的染色区域配置参数之后，以及在所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像之前，获取与所述染色区域配置参数对应的区域遮罩纹理图，根据所述区域遮罩纹理图确定所述待处理图像中与所述染色区域配置参数对应的目标染色区域，并对所述目标染色区域进行染色处理，生成染色预览图像。
可选的，所述目标遮罩纹理图包括头发全部区域的遮罩纹理图以及至少一个头发局部区域的遮罩纹理图。
可选的，所述区域遮罩模块设置为通过以下方式根据面部遮罩纹理图对目标染色区域进行染色处理：
确定所述待处理图像中的面部区域的面部遮罩纹理图，根据所述面部遮罩纹理图对所述目标染色区域进行染色处理。
可选的，所述区域遮罩模块设置为通过以下方式对目标染色区域除重叠区域之外的区域进行染色处理：
确定所述目标染色区域与所述面部遮罩纹理图的重叠区域，对所述目标染色区域出所述重叠区域之外的区域进行染色处理。
可选的，所述区域遮罩模块设置为通过以下方式进行颜色值融合：
针对所述目标染色区域中除所述重叠区域之外的区域中的每个像素点，将所述像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，得到所述像素点的目标颜色值。
可选的，所述区域遮罩模块设置为通过以下方式根据预设融合运算规则进行颜色值融合：
根据预设融合运算规则将像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，其中，所述预设融合运算规则包括求和运算、加权求和运算、乘积运算以及加权求乘积运算中的至少一项。
可选的，所述装置还包括：
颜色调整模块，设置为根据预设的颜色调整曲线对所述目标染色区域待染的颜色进行调整；和/或，根据预设的颜色调整曲线对染色后的目标染色区域的颜色进行调整。
本公开实施例所提供的图像处理装置可执行本公开任意实施例所提供的图像处理方法，具备执行图像处理方法相应的功能模块和有益效果。
值得注意的是，上述图像处理装置的实施例中，所包括的各个单元和模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，各功能单元的名称也只是为了便于相互区分。
图7为本公开实施例所提供的一种电子设备的结构示意图。下面参考图7，其示出了适于用来实现本公开实施例的电子设备(例如图7中的终端设备或服务器)700的结构示意图。本公开实施例中的终端设备可以包括诸如移动电话、笔记本电脑、数字广播接收器、个人数字助理(Personal Digital Assistant，PDA)、平板电脑(Portable Android Device，PAD)、便携式多媒体播放器(Portable Media Player，PMP)、车载终端(例如车载导航终端)等的移动终端以及诸如数字电视机(也即数字TV)、台式计算机等的固定终端。图7示出的电子设备仅仅是一个示例。
如图7所示，电子设备700可以包括处理装置(例如中央处理器、图形处理器等)701，处理装置701可以根据存储在只读存储器(Read Only Memory，ROM) 702中的程序或者从存储装置708加载到随机访问存储器(Random Access Memory，RAM)703中的程序而执行各种适当的动作和处理。在RAM 703中，还存储有电子设备700操作所需的各种程序和数据。处理装置701、ROM 702以及RAM 703通过总线704彼此相连。输入/输出(Input/Output，I/O)接口705也连接至总线704。
通常，以下装置可以连接至I/O接口705：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置706；包括例如液晶显示器(Liquid Crystal Display，LCD)、扬声器、振动器等的输出装置707；包括例如磁带、硬盘等的存储装置708；以及通信装置709。通信装置709可以允许电子设备700与其他设备进行无线或有线通信以交换数据。虽然图7示出了具有各种装置的电子设备700，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
在一实施例中，根据本公开的实施例，上文参考流程示意图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程示意图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置709从网络上被下载和安装，或者从存储装置708被安装，或者从ROM 702被安装。在该计算机程序被处理装置701执行时，执行本公开实施例的方法中限定的上述功能。
本公开实施例提供的电子设备与上述实施例提供的图像处理方法属于同一发明构思，未在本实施例中详尽描述的技术细节可参见上述实施例，并且本实施例与上述实施例具有相同的有益效果。
本公开实施例提供了一种计算机存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述实施例所提供的图像处理方法。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的组合。计算机可读存储介质例如可以是电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者以上的组合。计算机可读存储介质的示例可以包括：具有至少一个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(如电子可编程只读存储器(Electronic Programable Read Only Memory，EPROM)或闪存)、光纤、便携式紧凑磁盘只读存储器(Compact Disc-Read Only Memory，CD-ROM)、光存储器件、磁存储器件、或者上述的合适的组合。在本公开中，计算机可读存储介质可以是包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采 用多种形式，包括电磁信号、光信号或上述的合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用适当的介质传输，包括：电线、光缆、射频(Radio Frequency，RF)等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如超文本传输协议(HyperText Transfer Protocol，HTTP)之类的当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(Local Area Network，LAN)，广域网(Wide Area Network，WAN)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有至少一个程序，当上述至少一个程序被该电子设备执行时，使得该电子设备：
响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项；
于所述图像预览区域展示用于配置头发挑染特效的待处理图像；
接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括面向对象的程序设计语言诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络包括局域网(LAN)或广域网(WAN)连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程示意图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程示意图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含至少一个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于 附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程示意图中的每个方框、以及框图和/或流程示意图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定，例如，第一获取单元还可以被描述为“获取至少两个网际协议地址的单元”。
本文中以上描述的功能可以至少部分地由至少一个硬件逻辑部件来执行。例如，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(Field-Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产品(Application Specific Standard Parts，ASSP)、片上系统(System on Chip，SOC)、复杂可编程逻辑设备(Complex Programmable Logic Device，CPLD)等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的合适组合。机器可读存储介质的示例可以包括基于至少一个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的合适组合。
根据本公开的一个或多个实施例，【示例一】提供了一种图像处理方法，该方法包括：
响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项；
于所述图像预览区域内展示用于配置头发挑染特效的待处理图像；
接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
根据本公开的一个或多个实施例，【示例二】提供了一种图像处理方法，该方法包括：
可选的，所述于所述图像预览区域展示用于配置头发挑染特效的待处理图 像，包括：
接收基于所述图像预览区域的图像上传控件输入的图像上传操作，于所述图像预览区域展示上传的图像，将上传的图像作为用于配置头发挑染特效的待处理图像；或者，
接收基于所述图像预览区域的视频上传控件输入的视频上传操作，于所述图像预览区域展示上传的视频，将上传的视频中的符合预设条件的图像作为用于配置头发挑染特效的待处理图像。
根据本公开的一个或多个实施例，【示例三】提供了一种图像处理方法，该方法包括：
可选的，所述挑染配置项还包括颜色配置项和/或透明度配置项。
根据本公开的一个或多个实施例，【示例四】提供了一种图像处理方法，该方法包括：
可选的，接收基于所述颜色配置项输入的颜色配置操作；
所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像，包括：
于所述图像预览区域内，展示将所述颜色配置操作的对应的目标颜色作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域后的染色预览图像。
根据本公开的一个或多个实施例，【示例五】提供了一种图像处理方法，该方法包括：
接收基于所述透明度配置项输入的透明度配置操作；
所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像，包括：
于所述图像预览区域内，展示将所述透明度配置操作对应的目标颜色透明度作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域所染的目标颜色后的染色预览图像。
根据本公开的一个或多个实施例，【示例六】提供了一种图像处理方法，该方法包括：
可选的，在所述接收基于所述区域配置项输入的染色区域配置参数之后，以及在所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像之前，还包括：
获取与所述染色区域配置参数对应的区域遮罩纹理图，根据所述区域遮罩纹理图确定所述待处理图像中与所述染色区域配置参数对应的目标染色区域，并对所述目标染色区域进行染色处理，生成染色预览图像。
根据本公开的一个或多个实施例，【示例七】提供了一种图像处理方法，该方法包括：
可选的，所述目标遮罩纹理图包括头发全部区域的遮罩纹理图以及至少一个头发局部区域的遮罩纹理图。
根据本公开的一个或多个实施例，【示例八】提供了一种图像处理方法，该方法包括：
可选的，所述对所述目标染色区域进行染色处理，包括：
确定所述待处理图像中的面部区域的面部遮罩纹理图，根据所述面部遮罩纹理图对所述目标染色区域进行染色处理。
根据本公开的一个或多个实施例，【示例九】提供了一种图像处理方法，该方法包括：
可选的，所述根据所述面部遮罩纹理图对所述目标染色区域进行染色处理，包括：
确定所述目标染色区域与所述面部遮罩纹理图的重叠区域，对所述目标染色区域除所述重叠区域之外的区域进行染色处理。
根据本公开的一个或多个实施例，【示例十】提供了一种图像处理方法，该方法包括：
可选的，所述对所述目标染色区域中除所述重叠区域之外的区域进行染色处理，包括：
针对所述目标染色区域中除所述重叠区域之外的区域中的每个像素点，将所述像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，得到所述像素点的目标颜色值。
根据本公开的一个或多个实施例，【示例十一】提供了一种图像处理方法，该方法包括：
可选的，将所述像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，包括：
根据预设融合运算规则将像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，其中，所述预设融合运算规则包括求和运算、加权求和运算、乘积运算以及加权求乘积运算中的至少一项。
根据本公开的一个或多个实施例，【示例十二】提供了一种图像处理方法，
可选的，该方法还包括：根据预设的颜色调整曲线对所述目标染色区域待染的颜色进行调整；和/或，
根据预设的颜色调整曲线对染色后的目标染色区域的颜色进行调整。
根据本公开的一个或多个实施例，【示例十三】提供了一种图像处理装置， 该装置包括：
界面展示模块，设置为响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项；
待处理图像展示模块，设置为于所述图像预览区域内展示用于配置头发挑染特效的待处理图像；
染色效果展示模块，设置为接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。

Claims (15)

  1. 一种图像处理方法，包括：
    响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项；
    于所述图像预览区域内展示用于配置头发挑染特效的待处理图像；
    接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
  2. 根据权利要求1所述的图像处理方法，其中，所述于所述图像预览区域内展示用于配置头发挑染特效的待处理图像，包括：
    接收基于所述图像预览区域的图像上传控件输入的图像上传操作，于所述图像预览区域展示上传的图像，将上传的图像作为用于配置头发挑染特效的待处理图像；或者，
    接收基于所述图像预览区域的视频上传控件输入的视频上传操作，于所述图像预览区域展示上传的视频，将上传的视频中的符合预设条件的图像作为用于配置头发挑染特效的待处理图像。
  3. 根据权利要求1所述的图像处理方法，其中，所述挑染配置项还包括颜色配置项和透明度配置项中的至少之一。
  4. 根据权利要求3所述的图像处理方法，所述方法还包括：
    接收基于所述颜色配置项输入的颜色配置操作；
    所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置 参数对应的目标染色区域染色后的染色预览图像，包括：
    于所述图像预览区域内，展示将所述颜色配置操作的对应的目标颜色作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域后的染色预览图像。
  5. 根据权利要求3所述的图像处理方法，所述方法还包括：
    接收基于所述透明度配置项输入的透明度配置操作；
    所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像，包括：
    于所述图像预览区域内，展示将所述透明度配置操作对应的目标颜色透明度作用于所述待处理图像中与所述染色区域配置参数对应的目标染色区域所染的目标颜色后的染色预览图像。
  6. 根据权利要求1所述的图像处理方法，在所述接收基于所述区域配置项输入的染色区域配置参数之后，以及在所述于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像之前，所述方法还包括：
    获取与所述染色区域配置参数对应的区域遮罩纹理图，根据所述区域遮罩纹理图确定所述待处理图像中与所述染色区域配置参数对应的目标染色区域，并对所述目标染色区域进行染色处理，生成染色预览图像。
  7. 根据权利要求6所述的图像处理方法，其中，所述目标遮罩纹理图包括头发全部区域的遮罩纹理图以及至少一个头发局部区域的遮罩纹理图。
  8. 根据权利要求6所述的图像处理方法，其中，所述对所述目标染色区域 进行染色处理，包括：
    确定所述待处理图像中的面部区域的面部遮罩纹理图，根据所述面部遮罩纹理图对所述目标染色区域进行染色处理。
  9. 根据权利要求8所述的图像处理方法，其中，所述根据所述面部遮罩纹理图对所述目标染色区域进行染色处理，包括：
    确定所述目标染色区域与所述面部遮罩纹理图的重叠区域，对所述目标染色区域除所述重叠区域之外的区域进行染色处理。
  10. 根据权利要求9所述的图像处理方法，其中，所述对所述目标染色区域中除所述重叠区域之外的区域进行染色处理，包括：
    针对所述目标染色区域中除所述重叠区域之外的区域中的每个像素点，将所述像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，得到所述像素点的目标颜色值。
  11. 根据权利要求10所述的图像处理方法，其中，将所述像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，包括：
    根据预设融合运算规则将像素点的原始颜色值与所述目标染色区域待染的颜色的待染颜色值进行融合，其中，所述预设融合运算规则包括求和运算、加权求和运算、乘积运算以及加权求乘积运算中的至少一项。
  12. 根据权利要求6所述的图像处理方法，所述方法还包括以下至少之一：
    根据预设的颜色调整曲线对所述目标染色区域待染的颜色进行调整；
    根据预设的颜色调整曲线对染色后的目标染色区域的颜色进行调整。
  13. 一种图像处理装置，包括：
    界面展示模块，设置为响应于接收到的用于配置头发挑染特效的特效配置触发操作，展示挑染特效配置界面，其中，所述挑染特效配置界面展示有图像预览区域和至少一个挑染配置项，所述挑染配置项至少包括用于配置染色区域的区域配置项；
    待处理图像展示模块，设置为于所述图像预览区域内展示用于配置头发挑染特效的待处理图像；
    染色效果展示模块，设置为接收基于所述区域配置项输入的染色区域配置参数，于所述图像预览区域内展示对所述待处理图像中与所述染色区域配置参数对应的目标染色区域染色后的染色预览图像。
  14. 一种电子设备，所述电子设备包括：
    处理器；
    存储装置，设置为存储程序，
    当所述程序被所述处理器执行，使得所述处理器实现如权利要求1-12中任一所述的图像处理方法。
  15. 一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行如权利要求1-12中任一所述的图像处理方法。
PCT/CN2023/081335 2022-04-29 2023-03-14 图像处理方法、装置、电子设备和存储介质 WO2023207381A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210476183.9A CN115100305A (zh) 2022-04-29 2022-04-29 图像处理方法、装置、电子设备和存储介质
CN202210476183.9 2022-04-29

Publications (1)

Publication Number Publication Date
WO2023207381A1 true WO2023207381A1 (zh) 2023-11-02

Family

ID=83287906

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/081335 WO2023207381A1 (zh) 2022-04-29 2023-03-14 图像处理方法、装置、电子设备和存储介质

Country Status (2)

Country Link
CN (1) CN115100305A (zh)
WO (1) WO2023207381A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115100305A (zh) * 2022-04-29 2022-09-23 北京字跳网络技术有限公司 图像处理方法、装置、电子设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120075331A1 (en) * 2010-09-24 2012-03-29 Mallick Satya P System and method for changing hair color in digital images
CN113450431A (zh) * 2020-03-27 2021-09-28 北京达佳互联信息技术有限公司 虚拟头发染色方法、装置、电子设备及存储介质
KR102334030B1 (ko) * 2021-03-02 2021-12-03 (주)내스타일 컴퓨터 장치를 이용한 헤어 염색 방법
CN114240742A (zh) * 2021-12-17 2022-03-25 北京字跳网络技术有限公司 图像处理方法、装置、电子设备及存储介质
CN115100305A (zh) * 2022-04-29 2022-09-23 北京字跳网络技术有限公司 图像处理方法、装置、电子设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120075331A1 (en) * 2010-09-24 2012-03-29 Mallick Satya P System and method for changing hair color in digital images
CN113450431A (zh) * 2020-03-27 2021-09-28 北京达佳互联信息技术有限公司 虚拟头发染色方法、装置、电子设备及存储介质
KR102334030B1 (ko) * 2021-03-02 2021-12-03 (주)내스타일 컴퓨터 장치를 이용한 헤어 염색 방법
CN114240742A (zh) * 2021-12-17 2022-03-25 北京字跳网络技术有限公司 图像处理方法、装置、电子设备及存储介质
CN115100305A (zh) * 2022-04-29 2022-09-23 北京字跳网络技术有限公司 图像处理方法、装置、电子设备和存储介质

Also Published As

Publication number Publication date
CN115100305A (zh) 2022-09-23

Similar Documents

Publication Publication Date Title
CN110827378B (zh) 虚拟形象的生成方法、装置、终端及存储介质
CN110782515A (zh) 虚拟形象的生成方法、装置、电子设备及存储介质
CN110796721A (zh) 虚拟形象的颜色渲染方法、装置、终端及存储介质
US10984568B2 (en) Methods, devices, and computer-readable media for sharing image effects
US20230306700A1 (en) Virtual model processing method and apparatus, electronic device and storage medium
CN108737878B (zh) 用于结合视频呈现来修改用户界面颜色的方法和系统
CN109032470A (zh) 截图方法、装置、终端及计算机可读存储介质
WO2022142875A1 (zh) 图像处理方法、装置、电子设备及存储介质
WO2023207381A1 (zh) 图像处理方法、装置、电子设备和存储介质
CN110472558B (zh) 图像处理方法和装置
US20240119082A1 (en) Method, apparatus, device, readable storage medium and product for media content processing
WO2023109829A1 (zh) 图像处理方法、装置、电子设备及存储介质
CN111722775A (zh) 图像处理方法、装置、设备及可读存储介质
CN113596555B (zh) 视频播放方法、装置及电子设备
WO2024037557A1 (zh) 特效道具处理方法、装置、电子设备及存储介质
US20230360286A1 (en) Image processing method and apparatus, electronic device and storage medium
CN105611430B (zh) 用于处理视频内容的方法和系统
WO2023197648A1 (zh) 截图处理方法及装置、电子设备和计算机可读介质
US11810336B2 (en) Object display method and apparatus, electronic device, and computer readable storage medium
CN111292247A (zh) 图像处理方法和装置
CN116030185A (zh) 三维发丝生成方法和模型的训练方法
CN110209861A (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
CN114913058A (zh) 显示对象的确定方法、装置、电子设备及存储介质
WO2020011066A1 (zh) 终端的显示方法和装置、终端及可读介质
CN112764649B (zh) 虚拟形象的生成方法、装置、设备及存储介质

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: 23794817

Country of ref document: EP

Kind code of ref document: A1