CN110012145A - A kind of mobile phone stabilization function evaluating method based on image blur - Google Patents
A kind of mobile phone stabilization function evaluating method based on image blur Download PDFInfo
- Publication number
- CN110012145A CN110012145A CN201910274316.2A CN201910274316A CN110012145A CN 110012145 A CN110012145 A CN 110012145A CN 201910274316 A CN201910274316 A CN 201910274316A CN 110012145 A CN110012145 A CN 110012145A
- Authority
- CN
- China
- Prior art keywords
- mobile phone
- image
- group
- network
- stabilization function
- 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.)
- Granted
Links
- 230000006641 stabilisation Effects 0.000 title claims abstract description 53
- 238000011105 stabilization Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000011156 evaluation Methods 0.000 claims abstract description 22
- BYJQAPYDPPKJGH-UHFFFAOYSA-N 3-(2-carboxyethyl)-1h-indole-2-carboxylic acid Chemical compound C1=CC=C2C(CCC(=O)O)=C(C(O)=O)NC2=C1 BYJQAPYDPPKJGH-UHFFFAOYSA-N 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 abstract description 27
- 238000013135 deep learning Methods 0.000 abstract description 5
- 238000000605 extraction Methods 0.000 abstract description 2
- 238000012876 topography Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 2
- LULAYUGMBFYYEX-UHFFFAOYSA-N 3-chlorobenzoic acid Chemical compound OC(=O)C1=CC=CC(Cl)=C1 LULAYUGMBFYYEX-UHFFFAOYSA-N 0.000 description 1
- 206010044565 Tremor Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- QENJZWZWAWWESF-UHFFFAOYSA-N tri-methylbenzoic acid Natural products CC1=CC(C)=C(C(O)=O)C=C1C QENJZWZWAWWESF-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/24—Arrangements for testing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
-
- 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
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Studio Devices (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a kind of mobile phone stabilization function evaluating method based on image blur, pass through fixed mobile phone location, shoot still image, it is then turned on shake table, one group of image is shot respectively under mobile phone stabilization function opening and closing state, then, method based on deep learning calculates image blur, feature extraction is carried out using the deblurring network of deep learning, calculate the Wasserstein distance of feature vector, the fuzzy quantity of two groups of images is obtained, image blur evaluation result is finally generated according to fuzzy quantity.In its method, entire image can all participate in fuzziness calculating, compared with the existing assessment method calculated using topography, avoid different zones influence caused by calculated result, calculating is more reasonable, result is more acurrate, meanwhile, the fuzziness being calculated is made that mobile phone stabilization function and clearly divides in detail, the objectivity for improving assessment result makes user be more readily understood and hold.
Description
Technical field
The present invention relates to a kind of appraisal procedure, in particular to it is a kind of for mobile phone stabilization function, be based on image blur
Appraisal procedure, belong to mobile phone assessment field.
Background technique
Camera function is an important component of mobile phone, and the quality of shooting quality directly affects the pin of smart phone
It sells, so manufacturer is to the pursuit of shooting quality in constantly updating and improving.Mobile phone stabilization function is to take high-quality photo
A prerequisite, for smart phone class product, effect is more prominent and obvious.
The existing evaluation rubric for mobile phone stabilization function specifically includes that
1) mobile phone is placed on a vibration table, according in stabilization testing standard " CIPA DC-X011-Translation-2014 "
The photographing request of elaboration changes mobile phone shutter speed Shutter Speed (SS), shoots multiple groups picture A i (i=1,2,3 ...), claps
The target figure for taking the photograph color lump in length and breadth and width repetition photo composition that object is black and white jump, having a size of 1000mm X 750mm；
2) mobile phone is placed on a vibration table, stabilization testing standard " CIPA DC-X011- is selected according to mobile phone quality
Translation-2014 " described in correspond to waveform, make mobile phone as shake table is vibrated according to fixed waveform together, according to anti-
It trembles photographing request described in testing standard " CIPA DC-X011-Translation-2014 ", adjusts SS to identical in 1)
Gear is shot multiple groups photo Bi (i=1,2,3 ...)；
3) formula according to described in stabilization testing standard " CIPA DC-X011-Translation-2014 " and two groups of Ai, Bi
Photo is calculated:
I. under each SS, vibration meeting bring theory dynamic fuzzy numerical value (Theoretical Motion Blur Amount,
TMBA)；
Ii. under each SS, after closing stabilization, because of the fuzzy compensation value (Bokh of Oscillation Amplitude caused by other mechanical structures of fuselage
Offset Amount, BOA)；
Iii. under each SS, theoretical jitter amplitude when no stabilization function estimates comprehensive fuzzy quantity (Estimated
Comprehensive Bokeh Amount, ECBA)；
Iv. comprehensive fuzzy quantity (the Measured Comprehensive Bokeh of actual measurement under each SS, after opening stabilization
Amount, MCBA)；
V. under each SS, with reference to dynamic fuzzy amount (Reference Motion Blur Amount, RMBA)；
Vi. it under each SS, surveys dynamic fuzzy amount (Measured Motion Blur Amount, MMBA).
4) it is that SS gear, the longitudinal axis as fuzzy quantity draw 6 SS-fuzzy quantity curve under the same coordinate system using horizontal axis, refers to
The stabilization series that dynamic fuzzy amount, actual measurement dynamic fuzzy amount are respectively measured with 63 μm of horizontal intersection point spacing, as CIPA.
The above mobile phone stabilization function evaluation methods are industry unified standard, specify the preventing mobile phone of CIPA recognised standard
Performance Level test method is trembled, different mobile phones are evaluated using same way, and evaluation result can more have with lateral comparison
Take power, but the disadvantage is that:
1) standard content stresses to evaluate the description of operating process, and it is not clear enough that the calculating section of evaluation result is defined, and exists
Ambiguity causes in actual use, and user can obtain different evaluation results with different calculations；
2) evaluation method described in standard assesses the fuzzy quantity that object is captured picture just for the mobile phone for using optical anti-vibration,
The universality of evaluation method is reduced, some smart phones using modes such as electronic flutter-proof, digital stabilizations can not then be had
Effect evaluation；
3) standard evaluation result is stabilization grade, such as 1 grade of stabilization, 3 grades of stabilizations, and excessively generally, layman can not be to this
As a result it is correctly interpreted, influences judgement of the user to mobile phone stabilization performance.
Summary of the invention
In view of above-mentioned existing situation and deficiency, the present invention is intended to provide a kind of mobile phone stabilization function based on image blur
Appraisal procedure evaluates anti-shaking process to the removal degree of motion blur by being removed and control to image blur, from
And the quantitative evaluation of the stabilization function based on deblurring algorithm is more accurately provided as a result, the mobile phone for producer's production forms one
A unified evaluation criteria.
The present invention is achieved through the following technical solutions:
A kind of mobile phone stabilization function evaluating method based on image blur, specific steps include:
Step 1, mobile phone to be tested are fixed on a vibration table, using any scene or object that have third edge pattern as subject
It is moved to the position of mobile phone camera shape library to be tested, fixed subject keeps mobile phone to be tested and subject distance
Always it fixes.
Step 2 shoots S1 group image under mobile phone stationary state to be tested?.
Step 3 selects stabilization testing standard " CIPA DC-X011-Translation- according to mobile phone quality to be tested
2014 " it corresponds to waveform described in, opens shake table, make mobile phone to be tested as shake table is vibrated according to fixed waveform together.
Step 4 shoots A1 group image under the premise of closing mobile phone stabilization to be tested setting?；It is to be tested opening
Mobile phone stabilization shoots B1 group image under the premise of being arranged?.
Step 5 builds the DeblurGAN network architecture, includes two 1/2 convolution units being spaced, 9 residual units and two
A warp product unit, each residual unit are made of a convolutional layer, example normalization layer and ReLU activation.
Step 6 is loaded into pre-training model DeblurGANWILD, DeblurGANSynth or DeblurGANComb, right
DeblurGAN network ownership weight parameter is initialized.
Step 7 is setAny image in S1 group image is represented,, useReplace DeblurGAN network
The image that middle generator network G generates inputs in discriminator network D, exports the feature vector that full articulamentum obtains。
IfAny image in A1 group image is represented,, useIt replaces raw in DeblurGAN network
The image that network G of growing up to be a useful person generates inputs in discriminator network D, exports the feature vector that full articulamentum obtainsFA a。
IfAny image in B1 group image is represented,, useIt replaces raw in DeblurGAN network
The image that network G of growing up to be a useful person generates inputs in discriminator network D, exports the feature vector that full articulamentum obtainsFB b。
Step 8, according to Wasserstein distance calculation formula, use the substitution formula of equal value of its dual form to calculate special
Levy vectorWithWasserstein distance are as follows:
Wherein, E represents mathematic expectaion.
Step 9, to each image of A1 group and B1 group respectively with S1 groupImage is opened to calculate between feature vector
Wasserstein distance, then averages, the fuzzy quantity of as every image, calculation formula are as follows:
Step 10 is averaging the fuzzy magnitude of A1 group and all images of B1 group, obtains A1 group and the respective fuzzy quantity of B1 group, public
Formula is as follows:
Step 11, according to the ratio of A1 group and B1 group fuzzy quantity, generate image blur evaluation result, comprising:
If, the stabilization function of mobile phone is defined as difference；
If, the stabilization function of mobile phone is defined as good；
If,, the stabilization function of mobile phone is defined as excellent；
If, evaluation procedure error, evaluation result is invalid.
In the step 11,n=0.1。
In the above-mentioned steps,,,。
A kind of beneficial effect of mobile phone stabilization function evaluating method based on image blur of the present invention includes:
1, it is optimized for the existing method for shooting fixed graph card to shoot any qualified scene or object, eliminates and evaluated
Dependence of the journey to graph card keeps this appraisal procedure easier to operate and implements；
2, image blur is calculated using the method based on deep learning, carries out fuzziness meter using trained neural network
It calculates, entire image can all participate in calculating, and compared with the existing assessment method calculated using topography, avoid not same district
Domain is influenced caused by calculated result, and it is more reasonable that this method fuzziness calculates, and calculated result is more acurrate；
3, the fuzziness being calculated is made that division specific in detail, compared with the conventional method, optimization to mobile phone stabilization function
The perfect meaning of evaluation result and its representative, improves the objectivity of assessment result, it is easier to understanding and grasping mobile phone stabilization
The actual effect of function improves the transparency of tested preventing mobile phone shudder performance.
Specific embodiment
A kind of mobile phone stabilization function evaluating method based on image blur of the present invention, specific steps include:
Step 1, mobile phone to be tested are fixed on a vibration table, using any scene or object that have third edge pattern as subject
It is moved to the position of mobile phone camera shape library to be tested, fixed subject keeps mobile phone to be tested and subject distance
Always it fixes.
Wherein, moving process also includes the angle and focal length for adjusting mobile phone camera to be tested, is quickly adjusted, clearly with meeting
The requirement of clear focusing.And any scene or object with third edge pattern as subject, then it does not include no edge knot
Uniformly unconverted any scene or the object such as the white wall of structure, blank sheet of paper, Hei Qiang, black paper.
Step 2 shoots S1 group image under mobile phone stationary state to be tested, wherein, in this example,。
Step 3 selects stabilization testing standard " CIPA DC-X011-Translation- according to mobile phone quality to be tested
2014 " it corresponds to waveform described in, opens shake table, make mobile phone to be tested as shake table is vibrated according to fixed waveform together.
Step 4, the vibration with shake table close mobile phone stabilization setting to be tested, shoot A1 group image,, in this example,；It is then turned on mobile phone stabilization setting to be tested, shoots B1 group image,, in this example,。
Step 5 builds the DeblurGAN network architecture, includes two 1/2 convolution units being spaced, 9 residual units and two
A warp product unit, each residual unit are made of a convolutional layer, example normalization layer and ReLU activation；
In this example, image blur is calculated using the method based on deep learning, is carried out using the deblurring network of deep learning
Feature extraction, and by taking the discriminator network D of DeblurGAN as an example, extract characteristics of image.
Step 6 is loaded into pre-training model DeblurGANWILD, DeblurGANSynth or DeblurGANComb, right
DeblurGAN network ownership weight parameter is initialized.
Step 7 is setAny image in S1 group image is represented,, useReplace DeblurGAN network
The image that middle generator network G generates inputs in discriminator network D, exports the feature vector that full articulamentum obtains。
IfAny image in A1 group image is represented,, useIt replaces raw in DeblurGAN network
The image that network G of growing up to be a useful person generates inputs in discriminator network D, exports the feature vector that full articulamentum obtainsFA a。
IfAny image in B1 group image is represented,, useIt replaces raw in DeblurGAN network
The image that network G of growing up to be a useful person generates inputs in discriminator network D, exports the feature vector that full articulamentum obtainsFB b。
Wherein,、、A respectively variable, numerical value represent S1 group, A1 group, accordingly number in B1 group it is corresponding
Image.
Step 8, according to Wasserstein distance calculation formula:
For convenience of calculating, feature vector is calculated using the substitution formula of equal value of its dual formWith's
Wasserstein distance are as follows:
Wherein, E represents mathematic expectaion.
Step 9, to each image of A1 group and B1 group respectively with S1 groupImage is opened to calculate between feature vector
Wasserstein distance, then averages, the fuzzy quantity of as every image, calculation formula are as follows:
Step 10 is averaging the fuzzy magnitude of A1 group and all images of B1 group, obtains A1 group and the respective fuzzy quantity of B1 group, public
Formula is as follows:
Step 11, according to the ratio of A1 group and B1 group fuzzy quantity:
Generate image blur evaluation result, comprising:
If 1,, illustrate that stabilization function is not acted upon, or even negative shadow is caused to the camera function of mobile phone itself
It rings, the stabilization function of mobile phone is defined as difference.
If 2,, illustrate that stabilization function works normally but anti-shake effect is general, the stabilization function definition of mobile phone
It is good.
If 3,,, illustrate that stabilization function is worked normally and worked well, the stabilization of mobile phone
Function is defined as excellent.According to experience before, in this example, the value of n is 0.1.
If 4,, evaluation procedure error, evaluation result is invalid.
The image blur appraisal report formed through the above steps can promote the accurate of existing mobile phone stabilization functional evaluation
Property and operability, it is ensured that the objectivity of assessment result.
Claims (3)
1. a kind of mobile phone stabilization function evaluating method based on image blur, which is characterized in that specific steps include:
Step 1, mobile phone to be tested are fixed on a vibration table, using any scene or object that have third edge pattern as subject
It is moved to the position of mobile phone camera shape library to be tested, fixed subject keeps mobile phone to be tested and subject distance
Always it fixes；
Step 2 shoots S1 group image under mobile phone stationary state to be tested?；
Step 3 selects in stabilization testing standard " CIPA DC-X011-Translation-2014 " according to mobile phone quality to be tested
The correspondence waveform of elaboration opens shake table, makes mobile phone to be tested as shake table is vibrated according to fixed waveform together；
Step 4 shoots A1 group image under the premise of closing mobile phone stabilization to be tested setting?；
B1 group image is shot under the premise of opening mobile phone stabilization to be tested setting?；
Step 5 builds the DeblurGAN network architecture, anti-comprising two 1/2 convolution units being spaced, 9 residual units and two
Convolution unit, each residual unit are made of a convolutional layer, example normalization layer and ReLU activation；
Step 6 is loaded into pre-training model DeblurGANWILD, DeblurGANSynth or DeblurGANComb, right
DeblurGAN network ownership weight parameter is initialized；
Step 7 is setAny image in S1 group image is represented,, useIt replaces raw in DeblurGAN network
The image that network G of growing up to be a useful person generates inputs in discriminator network D, exports the feature vector that full articulamentum obtains；
IfAny image in A1 group image is represented,, useReplace generator in DeblurGAN network
The image that network G generates inputs in discriminator network D, exports the feature vector that full articulamentum obtainsFA a；
IfAny image in B1 group image is represented,, useReplace generator in DeblurGAN network
The image that network G generates inputs in discriminator network D, exports the feature vector that full articulamentum obtainsFB b；
Step 8, according to Wasserstein distance calculation formula, using the substitution formula of equal value of its dual form calculate feature to
AmountWithWasserstein distance are as follows:
Wherein, E represents mathematic expectaion；
Step 9, to each image of A1 group and B1 group respectively with S1 groupImage is opened to calculate between feature vector
Wasserstein distance, then averages, the fuzzy quantity of as every image, calculation formula are as follows:
Step 10 is averaging the fuzzy magnitude of A1 group and all images of B1 group, obtains A1 group and the respective fuzzy quantity of B1 group, public
Formula is as follows:
Step 11, according to the ratio of A1 group and B1 group fuzzy quantity, generate image blur evaluation result, comprising:
If, the stabilization function of mobile phone is defined as difference；
If, the stabilization function of mobile phone is defined as good；
If,, the stabilization function of mobile phone is defined as excellent；
If, evaluation procedure error, evaluation result is invalid.
2. a kind of mobile phone stabilization function evaluating method based on image blur according to claim 1, which is characterized in that
In the step 11n=0.1。
3. a kind of mobile phone stabilization function evaluating method based on image blur according to claim 1, which is characterized in that
It is described；It is described；It is described。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910274316.2A CN110012145B (en) | 2019-04-08 | 2019-04-08 | Mobile phone anti-shake function evaluation method based on image fuzziness |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910274316.2A CN110012145B (en) | 2019-04-08 | 2019-04-08 | Mobile phone anti-shake function evaluation method based on image fuzziness |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110012145A true CN110012145A (en) | 2019-07-12 |
| CN110012145B CN110012145B (en) | 2021-01-05 |
Family
ID=67170121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910274316.2A Active CN110012145B (en) | 2019-04-08 | 2019-04-08 | Mobile phone anti-shake function evaluation method based on image fuzziness |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110012145B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538263A (en) * | 2021-06-28 | 2021-10-22 | 江苏威尔曼科技有限公司 | Motion blur removing method, medium, and device based on improved DeblurgAN model |
| CN113676667A (en) * | 2021-08-23 | 2021-11-19 | Oppo广东移动通信有限公司 | Suppression ratio testing method, suppression ratio testing device, electronic equipment and storage medium |
| CN116896626A (en) * | 2023-09-11 | 2023-10-17 | 荣耀终端有限公司 | Method and device for detecting video motion blur degree |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110122296A1 (en) * | 2009-11-20 | 2011-05-26 | Hon Hai Precision Industry Co., Ltd. | System and method for deblurring motion blurred images |
| CN105872370A (en) * | 2016-03-31 | 2016-08-17 | 深圳中兴力维技术有限公司 | Video jitter removing method and device |
| CN106341688A (en) * | 2016-10-21 | 2017-01-18 | 北京小米移动软件有限公司 | Test method and equipment for anti-shake performance of camera |
| CN108416752A (en) * | 2018-03-12 | 2018-08-17 | 中山大学 | A method of image is carried out based on production confrontation network and removes motion blur |
| CN108550118A (en) * | 2018-03-22 | 2018-09-18 | 深圳大学 | Fuzzy processing method, device, equipment and the storage medium of motion blur image |
-
2019
- 2019-04-08 CN CN201910274316.2A patent/CN110012145B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110122296A1 (en) * | 2009-11-20 | 2011-05-26 | Hon Hai Precision Industry Co., Ltd. | System and method for deblurring motion blurred images |
| CN105872370A (en) * | 2016-03-31 | 2016-08-17 | 深圳中兴力维技术有限公司 | Video jitter removing method and device |
| CN106341688A (en) * | 2016-10-21 | 2017-01-18 | 北京小米移动软件有限公司 | Test method and equipment for anti-shake performance of camera |
| CN108416752A (en) * | 2018-03-12 | 2018-08-17 | 中山大学 | A method of image is carried out based on production confrontation network and removes motion blur |
| CN108550118A (en) * | 2018-03-22 | 2018-09-18 | 深圳大学 | Fuzzy processing method, device, equipment and the storage medium of motion blur image |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538263A (en) * | 2021-06-28 | 2021-10-22 | 江苏威尔曼科技有限公司 | Motion blur removing method, medium, and device based on improved DeblurgAN model |
| CN113676667A (en) * | 2021-08-23 | 2021-11-19 | Oppo广东移动通信有限公司 | Suppression ratio testing method, suppression ratio testing device, electronic equipment and storage medium |
| CN113676667B (en) * | 2021-08-23 | 2023-08-18 | Oppo广东移动通信有限公司 | Inhibition ratio test method, device, electronic equipment and storage medium |
| CN116896626A (en) * | 2023-09-11 | 2023-10-17 | 荣耀终端有限公司 | Method and device for detecting video motion blur degree |
| CN116896626B (en) * | 2023-09-11 | 2024-04-19 | 荣耀终端有限公司 | Method and device for detecting video motion blur degree |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110012145B (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110012145A (en) | A kind of mobile phone stabilization function evaluating method based on image blur | |
| CN103973989B (en) | Obtain the method and system of high-dynamics image | |
| CN101316368B (en) | Full view stabilizing method based on global characteristic point iteration | |
| CN105651203B (en) | A kind of high dynamic range 3 D measuring method of adaptive striped brightness | |
| CN110033461B (en) | Mobile phone anti-shake function evaluation method based on target displacement estimation | |
| CN107633536A (en) | A kind of camera calibration method and system based on two-dimensional planar template | |
| CN107025670A (en) | A kind of telecentricity camera calibration method | |
| CN102422124A (en) | Imaging device, imaging means and program | |
| US20210150251A1 (en) | Method and apparatus for calculating a luminance value of a region of interest | |
| CN104270560A (en) | Multi-point focusing method and device | |
| CN108090896B (en) | Wood board flatness detection and machine learning method and device and electronic equipment | |
| US7706676B2 (en) | Automatic exposure control method | |
| CN102572275B (en) | Imaging device, image processing device, image processing method and image processing software | |
| CN104320575A (en) | Image processing method and image processing apparatus for portable terminal | |
| CN110493522A (en) | Anti-fluttering method and device, electronic equipment, computer readable storage medium | |
| CN110261069B (en) | Detection method for optical lens | |
| CN109660736A (en) | Method for correcting flat field and device, image authentication method and device | |
| CN104994376B (en) | Method and system for automatically simulating projection colors of projector | |
| CN111325803B (en) | Calibration method for evaluating internal and external participation time synchronization of binocular camera | |
| CN109035345A (en) | The TOF camera range correction method returned based on Gaussian process | |
| CN105100546A (en) | Movement estimation method and device | |
| CN110197479A (en) | A kind of modified quality determining method in surface | |
| CN106657803A (en) | Automatic exposure method for high-speed camera applied to electro-optic theodolite | |
| CN110022393A (en) | A kind of method of self-adaptive estimation mobile phone stabilization function | |
| CN108885098A (en) | Apart from measuring device and apart from measuring method |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190712 Assignee: Zhongguancun Technology Leasing Co.,Ltd. Assignor: BEIJING E-CREDENCE INFORMATION TECHNOLOGY Co.,Ltd. Contract record no.: X2022980003097 Denomination of invention: An evaluation method of mobile phone anti shake function based on image ambiguity Granted publication date: 20210105 License type: Exclusive License Record date: 20220323 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An evaluation method of mobile phone anti shake function based on image ambiguity Effective date of registration: 20220324 Granted publication date: 20210105 Pledgee: Zhongguancun Technology Leasing Co.,Ltd. Pledgor: BEIJING E-CREDENCE INFORMATION TECHNOLOGY Co.,Ltd. Registration number: Y2022980003183 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| EC01 | Cancellation of recordation of patent licensing contract |
Assignee: Zhongguancun Technology Leasing Co.,Ltd. Assignor: BEIJING E-CREDENCE INFORMATION TECHNOLOGY Co.,Ltd. Contract record no.: X2022980003097 Date of cancellation: 20240329 |
|
| EC01 | Cancellation of recordation of patent licensing contract | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Granted publication date: 20210105 Pledgee: Zhongguancun Technology Leasing Co.,Ltd. Pledgor: BEIJING E-CREDENCE INFORMATION TECHNOLOGY Co.,Ltd. Registration number: Y2022980003183 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right |