CN109714519B - Method and system for automatically adjusting image frame - Google Patents
Method and system for automatically adjusting image frame Download PDFInfo
- Publication number
- CN109714519B CN109714519B CN201711004954.XA CN201711004954A CN109714519B CN 109714519 B CN109714519 B CN 109714519B CN 201711004954 A CN201711004954 A CN 201711004954A CN 109714519 B CN109714519 B CN 109714519B
- Authority
- CN
- China
- Prior art keywords
- image
- definition
- camera
- picture
- amplitude
- 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
Abstract
The invention discloses a method and a system for automatically adjusting an image frame. In order to solve the problem of unclear focusing caused by unobvious definition of the image definition of a projected image in the prior art, the technical scheme provided by the invention establishes a classifier for learning the image definition from the clearest level to the most blurred level, so as to identify the clear image, and then identifies the gradual camera to adjust the focal length according to the definition of the image, so as to complete automatic focusing adjustment, thereby obtaining a clearer and efficient automatic focusing effect. The technical scheme of the invention has the advantages of strong automation, high calculation algorithm efficiency, capability of completing automatic high-definition focusing of the projection equipment in a short time, shortening preparation time for using the projection equipment, and retaining more details of a focused image, so that the projected image can obtain better definition integrally, and a user can obtain better using effect.
Description
Technical Field
The invention relates to the field of projection control, in particular to a method and a system for automatically adjusting an image frame.
Background
With the development of projection technology, projection devices are becoming more popular in the office and home fields, wherein the focus definition of a projection image is an important factor determining user experience. Existing projection focus adjustments mainly include two types: manual adjustment and automatic adjustment. The traditional manual focusing adjustment not only consumes time and labor, but also has poor adjustment effect and definition and fineness. In the conventional projector automatic focusing, a camera is used for continuously shooting a current picture, then a definition value of the current picture is calculated by using a definition method and is transmitted back to the camera, the camera continuously performs front and back adjustment on an internal motor by comparing the definition values of the front picture and the back picture, and the motor drives an optical machine to shoot pictures with different focal lengths. Finally, when the contrast between the front and the back of the shot picture is highest, the motor parameter is fixed, the camera adjustment is stopped, and the focusing function is completed.
The projection automatic focusing method in the prior art has a certain effect, however, the definition value of a projected image is not defined obviously by the existing definition calculation method, certain cross fluctuation can occur in the continuous back-and-forth calculation of a motor, which causes a certain error to occur in the automatic focusing of a projector, so that the image after the automatic focusing is finished has the defects of insufficient definition and fineness of the image or insufficient definition of part of a display area.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides an automatic image picture adjusting method and system, aiming at solving the problem of unclear focusing caused by unobvious definition of the picture definition of a projected image in the prior art, a classifier for learning the picture definition from clearest to most fuzzy in several levels is established to achieve the purpose of identifying the clear image, then the focus of a camera is adjusted according to the definition identification of the picture of the image, and the automatic focusing adjustment is completed, so that a clearer and more efficient automatic focusing effect is obtained.
The invention adopts the following technical scheme:
a method for automatically adjusting image frames comprises the following steps:
step 1, collecting a plurality of images with different definitions under different focal lengths in different scenes respectively so as to collect a plurality of types of image data;
step 2, performing definition judgment on a plurality of collected images with different definitions, and indexing each image according to the judged definition;
step 3, training a neural network model based on the indexed image data and the corresponding label information, and storing model parameters after the neural network training is finished;
step 4, photographing the current projection picture, transmitting the image picture at the moment into the trained convolutional neural network, and obtaining the definition category of the picture at the moment through calculation;
step 5, adjusting camera motor parameters respectively according to the definition judgment result of the picture to automatically adjust the focal distance of the camera;
and 6, when the image picture is judged to be the clearest type, stopping the adjustment of the camera, and freezing the camera focal length and the picture at the moment to finish automatic focusing.
The definition of the image comprises four orders of clearest, sub-clearness, sub-blur and most-blur, and corresponds to four types of label information; the indexing of each image includes labeling each image with a label corresponding to a sharpness level of the image.
Wherein, the adopted neural network is a Convolutional Neural Network (CNN).
If the definition of the current image belongs to the most fuzzy category, adjusting the motor parameter of the camera to carry out coarse adjustment on the focal length of the camera according to a first amplitude; if the current image lake surface definition belongs to 'secondary blurring', adjusting the camera motor parameter to carry out coarse adjustment on the camera focal length according to a second amplitude; and if the definition of the current image frame belongs to 'sub-definition', adjusting the motor parameter in the camera to finely adjust the focal length of the camera according to a third amplitude.
The magnitude relation of the first amplitude, the second amplitude and the third amplitude is that the first amplitude is larger than the second amplitude and larger than the third amplitude.
A system for automatically adjusting image frames comprises a model training module and an image adjusting module, wherein,
the model training module is used for establishing a training model of image definition based on the acquisition and processing of training data, and comprises the following processing units:
the data acquisition unit is used for acquiring a plurality of images with different definitions under different focal lengths in different scenes so as to acquire a plurality of types of data;
the data indexing unit is used for judging the definition of a plurality of images with different definitions and indexing each image according to the judged definition;
the network training unit is used for training a neural network model based on the indexed image data and the corresponding label information, and storing model parameters after the convolutional neural network training is finished;
the automatic adjustment module is used for automatically adjusting the current projection image picture based on the trained neural network model so as to obtain the best clear picture, and comprises the following processing units:
a definition judging unit for taking a picture of the current projection picture by using a projection camera, transmitting the picture of the current picture into the trained convolutional neural network, obtaining the definition category of the current picture by calculation,
the focal length adjusting unit is used for respectively adjusting the motor parameters of the camera according to the definition judgment result of the picture to adjust the focal length of the camera;
and the freeze processing unit is used for stopping the adjustment of the camera when the image picture is judged to be the clearest type, freezing the camera focal length and the picture at the moment and finishing automatic focusing.
The definition of the image comprises four orders of clearest, sub-clearness, sub-blur and most-blur, and corresponds to four types of label information; the indexing of each image includes labeling each image with a label corresponding to a sharpness level of the image.
The neural network used is a Convolutional Neural Network (CNN).
If the definition of the current image belongs to the most fuzzy category, adjusting the motor parameter of the camera to carry out coarse adjustment on the focal length of the camera according to a first amplitude; if the current image lake surface definition belongs to 'secondary blurring', adjusting the camera motor parameter to carry out coarse adjustment on the camera focal length according to a second amplitude; and if the definition of the current image frame belongs to 'sub-definition', adjusting the motor parameter in the camera to finely adjust the focal length of the camera according to a third amplitude.
The magnitude relation of the first amplitude, the second amplitude and the third amplitude is that the first amplitude is larger than the second amplitude and larger than the third amplitude.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. the automatic adjustment method and the automatic adjustment system provided by the invention can adjust the motor parameters of the projection image in one dimension according to the image definition magnitude, have strong automation, and avoid the situations that the projection image picture cannot reach the optimal definition after loss and calculation data fluctuation caused by repeated back and forth adjustment of the motor.
2. The automatic adjustment method and the automatic adjustment system provided by the invention have the advantages of high innovation, avoidance of excessive repeated comparison calculation, high calculation algorithm efficiency, capability of completing automatic high-definition focusing of the projection equipment in a short time and shortening of the preparation time for using the projection equipment.
3. The automatic adjustment method and the automatic adjustment system provided by the invention can keep more details of the focusing image, so that the whole projection image can obtain better definition, and a user can obtain better experience effect.
Drawings
Fig. 1 is a method for automatically adjusting an image frame according to an embodiment of the present invention.
Fig. 2 is a system for automatically adjusting an image frame according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the following description of the technical solutions of the present invention with reference to the accompanying drawings of the present invention is made clearly and completely, and other similar embodiments obtained by a person of ordinary skill in the art without any creative effort based on the embodiments in the present application shall fall within the protection scope of the present application.
The embodiment 1 of the invention provides a method for automatically adjusting images, which is used for projection equipment such as a miniature projector and the like and comprises a model training stage and an automatic adjusting stage. The specific process steps of the adjustment method of the present embodiment are described in detail below with reference to fig. 1.
In the model training stage, a training model for establishing the image definition based on the acquisition and processing of training data is required, and the method comprises the following steps:
step 1, manually acquiring data: under the condition of being observable by naked eyes, a plurality of images with different definitions under different focal lengths are collected under different scenes respectively, so that a plurality of types of image data are collected. The image acquisition equipment can be equipment with a camera, such as a camera or a projector, a mobile phone, a computer and the like, and the camera or the camera can be focused manually or automatically to obtain image data under different focal lengths;
and 2, judging the definition of the collected images with different definitions, and indexing each image according to the judged definition.
The definition of each image may be determined by manual reading and visual determination, or may be determined by calculation, such as calculating a feature value or an evaluation function of the image, as long as the definition category corresponding to each image can be obtained. After the images are indexed according to definition, all the indexed images are divided into a plurality of image groups.
The definition of the image comprises four orders of clearest, second clearness, second blur and clearest and corresponds to four types of label information, each type of definition category under each scene comprises a plurality of pieces of data, and the number of the data is good for enabling a model training result and a definition judgment result to be accurate. In one embodiment the number of images per type of sharpness is 20-30 per scene.
The indexing of each image includes labeling each image with a label corresponding to a sharpness level of the image.
And 3, training a neural network model based on the four types of indexed image data and the corresponding label information, and storing model parameters after the neural network training is finished.
The neural network adopted in the example is a Convolutional Neural Network (CNN), which is a classical model in Deep Learning (DL), and is a multilayer perceptron designed for identifying two-dimensional images, the network structure has high invariance to the translation, scaling, inclination and other transformations of images, and the working principle is to obtain the intrinsic two-dimensional feature representation of data through a series of local Convolution and pooling alternating operations, and to access the features to a classification layer through full connection processing for classification and identification of targets.
In the automatic adjustment stage, the current picture is continuously acquired in the process, and the trained neural network model is used for judging the category to which the definition effect of the picture belongs, so that the camera motor is adjusted to move back and forth, the optical machine is driven to change the focal length, and the focusing of the camera is completed.
And 4, photographing the current projection picture, transmitting the image picture at the moment into the trained convolutional neural network, and obtaining the definition category of the picture at the moment through calculation.
When the projector is used, light projected by the projector forms a projection area on the projection surface, and an image included in the projection area is a projection image picture. Since the projector needs to perform auto-focusing on a projection image, a camera of the projector needs to capture a current projection image and use the captured image as input data for projection adjustment.
And 5, respectively adjusting the camera motor parameters according to the definition judgment result of the picture to automatically adjust the focal distance of the camera. The concrete embodiment is as follows: if the definition of the current image belongs to the most fuzzy category, adjusting the motor parameter of the camera to carry out coarse adjustment on the focal length of the camera according to a first amplitude; if the current image lake surface definition belongs to 'secondary blurring', adjusting the camera motor parameter to carry out coarse adjustment on the camera focal length according to a second amplitude; and if the definition of the current image frame belongs to 'sub-definition', adjusting the motor parameter in the camera to finely adjust the focal length of the camera according to a third amplitude.
The relationship among the first amplitude, the second amplitude and the third amplitude is that the first amplitude is larger than the second amplitude and larger than the third amplitude, the first amplitude and the second amplitude need to enable the motor to carry out coarse adjustment in a larger range, the third amplitude enables the motor to carry out fine adjustment in a small range, specific parameter values or ranges of the first amplitude, the second amplitude and the third amplitude are selected, and technicians can carry out reasonable setting according to projection parameters of a specific projector and an optical path of the motor.
And 6, when the image picture is judged to be the clearest type, stopping the adjustment of the camera, and freezing the camera focal length and the picture at the moment to finish automatic focusing.
The automatic adjustment method in the steps can automatically adjust the motor parameters on one dimension according to the image definition magnitude, and avoids the situations that the loss caused by repeated adjustment of the motor and the projection image picture cannot reach the optimal definition after calculating data fluctuation.
Fig. 2 is a block diagram of embodiment 2, which provides a system for automatically adjusting an image, and the system includes a model training module and an image adjusting module.
The model training module is used for establishing a training model of image definition based on the acquisition and processing of training data, and comprises the following processing units:
the data acquisition unit is used for acquiring a plurality of images with different definitions under different focal lengths in different scenes so as to acquire a plurality of types of data;
the data indexing unit is used for judging the definition of a plurality of images with different definitions and indexing each image according to the judged definition;
the judged definition comprises four orders of clearest, second fuzzy and most fuzzy and corresponds to four types of label information, and each type of definition category in each scene contains N pieces of data;
the indexing of the images includes labeling each image with a label corresponding to a sharpness level of the image.
And the network training unit is used for training a Convolutional Neural Network (CNN) model based on the four types of indexed image data and corresponding label information, and storing model parameters after the training of the CNN is finished.
The automatic adjustment module is used for automatically adjusting the current projection image picture based on the trained neural network model so as to obtain the best clear picture, and comprises the following processing units:
and the definition judging unit is used for photographing the current projection picture by using the projection camera, transmitting the image picture at the moment into the trained convolutional neural network, and obtaining the definition category of the picture at the moment through calculation.
The focal length adjusting unit is used for respectively adjusting the motor parameters of the camera according to the definition judgment result of the picture to adjust the focal length of the camera, and the focal length adjusting unit is specifically embodied as follows: if the definition of the current image belongs to the most fuzzy category, adjusting the motor parameter of the camera to carry out coarse adjustment on the focal length of the camera according to a first amplitude; if the current image lake surface definition belongs to 'secondary blurring', adjusting the camera motor parameter to carry out coarse adjustment on the camera focal length according to a second amplitude; and if the definition of the current image frame belongs to 'sub-definition', adjusting the motor parameter in the camera to finely adjust the focal length of the camera according to a third amplitude.
And the freeze processing unit is used for stopping the adjustment of the camera when the image picture is judged to be in the clearest category, freezing the camera focal length and the picture at the moment and finishing automatic focusing.
Any feature disclosed in this specification (including any accompanying claims, abstract) may be replaced by alternative features serving equivalent or similar purposes, unless expressly stated otherwise. That is, unless expressly stated otherwise, each feature is only an example of a generic series of equivalent or similar features.
The invention is not limited to the foregoing embodiments. The invention extends to any novel feature or any novel combination of features disclosed in this specification and any novel method or process steps or any novel combination of features disclosed.
Claims (10)
1. A method for automatically adjusting image frames comprises the following steps:
step 1, collecting a plurality of images with different definitions under different focal lengths in different scenes respectively so as to collect a plurality of types of image data;
step 2, performing definition judgment on a plurality of collected images with different definitions, and indexing each image according to the judged definition;
step 3, training a neural network model based on the indexed image data and the corresponding label information, and storing model parameters after the neural network training is finished;
step 4, photographing the current projection picture, transmitting the image picture at the moment into the trained convolutional neural network, and obtaining the definition category of the picture at the moment through calculation;
step 5, adjusting camera motor parameters according to the definition categories of the pictures respectively to automatically adjust the focal distance of the camera;
and 6, when the image picture is judged to be the clearest type, stopping the adjustment of the camera, and freezing the camera focal length and the picture at the moment to finish automatic focusing.
2. The method for automatically adjusting image frames according to claim 1, wherein the definition of the image comprises four orders of magnitude of clearest, sub-clearness, sub-blur and blurriest, and corresponds to four types of label information;
the indexing of each image includes labeling each image with a label corresponding to a sharpness level of the image.
3. The method of automatically adjusting picture frames according to claim 1, wherein the neural network employed is a convolutional neural network.
4. The method of automatically adjusting an image frame as set forth in claim 1, wherein if the sharpness of the current image frame belongs to the "blurriest" category, the camera motor parameters are adjusted to coarsely adjust the camera focal length by a first margin; if the current image lake surface definition belongs to 'secondary blurring', adjusting the camera motor parameter to carry out coarse adjustment on the camera focal length according to a second amplitude; and if the definition of the current image frame belongs to 'sub-definition', adjusting the motor parameter in the camera to finely adjust the focal length of the camera according to a third amplitude.
5. The method as claimed in claim 4, wherein the first amplitude, the second amplitude, and the third amplitude are related to a first amplitude > a second amplitude > a third amplitude.
6. A system for automatically adjusting image frames comprises a model training module and an image adjusting module, wherein,
the model training module is used for establishing a training model of image definition based on the acquisition and processing of training data, and comprises the following processing units:
the data acquisition unit is used for acquiring a plurality of images with different definitions under different focal lengths in different scenes so as to acquire a plurality of types of data;
the data indexing unit is used for judging the definition of a plurality of images with different definitions and indexing each image according to the judged definition;
the network training unit is used for training a neural network model based on the indexed image data and the corresponding label information, and storing model parameters after the convolutional neural network training is finished;
the automatic adjustment module is used for automatically adjusting the current projection image picture based on the trained neural network model so as to obtain the best clear picture, and comprises the following processing units:
a definition judging unit for taking a picture of the current projection picture by using a projection camera, transmitting the picture of the current picture into the trained convolutional neural network, obtaining the definition category of the current picture by calculation,
the focal length adjusting unit is used for respectively adjusting the motor parameters of the camera according to the definition category of the picture to adjust the focal length of the camera;
and the freeze processing unit is used for stopping the adjustment of the camera when the image picture is judged to be the clearest type, freezing the camera focal length and the picture at the moment and finishing automatic focusing.
7. The system for automatically adjusting picture of image as claimed in claim 6, wherein the sharpness of said image comprises four orders of magnitude of clearest, sub-clearness, sub-blur and blurriest, and corresponds to four types of label information;
the indexing of each image includes labeling each image with a label corresponding to a sharpness level of the image.
8. The system for automatically adjusting picture of image as claimed in claim 6, wherein the neural network used is a Convolutional Neural Network (CNN).
9. The system for automatically adjusting an image frame as recited in claim 6, wherein if the sharpness of the current image frame belongs to the "blurriest" category, the camera motor parameters are adjusted to coarsely adjust the camera focal length by a first amount; if the current image lake surface definition belongs to 'secondary blurring', adjusting the camera motor parameter to carry out coarse adjustment on the camera focal length according to a second amplitude; and if the definition of the current image frame belongs to 'sub-definition', adjusting the motor parameter in the camera to finely adjust the focal length of the camera according to a third amplitude.
10. The system of claim 9, wherein the first amplitude, the second amplitude, and the third amplitude are related to a magnitude of the first amplitude > the second amplitude > the third amplitude.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711004954.XA CN109714519B (en) | 2017-10-25 | 2017-10-25 | Method and system for automatically adjusting image frame |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711004954.XA CN109714519B (en) | 2017-10-25 | 2017-10-25 | Method and system for automatically adjusting image frame |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109714519A CN109714519A (en) | 2019-05-03 |
| CN109714519B true CN109714519B (en) | 2021-02-02 |
Family
ID=66251912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711004954.XA Active CN109714519B (en) | 2017-10-25 | 2017-10-25 | Method and system for automatically adjusting image frame |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109714519B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428375B (en) * | 2019-07-24 | 2024-03-01 | 东软医疗系统股份有限公司 | DR image processing method and device |
| CN110736747B (en) * | 2019-09-03 | 2022-08-19 | 深思考人工智能机器人科技（北京）有限公司 | Method and system for positioning under cell liquid-based smear mirror |
| CN113497925A (en) * | 2020-04-02 | 2021-10-12 | 深圳光峰科技股份有限公司 | Projection focusing method and projection focusing device |
| CN111601031B (en) * | 2020-04-02 | 2022-02-01 | 维沃移动通信有限公司 | Shooting parameter adjusting method and device |
| CN113709353B (en) * | 2020-05-20 | 2023-03-24 | 杭州海康威视数字技术股份有限公司 | Image acquisition method and device |
| CN111629147B (en) * | 2020-06-04 | 2021-07-13 | 中国科学院长春光学精密机械与物理研究所 | Automatic focusing method and system based on convolutional neural network |
| CN111885297B (en) * | 2020-06-16 | 2022-09-06 | 北京迈格威科技有限公司 | Image definition determining method, image focusing method and device |
| CN112135048B (en) * | 2020-09-23 | 2022-02-15 | 创新奇智(西安)科技有限公司 | Automatic focusing method and device for target object |
| CN112954315B (en) * | 2021-02-25 | 2022-06-14 | 深圳市中西视通科技有限公司 | Image focusing measurement method and system for security camera |
| CN114757994B (en) * | 2022-06-14 | 2022-09-20 | 深圳深知未来智能有限公司 | Automatic focusing method and system based on deep learning multitask |
| CN114760419B (en) * | 2022-06-15 | 2022-09-20 | 深圳深知未来智能有限公司 | Automatic focusing method and system based on deep learning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1696665A2 (en) * | 2003-09-26 | 2006-08-30 | Seiko Epson Corporation | Image processing system, projector information storage medium, and image processing method |
| CN104052951A (en) * | 2013-03-13 | 2014-09-17 | 株式会社理光 | Projector, method of controlling projector |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102967991A (en) * | 2012-11-08 | 2013-03-13 | 广东欧珀移动通信有限公司 | Method, device, system and mobile terminal for adjusting projector focal length |
| CN104184977A (en) * | 2013-05-27 | 2014-12-03 | 联想(北京)有限公司 | Projection method and electronic equipment |
| JP6529879B2 (en) * | 2015-09-29 | 2019-06-12 | オリンパス株式会社 | Image pickup apparatus and control method of image pickup apparatus |
| CN106291869A (en) * | 2016-09-27 | 2017-01-04 | 青岛海信宽带多媒体技术有限公司 | The control method of a kind of projector start auto-focusing and device |
| CN106488122A (en) * | 2016-10-14 | 2017-03-08 | 北京信息科技大学 | A kind of dynamic auto focusing algorithm based on improved sobel method |
| CN106899838A (en) * | 2017-03-01 | 2017-06-27 | 成都市极米科技有限公司 | A kind of focusing method and system |
| CN106920224B (en) * | 2017-03-06 | 2019-11-05 | 长沙全度影像科技有限公司 | A method of assessment stitching image clarity |
| CN107133948B (en) * | 2017-05-09 | 2020-05-08 | 电子科技大学 | Image blurring and noise evaluation method based on multitask convolution neural network |
| CN106993174B (en) * | 2017-05-24 | 2019-04-05 | 青岛海信宽带多媒体技术有限公司 | A kind of projection device electromotive focusing method and device |
-
2017
- 2017-10-25 CN CN201711004954.XA patent/CN109714519B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1696665A2 (en) * | 2003-09-26 | 2006-08-30 | Seiko Epson Corporation | Image processing system, projector information storage medium, and image processing method |
| CN104052951A (en) * | 2013-03-13 | 2014-09-17 | 株式会社理光 | Projector, method of controlling projector |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109714519A (en) | 2019-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109714519B (en) | Method and system for automatically adjusting image frame | |
| CN101309367B (en) | Imaging apparatus | |
| WO2021052487A1 (en) | Method and apparatus for obtaining extended depth of field image, and electronic device | |
| CN109413336A (en) | Image pickup method, device, electronic equipment and computer readable storage medium | |
| CN107835372A (en) | Imaging method, device, mobile terminal and storage medium based on dual camera | |
| CN104102068B (en) | Atomatic focusing method and automatic focusing mechanism | |
| CN108076278A (en) | A kind of Atomatic focusing method, device and electronic equipment | |
| CN105245786A (en) | Self-timer method based on intelligent light measurement, self-timer system and photographing terminal | |
| EP3005286B1 (en) | Image refocusing | |
| CN106231201B (en) | Automatic focusing method and device | |
| CN110210333A (en) | A kind of focusing iris image acquiring method and device automatically | |
| Wang et al. | Intelligent autofocus | |
| CN111062961A (en) | Contact lens edge defect detection method based on deep learning | |
| CN106125246A (en) | A kind of from the method seeking laser focal plane | |
| CN108024058A (en) | Image virtualization processing method, device, mobile terminal and storage medium | |
| CN108093170B (en) | User photographing method, device and equipment | |
| CN111199536B (en) | Focusing evaluation method and device | |
| CN112449115B (en) | Shooting method and device and electronic equipment | |
| Kim et al. | Video depth-from-defocus | |
| CN109598195B (en) | Method and device for processing clear face image based on monitoring video | |
| CN116347056A (en) | Image focusing method, device, computer equipment and storage medium | |
| CN112585945A (en) | Focusing method, device and equipment | |
| CN105893578A (en) | Method and device for selecting photos | |
| JP2003195151A (en) | Autofocus device | |
| CN110896469A (en) | Resolution testing method for three-shot photography and application 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 610000 Tianfu Software Park Area A, 1129 Century City Road, Chengdu High-tech Zone, Sichuan Province Applicant after: Chengdu Jimi Technology Co., Ltd. Address before: 610000 No. 501, 5th floor, 7th building, Tianfu Software Park Area A, 1129 Century City Road, Chengdu High-tech Zone, Sichuan Province Applicant before: CHENGDU XGIMI TECHNOLOGY CO., LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |