CN109274885B - Fine adjustment method for photographing - Google Patents
Fine adjustment method for photographing Download PDFInfo
- Publication number
- CN109274885B CN109274885B CN201811056889.XA CN201811056889A CN109274885B CN 109274885 B CN109274885 B CN 109274885B CN 201811056889 A CN201811056889 A CN 201811056889A CN 109274885 B CN109274885 B CN 109274885B
- Authority
- CN
- China
- Prior art keywords
- picture
- evaluation score
- pictures
- shooting
- camera
- 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.)
- Active
Links
Images
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
- H04N23/60—Control of cameras or camera modules
- H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a photo fine-adjustment method, which comprises the steps of shooting an object to be shot at an original position through a camera, sending a first picture obtained by shooting to a trained CNN network, outputting an evaluation score, moving the camera according to a preset motion track, shooting to obtain a second picture, sending the second picture to the trained CNN network, and finally fine-adjusting the position of the camera according to the first evaluation score and the second evaluation score to achieve an optimal shooting position. By automatically adjusting the position of the camera instead of manually adjusting the camera in a complicated manner, the technical scheme of the invention can more quickly find the optimal shooting position, thereby effectively improving the efficiency of obtaining high-quality pictures. In addition, the method adopts a deep learning target detection technology to quickly grade the shot picture, and further improves the efficiency of obtaining high-quality pictures.
Description
Technical Field
The invention relates to the field of machine vision, in particular to a photographing fine adjustment method.
Background
In modern society, photographing is a common behavior, and a photographing mode can be used for achieving the purpose when recording certain information. In the process of photographing, the photographing position needs to be adjusted continuously, so that the quality of the obtained picture is higher, and the information recorded by the picture is more comprehensive.
The existing shooting fine adjustment method is based on visual feedback of shooting personnel, achieves a shooting position considered to be optimal by manually adjusting a camera, has small deviation, cannot accurately adjust the camera to the optimal shooting position, and rapidly obtains a high-quality picture.
Disclosure of Invention
The embodiment of the invention aims to provide a shooting fine adjustment method, which can replace the manual and tedious regulation of a camera to quickly find the optimal shooting position by automatically regulating the position of the camera, thereby effectively improving the efficiency of obtaining high-quality pictures.
In order to achieve the above object, an embodiment of the present invention provides a method for fine tuning photographing, including:
shooting an object to be shot at an original position through a camera to obtain a first picture;
extracting first picture information of the first picture, sending the first picture information to a trained CNN network, and outputting a first evaluation score; wherein the first picture information comprises a category, a time, a location, and a pixel of the first picture;
controlling the camera to move to a second position according to a preset moving track, and shooting the object to be shot to obtain a second picture;
extracting second picture information of the second picture, sending the second picture information to the trained CNN network, and outputting a second evaluation score;
if the first evaluation score is larger than the second evaluation score, moving the camera to the original position, moving the camera to a third position according to the opposite direction of the moving track, and shooting the object to be shot again;
and if the first evaluation score is smaller than the second evaluation score, moving the camera to a fourth position according to the positive direction of the moving track, and shooting the object to be shot again.
Further, the photographing fine adjustment method further includes:
when the camera moves to the third position, shooting the object to be shot to obtain a third picture;
extracting third picture information of the third picture, sending the third picture information to the trained CNN network, and outputting a third evaluation score;
if the first evaluation score is larger than the third evaluation score, the original position is used as the optimal shooting position;
and if the first evaluation score is smaller than the third evaluation score, moving the camera to a fifth position in the opposite direction of the moving track, and shooting the object to be shot again.
Further, the photographing fine adjustment method further includes:
when the camera moves to the fourth position, shooting the object to be shot to obtain a fourth picture;
extracting fourth picture information of the fourth picture, sending the fourth picture information to the trained CNN network, and outputting a fourth evaluation score;
if the second evaluation score is larger than the fourth evaluation score, the second position is used as the optimal shooting position;
and if the second evaluation score is smaller than the fourth evaluation score, moving the camera to a sixth position according to the positive direction of the moving track, and shooting the object to be shot again.
Further, the preset moving track specifically includes:
and taking the front side of the object to be shot as a shooting object, taking the range between the camera and the object to be shot within 2 meters as a shooting distance, and moving the camera from left to right to serve as the preset moving track.
