CN112862735A - Image processing method and system, electronic device and storage medium - Google Patents
Image processing method and system, electronic device and storage medium Download PDFInfo
- Publication number
- CN112862735A CN112862735A CN202110144880.XA CN202110144880A CN112862735A CN 112862735 A CN112862735 A CN 112862735A CN 202110144880 A CN202110144880 A CN 202110144880A CN 112862735 A CN112862735 A CN 112862735A
- Authority
- CN
- China
- Prior art keywords
- image
- processing
- scenic spot
- portrait
- fused
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 65
- 238000003709 image segmentation Methods 0.000 claims abstract description 32
- 230000004927 fusion Effects 0.000 claims abstract description 30
- 239000002131 composite material Substances 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000007499 fusion processing Methods 0.000 claims abstract description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 description 18
- 238000012549 training Methods 0.000 description 13
- 230000011218 segmentation Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 2
- 210000001145 finger joint Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a method and a system for processing an image, an electronic device and a storage medium, wherein the processing method comprises the following steps: carrying out image segmentation processing on an image to be processed to obtain a portrait image; respectively carrying out image fusion processing on the portrait image and different scenic spot images to be fused to obtain different composite images; and dynamically displaying the composite image. According to the invention, through image segmentation, image fusion and other processing, the portrait image can be synthesized with various different scenic spot images and dynamically displayed, so that the immersive experience of the user in different scenic spots is presented; the invention can also be applied to large passenger flow places such as airports, stations and the like to realize the popularization and the promotion of the urban image of the scenic spot.
Description
Technical Field
The invention relates to the technical field of graphic image processing, in particular to an image processing method and system, electronic equipment and a storage medium.
Background
With the rise of deep learning and the gradual maturity of high and new technologies such as virtual reality and virtual scenes, and the social drive such as recent epidemic situation, the cloud tourism becomes possible and is gradually popularized. The cloud tourism is an online tourism technology which enables a user to feel personally on a certain scenic spot without going out or in a remote place by relying on technologies such as virtual reality and the like.
However, most of the current cloud travel technologies are based on relatively complex software and hardware environments and topology designs, and because the processing mode of the images is not intelligent enough, the cloud travel technologies are not easy to be laid out, constructed and applied in various places deeply.
Disclosure of Invention
The invention provides an image processing method and system, an electronic device and a storage medium, and aims to overcome the defect that an image processing mode in the prior art cannot intelligently cause that online tourism cannot be widely and flexibly applied.
The invention solves the technical problems through the following technical scheme:
the invention provides an image processing method, which comprises the following steps:
carrying out image segmentation processing on an image to be processed to obtain a portrait image;
respectively carrying out image fusion processing on the portrait image and different scenic spot images to be fused to obtain different composite images;
and dynamically displaying the composite image.
Preferably, the processing method further comprises:
recognizing the portrait image to obtain gesture information;
selecting a scenic spot image to be fused from at least two scenic spot images according to the gesture information;
recognizing the portrait image to obtain gesture information;
and selecting the scenic spot image to be fused from the at least two scenic spot images according to the gesture information.
Preferably, the processing method further comprises:
receiving a voice instruction;
and selecting the scenic spot image to be fused corresponding to the voice instruction.
Preferably, the processing method further comprises: and selecting the scenic spot images to be fused from the at least two scenic spot images according to a preset sequence.
Preferably, the step of performing image segmentation processing on the image to be processed to obtain the portrait image includes:
and if the number of the portrait images obtained by carrying out image segmentation processing on the image to be processed is more than one, selecting the portrait image with the largest area to carry out image fusion operation.
The invention also provides an image processing system, comprising:
the image segmentation module is used for carrying out image segmentation processing on the image to be processed to obtain a portrait image;
the image fusion module is used for respectively carrying out image fusion processing on the portrait image and different scenic spot images to be fused so as to obtain different composite images;
and the image display module is used for dynamically displaying the composite image.
Preferably, the processing system further comprises:
the gesture acquisition module is used for identifying the portrait image to acquire gesture information;
and the first image selection module is used for selecting the scenic spot image to be fused from the at least two scenic spot images according to the gesture information.
Preferably, the processing system further comprises:
the voice receiving module is used for receiving a voice instruction;
and the second image selection module is used for selecting the scenic spot image to be fused corresponding to the voice instruction.
Preferably, the processing system further includes a third image selecting module, configured to select, according to a preset sequence, a scenic spot image to be fused from the at least two scenic spot images.
Preferably, if the number of the portrait images obtained by performing the image segmentation processing on the image to be processed is greater than one, the image segmentation module is further configured to select the portrait image with the largest area to perform the image fusion operation.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the image processing method of any one of the above items when executing the computer program.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of processing an image described above.
The positive progress effects of the invention are as follows: according to the invention, through image segmentation, image fusion and other processing, the portrait image can be synthesized with various different scenic spot images and dynamically displayed, so that the user can experience immersion in different scenic spots; the invention can also be applied to the large passenger flow fields such as airports, stations and the like to realize the popularization and the promotion of the urban image of the scenic spots.
Drawings
Fig. 1 is a flowchart of an image processing method according to embodiment 1 of the present invention.
Fig. 2 is a block diagram of an image processing system according to embodiment 2 of the present invention.
Fig. 3 is a block diagram of an electronic device according to embodiment 3 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
As shown in fig. 1, this embodiment specifically provides an image processing method, where the image processing method includes the following steps:
s1, carrying out image segmentation processing on an image to be processed to obtain a portrait image.
And S2, respectively carrying out image fusion processing on the portrait image and different scenic spot images to be fused to obtain different composite images.
And S3, dynamically displaying the composite image.
In step S1, the source of the portrait image included in the image to be processed is multi-channel, and may be, for example, a portrait image captured by a camera in real time, or a portrait image uploaded by a user through a mobile terminal.
The previously labeled portrait segmentation data set can be utilized to perform deep neural network training on the convolution network model, and then image segmentation processing is performed on the image to be processed through the convolution network model. Data of the portrait segmentation data set is preferably selected to fit an actual application scene, and various images and environment variables such as contrast, brightness, sharpness, resolution and the like are comprehensively considered; therefore, the image segmentation model is suitable for more and wider conditions, and the training effect is more optimized.
It will be appreciated by those skilled in the art that the processing for the segmentation of the human image may be implemented by other models, algorithms, and is not limited to the convolutional network model. In the embodiment, a spindle-shaped full convolution network containing deconvolution operation is used for training a portrait segmentation model, and different topics such as squares, scenic spots, exhibition halls and the like are set in a refining mode; therefore, the portrait segmentation model can accurately segment the portrait image from each to-be-processed image to obtain the portrait image for subsequent processing, and as a preferred implementation manner, the mask image of the portrait image is obtained in the embodiment.
In this embodiment, in step S2, the portrait image needs to be fused with the scenic spot image, and the scenic spot image is used as the background image and the portrait image obtained in the previous step is subjected to image fusion. The scenic spot images can be obtained by constructing a famous scenic spot high-definition background gallery, and a scenic spot introduction gallery corresponding to each scenic spot is preset, so that the divided portrait images and the scenic spot images can be subjected to image fusion, and introduction of related scenic spots or places can be displayed at the same time.
The image fusion operation of the scenic region image and the portrait image can be carried out in a pixel-level image fusion mode, so that the obtained image has more detail information such as edges and textures, the further analysis and processing of the image are facilitated, the information in the source image is stored as much as possible, the content and the details of the fused image are increased, and the fused image can be used for playing advantages in application scenes with high requirements on the details of the image, such as large-screen delivery of subways, squares and stadiums.
In some application scenes with large data processing amount and long processing time, the image after the fusion operation can be displayed in real time in time; and the fused image has high definition through strict registration of the image, and the feature level image fusion can be performed under the condition that a mask image of the portrait image is obtained, namely the portrait image is directly pasted to a background image to be fused without fine edge processing. The memory and time consumed by computer analysis and processing in the image fusion process are reduced compared with the pixel-level image fusion, and the real-time performance of the required image is improved. In situations where the requirements for detailed features are not very high, such as some exhibition venues, small exhibitions, etc., better real-time and interactivity can be provided.
In addition, different registration specifications can be preset according to the situation that different scenic spot images are taken as backgrounds, for example, coordinates of inserted reference points, portrait registration proportion and the like are adjusted, so that a better image display effect is presented. On the basis, step S3 further performs dynamic presentation on the fused image, for example, each updated instant presentation is combined with a timed scrolling presentation, thereby providing an immersive scenery experience for the viewer.
As a preferred implementation, the method for processing an image according to this embodiment further includes:
recognizing the portrait image to obtain gesture information;
and selecting the scenic spot image to be fused from the at least two scenic spot images according to the gesture information.
In the embodiment, a gesture detection training set is also constructed, wherein the gesture detection training set comprises a large number of marked human hand pictures and is used for training a convolution network model capable of recognizing gestures; thereby recognizing the gesture information from the portrait image using the convolutional network model. Specifically, a classic yolo v4 (a visual target detection network model structure) network structure can be used to train a model capable of detecting and recognizing left and right gestures, although those skilled in the art will appreciate that the detection and recognition gesture information is not limited to the yolo v4 network structure, such as yolo v1-v3 classic target detection model, OpenCV hand key detection model, RGB-D image detection model, etc., and can be used to detect gesture information. And the detection of gesture information is not limited to the left and right, and although the gesture of the left to the right corresponds to the operation intention of page turning forward and backward in the present embodiment, it is not excluded that more information corresponding to the user intention or instruction can be acquired by gesture recognition of other gestures, even finger joints.
And selecting the scenic spot image to be fused according to the gesture information, wherein a leftward gesture is used for representing the intention of a user to turn a page forward in the embodiment, and after receiving the instruction, the image of the previous page of the current scenic spot image is obtained and used as the image to be fused. And similarly, representing the intention of the user to turn back by using a rightward gesture, and acquiring an image of a page behind the current scenic spot image after receiving the instruction to be used as an image to be fused. As an alternative processing method, for example, the recognition result of the gesture is that the page is turned forward and the first scenic spot image is already at the moment; or if the gesture recognition result is that the page is turned backwards and the last scenic spot image is displayed at the moment, a corresponding prompt is made to the user, for example: "has been the first drawing! "OR" is already the last drawing! ".
As a preferred implementation manner, the image processing method of the embodiment further includes:
receiving a voice instruction;
and selecting the scenic spot image to be fused corresponding to the voice instruction.
The embodiment determines the scenic spot images to be fused through the voice command. In many application scenes, the user cannot or inconveniently convey the demand intention for the background image through gestures due to factors such as space, light and the like; and if the application scene is suitable for voice capture, the intention of the user for background selection can be fed back more quickly and accurately. The voice command can be received through a sound pickup device such as a microphone on site, or a sound file input by the user in a linkage manner can be acquired through a wireless device, for example, a real-time or delayed sound file transmitted to the user through a Bluetooth device.
For the acquired voice command, the integrated voice recognition function receives the intention of the user, and generally, the input voice command is not mass data, so that the requirements on software and hardware of voice recognition are not high, and a complex algorithm is not required. But considering factors such as age, region, habit and the like of the user; an endpoint activity detection technique may be incorporated to segment the incoming audio stream in real time by recognizing silence and to output simultaneously an audio alert converted from recognized text in the state of picking up audio, such as "you will now go to the national village to visit" by on-line synchronous recognition to prompt the user making the voice command that has been employed. Synchronously, at this time, the background searches the corresponding scenic spot image in the background picture library as the image to be fused according to the recognition result, such as 'Jiuzhaigou' as a key word.
As a preferred implementation, the method for processing an image according to this embodiment may further include: and selecting the scenic spot images to be fused from the at least two scenic spot images according to a preset sequence.
In the present embodiment, the scenic spot images in the background picture library are preset in sequence, and the scenic spot images to be fused are set in the preset sequence. The preset sequence can be arranged according to the number, date and the like of the pictures, and can also be arranged according to the grouping of subjects such as Europe, Han Ri, natural scenery, domestic humanity and the like.
In addition, the embodiment can be used as a default option under the condition that no voice instruction and gesture information are acquired; for example, if the user has no voice signal input and no gesture information, all the scenic spot images under the theme of 'domestic human characters' are set as images to be fused in a circulating mode at a certain rate.
As a preferred embodiment, the step of performing image segmentation processing on the image to be processed to obtain the portrait image includes: if the image to be processed is divided into more than one portrait image, the portrait image with the largest area is selected for image fusion operation, and the portrait image is considered to be closest to the camera.
The image processing method provided by the embodiment enables the human image to be synthesized and dynamically displayed with various different scenic spot images through image segmentation, image fusion and other processing, so that the user can be presented with immersive experience of being placed in different scenic spots; meanwhile, ways such as voice instructions, gesture recognition, preset sequences and the like are provided, so that a user can conveniently select different scenic spot images for experience. The image processing method of the embodiment can also be used for carrying out visual propaganda in large passenger flow fields such as airports, stations and the like so as to realize the popularization and promotion of urban images.
Example 2
As shown in fig. 2, this embodiment specifically provides an image processing system, which includes:
the image segmentation module 1 is used for performing image segmentation processing on an image to be processed to obtain a portrait image;
the image fusion module 2 is used for respectively carrying out image fusion processing on the portrait image and different scenic spot images to be fused so as to obtain different composite images;
and the image display module 3 is used for dynamically displaying the composite image.
The image segmentation module 1 is configured to perform image segmentation on an image to be processed to obtain a portrait image, where the source of the portrait image included in the image to be processed is multi-channel, and may be, for example, a portrait image shot by a camera in real time, or a portrait image uploaded by a user through a mobile terminal.
A previously labeled human image segmentation data set comprising a number of segmented human image slices as training data may be used for deep training of a convolutional network model, and thereafter image segmentation of the image to be processed by the convolutional network model. Data of the portrait segmentation data set is preferably selected to fit with practical application scenes, and various images and environment variables such as contrast, brightness, sharpness, resolution and the like are comprehensively considered; therefore, the image segmentation model is suitable for more and wider conditions, and the training effect is more optimized.
It will be appreciated by those skilled in the art that the processing for the segmentation of the human image may be implemented by other models, algorithms, and is not limited to the convolutional network model. In this embodiment, a spindle-shaped full convolution network including deconvolution operation is used to train a portrait segmentation model, and different topics such as squares, scenic spots, exhibition halls and the like are set in a refined manner, so that the portrait segmentation model can accurately segment a portrait image from each image to be processed to obtain a portrait image for subsequent processing.
In this embodiment, the image fusion module 2 needs to fuse the portrait image with the scenic spot image, and the scenic spot image is used as a background image to perform image fusion with the portrait image obtained in the previous step. The scenic spot images can be obtained by constructing a famous scenic spot high-definition background gallery, and a scene point introduction gallery corresponding to each scenic spot is preset, so that the segmented portrait images and the scenic spot images can be subjected to image fusion, and simultaneously the introduction of related scenic spots or places can be displayed.
The image fusion operation of the scenic region image and the portrait image can be performed in a pixel-level image fusion mode, so that the obtained image has more detail information such as edges and textures, further analysis, processing and understanding of the image are facilitated, the information in the source image is stored as much as possible, the content and the details of the fused image are increased, and the fused image has advantages in application scenes with high requirements on the details of the image, such as large-screen delivery of subways, squares and stadiums.
In some application scenes with large data processing amount and long processing time, the image after the fusion operation can be displayed in real time in time; and the fused image has high definition through strict registration of the image, and the feature level image fusion can be performed under the condition that a mask image of the portrait image is obtained, namely the portrait image is directly pasted to a background image to be fused without fine edge processing. The memory and time consumed by computer analysis and processing in the image fusion process are reduced compared with the pixel-level image fusion, and the real-time performance of the required image is improved. In situations where the requirements for detailed features are not very high, such as some exhibition venues, small exhibitions, etc., better real-time and interactivity can be provided.
In addition, different registration specifications can be preset according to the situation that different scenic spot images are taken as backgrounds, for example, coordinates of inserted reference points, portrait registration proportion and the like are adjusted, so that a better image display effect is presented. On the basis, the image display module 3 further performs dynamic display on the fused image, for example, each updated instant display is combined with a timed scrolling display, thereby providing an immersive scene experience for the viewer.
As a preferred implementation manner, the image processing system of this embodiment further includes:
the gesture acquisition module is used for identifying the portrait image to acquire gesture information;
and the first image selection module is used for selecting the scenic spot image to be fused from the at least two scenic spot images according to the gesture information.
In the embodiment, a gesture detection training set is also constructed, wherein the gesture detection training set comprises a large number of marked human hand pictures and is used for training a convolution network model capable of identifying human gestures; thereby recognizing the gesture information from the portrait image using the convolutional network model. The gesture information may be obtained by training a model capable of detecting and recognizing left and right gestures using a classic yolo v4 (a visual target detection network model structure), but those skilled in the art will recognize that the detection and recognition gesture information is not limited to the yolo v4 network structure, such as yolo v1-v3 target detection classic model, OpenCV hand key point detection model, RGB-D image detection model, etc., and the gesture obtaining module may be used to detect gesture information. And the detection of gesture information is not limited to left and right, and although the gesture of left and right corresponds to the operation intention of page turning forward and backward in the present embodiment, it is not excluded that more corresponding information that can represent the user intention or instruction can be acquired through gesture recognition of other gestures, even finger joints.
The first image selection module selects the scenic spot images to be fused according to the gesture information, in this embodiment, the intention of the user to turn the page forward is represented by a left gesture, and after receiving the instruction, the image of the previous page of the current scenic spot image is obtained and used as the image to be fused for image fusion. And similarly, representing the intention of the user for turning back by using a rightward gesture, and after receiving the instruction, acquiring an image of a page behind the current scenic spot image by using the first image selection module as an image to be fused for image fusion. Other gestures, such as the intended representation of an up or down gesture, are ignored under this premise. As an alternative processing method, for example, the recognition result of the gesture is that the page is turned forward and the first scenic spot image is already at the moment; or if the gesture recognition result is that the page is turned backwards and the last scenic spot image is displayed at the moment, a corresponding prompt is made to the user, for example: "has been the first drawing! "OR" is already the last drawing! ".
As a preferred implementation manner, the image processing system of this embodiment further includes:
the voice receiving module is used for receiving a voice instruction;
and the second image selection module is used for selecting the scenic spot image to be fused corresponding to the voice instruction.
The embodiment determines the scenic spot images to be fused through the voice command. In many application scenes, the user cannot or inconveniently convey the demand intention for the background image through gestures due to factors such as space, light and the like; and if the application scene is suitable for voice capture, the intention of the user for background selection can be fed back more quickly and accurately. The voice receiving module can receive voice commands through a field sound pickup device, such as a microphone which is applied in a light mode or a dark mode, and can also acquire sound files input by the user in a linkage mode through wireless equipment, for example, real-time or delayed sound files transmitted to the user through a Bluetooth device.
For the voice instruction obtained by the voice receiving module, the integrated voice recognition function receives the intention of the user, and generally, because the input voice instruction is not mass data, the requirements on software and hardware of voice recognition are not high, and a complex algorithm is not required. But considering factors such as the age, region, and habit of the user; an endpoint activity detection technique may be incorporated to segment the incoming audio stream on-the-fly by recognizing silence and to output simultaneously an audio cue converted from recognized text in the state of picking up audio, such as "you will now visit jiuzhaigou for a tour", by on-line synchronous recognition, to prompt the user who made the voice command that has been employed. Synchronously, at this time, the second image selecting module searches the corresponding scenic spot image in the background picture library as the image to be fused according to the identified result, such as 'Jiuzhaigou' as a key word.
As a preferred implementation manner, the image processing system of this embodiment further includes a third image selecting module, configured to select, according to a preset sequence, a scenic spot image to be fused from the at least two scenic spot images.
In this embodiment, the third image selecting module sets the scenic spot images to be fused in a preset order with respect to the scenic spot images in the background picture library. The preset sequence can be arranged according to the number, date and the like of the pictures, and can also be arranged according to the grouping of subjects such as Europe, Han Ri, natural scenery, domestic humanity and the like.
In addition, the embodiment can be used as a default option under the condition that no voice instruction and gesture information are acquired; for example, if the user has no voice signal input and no gesture information, the third image selection module circularly sets all scenic spot images under the theme of 'domestic human characters' as images to be fused according to a certain rate.
Preferably, if the number of the portrait images obtained by performing the image segmentation processing on the image to be processed is at least two, the image segmentation module performs the image fusion operation on the portrait image with the largest selected area.
The image processing system provided by the embodiment enables the human image to be synthesized and dynamically displayed with various different scenic spot images through image segmentation, image fusion and other processing, so that the user can be presented with immersive experience of being placed in different scenic spots; meanwhile, ways such as voice instructions, gesture recognition, preset sequences and the like are provided, so that a user can conveniently select different scenic spot images for experience. The image processing system of the embodiment can also be used for carrying out visual propaganda in large passenger flow fields such as airports, stations and the like so as to realize the popularization and promotion of urban images.
Example 3
Fig. 3 is a schematic structural diagram of an electronic device according to embodiment 3 of the present invention. The electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the image processing method in embodiment 1 when executing the program. The electronic device 30 shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in FIG. 3, electronic device 30 may take the form of a general purpose computing device, which may be a server device, for example. The components of the electronic device 30 may include, but are not limited to: the at least one processor 31, the at least one memory 32, and a bus 33 connecting the various system components (including the memory 32 and the processor 31).
The bus 33 includes a data bus, an address bus, and a control bus.
The memory 32 may include volatile memory, such as Random Access Memory (RAM)321 and/or cache memory 322, and may further include Read Only Memory (ROM) 323.
The processor 31 executes various functional applications and data processing, such as a processing method of an image in embodiment 1 of the present invention, by running the computer program stored in the memory 32.
The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). Such communication may be through input/output (I/O) interfaces 35. Also, model-generated device 30 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) via network adapter 36. As shown in FIG. 3, network adapter 36 communicates with the other modules of model-generating device 30 via bus 33. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the model-generated device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the electronic device are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module according to embodiments of the invention. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
Example 4
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the steps in the method of processing an image in embodiment 1.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible embodiment, the present invention can also be implemented in the form of a program product including program code for causing a terminal device to execute the steps in the processing method for implementing the image in embodiment 1 when the program product is run on the terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may execute entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of illustration only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (10)
1. A method for processing an image, the method comprising:
carrying out image segmentation processing on an image to be processed to obtain a portrait image;
respectively carrying out image fusion processing on the portrait image and different scenic spot images to be fused to obtain different composite images;
and dynamically displaying the composite image.
2. The method of processing an image according to claim 1, further comprising:
recognizing the portrait image to obtain gesture information;
and selecting the scenic spot image to be fused from the at least two scenic spot images according to the gesture information.
3. The method of processing an image according to claim 1, further comprising:
receiving a voice instruction;
and selecting the scenic spot image to be fused corresponding to the voice instruction.
4. The method of processing an image according to claim 1, further comprising: and selecting the scenic spot images to be fused from the at least two scenic spot images according to a preset sequence.
5. The method for processing the image according to any one of claims 1 to 4, wherein the step of performing the image segmentation process on the image to be processed to obtain the portrait image comprises:
and if the number of the portrait images obtained by carrying out image segmentation processing on the image to be processed is more than one, selecting the portrait image with the largest area to carry out image fusion operation.
6. A system for processing an image, the system comprising:
the image segmentation module is used for carrying out image segmentation processing on the image to be processed to obtain a portrait image;
the image fusion module is used for respectively carrying out image fusion processing on the portrait image and different scenic spot images to be fused so as to obtain different composite images;
and the image display module is used for dynamically displaying the composite image.
7. The system for processing an image according to claim 6, further comprising:
the gesture acquisition module is used for identifying the portrait image to acquire gesture information;
the first image selection module is used for selecting a scenic spot image to be fused from at least two scenic spot images according to the gesture information;
alternatively, the first and second electrodes may be,
the processing system further comprises:
the voice receiving module is used for receiving a voice instruction;
the second image selection module is used for selecting the scenic spot image to be fused corresponding to the voice instruction;
alternatively, the first and second electrodes may be,
the processing system further comprises:
and the third image selection module is used for selecting the scenic spot images to be fused from the at least two scenic spot images according to the preset sequence.
8. The image processing system according to any one of claims 6 to 7, wherein if the number of the portrait images obtained by performing the image segmentation processing on the image to be processed is greater than one, the image segmentation module is further configured to select the portrait image with the largest area for performing the image fusion operation.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of processing an image according to any one of claims 1-5 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of processing an image according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110144880.XA CN112862735A (en) | 2021-02-02 | 2021-02-02 | Image processing method and system, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110144880.XA CN112862735A (en) | 2021-02-02 | 2021-02-02 | Image processing method and system, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112862735A true CN112862735A (en) | 2021-05-28 |
Family
ID=75986389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110144880.XA Pending CN112862735A (en) | 2021-02-02 | 2021-02-02 | Image processing method and system, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862735A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102625129A (en) * | 2012-03-31 | 2012-08-01 | 福州一点通广告装饰有限公司 | Method for realizing remote reality three-dimensional virtual imitated scene interaction |
| CN103731583A (en) * | 2013-12-17 | 2014-04-16 | 四川金手指时代投资管理有限公司 | Integrated device for intelligent photograph synthesizing and printing and processing method for intelligent photograph synthesizing and printing |
| CN106097435A (en) * | 2016-06-07 | 2016-11-09 | 北京圣威特科技有限公司 | A kind of augmented reality camera system and method |
| CN107590754A (en) * | 2017-11-01 | 2018-01-16 | 首都师范大学 | A kind of system and method based on augmented reality lifting national park Tourist Experience |
| CN111026261A (en) * | 2018-10-09 | 2020-04-17 | 上海奈飒翱网络科技有限公司 | Method for AR interactive display of tourist attractions |
| US20200204738A1 (en) * | 2017-07-26 | 2020-06-25 | Vivo Mobile Communication Co., Ltd. | Photographing method and mobile terminal |
| CN111667588A (en) * | 2020-06-12 | 2020-09-15 | 上海商汤智能科技有限公司 | Person image processing method, person image processing device, AR device and storage medium |
-
2021
- 2021-02-02 CN CN202110144880.XA patent/CN112862735A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102625129A (en) * | 2012-03-31 | 2012-08-01 | 福州一点通广告装饰有限公司 | Method for realizing remote reality three-dimensional virtual imitated scene interaction |
| CN103731583A (en) * | 2013-12-17 | 2014-04-16 | 四川金手指时代投资管理有限公司 | Integrated device for intelligent photograph synthesizing and printing and processing method for intelligent photograph synthesizing and printing |
| CN106097435A (en) * | 2016-06-07 | 2016-11-09 | 北京圣威特科技有限公司 | A kind of augmented reality camera system and method |
| US20200204738A1 (en) * | 2017-07-26 | 2020-06-25 | Vivo Mobile Communication Co., Ltd. | Photographing method and mobile terminal |
| CN107590754A (en) * | 2017-11-01 | 2018-01-16 | 首都师范大学 | A kind of system and method based on augmented reality lifting national park Tourist Experience |
| CN111026261A (en) * | 2018-10-09 | 2020-04-17 | 上海奈飒翱网络科技有限公司 | Method for AR interactive display of tourist attractions |
| CN111667588A (en) * | 2020-06-12 | 2020-09-15 | 上海商汤智能科技有限公司 | Person image processing method, person image processing device, AR device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022001593A1 (en) | Video generation method and apparatus, storage medium and computer device | |
| JP7270661B2 (en) | Video processing method and apparatus, electronic equipment, storage medium and computer program | |
| CN107909022B (en) | Video processing method and device, terminal equipment and storage medium | |
| TWI752502B (en) | Method for realizing lens splitting effect, electronic equipment and computer readable storage medium thereof | |
| CN111225236B (en) | Method and device for generating video cover, electronic equipment and computer-readable storage medium | |
| CN111097168B (en) | Display control method and device in game live broadcast, storage medium and electronic equipment | |
| CN113630615A (en) | Live broadcast room virtual gift display method and device | |
| CN113934297B (en) | Interaction method and device based on augmented reality, electronic equipment and medium | |
| CN112188228A (en) | Live broadcast method and device, computer readable storage medium and electronic equipment | |
| CN108335342B (en) | Method, apparatus and computer program product for multi-person drawing on a web browser | |
| WO2022218042A1 (en) | Video processing method and apparatus, and video player, electronic device and readable medium | |
| WO2022111458A1 (en) | Image capture method and apparatus, electronic device, and storage medium | |
| CN111540032A (en) | Audio-based model control method, device, medium and electronic equipment | |
| TW202248808A (en) | Augmented reality data presentation method, electronic equipment and computer-readable storage medium | |
| CN114708443A (en) | Screenshot processing method and device, electronic equipment and computer readable medium | |
| CN112199534A (en) | Sticker recommendation method and device, electronic equipment and storage medium | |
| US11451721B2 (en) | Interactive augmented reality (AR) based video creation from existing video | |
| CN113596574A (en) | Video processing method, video processing apparatus, electronic device, and readable storage medium | |
| WO2022257844A1 (en) | Travel note generation method and apparatus | |
| CN114449355B (en) | Live interaction method, device, equipment and storage medium | |
| CN112862735A (en) | Image processing method and system, electronic device and storage medium | |
| CN111652986B (en) | Stage effect presentation method and device, electronic equipment and storage medium | |
| CN112788390B (en) | Control method, device, equipment and storage medium based on man-machine interaction | |
| CN114967914A (en) | Virtual display method, device, equipment and storage medium | |
| CN113350780A (en) | Cloud game control method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |