CN107392882A - A kind of method of the unzoned lens PSF iteration optimization initial values based on Corner Detection - Google Patents
A kind of method of the unzoned lens PSF iteration optimization initial values based on Corner Detection Download PDFInfo
- Publication number
- CN107392882A CN107392882A CN201710635196.5A CN201710635196A CN107392882A CN 107392882 A CN107392882 A CN 107392882A CN 201710635196 A CN201710635196 A CN 201710635196A CN 107392882 A CN107392882 A CN 107392882A
- Authority
- CN
- China
- Prior art keywords
- psf
- picture
- blurred picture
- unzoned lens
- generation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000005457 optimization Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- ZZUFCTLCJUWOSV-UHFFFAOYSA-N furosemide Chemical class C1=C(Cl)C(S(=O)(=O)N)=CC(C(O)=O)=C1NCC1=CC=CO1 ZZUFCTLCJUWOSV-UHFFFAOYSA-N 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000009738 saturating Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses the lens PSF iteration optimization initial value methods based on Corner Detection, it is related to image restoration field, including：Picture rich in detail and chessboard table images are shot with unzoned lens, obtain blurred picture and chessboard table images；Based on chessboard table images, using angular-point detection method, the picture rich in detail precisely matched and blurred picture pair；According to unzoned lens PSF priori, a series of discoid PSF of different fog-levels of generation；The picture rich in detail after matching is carried out into convolution with a series of PSF of generation respectively to obtain generating blurred picture, similarity degree after comparing generation blurred picture and matching between blurred picture, and the initial value using the PSF corresponding to most like generation blurred picture as unzoned lens PSF estimation iterative optimization procedures；Selected PSF initial values are substituted into PSF Estimation Optimization algorithms, quickly estimate PSF corresponding to unzoned lens.This method can avoid influence of the locally optimal solution of optimized algorithm to PSF precision, improve final image restoration quality.
Description
Technical field
The present invention relates to digital picture Intelligent treatment field, more particularly, to image restoration field, refers in particular to one kind and is based on angle
The method of the unzoned lens PSF iteration optimization initial values of point detection.
Background technology
At present, slr camera plays more and more important effect in daily life.It is however, single anti-to make up
The geometric distortion of eyeglass and aberration in camera lens, image quality is further improved, the design of single anti-camera lens is increasingly complicated, or even includes
The optics of dozens of independence.Complicated camera lens can also increase the volume and weight of camera lens, lead while image quality is improved
Camera lens cost is caused to greatly improve.In recent years, with the development for calculating camera work, simple camera lens combination later image restoration algorithm
It is whole to be increasingly becoming the one new research direction in camera design field and image processing field.
Simple camera lens only includes an eyeglass, is influenceed in imaging process by camera lens aberration and dispersion, by simple camera lens
The image directly shot is fuzzy, and picture quality is not high, so can not directly apply, it is necessary to be carried out suitably to image first
Restoration disposal.The key of unzoned lens image restoration is the PSF for accurately estimating unzoned lens first, is then based on what is obtained
PSF, picture rich in detail is obtained using certain Image Restoration Algorithm.
The PSF of unzoned lens is typically estimated as obtaining by blind convolved image restoration algorithm, and PSF estimations are generally empty in yardstick
Between middle progress, as shown in Fig. 2 in metric space, typically choose 3 × 3 Gaussian function or delta function as PSF's
Initial value, final preferable PSF is progressively tried to achieve by the iteration in different levels metric space successively.And at each layer
Metric space, first using the PSF tried to achieve in last layer subdimension space as initial value, tried to achieve potentially with reference to blurred picture
Picture rich in detail, then again using picture rich in detail and PSF as known terms, then obtain picture rich in detail.This process is also required to through excessive
Secondary iteration can just obtain PSF ideal in this level metric space.Because the Gauss of existing PSF initial values such as 3 × 3
Function or delta function fall far short with real unzoned lens PSF, so estimation PSF iteration optimization algorithms often need
Want iteration just to obtain optimal solution many times, it is very long to calculate the time.And in optimization process, if obtaining locally optimal solution,
Algorithm can also stop, and locally optimal solution is not final PSF, and this can influence unzoned lens PSF estimated accuracy.
A kind of quick PSF demarcation of simple lens imaging is described in Chinese Patent Application No. ZL201410064041.7 to calculate
Method, this method proposition can make a collection of same unzoned lens, then estimate the PSF of each unzoned lens respectively, and
Initial value using these PSF average value as PSF estimation iteration optimization algorithms.Although this method to a certain extent can be with
Obtain being more nearly true PSF initial value, but subject matter existing for this method is：It is simple saturating in order to estimate one
The PSF of mirror is not easy to realize in actual applications, even and same type of, it is necessary to make a collection of same unzoned lens
Unzoned lens, there is also error in manufacturing process.An it is therefore proposed that unzoned lens that is more reasonable and easily realizing
PSF iteration optimization initial values are the problem of needing to consider.
The content of the invention
The present invention is to overcome the above situation insufficient, it is intended to proposes that a kind of unzoned lens PSF iteration based on Corner Detection is excellent
Change the method for initial value.
Mainly include the following steps that：
Step 1：Picture rich in detail and chessboard table images are shown on computer screen respectively, is shot, obtained with unzoned lens
The blurred picture and chessboard table images of shooting；With unzoned lens shooting clear image with being wanted during chessboard table images in the step 1
Ensure that shooting condition is consistent；
Step 2：Chessboard table images based on shooting, using angular-point detection method, the picture rich in detail precisely matched with
Blurred picture pair；
Step 3：According to unzoned lens PSF priori, a series of discoid PSF of different fog-levels of generation；
Step 4：The picture rich in detail after matching is carried out into convolution with a series of PSF of generation respectively to obtain generating fuzzy graph
Picture, the conv2 functions in specifically used matlab softwares；Obscured after comparing the matching obtained in generation blurred picture and step 2
Similarity degree between image, blurred picture carries out phase reducing after generating blurred picture and match, as shown in formula (1),
Two image subtraction numerical results are smaller, it is believed that similarity degree is bigger；
S=∑s | I1(i,j)-I2(i,j)| (1)
Wherein, S represents the numerical result of two image subtractions, and ∑ represents sum operation, I1(i, j) represents the fuzzy of generation
Image, I2(i, j) represents the blurred picture after matching, and (i, j) represents the coordinate of pixel in image, | | represent absolute value；
And the PSF corresponding to most like generation blurred picture is estimated into iterative optimization procedure as unzoned lens PSF
Initial value；
Step 5：Selected PSF initial values are substituted into PSF Estimation Optimization algorithms, it is corresponding quickly to estimate unzoned lens
PSF.
Further, the picture rich in detail and blurred picture precisely matched in the angular-point detection method in the step 2
To process it is as follows：Fuzzy gridiron pattern is obtained for the clear chessboard table images being shown on computer screen and shooting, is used respectively
The method of Corner Detection detects the angle point of chessboard table images, then passes through the corresponding pass between this two gridiron pattern image angle points
System, picture rich in detail is mapped to the position corresponding with shooting blurred picture, accurate can be obtained by suitably cutting edge
The picture rich in detail matched somebody with somebody and blurred picture pair.
Further, unzoned lens PSF priori refers in the step 3, and preferable unzoned lens PSF is in circle
Plate-like, and there is spatial symmetry；The different fog-levels that discoid PSF is generated in the step 3 refer to PSF size
It is different.
The present invention makes full use of shooting computer screen and angular-point detection method, and the picture rich in detail precisely matched is with obscuring
Image pair, unzoned lens PSF priori is recycled, firstly generates a series of PSF, then pass through convolution operation and similarity ratio
The initial value closest to the PSF iteration optimizations the most of truth is relatively found, then can be by the beginning of the PSF in successive image calculating
Initial value is brought directly to corresponding blind convolved image restoration algorithm, is reduced while Optimized Iterative number is reduced needed for optimized algorithm
Time, but also original optimized algorithm can be avoided to obtain locally optimal solution, so as to influence the PSF degrees of accuracy.Quick and precisely estimate
Count out PSF and be advantageous to the follow-up further processing of unzoned lens imaging.
The additional aspect and advantage of the present invention will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is schematic structural view of the invention；
Fig. 2 is the iterative optimization procedure schematic diagram that PSF is estimated in metric space；
Fig. 3 is original picture rich in detail；
Fig. 4 is original chessboard table images；
Fig. 5 is shooting blurred picture；
Fig. 6 is shooting chessboard table images；
Fig. 7 (a) and (b) are the picture rich in detail and blurred picture pair precisely matched；
Fig. 8 (a) (b) (c) (d) is respectively that PSF sizes are the discoid fuzzy of 15,21,35 and 49 sizes；
Fig. 9 is that the picture rich in detail in Fig. 7 (a) carries out the blurred picture that convolution obtains respectively at four PSF in Fig. 8；
Figure 10 is the final PSF of the unzoned lens estimated；
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
A kind of method for unzoned lens PSF iteration optimization initial values based on Corner Detection that the present embodiment provides, such as Fig. 1
It is shown, comprise the following steps：
Step 1：Picture rich in detail and chessboard table images are shown on computer screen respectively, is shot, obtained with unzoned lens
The blurred picture and chessboard table images of shooting.Shooting clear image with to ensure that shooting condition is consistent during chessboard table images, including
The primary conditions such as illumination, aperture；Original picture rich in detail as shown in figure 3, original chessboard table images as shown in figure 4, shooting fuzzy graph
As shown in figure 5, shooting chessboard table images are as shown in Figure 6.
Step 2：Chessboard table images based on shooting, using angular-point detection method, the picture rich in detail precisely matched with
Blurred picture pair.Corner Detection uses existing method.The process of the picture rich in detail precisely matched and blurred picture pair
It is as follows：Fuzzy gridiron pattern is obtained for the clear chessboard table images being shown on computer screen and shooting, uses Corner Detection respectively
Method detect the angle points of chessboard table images, will be clear then by the corresponding relation between this two gridiron pattern image angle points
Clear image be mapped to the corresponding position of shooting blurred picture, by suitably cut edge can precisely be matched it is clear
Image and blurred picture pair, as shown in Figure 7；
Step 3：According to unzoned lens PSF priori, a series of discoid PSF of different fog-levels of generation.Letter
Simple lens PSF priori refers to that preferable unzoned lens PSF is in the form of annular discs, and has spatial symmetry.Generate disk
Shape PSF different fog-levels refer to that PSF size is different.
During specific implementation, it is respectively 15,21,35 and 49 that we, which select PSF size, the corresponding disk generated
Shape PSF is as shown in Figure 8.
Step 4：The picture rich in detail after matching is carried out into convolution with a series of PSF of generation respectively to obtain generating fuzzy graph
Picture, compare the similarity degree after obtained matching between blurred picture in generation blurred picture and step 2, and will be most like
Generate initial values of the PSF as unzoned lens PSF estimation iterative optimization procedures corresponding to blurred picture.Will be clear after matching
Image carries out convolution with a series of PSF of generation respectively and obtains generating the conv2 in the specifically used matlab softwares of blurred picture
Function.Compare the similarity degree in generation blurred picture and step 2 after obtained matching between blurred picture to refer to, will generate
Blurred picture with match after blurred picture carry out phase reducing, as shown in formula (1), two image subtraction numerical results are smaller,
It is believed that similarity degree is bigger.
S=∑s | I1(i,j)-I2(i,j)| (1)
Wherein, S represents the numerical result of two image subtractions, and ∑ represents sum operation, I1(i, j) represents the fuzzy of generation
Image, I2(i, j) represents the blurred picture after matching, and (i, j) represents the coordinate of pixel in image, | | represent absolute value.
During specific implementation, the generation blurred picture obtained by convolution operation is as shown in figure 9, by formula (1)
Calculating, obtained generation blurred picture blurred picture corresponding with Fig. 7 (b) is closest when PSF sizes are 21, so
Select size for 21 initial values of the discoid PSF as iteration optimization.
Step 5：Selected PSF initial values are substituted into PSF Estimation Optimization algorithms, it is corresponding quickly to estimate unzoned lens
PSF, as shown in Figure 10.During specific implementation, the PSF iteration optimization initial values selected in step 4 are brought into existing
Some is directed in the blind convolved image restoration algorithm of unzoned lens, the initial value as optimized algorithm.Iterations can be from original
100 times come drop to 20 times, you can obtain satisfied final PSF.Time needed for optimized algorithm also greatly reduces.
The method of the present invention makes full use of shooting computer screen and angular-point detection method, the picture rich in detail precisely matched
With blurred picture pair, unzoned lens PSF priori is recycled, firstly generates a series of PSF, then pass through convolution operation and phase
Compare the initial value that finds closest to the PSF iteration optimizations the most of truth like degree, then can should in successive image calculating
PSF initial values are brought directly to corresponding blind convolved image restoration algorithm, and optimization is reduced while Optimized Iterative number is reduced and is calculated
Time needed for method, but also original optimized algorithm can be avoided to obtain locally optimal solution, so as to influence the PSF degrees of accuracy.Quickly
The accurate PSF that estimates is advantageous to the follow-up further processing of unzoned lens imaging.
The above disclosed power for being only a kind of preferred embodiment of the present invention, the present invention can not being limited with this certainly
Sharp scope, therefore the equivalent variations made according to the claims in the present invention, still belong to the scope that the present invention is covered.
Claims (3)
- A kind of 1. method of the unzoned lens PSF iteration optimization initial values based on Corner Detection, it is characterised in that it is main include with Lower step：Step 1：Picture rich in detail and chessboard table images are shown on computer screen respectively, is shot, is shot with unzoned lens Blurred picture and chessboard table images；To ensure shooting condition one during with unzoned lens shooting clear image and chessboard table images Cause；Step 2：Chessboard table images based on shooting, using angular-point detection method, the picture rich in detail precisely matched is with obscuring Image pair；Step 3：According to unzoned lens PSF priori, a series of discoid PSF of different fog-levels of generation；Step 4：Picture rich in detail after matching is carried out to convolution with a series of PSF of generation respectively to obtain generating blurred picture, tool Body uses the conv2 functions in matlab softwares；Compare blurred picture after the matching obtained in generation blurred picture and step 2 Between similarity degree, will generation blurred picture and blurred picture progress phase reducing after matching, as shown in formula (1), two Image subtraction numerical result is smaller, it is believed that similarity degree is bigger；S=∑s | I1(i,j)-I2(i,j)| (1)Wherein, S represents the numerical result of two image subtractions, and ∑ represents sum operation, I1(i, j) represents the blurred picture of generation, I2(i, j) represents the blurred picture after matching, and (i, j) represents the coordinate of pixel in image, | | represent absolute value；And the PSF corresponding to most like generation blurred picture is estimated into the initial of iterative optimization procedure as unzoned lens PSF Value；Step 5：Selected PSF initial values are substituted into PSF Estimation Optimization algorithms, quickly estimated corresponding to unzoned lens PSF。
- 2. the method for the unzoned lens PSF iteration optimization initial values according to claim 1 based on Corner Detection, its feature It is, the process of the picture rich in detail precisely matched in the angular-point detection method in the step 2 and blurred picture pair is such as Under：Fuzzy gridiron pattern is obtained for the clear chessboard table images being shown on computer screen and shooting, respectively with Corner Detection Method detects the angle point of chessboard table images, will be clear then by the corresponding relation between this two gridiron pattern image angle points Image is mapped to the position corresponding with shooting blurred picture, the clear figure that can be precisely matched by suitably cutting edge Picture and blurred picture pair.
- 3. the method for the unzoned lens PSF iteration optimization initial values according to claim 1 based on Corner Detection, its feature It is, unzoned lens PSF priori refers in the step 3, and preferable unzoned lens PSF is in the form of annular discs, and has Spatial symmetry；The different fog-levels that discoid PSF is generated in the step 3 refer to that PSF size is different.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710635196.5A CN107392882A (en) | 2017-07-30 | 2017-07-30 | A kind of method of the unzoned lens PSF iteration optimization initial values based on Corner Detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710635196.5A CN107392882A (en) | 2017-07-30 | 2017-07-30 | A kind of method of the unzoned lens PSF iteration optimization initial values based on Corner Detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107392882A true CN107392882A (en) | 2017-11-24 |
Family
ID=60342159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710635196.5A Pending CN107392882A (en) | 2017-07-30 | 2017-07-30 | A kind of method of the unzoned lens PSF iteration optimization initial values based on Corner Detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107392882A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108074221A (en) * | 2017-12-19 | 2018-05-25 | 长沙全度影像科技有限公司 | A kind of parametrization unzoned lens PSF methods of estimation |
| CN109410152A (en) * | 2018-11-26 | 2019-03-01 | Oppo广东移动通信有限公司 | Imaging method and apparatus, electronic device, computer-readable storage medium |
| CN113643192A (en) * | 2020-05-11 | 2021-11-12 | 上海耕岩智能科技有限公司 | Fuzzy function processing method and device for imaging system, image acquisition equipment and storage medium |
| CN118036166A (en) * | 2024-04-15 | 2024-05-14 | 中核第四研究设计工程有限公司 | Method and device for calculating permeability coefficient, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103856723A (en) * | 2014-02-25 | 2014-06-11 | 中国人民解放军国防科学技术大学 | A Fast PSF Calibration Method for Single Lens Imaging |
| CN104794727A (en) * | 2015-05-05 | 2015-07-22 | 中国人民解放军国防科学技术大学 | Symmetry based fast calibration method of PSF (Point Spread Function) for single-lens imaging calculation |
| CN105959669A (en) * | 2016-06-06 | 2016-09-21 | 四川大学 | Remapping-based integral imaging micro-image array rapid generation method |
| US20160301922A1 (en) * | 2015-04-08 | 2016-10-13 | Algolux Inc. | Method for providing an estimation of a point spread function indicative of intrinsic camera blur |
| CN106447626A (en) * | 2016-09-07 | 2017-02-22 | 华中科技大学 | Blurred kernel dimension estimation method and system based on deep learning |
-
2017
- 2017-07-30 CN CN201710635196.5A patent/CN107392882A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103856723A (en) * | 2014-02-25 | 2014-06-11 | 中国人民解放军国防科学技术大学 | A Fast PSF Calibration Method for Single Lens Imaging |
| US20160301922A1 (en) * | 2015-04-08 | 2016-10-13 | Algolux Inc. | Method for providing an estimation of a point spread function indicative of intrinsic camera blur |
| CN104794727A (en) * | 2015-05-05 | 2015-07-22 | 中国人民解放军国防科学技术大学 | Symmetry based fast calibration method of PSF (Point Spread Function) for single-lens imaging calculation |
| CN105959669A (en) * | 2016-06-06 | 2016-09-21 | 四川大学 | Remapping-based integral imaging micro-image array rapid generation method |
| CN106447626A (en) * | 2016-09-07 | 2017-02-22 | 华中科技大学 | Blurred kernel dimension estimation method and system based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 李卫丽: "单透镜高质量计算成像技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108074221A (en) * | 2017-12-19 | 2018-05-25 | 长沙全度影像科技有限公司 | A kind of parametrization unzoned lens PSF methods of estimation |
| CN109410152A (en) * | 2018-11-26 | 2019-03-01 | Oppo广东移动通信有限公司 | Imaging method and apparatus, electronic device, computer-readable storage medium |
| CN113643192A (en) * | 2020-05-11 | 2021-11-12 | 上海耕岩智能科技有限公司 | Fuzzy function processing method and device for imaging system, image acquisition equipment and storage medium |
| CN118036166A (en) * | 2024-04-15 | 2024-05-14 | 中核第四研究设计工程有限公司 | Method and device for calculating permeability coefficient, electronic equipment and readable storage medium |
| CN118036166B (en) * | 2024-04-15 | 2024-08-09 | 中核第四研究设计工程有限公司 | Method and device for calculating permeability coefficient, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Single-image vignetting correction | |
| CN107316326B (en) | Edge-based disparity map calculation method and device applied to binocular stereo vision | |
| JP6355346B2 (en) | Image processing apparatus, image processing method, program, and storage medium | |
| CN109035170B (en) | Adaptive wide-angle image correction method and device based on single-grid image segmentation mapping | |
| US9066002B2 (en) | System and method for utilizing enhanced scene detection in a depth estimation procedure | |
| CN107392882A (en) | A kind of method of the unzoned lens PSF iteration optimization initial values based on Corner Detection | |
| CN113301320B (en) | Image information processing method and device and electronic equipment | |
| KR100996897B1 (en) | Circumferential Distortion Image Correction Method of Wide Angle Lens by Linear Fitting | |
| CN103116889A (en) | Positioning method and electronic device | |
| CN106231201B (en) | Automatic focusing method and device | |
| WO2017206444A1 (en) | Method and device for detecting imaging difference, and computer storage medium | |
| CN106251348B (en) | An adaptive multi-cue fusion background subtraction method for depth cameras | |
| CN103327245A (en) | Automatic focusing method of infrared imaging system | |
| WO2016160093A1 (en) | Depth estimation from image defocus using multiple resolution gaussian difference | |
| CN104036517A (en) | Image matting method based on gradient sampling | |
| CN101315664A (en) | Text Image Preprocessing Method for Text Recognition | |
| CN110838148A (en) | Binocular camera self-calibration method | |
| JP7312026B2 (en) | Image processing device, image processing method and program | |
| CN118799394A (en) | A cutting positioning method, system, device and medium based on machine vision | |
| CN113674303A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| US20080226159A1 (en) | Method and System For Calculating Depth Information of Object in Image | |
| US8564712B2 (en) | Blur difference estimation using multi-kernel convolution | |
| WO2022111461A1 (en) | Recognition method and apparatus, and electronic device | |
| CN113938578B (en) | Image blurring method, storage medium and terminal equipment | |
| Gao et al. | Depth error elimination for RGB-D cameras |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171124 |
|
| WD01 | Invention patent application deemed withdrawn after publication |