Further, the trained CNN network is obtained according to the following steps:
acquiring a plurality of network pictures and extracting picture information of the network pictures; wherein the picture information of the plurality of network pictures comprises praise amount, forwarding amount, comment amount, category, time, place and pixel of the plurality of network pictures;
respectively calculating to obtain evaluation scores of the plurality of network pictures according to the picture information of the plurality of network pictures, the preset total average praise number and the preset type average praise number corresponding to each picture; wherein the evaluation score is proportional to the picture quality of the plurality of network pictures;
and taking the category, time, place and pixel of the network pictures as input of a training set, and taking the evaluation scores of the network pictures as output of the training set to construct the trained CNN network.
Further, the categories include: people, objects, and landscapes.
Further, the class average praise number comprises a human class average praise number, an object class average praise number and a landscape class average praise number;
the average praise number of the people is the ratio of the total praise amount of the pictures belonging to the people in the pictures to the total vermicelli amount of the users;
the average praise number of the object class is the ratio of the total praise amount of the pictures belonging to the object class in the plurality of pictures to the total vermicelli amount of the plurality of users;
the average praise number of the scenic class is a ratio of a total praise amount of pictures belonging to the scenic class in the plurality of pictures to a total vermicelli amount of the users.
Further, the calculating, according to the picture information of the plurality of network pictures, the preset total average praise number and the preset class average praise number corresponding to each picture, to obtain the evaluation scores of the plurality of network pictures specifically is:
taking the total average praise number as a first parameter;
dividing the praise amount of the network pictures by the total average praise amount to obtain a plurality of second parameters;
dividing the praise amount of the plurality of network pictures by the preset average praise number corresponding to each picture to obtain a plurality of third parameters;
dividing the forwarding amounts of the network pictures by the total average praise number respectively to obtain a plurality of fourth parameters;
dividing the forwarding amounts of the network pictures by preset class average praise numbers corresponding to the pictures respectively to obtain a plurality of fifth parameters;
dividing the comment amount of the plurality of network pictures by the total average praise number respectively to obtain a plurality of sixth parameters;
dividing the comment amount of the plurality of network pictures by the preset class average praise number corresponding to each picture to obtain a plurality of seventh parameters;
obtaining the evaluation scores of the network pictures according to the first parameters, the second parameters, the third parameters, the fourth parameters, the fifth parameters, the sixth parameters, the seventh parameters and preset weights.
The embodiment of the invention has the following beneficial effects:
compared with the prior art, the photographing fine-tuning method provided by the embodiment of the invention has the advantages that the camera shoots an object to be shot at the original position, the shot first picture is sent to the trained CNN network, the evaluation score is output, then the camera moves according to the preset motion track and shoots to obtain a second picture, the second picture is sent to the trained CNN network, and finally the position of the camera is fine-tuned according to the first evaluation score and the second evaluation score to reach the optimal shooting position. By automatically adjusting the position of the camera instead of manually adjusting the camera in a complicated manner, the technical scheme of the invention can more quickly find the optimal shooting position, thereby effectively improving the efficiency of obtaining high-quality pictures. In addition, the method adopts a deep learning target detection technology to quickly grade the shot picture, and further improves the efficiency of obtaining high-quality pictures.
Drawings
FIG. 1 is a flowchart illustrating a photo trimming method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating another embodiment of a photo trimming method according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic flowchart of an embodiment of a photo trimming method provided by the present invention; the embodiment of the invention provides a method for checking the safety dressing of workers on an operation site, which comprises the steps of S1 to S5;
s1, shooting an object to be shot at an original position through a camera to obtain a first picture;
s2, extracting first picture information of the first picture, sending the first picture information to the trained CNN network, and outputting a first evaluation score;
it should be noted that the first picture information includes a category, time, location, and pixel of the first picture; wherein the categories include: people, objects, and landscapes; the time is the time for shooting the first picture; the place is a place for shooting a first picture; the pixels are pixel values of the first picture.
S3, controlling the camera to move to a second position according to a preset moving track, shooting an object to be shot, and obtaining a second picture;
it should be noted that the preset moving track is as follows: taking the front side of the object to be shot as a shooting object, taking the range between the camera and the object to be shot within 2 meters as a shooting distance, and moving the camera from left to right to serve as the preset moving track; the distance of the moving camera is preset and is 0-1cm, and a more accurate shooting position can be obtained through the preset moving distance, so that a higher-quality picture can be obtained.
In the present embodiment, the lens of the camera is directed to the front of the object to be photographed, regardless of how the camera is moved.
S4, extracting second picture information of a second picture, sending the second picture information to the trained CNN network, and outputting a second evaluation score;
s5, if the first evaluation score is larger than the second evaluation score, moving the camera to the original position, moving the camera to a third position according to the opposite direction of the moving track, and shooting the object to be shot again; if the first evaluation score is smaller than the second evaluation score, moving the camera to a fourth position according to the positive direction of the moving track, and shooting the object to be shot again;
referring to fig. 2 as another embodiment of the present invention, fig. 2 is a schematic flowchart of another embodiment of the fine-tuning method for photographing according to the present invention, and fig. 1 is different from fig. 2 in that after step S5 is executed, steps S6 to S11 are further included.
S6, when the camera moves to a third position, shooting an object to be shot to obtain a third picture; extracting third picture information of a third picture, sending the third picture information to the trained CNN network, and outputting a third evaluation score;
s7, if the first evaluation score is larger than the third evaluation score, moving the camera to the original position, and taking the original position as the optimal shooting position;
s8, if the first evaluation score is smaller than the third evaluation score, moving the camera to a fifth position in the opposite direction of the moving track, and shooting the object to be shot again;
it should be noted that, if the evaluation score of the next position is still higher than the evaluation score of the previous position, the movement is continued to the next position according to the opposite direction of the movement track until the evaluation score is not incremented any more.
S9, when the camera moves to a fourth position, shooting an object to be shot to obtain a fourth picture; extracting fourth picture information of a fourth picture, sending the fourth picture information to the trained CNN network, and outputting a fourth evaluation score;
s10, if the second evaluation score is larger than the fourth evaluation score, moving the camera to a second position, and taking the second position as an optimal shooting position;
s11, if the second evaluation score is smaller than the fourth evaluation score, moving the camera to a sixth position according to the positive direction of the moving track, and shooting the object to be shot again;
if the evaluation score of the next position is still higher than the evaluation score of the previous position, the user continues to move in the positive direction of the movement track to the next position until the evaluation score is not increased any more.
As a further improvement of the embodiment of the present invention, the trained CNN network is obtained according to the following steps:
acquiring a plurality of network pictures and extracting picture information of the network pictures; the picture information of the network pictures comprises praise amount, forwarding amount, comment amount, category, time, place and pixel of the network pictures;
respectively calculating to obtain evaluation scores of the plurality of network pictures according to the picture information of the plurality of network pictures, the preset total average praise number and the preset type average praise number corresponding to each picture; wherein the evaluation score is in direct proportion to the picture quality of the plurality of network pictures;
the trained CNN network is constructed by inputting the categories, times, locations, and pixels of the plurality of network pictures as a training set and outputting the evaluation scores of the plurality of network pictures as the training set.
In this embodiment, the class average praise number includes a person class average praise number, an object class average praise number, and a landscape class average praise number; the average praise number of the people is the ratio of the total praise amount of the pictures belonging to the people in the plurality of pictures to the total vermicelli amount of the users; the average praise number of the object class is the ratio of the total praise amount of the pictures belonging to the object class in the plurality of pictures to the total vermicelli amount of the plurality of users; the average praise number of the scenery is the ratio of the total praise amount of the pictures belonging to the scenery in the plurality of pictures to the total vermicelli amount of the users.
It should be noted that by classifying the class average praise number, the final evaluation score can be more accurate, and the accuracy of the shooting position is further improved, so that a higher-quality picture is obtained.
In this embodiment, the total average praise number is taken as a first parameter; dividing the praise amount of the network pictures by the total average praise number respectively to obtain a plurality of second parameters; dividing the praise amount of the plurality of network pictures by the preset average praise number corresponding to each picture to obtain a plurality of third parameters; dividing the forwarding amounts of the network pictures by the total average praise number respectively to obtain a plurality of fourth parameters; dividing the forwarding amounts of the multiple network pictures by the preset class average praise number corresponding to each picture to obtain multiple fifth parameters; dividing the comment amount of the plurality of network pictures by the total average praise number respectively to obtain a plurality of sixth parameters; dividing the comment amount of the plurality of network pictures by the preset class average praise number corresponding to each picture to obtain a plurality of seventh parameters; and obtaining the evaluation scores of the network pictures according to the first parameters, the second parameters, the third parameters, the fourth parameters, the fifth parameters, the sixth parameters, the seventh parameters and the preset weight. Wherein the evaluation score is proportional to the picture quality of the plurality of network pictures.
In order to better explain the working principle of the present invention, the following is the flow steps of the photo fine tuning method of the present invention. Firstly, shooting an object to be shot at an original position through a camera to obtain a first picture; sending the first picture to a trained CNN network, and outputting a first evaluation score; then taking the front side of the object to be shot as a shooting object, taking the range between the camera and the object to be shot within 2 meters as a shooting distance, and moving the camera by 0.5cm from left to right; taking a picture at the current position to obtain a second picture; sending the second picture to the trained CNN network, and outputting a second evaluation score; comparing the first rating score to the second rating score, two cases 1, 2 occur:
1. if the first evaluation score is larger than the second evaluation score, moving the camera to the original position, moving the camera to a third position according to the opposite direction of the moving track, and shooting the object to be shot again to obtain a third picture; sending the third picture information to the trained CNN network, and outputting a third evaluation score; comparing the first evaluation score with the third evaluation score, two cases 1.1, 1.2 occur:
1.1, if the first evaluation score is larger than the third evaluation score, moving the camera to the original position, and taking the original position as the optimal shooting position.
1.2, if the first evaluation score is smaller than the third evaluation score, moving the camera to a fifth position in the opposite direction of the moving track, and shooting the object to be shot again; if the evaluation score of the next position is still higher than that of the previous position, the movement is continued to the next position according to the reverse direction of the movement track until the evaluation score is not increased any more. Such as: and if the first evaluation score is 80 scores, the second evaluation score is 70 scores and the third evaluation score is 90 scores, the camera continues to move in the opposite direction to obtain a fourth evaluation score of 89 scores, and the position corresponding to the third evaluation score is taken as the optimal shooting position.
2. If the first evaluation score is smaller than the second evaluation score, moving the camera to a fourth position according to the positive direction of the moving track, and shooting the object to be shot again to obtain a fourth picture; sending the fourth picture information to the trained CNN network, and outputting a fourth evaluation score; comparing the second evaluation score with the fourth evaluation score, two cases 2.1, 2.2 occur:
2.1, if the second evaluation score is larger than the fourth evaluation score, moving the camera to a second position, and taking the second position as an optimal shooting position;
2.2, if the second evaluation score is smaller than the fourth evaluation score, moving the camera to a sixth position according to the positive direction of the moving track, and shooting the object to be shot again; and if the evaluation score of the next position is still higher than that of the previous position, continuing to move in the positive direction of the movement track to the next position until the evaluation score is not increased any more. Such as: and if the first evaluation score is 80 scores, the second evaluation score is 85 scores and the third evaluation score is 90 scores, the camera continues to move in the positive direction to obtain a fourth evaluation score of 89 scores, and the position corresponding to the third evaluation score is taken as the optimal shooting position.
It should be noted that when the optimal shooting position is obtained, the camera is used to shoot the object to be shot, and the obtained picture is a high-quality picture required by the user.
According to the photo fine-tuning method provided by the embodiment of the invention, the camera shoots an object to be shot at an original position, a first picture obtained by shooting is sent to a trained CNN network, an evaluation score is output, then the camera moves according to a preset motion track and shoots to obtain a second picture, the second picture is sent to the trained CNN network, and finally the position of the camera is fine-tuned according to the first evaluation score and the second evaluation score to reach an optimal shooting position. By automatically adjusting the position of the camera instead of manually adjusting the camera in a complicated manner, the technical scheme of the invention can more quickly find the optimal shooting position, thereby effectively improving the efficiency of obtaining high-quality pictures. In addition, the method adopts a deep learning target detection technology to quickly grade the shot picture, and further improves the efficiency of obtaining high-quality pictures.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (7)
1. A photographing fine adjustment method is characterized by comprising the following steps:
shooting an object to be shot at an original position through a camera to obtain a first picture;
extracting first picture information of the first picture, sending the first picture information to a trained CNN network, and outputting a first evaluation score; wherein the first picture information comprises a category, a time, a location, and a pixel of the first picture;
controlling the camera to move to a second position according to a preset moving track, and shooting the object to be shot to obtain a second picture;
extracting second picture information of the second picture, sending the second picture information to the trained CNN network, and outputting a second evaluation score;
if the first evaluation score is larger than the second evaluation score, moving the camera to the original position, moving the camera to a third position according to the opposite direction of the moving track, and shooting the object to be shot again;
if the first evaluation score is smaller than the second evaluation score, moving the camera to a fourth position according to the positive direction of the moving track, and shooting the object to be shot again;
wherein the trained CNN network is obtained according to the following steps:
acquiring a plurality of network pictures and extracting picture information of the network pictures; wherein the picture information of the plurality of network pictures comprises praise amount, forwarding amount, comment amount, category, time, place and pixel of the plurality of network pictures;
respectively calculating to obtain evaluation scores of the plurality of network pictures according to the picture information of the plurality of network pictures, the preset total average praise number and the preset type average praise number corresponding to each picture; wherein the evaluation score is proportional to the picture quality of the plurality of network pictures;
and taking the category, time, place and pixel of the network pictures as input of a training set, and taking the evaluation scores of the network pictures as output of the training set to construct the trained CNN network.
2. The fine-tuning method for photographing according to claim 1, further comprising:
when the camera moves to the third position, shooting the object to be shot to obtain a third picture;
extracting third picture information of the third picture, sending the third picture information to the trained CNN network, and outputting a third evaluation score;
if the first evaluation score is larger than the third evaluation score, the original position is used as the optimal shooting position;
and if the first evaluation score is smaller than the third evaluation score, moving the camera to a fifth position in the opposite direction of the moving track, and shooting the object to be shot again.
3. The fine-tuning method for photographing according to claim 1, further comprising:
when the camera moves to the fourth position, shooting the object to be shot to obtain a fourth picture;
extracting fourth picture information of the fourth picture, sending the fourth picture information to the trained CNN network, and outputting a fourth evaluation score;
if the second evaluation score is larger than the fourth evaluation score, the second position is used as the optimal shooting position;
and if the second evaluation score is smaller than the fourth evaluation score, moving the camera to a sixth position according to the positive direction of the moving track, and shooting the object to be shot again.
4. The fine-tuning method for photographing according to claim 1, wherein the predetermined movement trajectory specifically includes:
and taking the front side of the object to be shot as a shooting object, taking the range between the camera and the object to be shot within 2 meters as a shooting distance, and moving the camera from left to right to serve as the preset moving track.
5. The photo trimming method of claim 4, wherein the categories include: people, objects, and landscapes.
6. The photo fine-tuning method of claim 5, wherein the class average praise numbers comprise a people class average praise number, an objects class average praise number, and a landscape class average praise number;
the average praise number of the people is the ratio of the total praise amount of the pictures belonging to the people in the pictures to the total vermicelli amount of the users;
the average praise number of the object class is the ratio of the total praise amount of the pictures belonging to the object class in the plurality of pictures to the total vermicelli amount of the plurality of users;
the average praise number of the scenic class is the ratio of the total praise amount of the pictures belonging to the scenic class in the plurality of pictures to the total vermicelli amount of a plurality of users.
7. The fine-tuning method for photographing according to claim 5, wherein the evaluation scores of the plurality of network pictures are respectively calculated according to the picture information of the plurality of network pictures, a preset total average praise number and a preset type average praise number corresponding to each picture, and specifically:
taking the total average praise number as a first parameter;
dividing the praise amount of the network pictures by the total average praise amount to obtain a plurality of second parameters;
dividing the praise amount of the plurality of network pictures by the preset average praise number corresponding to each picture to obtain a plurality of third parameters;
dividing the forwarding amounts of the network pictures by the total average praise number respectively to obtain a plurality of fourth parameters;
dividing the forwarding amounts of the network pictures by preset class average praise numbers corresponding to the pictures respectively to obtain a plurality of fifth parameters;
dividing the comment amount of the plurality of network pictures by the total average praise number respectively to obtain a plurality of sixth parameters;
dividing the comment amount of the plurality of network pictures by the preset class average praise number corresponding to each picture to obtain a plurality of seventh parameters;
obtaining the evaluation scores of the network pictures according to the first parameters, the second parameters, the third parameters, the fourth parameters, the fifth parameters, the sixth parameters, the seventh parameters and preset weights.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811056889.XA CN109274885B (en) | 2018-09-11 | 2018-09-11 | Fine adjustment method for photographing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811056889.XA CN109274885B (en) | 2018-09-11 | 2018-09-11 | Fine adjustment method for photographing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109274885A CN109274885A (en) | 2019-01-25 |
| CN109274885B true CN109274885B (en) | 2021-03-26 |
Family
ID=65189115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811056889.XA Active CN109274885B (en) | 2018-09-11 | 2018-09-11 | Fine adjustment method for photographing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109274885B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1763624A (en) * | 2004-10-22 | 2006-04-26 | 亚洲光学股份有限公司 | Automatic focusing method and automatic focusing apparatus of electronic camera |
| CN102414717A (en) * | 2009-04-29 | 2012-04-11 | 皇家飞利浦电子股份有限公司 | Method of selecting an optimal viewing angle position for a camera |
| CN102572265A (en) * | 2010-09-01 | 2012-07-11 | 苹果公司 | Auto-focus control using image statistics data with coarse and fine auto-focus scores |
| CN102945279A (en) * | 2012-11-14 | 2013-02-27 | 清华大学 | Evaluating method and device of influence effect of microblog users |
| 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 |
| CN106202089A (en) * | 2015-05-04 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus determining picture quality and web page display |
| CN106408603A (en) * | 2016-06-21 | 2017-02-15 | 北京小米移动软件有限公司 | Camera method and device |
| CN106803206A (en) * | 2015-11-25 | 2017-06-06 | 小米科技有限责任公司 | Photo processing method and device |
| CN107945175A (en) * | 2017-12-12 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Evaluation method, device, server and the storage medium of image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6071436B2 (en) * | 2012-11-05 | 2017-02-01 | オリンパス株式会社 | Imaging apparatus, imaging method, and program |
-
2018
- 2018-09-11 CN CN201811056889.XA patent/CN109274885B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1763624A (en) * | 2004-10-22 | 2006-04-26 | 亚洲光学股份有限公司 | Automatic focusing method and automatic focusing apparatus of electronic camera |
| CN102414717A (en) * | 2009-04-29 | 2012-04-11 | 皇家飞利浦电子股份有限公司 | Method of selecting an optimal viewing angle position for a camera |
| CN102572265A (en) * | 2010-09-01 | 2012-07-11 | 苹果公司 | Auto-focus control using image statistics data with coarse and fine auto-focus scores |
| CN102945279A (en) * | 2012-11-14 | 2013-02-27 | 清华大学 | Evaluating method and device of influence effect of microblog users |
| 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 |
| CN106202089A (en) * | 2015-05-04 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus determining picture quality and web page display |
| CN106803206A (en) * | 2015-11-25 | 2017-06-06 | 小米科技有限责任公司 | Photo processing method and device |
| CN106408603A (en) * | 2016-06-21 | 2017-02-15 | 北京小米移动软件有限公司 | Camera method and device |
| CN107945175A (en) * | 2017-12-12 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Evaluation method, device, server and the storage medium of image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109274885A (en) | 2019-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104885125B (en) | Message processing device, information processing system and information processing method | |
| CN103929596B (en) | Guide the method and device of shooting composition | |
| US9591211B2 (en) | Photographing method and apparatus | |
| CN108234870A (en) | Image processing method, device, terminal and storage medium | |
| CN104820328B (en) | Rapid automatic focusing method of calculating focusing position on the basis of defocusing model curve | |
| US8189916B2 (en) | Image processing method, system, and computer readable medium | |
| TWI532361B (en) | Automatic photographing method and system thereof | |
| CN108537782A (en) | A method of building images match based on contours extract with merge | |
| CN104092947A (en) | Image pick-up apparatus and method of recognizing face | |
| CN109714519A (en) | A kind of method and system of adjust automatically image frame | |
| CN104506773A (en) | Camera automatic zoom control method based on human eye distance | |
| CN103237175A (en) | Automatic exposure method of digital camera based on human visual characteristics | |
| CN104751407A (en) | Method and device used for blurring image | |
| US11736800B2 (en) | Method, apparatus, and device for image capture, and storage medium | |
| CN109801314A (en) | A kind of binocular dynamic visual sensor solid matching method based on deep learning | |
| CN111756996A (en) | Video processing method, video processing apparatus, electronic device, and computer-readable storage medium | |
| CN110210333A (en) | A kind of focusing iris image acquiring method and device automatically | |
| CN105338235A (en) | Automatic aperture adjustment method and device | |
| CN106506946B (en) | A kind of camera automatic focusing method and video camera | |
| CN112601063A (en) | Mixed color temperature white balance method | |
| CN116311061A (en) | Material identification method based on image processing | |
| CN109274885B (en) | Fine adjustment method for photographing | |
| CN105763814A (en) | Night scene shooting method and apparatus thereof | |
| CN110336948A (en) | A kind of method, apparatus, storage medium and electronic device that presumptive area focuses | |
| TW201541143A (en) | Auto-focus system for multiple lens and method thereof |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |