CN107018330A - A kind of guidance method and device of taking pictures in real time - Google Patents
A kind of guidance method and device of taking pictures in real time Download PDFInfo
- Publication number
- CN107018330A CN107018330A CN201710257194.7A CN201710257194A CN107018330A CN 107018330 A CN107018330 A CN 107018330A CN 201710257194 A CN201710257194 A CN 201710257194A CN 107018330 A CN107018330 A CN 107018330A
- Authority
- CN
- China
- Prior art keywords
- erect
- scoring
- viewfinder image
- positions
- virtual
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/62—Control of parameters via user interfaces
Abstract
The invention discloses a kind of guidance method and device of taking pictures in real time.This method includes：Obtain the current viewfinder image in smart machine；Several virtual erect-positions are generated in viewfinder image；Viewfinder image carries out aesthstic scoring respectively with reference to several virtual erect-positions, obtains recommending erect-position and shows according to aesthetics scoring.The guidance method of taking pictures in real time of the present invention passes through Intelligent Recognition photographed scene, obtain recommending erect-position, so that the portrait that the user for not possessing Professional Photography knowledge also can easily take high aesthetic feeling shines, effectively overcome various shortcoming of the prior art and have high industrial utilization.
Description
Technical field
The present invention relates to image processing field, more particularly to a kind of guidance method and device of taking pictures in real time.
Background technology
Camera function has become one of indispensable critical function of current smart machine, when running into the landscape of beauty, user
Wish to leave the figure of oneself in landscape, the where but domestic consumer does not know but to find a view in picture is only optimal station of taking pictures
Position, a kind of method of erect-position accordingly, it would be desirable to which energy intelligent guidance is taken pictures.Some inventions that can be instructed taking pictures are had at present
Patent.Application No. CN201410180886.2 invention enters when taking pictures preview mode, is given birth to according to the image information got
Into related pattern data, and the pattern data is sent to cloud server；The pattern data of cloud server search matching, and
Optimal patterning scheme data are obtained by calculation process, and the optimal patterning scheme data are sent to mobile terminal；It is mobile
Terminal is taken pictures in the corresponding optimal patterning positions prompting of display in preview interface of taking pictures, user according to prompting adjustment position.The hair
Bright realize is patterned guidance when taking pictures, but can not intelligent recommendation go out to be photographed the optimal erect-position of people.Application No.
CN201510599253.X invention can realize the human face posture information that the user is obtained during finding a view；Will be default
The human face posture information for template of taking pictures is compared with the human face posture information of the user；Used according to comparison result prompting is described
Family carries out human face posture adjustment.The invention is realized carries out guidance of taking pictures to the human face posture of user, but face takes pictures template not
Adaptive guidance of taking pictures can be carried out according to scene, and a variety of erect-positions of taking pictures can not be recommended.
The content of the invention
In view of the above problems, the invention provides a kind of guidance method and device of taking pictures in real time.
The real-time guidance method of taking pictures of one kind that the present invention is provided, including：
Obtain the current viewfinder image in smart machine；
Several virtual erect-positions are generated in the viewfinder image；
The viewfinder image carries out aesthstic scoring respectively with reference to several virtual erect-positions, obtains recommending station according to aesthetics scoring
Position is simultaneously shown.
Present invention also offers a kind of take pictures in real time guiding device, including image collection module, first processing module, second
Processing module, display module：
Described image acquisition module, for obtaining the current viewfinder image in smart machine；
The first processing module, for generating several virtual erect-positions in the viewfinder image；
The Second processing module, aesthstic scoring is carried out for the viewfinder image respectively with reference to several virtual erect-positions,
Obtain recommending erect-position and show according to aesthetics scoring.
The present invention has the beneficial effect that：
The real-time of the embodiment of the present invention takes pictures guidance method by Intelligent Recognition photographed scene, provides recommendation erect-position so that
Not possessing the user of Professional Photography knowledge also can easily take the portrait photograph of high aesthetic feeling, effectively overcome of the prior art a variety of
Shortcoming and with high industrial utilization.
Brief description of the drawings
Fig. 1 is the flow chart of the guidance method of taking pictures in real time of the inventive method embodiment；
Fig. 2 is the structural representation of the guiding device of taking pictures in real time of apparatus of the present invention embodiment.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
In order to solve prior art can not intelligent recommendation go out to be photographed people optimal erect-position or face take pictures template can not root
Carry out adaptive guidances of taking pictures according to scene, and can not recommend it is a variety of take pictures erect-position the problem of, the invention provides a kind of real-time
Guidance method of taking pictures and device, below in conjunction with accompanying drawing and embodiment, the present invention will be described in further detail.It should manage
Solution, the specific embodiments described herein are merely illustrative of the present invention, does not limit the present invention.
The method according to the invention embodiment is there is provided a kind of guidance method of taking pictures in real time, and Fig. 1 is that the inventive method is implemented
The flow chart of the guidance method of taking pictures in real time of example, as shown in figure 1, according to the guidance method of taking pictures in real time of the inventive method embodiment
Including following processing：
Step 101, the current viewfinder image in smart machine is obtained.
Specifically, the smart machine includes PC, smart mobile phone, tablet personal computer, intelligent glasses, and other tools
There is the equipment of camera and data processing function.
Step 102, several virtual erect-positions are generated in the viewfinder image.
Comprise the following steps specifically, generating several virtual erect-positions in the viewfinder image：
Traveled through in the viewfinder image by multi-scale sliding window mouthful, obtain several virtual erect-positions；Preferably, slide
The distant corresponding positional information in region of background object is chosen in window ergodic process as the virtual erect-position information of candidate.
Step 103, the viewfinder image carries out aesthstic scoring respectively with reference to several virtual erect-positions, is scored according to aesthetics
To recommending erect-position and to show.
Specifically, described recommend erect-position to choose the multiple phantom stations of optimal erect-position or aesthetics scoring more than or equal to lowest threshold
One or more of position.
More specific, choose the corresponding virtual erect-position of highest aesthetics scoring and be used as optimal erect-position；Aesthetics scoring be more than etc.
Arranged in multiple virtual erect-positions of lowest threshold according to the order of aesthetics scoring from high to low.
Specifically, the viewfinder image carries out aesthstic scoring respectively in connection with several virtual erect-positions, scored according to aesthetics
Include to erect-position is recommended：
The viewfinder image and any one virtual erect-position are input in default aesthetic evaluation model to described virtual
Erect-position carries out aesthstic scoring, and several described virtual erect-positions of traversal obtain several aesthetics scorings；
Obtain recommending erect-position according to several described aesthetics scorings.
The guidance method of taking pictures in real time of the inventive method embodiment, it is further comprising the steps of：When several described phantom stations
When the aesthetics scoring of position is respectively less than lowest threshold, user's adjustment is pointed out to find a view position.
Specifically, preview interface prompts for graphical cues and/or text prompt and/or voice message.
As another embodiment of the inventive method embodiment, before aesthstic scoring is carried out to several images of taking pictures,
It is further comprising the steps of：
Using default image scene classification algorithm, the viewfinder image is identified and analyzed, described find a view is obtained
The classification results of the affiliated scene of image；
It should be noted that having there is the scene classification algorithm of many maturations in the prior art, therefore it will not be repeated here.
Further, the viewfinder image carries out aesthetics scoring respectively in connection with several virtual erect-positions includes：
By the viewfinder image and any one virtual erect-position and the classification results (example of the affiliated scene of the viewfinder image
Such as scene tag) it is input in default aesthetic evaluation model to the virtual aesthstic scoring of erect-position progress, travel through described some
Individual virtual erect-position, obtains several aesthetics scorings.
Specifically, the default aesthetic evaluation model is obtained by training, the machine learning method used includes convolution
Neutral net, limited Boltzmann machine, depth confidence network etc..
More specific, the training method of the aesthetic evaluation model comprises the following steps：
Obtain several images of known aesthetics scoring and personage's erect-position information；
Default aesthetic evaluation model is instructed using several images of known aesthetics scoring and personage's erect-position information
Practice, or using the scene tag belonging to several images and image of known aesthetics scoring and personage's erect-position information to default
Aesthetic evaluation model is trained, the aesthetic evaluation model after being trained.
The real-time of the embodiment of the present invention takes pictures guidance method by Intelligent Recognition photographed scene, recommends optimal shooting station
Position so that not possessing the user of Professional Photography knowledge also can easily take the portrait photograph of high aesthetic feeling, effectively overcome prior art
In various shortcoming and have high industrial utilization.
Embodiment of the method with the present invention is corresponding, and device embodiment of the invention provides a kind of guidance dress of taking pictures in real time
Put, Fig. 2 is the structural representation of the guiding device of taking pictures in real time of apparatus of the present invention embodiment, as shown in Fig. 2 according to present invention dress
The guiding device of taking pictures in real time of embodiment is put, including：Image collection module 20, first processing module 22, Second processing module 24,
The modules of the embodiment of the present invention are described in detail below.
Specifically, described image acquisition module 20, for obtaining the current viewfinder image in smart machine.
The first processing module 22, for generating several virtual erect-positions in the viewfinder image.
Specifically, being traveled through in the viewfinder image by multi-scale sliding window mouthful, several virtual erect-positions are obtained.
The Second processing module 24, carries out aesthetics with reference to several virtual erect-positions for the viewfinder image and comments respectively
Point, obtain recommending erect-position and show according to aesthetics scoring.
Specifically, described recommend erect-position to choose the multiple phantom stations of optimal erect-position or aesthetics scoring more than or equal to lowest threshold
One or more of position.
More specific, choose the corresponding virtual erect-position of highest aesthetics scoring and be used as optimal erect-position；Aesthetics scoring be more than etc.
Arranged in multiple virtual erect-positions of lowest threshold according to the order of aesthetics scoring from high to low.
Specifically, the Second processing module 24 specifically for：
The viewfinder image and any one virtual erect-position are input in default aesthetic evaluation model to described virtual
Erect-position carries out aesthstic scoring, and several described virtual erect-positions of traversal obtain several aesthetics scorings；
Obtain recommending erect-position according to several described aesthetics scorings.
It is used as another embodiment of apparatus of the present invention embodiment, in addition to scene classification module：
The scene classification module, for using default image scene classification algorithm, knows to the viewfinder image
Other and analysis, obtains the classification results of the affiliated scene of the viewfinder image；
It should be noted that having there is the scene classification algorithm of many maturations in the prior art, therefore it will not be repeated here.
Further, the Second processing module 24, be additionally operable to the viewfinder image and any one virtual erect-position and
The classification results of the affiliated scene of viewfinder image are input in default aesthetic evaluation model carries out U.S. to the virtual erect-position
Scoring is learned, several described virtual erect-positions of traversal obtain several aesthetics scorings.
Specifically, the default aesthetic evaluation model is obtained by training, the machine learning method used includes convolution
Neutral net, limited Boltzmann machine, depth confidence network etc..
It is used as another embodiment of apparatus of the present invention embodiment, in addition to reminding module, the reminding module, for working as
When the aesthetics scoring for stating several virtual erect-positions is respectively less than lowest threshold, user is pointed out to adjust position of finding a view.
It is used as another embodiment of apparatus of the present invention embodiment, in addition to model training module.
The model training module is used for：
Obtain several images of known aesthetics scoring and personage's erect-position information；
Default aesthetic evaluation model is instructed using several images of known aesthetics scoring and personage's erect-position information
Practice, or using the scene tag belonging to several images and image of known aesthetics scoring and personage's erect-position information to default
Aesthetic evaluation model is trained, the aesthetic evaluation model after being trained.
Take pictures in real time guidance method and the system of the present invention, has the advantages that：
1st, using scene classification algorithm different scenes are carried out with adaptive aesthetic evaluation, and avoids taking general aesthetics
The classification performance limitation of identification tactic, improves the accuracy of final erect-position recommendation of taking pictures.
2nd, aesthetic evaluation model is obtained by training, it is to avoid the subjectivity and one-sidedness of artificial rule model.
3rd, the present invention supports horizontal and vertical exposal model, can recommend a variety of optimal shooting erect-positions, voluntarily be selected for user
Select.
For the more detailed explanation embodiment of the present invention, example 1 is provided, example 1 comprises the following steps：
Step S1：Into after exposal model, smart machine obtains current viewfinder image.
Step S2：Scene of taking pictures is recognized using image scene classification algorithm, photo is divided into by landscape according to recognition result, built
Build two classifications.
Step S3：By the classification results of viewfinder image and the affiliated scene of some virtual erect-position information and the viewfinder image
As input, the optimal erect-position information of people is calculated using convolutional neural networks aesthetic evaluation model.
Step S4：Smart machine goes out optimal erect-position prompting mark in the interface display of finding a view of taking pictures, and user instructs according to prompting
The person of being taken shift position.If user is unsatisfied with optimal erect-position, interface provides handoff options, shows that other recommend erect-position；If no
In the presence of erect-position is recommended, interface prompt user needs adjustment to find a view position.
In the step S1, into after exposal model, smart machine obtains current viewfinder image.
In the step S2, graphic collection can be landscape, building two by the result gone out according to scene classification Algorithm Analysis
Individual classification, that is, obtain the affiliated scene classification result of photo.
It should be noted that having there is the scene classification algorithm of many maturations in the prior art, therefore it will not be repeated here.
In the step S3, by viewfinder image and the affiliated scene of some virtual erect-position information and the viewfinder image
Classification results calculate the optimal group photo positional information of people using convolutional neural networks aesthetic evaluation model as input.Volume
Product neutral net aesthetic evaluation model is obtained by training, it is to avoid the subjectivity and one-sidedness of artificial rule model.
It should be noted that aesthetic evaluation model includes being not limited to use convolutional neural networks, other machines can be also used
Device learning method, for example, be limited Boltzmann machine, depth confidence network.
In the step S4, smart machine shows optimal erect-position prompting mark, user in the preview interface of finding a view of taking pictures
According to the prompting guidance person of being taken shift position.If user is unsatisfied with optimal erect-position, interface provides handoff options, shows that other are pushed away
Recommend erect-position；If in the absence of erect-position is recommended, interface prompt user needs adjustment to find a view position.
Specifically, the smart machine includes being not limited to PC, smart mobile phone, tablet personal computer, intelligent glasses, with
And other have the equipment of camera and data processing function.Scene classification result can be used as convolutional neural networks aesthetic evaluation
The input parameter of model, can also use and individually set up its corresponding convolutional neural networks aesthetic evaluation for each scene classification
Model.Preview interface prompts for graphical cues and/or text prompt and/or voice message.Other recommend erect-position information be
Other the virtual erect-position information chosen successively from high to low by aesthetics scoring.It is aesthstic appraisal result in the absence of optimal erect-position information
It is unsatisfactory for lowest threshold requirement.
The embodiment of the present invention can be realized recommends the people's erect-position that is taken automatically, and carries out scene point to viewfinder image in advance
Class, the accuracy that lifting erect-position is recommended；The convolutional neural networks aesthetic evaluation model obtained using training, it is to avoid artificial rule mould
The subjectivity and one-sidedness of type；Horizontal and vertical exposal model is supported, multiple optimal shooting erect-positions can be recommended, for user voluntarily
Selection.The scope that this method and system can be applicable is wide, can be generally applicable in smart machine.
Embodiments of the invention are the foregoing is only, are not intended to limit the invention, for those skilled in the art
For member, the present invention can have various modifications and variations.Any modification within the spirit and principles of the invention, being made,
Equivalent substitution, improvement etc., should be included within scope of the presently claimed invention.
Claims (10)
1. a kind of guidance method of taking pictures in real time, it is characterised in that including：
Obtain the current viewfinder image in smart machine；
Several virtual erect-positions are generated in the viewfinder image；
The viewfinder image carries out aesthstic scoring respectively with reference to several virtual erect-positions, obtains recommending erect-position simultaneously according to aesthetics scoring
Display.
2. guidance method as claimed in claim 1 of taking pictures in real time, it is characterised in that the viewfinder image is respectively in connection with several
Virtual erect-position carries out aesthstic scoring, obtains recommending erect-position to include according to aesthetics scoring：
The viewfinder image and any one virtual erect-position are input in default aesthetic evaluation model to the virtual erect-position
Aesthstic scoring is carried out, several described virtual erect-positions of traversal obtain several aesthetics scorings；
Obtain recommending erect-position according to several described aesthetics scorings.
3. guidance method as claimed in claim 2 of taking pictures in real time, it is characterised in that combine several in the viewfinder image empty
Plan erect-position is carried out before aesthstic scoring respectively, in addition to：
Using default image scene classification algorithm, the viewfinder image is identified and analyzed, the viewfinder image is obtained
The classification results of affiliated scene；
The viewfinder image carries out aesthetics scoring respectively in connection with several virtual erect-positions to be included：
The classification results of the viewfinder image and any one virtual erect-position and the affiliated scene of the viewfinder image are input to pre-
If aesthetic evaluation model in aesthstic scoring is carried out to the virtual erect-position, several described virtual erect-positions of traversal obtain some
Individual aesthetics scoring.
4. as claimed in claim 1 guidance method of taking pictures in real time, it is characterised in that the recommendation erect-position choose optimal erect-position or
Aesthetics scoring is more than or equal to one or more of multiple virtual erect-positions of lowest threshold.
5. guidance method as claimed in claim 1 of taking pictures in real time, it is characterised in that also include：
When the aesthetics scoring of several virtual erect-positions is respectively less than lowest threshold, user is pointed out to adjust position of finding a view.
6. a kind of guiding device of taking pictures in real time, it is characterised in that including image collection module, first processing module, second processing
Module：
Described image acquisition module, for obtaining the current viewfinder image in smart machine；
The first processing module, for generating several virtual erect-positions in the viewfinder image；
The Second processing module, aesthstic scoring is carried out for the viewfinder image respectively with reference to several virtual erect-positions, according to
Aesthetics scoring is obtained recommending erect-position and shown.
7. as claimed in claim 6 guiding device of taking pictures in real time, it is characterised in that the Second processing module specifically for：
The viewfinder image and any one virtual erect-position are input in default aesthetic evaluation model to the virtual erect-position
Aesthstic scoring is carried out, several described virtual erect-positions of traversal obtain several aesthetics scorings；
Obtain recommending erect-position according to several described aesthetics scorings.
8. guiding device as claimed in claim 7 of taking pictures in real time, it is characterised in that also including scene classification module：
The scene classification module, for use default image scene classification algorithm, the viewfinder image is identified and
Analysis, obtains the classification results of the affiliated scene of the viewfinder image；
The Second processing module, is additionally operable to the viewfinder image and any one virtual erect-position and viewfinder image institute
The classification results of category scene are input in default aesthetic evaluation model carries out aesthstic scoring to the virtual erect-position, and traversal is described
Several virtual erect-positions, obtain several aesthetics scorings.
9. as claimed in claim 6 guiding device of taking pictures in real time, it is characterised in that the recommendation erect-position choose optimal erect-position or
Aesthetics scoring is more than or equal to one or more of multiple virtual erect-positions of lowest threshold.
10. guiding device as claimed in claim 6 of taking pictures in real time, it is characterised in that also including reminding module：
The reminding module, for when the aesthetics scoring of several virtual erect-positions is respectively less than lowest threshold, pointing out user
Adjust position of finding a view.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710257194.7A CN107018330A (en) | 2017-04-19 | 2017-04-19 | A kind of guidance method and device of taking pictures in real time |
| PCT/CN2017/116058 WO2018192244A1 (en) | 2017-04-19 | 2017-12-14 | Shooting guidance method for intelligent device |
| PCT/CN2017/116059 WO2018192245A1 (en) | 2017-04-19 | 2017-12-14 | Automatic scoring method for photo based on aesthetic assessment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710257194.7A CN107018330A (en) | 2017-04-19 | 2017-04-19 | A kind of guidance method and device of taking pictures in real time |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107018330A true CN107018330A (en) | 2017-08-04 |
Family
ID=59446896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710257194.7A Pending CN107018330A (en) | 2017-04-19 | 2017-04-19 | A kind of guidance method and device of taking pictures in real time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107018330A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107705307A (en) * | 2017-11-09 | 2018-02-16 | 睿魔智能科技（东莞）有限公司 | A kind of shooting patterning process and system based on deep learning |
| CN107995419A (en) * | 2017-11-24 | 2018-05-04 | 维沃移动通信有限公司 | One kind is taken pictures suggesting method, device and mobile terminal |
| WO2018192245A1 (en) * | 2017-04-19 | 2018-10-25 | 中国电子科技集团公司电子科学研究院 | Automatic scoring method for photo based on aesthetic assessment |
| CN109410163A (en) * | 2018-10-23 | 2019-03-01 | 北京旷视科技有限公司 | Recommended location of taking pictures acquisition methods, device, terminal and computer storage medium |
| CN110719327A (en) * | 2019-10-08 | 2020-01-21 | 珠海格力电器股份有限公司 | Interactive method and device for uploading image and storage medium |
| CN110958384A (en) * | 2019-11-06 | 2020-04-03 | 苏州佳世达光电有限公司 | Intelligent auxiliary photographing system and method |
| CN111095293A (en) * | 2017-12-15 | 2020-05-01 | 华为技术有限公司 | Image aesthetic processing method and electronic equipment |
| WO2020171512A1 (en) * | 2019-02-19 | 2020-08-27 | Samsung Electronics Co., Ltd. | Electronic device for recommending composition and operating method thereof |
| CN111614897A (en) * | 2020-05-13 | 2020-09-01 | 南京邮电大学 | Intelligent photographing method based on multi-dimensional driving of user preference |
| CN113596306A (en) * | 2021-07-27 | 2021-11-02 | 重庆电子工程职业学院 | Shooting range prompting device of photographic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218619A (en) * | 2013-03-15 | 2013-07-24 | 华南理工大学 | Image aesthetics evaluating method |
| CN104182970A (en) * | 2014-08-08 | 2014-12-03 | 浙江大学 | Souvenir photo portrait position recommendation method based on photography composition rule |
| CN104184934A (en) * | 2013-05-23 | 2014-12-03 | 北京千橡网景科技发展有限公司 | Method and apparatus for providing auxiliary reference for shooting |
| CN104243787A (en) * | 2013-06-06 | 2014-12-24 | 华为技术有限公司 | Photographing method and equipment, and photo management method |
| CN104301613A (en) * | 2014-10-16 | 2015-01-21 | 深圳市中兴移动通信有限公司 | Mobile terminal and photographing method thereof |
| CN104717413A (en) * | 2013-12-12 | 2015-06-17 | 北京三星通信技术研究有限公司 | Shooting assistance method and equipment |
| CN105827930A (en) * | 2015-05-27 | 2016-08-03 | 广东维沃软件技术有限公司 | Method and device of auxiliary photographing |
-
2017
- 2017-04-19 CN CN201710257194.7A patent/CN107018330A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218619A (en) * | 2013-03-15 | 2013-07-24 | 华南理工大学 | Image aesthetics evaluating method |
| CN104184934A (en) * | 2013-05-23 | 2014-12-03 | 北京千橡网景科技发展有限公司 | Method and apparatus for providing auxiliary reference for shooting |
| CN104243787A (en) * | 2013-06-06 | 2014-12-24 | 华为技术有限公司 | Photographing method and equipment, and photo management method |
| CN104717413A (en) * | 2013-12-12 | 2015-06-17 | 北京三星通信技术研究有限公司 | Shooting assistance method and equipment |
| CN104182970A (en) * | 2014-08-08 | 2014-12-03 | 浙江大学 | Souvenir photo portrait position recommendation method based on photography composition rule |
| CN104301613A (en) * | 2014-10-16 | 2015-01-21 | 深圳市中兴移动通信有限公司 | Mobile terminal and photographing method thereof |
| CN105827930A (en) * | 2015-05-27 | 2016-08-03 | 广东维沃软件技术有限公司 | Method and device of auxiliary photographing |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018192245A1 (en) * | 2017-04-19 | 2018-10-25 | 中国电子科技集团公司电子科学研究院 | Automatic scoring method for photo based on aesthetic assessment |
| CN107705307A (en) * | 2017-11-09 | 2018-02-16 | 睿魔智能科技（东莞）有限公司 | A kind of shooting patterning process and system based on deep learning |
| CN107705307B (en) * | 2017-11-09 | 2021-01-01 | 睿魔智能科技（东莞）有限公司 | Shooting composition method and system based on deep learning |
| CN107995419A (en) * | 2017-11-24 | 2018-05-04 | 维沃移动通信有限公司 | One kind is taken pictures suggesting method, device and mobile terminal |
| CN107995419B (en) * | 2017-11-24 | 2019-10-15 | 维沃移动通信有限公司 | One kind is taken pictures suggesting method, device and mobile terminal |
| CN111095293B (en) * | 2017-12-15 | 2023-09-12 | 华为技术有限公司 | Image aesthetic processing method and electronic equipment |
| CN111095293A (en) * | 2017-12-15 | 2020-05-01 | 华为技术有限公司 | Image aesthetic processing method and electronic equipment |
| CN109410163A (en) * | 2018-10-23 | 2019-03-01 | 北京旷视科技有限公司 | Recommended location of taking pictures acquisition methods, device, terminal and computer storage medium |
| WO2020171512A1 (en) * | 2019-02-19 | 2020-08-27 | Samsung Electronics Co., Ltd. | Electronic device for recommending composition and operating method thereof |
| US11128795B2 (en) | 2019-02-19 | 2021-09-21 | Samsung Electronics Co., Ltd. | Electronic device for recommending composition and operating method thereof |
| US11671701B2 (en) | 2019-02-19 | 2023-06-06 | Samsung Electronics Co., Ltd. | Electronic device for recommending composition and operating method thereof |
| CN110719327A (en) * | 2019-10-08 | 2020-01-21 | 珠海格力电器股份有限公司 | Interactive method and device for uploading image and storage medium |
| CN110958384A (en) * | 2019-11-06 | 2020-04-03 | 苏州佳世达光电有限公司 | Intelligent auxiliary photographing system and method |
| CN111614897A (en) * | 2020-05-13 | 2020-09-01 | 南京邮电大学 | Intelligent photographing method based on multi-dimensional driving of user preference |
| CN113596306A (en) * | 2021-07-27 | 2021-11-02 | 重庆电子工程职业学院 | Shooting range prompting device of photographic equipment |
| CN113596306B (en) * | 2021-07-27 | 2023-05-05 | 重庆电子工程职业学院 | Shooting range prompting device of photographic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107018330A (en) | A kind of guidance method and device of taking pictures in real time | |
| US11790589B1 (en) | System and method for creating avatars or animated sequences using human body features extracted from a still image | |
| US11736756B2 (en) | Producing realistic body movement using body images | |
| CN107146198B (en) | Intelligent photo cutting method and device | |
| CN108986801A (en) | A kind of man-machine interaction method, device and human-computer interaction terminal | |
| WO2020093799A1 (en) | Image processing method and apparatus | |
| CN110543578A (en) | object recognition method and device | |
| CN101308571A (en) | Method for generating novel human face by combining active grid and human face recognition | |
| CN108388882A (en) | Based on the gesture identification method that the overall situation-part is multi-modal RGB-D | |
| US20190332854A1 (en) | Hybrid deep learning method for recognizing facial expressions | |
| WO2016165614A1 (en) | Method for expression recognition in instant video and electronic equipment | |
| CN109472795A (en) | A kind of image edit method and device | |
| CN110868538A (en) | Method and electronic equipment for recommending shooting posture | |
| US20200293755A1 (en) | Hybrid deep learning method for recognizing facial expressions | |
| CN113506377A (en) | Teaching training method based on virtual roaming technology | |
| CN111078005B (en) | Virtual partner creation method and virtual partner system | |
| Lee et al. | Emotion-Based Painting Image Display System. | |
| CN109886266A (en) | Method, relevant apparatus and the system of image procossing | |
| CN115131879B (en) | Action evaluation method and device | |
| CN117115917A (en) | Teacher behavior recognition method, device and medium based on multi-modal feature fusion | |
| CN113362455B (en) | Video conference background virtualization processing method and device | |
| CN110620877B (en) | Position information generation method, device, terminal and computer readable storage medium | |
| CN114529944A (en) | Human image scene identification method combining human body key point heat map features | |
| CN107016351A (en) | Shoot the acquisition methods and device of tutorial message | |
| CN115587829A (en) | Dish recommendation method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170804 |