CN107194897B - A kind of precedence algorithm and image repair method based on architectural difference Yu marginal texture coefficient to be repaired - Google Patents
A kind of precedence algorithm and image repair method based on architectural difference Yu marginal texture coefficient to be repaired Download PDFInfo
- Publication number
- CN107194897B CN107194897B CN201710438763.8A CN201710438763A CN107194897B CN 107194897 B CN107194897 B CN 107194897B CN 201710438763 A CN201710438763 A CN 201710438763A CN 107194897 B CN107194897 B CN 107194897B
- Authority
- CN
- China
- Prior art keywords
- repaired
- area
- point
- image
- boundary
- 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.)
- Expired - Fee Related
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 40
- 230000008439 repair process Effects 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 22
- 239000000284 extract Substances 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000010354 integration Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 6
- 230000007547 defect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000012152 algorithmic method Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005457 optimization 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
- G06T5/77—Retouching; Inpainting; Scratch removal
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of precedence algorithm and image repair method based on architectural difference Yu marginal texture coefficient to be repaired, algorithm steps include: to read damaged image, and mark area to be repaired;Extract all known pixels point information in target area;According to the known pixels of extraction point information architecture architectural difference matrix;The window area centered on point p to be repaired any on the boundary of area to be repaired that a certain size is extracted in target area, calculates marginal texture coefficient T (p), the standard deviation criteria S of complex point p to be repairedp(p) and confidence level parameter C (p);According to formula P (p)=T (p) C (p) Sp(p) the priority valve P (p) of this complex point to be repaired is calculated;All complex points to be repaired on the boundary of area to be repaired are traversed, repair the window area centered on the maximum complex point to be repaired of priority valve, and update area to be repaired boundary;It repeats the above steps, until area to be repaired is repaired completely.The present invention obtains stable priority valve according to the difference size of each target area, greatly reduces the calculating time of priority.
Description
Technical field
The present invention relates to technical field of image processing, in particular relate to one kind based on architectural difference and marginal texture to be repaired
The precedence algorithm and image repair method of coefficient.
Background technique
Image repair is an ancient art, originating from European the Renaissance, is often referred to restore to lose in image
Either damaged pixel or region.People are very sensitive to discontinuous boundary, and lost regions generally comprise structure, texture
With it is smooth, structure is coherent closer to true visual effect, therefore researcher separates this three layers, and restoring structure sheaf is wherein
Important part.The selection of reparation sequence is very big to the influence for repairing result, and the general block with structural type is should be by
It repairs first.Criminisi utilizes the isophote direction of local boundary and the fill order of unit normal direction definition block,
After the sample block preferentially filled, best matching blocks are found in known region in the way of global search, and by best
Match block fills sample block to be repaired.
There are also certain methods using choosing image block centered on the boundary point of area to be repaired, then with selected block and neighborhood block
Difference size calculate similarity weight, with all known neighborhood blocks similarity weight construct structure degree of rarefication, use structure
Degree of rarefication calculates fill order.Repairing block building is to improve reparation using the rarefaction representation of multiple match blocks as filling information
The quality of image.In addition, also similar block can be calculated in the known region of image, and block compensation is calculated, most of image has
Similar compensation, the peak value for compensating distribution are related to main compensation.According to main compensation, input picture, which forms, much displacement
Version image.These have the image of displacement to merge by the global MRF energy function of optimization.These methods are produced to image is repaired
Good visual effect and connectivity are given birth to, particularly, the defect area being repaired has uniform texture and a small number of structures.
For the image repair problem that object removes, some scholars propose the image combined based on sample block and depth
Algorithm is repaired, the sequence of the repaired object of purpose image and the multi-angle of view figure of object are found with the depth map of image, then goes to fill out
Perforations adding hole.In order to reduce the size of database, the method that main perspective extracts (Keyview Extraction) is proposed, and use
A kind of algorithm progress object retrieval with flash ranging degree of geometry.There are also exemplary method is based on, priority feature is improved,
The priority that linear structure is considered in pri function, and makes algorithm linear structure earlier, with solve completion sequence and
Linear structure propagation problem.In addition, having used structure tensor and image in priority to detect most effective structure
The combination of gradient.
Although above-mentioned algorithm can realize image repair function to a certain extent, algorithm exists and some can not overcome
The problem of, such as fill order is not sufficiently stable, matching criterior is not reasonable, is taken a long time.
Summary of the invention
It is a kind of using between small image block the invention aims to provide in view of deficiency existing for prior art
The precedence algorithm of difference size discrimination complex point region to be repaired.
To achieve the goals above, technical solution of the present invention is as follows:
A kind of precedence algorithm based on architectural difference Yu marginal texture coefficient to be repaired, which is characterized in that its step packet
It includes:
S1 reads damaged image, and marks area to be repaired;
S2 is extracted comprising including the boundary of area to be repaired, and the target area that size is certain, and extracts institute in target area
There is known pixels point information;
S3 is according to the known pixels point information architecture architectural difference matrix of extraction;
S4 extracts a certain size the window centered on point p to be repaired any on the boundary of area to be repaired in target area
Mouth region domain calculates the marginal texture coefficient T (p) of complex point p to be repaired;
S5 calculates standard deviation criteria S of the complex point p to be repaired in the window area centered on itp(p) and confidence level is joined
Number C (p);
It is to be repaired that S6 according to marginal texture coefficient, complex point standard deviation criteria to be repaired and pixel confidence parameter to be repaired calculates this
The priority valve P (p) of point, calculation formula are P (p)=T (p) C (p) Sp(p);
S7 repeats step S5-S6, until all complex points to be repaired on traversal area to be repaired boundary, obtain corresponding priority
Set;
S8 repairs window area centered on the maximum complex point to be repaired of priority valve, and update area to be repaired boundary and
Architectural difference matrix;
S9 repeats step S4-S8, until area to be repaired is repaired completely.
It is another object of the present invention to provide a kind of image repair method based on above-mentioned precedence algorithm, feature exists
In including the following steps:
Step 1 reads restored image to be repaired, and determines area to be repaired boundary point;
Step 2 calculates each corresponding priority valve of complex point to be repaired in area to be repaired boundary;
Step 3 searches the maximum complex point to be repaired of priority valve, and repairs the target area figure centered on this complex point to be repaired
As block;
Step 4 refreshes architectural difference matrix, judges whether that there are also the regions that do not repair, if so, thening follow the steps 2- step
Rapid 3, until image repair is complete.
Compared with prior art, beneficial effects of the present invention:
The present invention obtains stable priority according to the position characteristics of the difference size discrimination complex point to be repaired of each target area
Value;The difference between target area is deposited in a manner of standard deviation in architectural difference matrix simultaneously, due to adjacent complex point to be repaired
Neighborhood exist and be significantly overlapped, information in reusable architectural difference matrix calculates priority, to substantially reduce
Calculating time of priority.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is precedence algorithm flow chart of the present invention;
Fig. 2 a is image texture example region figure;
Fig. 2 b is picture structure example region figure;
Fig. 3 is image repair method flow chart of the present invention;
Fig. 4 is the present invention and comparison algorithm repairing effect comparison diagram.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
The present invention devises a kind of difference size discrimination complex point region to be repaired using between small image block
Precedence algorithm and image repair method, with reference to the accompanying drawing and specific embodiment further illustrates technical side of the invention
Case:
As shown in Figure 1, the step of precedence algorithm based on architectural difference and marginal texture coefficient to be repaired, includes:
S1 reads damaged image, and marks area to be repaired.
S2 is extracted comprising including the boundary of area to be repaired, and the target area that size is certain, and extracts institute in target area
There is known pixels point information.
S3 includes: according to the known pixels point information architecture architectural difference matrix of extraction, step
Breakage image is accordingly divided into three layers on tri- Color Channels of R, B, G by S31, extract respectively in target area it is each
Know the pixel value of pixel.
Continuity in the present invention for guarantee restoring area and known region in structure, it is necessary to ensure that calculated preferential
Power is maximum in structural region numerical value, smaller in texture region numerical value, is also minimum in smooth region numerical value.In view of structural region
There are boundary, the characteristics of color difference is larger, smooth region color is almost without difference, can be distinguished very well using standard deviation
Structural region and smooth region.But there may be biggish differences for texture region color, so simple use standard deviation carries out
Calculating can not distinguish texture region and structural region.Although and texture region color difference is larger, is evenly distributed using it
The characteristics of it can also be distinguished with structural region.
S32 calculates separately each layer pixel value standard deviation S in target aream(i, j), calculation formula are as follows:
Wherein, Pm(i, j) is m layers of target area image, the i-th row, and jth column point pixel value, n is in target area image
The number of known pixels point, as the preferred embodiments of the invention, it is the pixel period of m layers of corresponding position that n, which takes 9, E (i, j),
It hopes, it may be assumed that
Each layer pixel value standard deviation of S33 integration objective area image, is calculated architectural difference matrix and corresponds to each pixel
The value S (i, j) of position, calculation formula are as follows:
It is possible to be 0 due to smooth region standard deviation, 1 is integrally added in formula, it is poor that obtained value is stored in structure
The corresponding position of different matrix.Structural region and the corresponding matrix numerical value of texture region are larger in image, and smooth region is close to 1.
Relatively, edge point value can be bigger than surrounding point for similar texture region numerical value, but not necessarily than not surrounding
The value of other texture regions is big.The value of texture region and borderline region can not be distinguished well, so if simple uses square
The corresponding value of battle array is obviously unreasonable as priority.It has clearly a need for being further processed.As the preferable embodiment of the present invention, with
Lesser image block is unit around complex point to be repaired, constructs priority condition structural coefficient.
S4 extracts a certain size the window centered on point p to be repaired any on the boundary of area to be repaired in target area
Mouth region domain calculates the marginal texture coefficient T (p) of complex point p to be repaired, and calculation formula is as follows:
Wherein, NsIt (p) is window area, | Ns(p) | for known element number in window area, Vp,kIt is the neighbour of complex point to be repaired
Domain point normalization as a result, is defined as:
Wherein Z (p) is normaliztion constant, is defined as:
In order to guarantee that structural region priority valve is maximum, point in the rectangular window centered on complex point to be repaired is selected in a matrix
Corresponding all values being not zero, definition calculate the condition of priority.
Difference in view of structural region and texture region is to contain boundary in structural region, and the corresponding value in boundary compares surrounding values
Big, in order to protrude this feature, and it is successive to allow the region for causing standard deviation different because of texture difference to be in similar reparation
Position, the present invention, which uses, is normalized point corresponding value in architectural difference matrix around point to be repaired, then squared
The mode differential expression of sum.It can be very good specification configuration region and texture region in this way.
The value of quadratic sum can in quadratic sum the biggish value of element number reduce and increase, and structural region compared to
The difference of texture region is that only fewer parts is the biggish fringe region of value, can ground differentiation texture region and structural area with this
Domain.Although different texture regional value differs greatly, the value difference in identical texture region is different smaller, thus to target point around
Point is normalized, all texture regions can be made be in similar preferential position and lower than the preferential position of structural region.
With the increase of summation element number, numerical value can become smaller, and influence the stability of priority value.It therefore need to be multiplied by ginseng
It is balanced with the summation number of element.So providing the structural coefficient T (p) of complex point p to be repaired.
As the preferable embodiment of the present invention, as unit of image block lesser around complex point to be repaired, priority is constructed
Structural coefficient.It is texture region or structural region that the value, which can distinguish band and repair block, but but cannot if it is structural region
The center for ensuring multiblock to be repaired is the junction section of pattern.Because when image block is in the same area and wherein containing identical
When the junction section of length, obtained value can be close.Such as Fig. 2 a and Fig. 2 b is compared, it is small both for one around complex point to be repaired
Region, it is clear that Fig. 2 a belongs to texture region, and Fig. 2 b has apparent structure feature, and first repairs pattern junction section in figure b,
It can obtain better repairing effect.Therefore the difference of the one lesser known region in multiblock center to be repaired is added in priority
Closer to the point at boundary center in value (because when repairing image, central point is located at breakage image edge) proximate region Lai Fang great.
S5 calculates standard deviation criteria S of the complex point p to be repaired in the window area centered on itp(p) and confidence level is joined
Number C (p), in which:
Standard deviation criteria Sp(p) calculation formula are as follows:
Confidence level parameter C (p) is the ratio of known pixels point number and whole pixel numbers in window area.
It is to be repaired that S6 according to marginal texture coefficient, complex point standard deviation criteria to be repaired and pixel confidence parameter to be repaired calculates this
The priority valve P (p) of point, calculation formula are P (p)=T (p) C (p) Sp(p);
S7 repeats step S5-S6, until all complex points to be repaired on traversal area to be repaired boundary, obtain corresponding priority
Set.
S8 repairs window area centered on the maximum complex point to be repaired of priority valve, and update area to be repaired boundary and
Architectural difference matrix.
S9 repeats step S4-S8, until area to be repaired is repaired completely.
The present invention also provides a kind of image repair methods based on above-mentioned precedence algorithm, according to provincial characteristics building weight
The architectural difference matrix used again calculates priority, that is, ensure that the continuity of picture structure part, while also reducing image
Operand in repair process.As shown in figure 3, its step includes:
Step 1 reads restored image to be repaired, and determines area to be repaired boundary point;
Step 2 calculates each corresponding priority valve of complex point to be repaired in area to be repaired boundary;
Step 3 searches the maximum complex point to be repaired of priority valve, and repairs the target area figure centered on this complex point to be repaired
As block;
Step 4 refreshes architectural difference matrix, judges whether that there are also the regions that do not repair, if so, thening follow the steps 2- step
Rapid 3, until image repair is complete.
It is further that progress is done to precedence algorithm of the present invention and image mending method combined with specific embodiments below
Explanation.This algorithm is based on Windows7 system, Visual.Studio2013+OpenCV v2.4 as experiment porch.Embodiment
In the Criminisi algorithm in the prior art for not considering structural coefficient algorithm as a comparison is respectively adopted, and invent the calculation
Method is compared, as shown in figure 4, repairing the comparing result of image for two methods, (a) column indicate the original of not breakage in figure
Image, (b) column indicate the damaged image repaired, and (c) column indicate the effect repaired using comparison algorithm, (d)
Column indicate the effect repaired using this algorithm.
As can be seen from Figure, at piece image forehead, comparison algorithm is there are obvious shortcoming, and inventive algorithm
Preferably picture can be restored;Have the defects that at bridge opening for the second width image comparison algorithmic method more serious, is
Because of the unstability of reparation sequence, caused by the junction section without first repairing bridge opening bottom and side, and the algorithm of this paper
Preferably overcome this problem.For third width picture comparison algorithmic method there are apparent defect on the wing of aircraft,
This is because the sequence of priority is not reasonable, cause caused by reusing single match block, this algorithm is by using area
Domain characteristic preferably constructs the sequencing of priority, therefore does not occur problems, the 4th width figure and above situation class
Seemingly.
For the more objective using effect for embodying two kinds of algorithms, using Y-PSNR PSNR (Peak Singe To
Noise Ratio) (unit decibel) come measure repair after image and original image difference, the value of Y-PSNR is bigger, table
Show that the image after repairing and original undamaged image difference are smaller, the effect of reparation is better.The application algorithm and comparison algorithm
Y-PSNR it is as shown in table 1:
1 this patent algorithm of table is compared with comparing arithmetic result
By table 1 it is found that inventive algorithm performance relatively comparison algorithm increases, this is because the region using picture is special
Property come construct priority determine repair sequencing, optimize matching criterior and increase stability.And then structure is kept well
Partial continuity and it is not likely to produce error hiding phenomenon.
The invention discloses a kind of precedence algorithms based on image edge area feature construction to be repaired.The algorithm is first
Architectural difference matrix is constructed according to the provincial characteristics on area to be repaired boundary, constructs edge to be repaired further according to architectural difference matrix
Structural coefficient determines fill order finally according to the marginal texture coefficient priority resolution to be repaired of building.Gained priority is steady
It is fixed reliable, and a large amount of operation time can be saved based on the calculating of the priority of architectural difference matrix, replicability is strong.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (4)
1. a kind of precedence algorithm based on architectural difference Yu marginal texture coefficient to be repaired, which is characterized in that its step includes:
S1 reads damaged image, and marks area to be repaired;
S2 is extracted comprising including the boundary of area to be repaired, and the target area that size is certain, and extract in target area it is all
Know pixel information;
S3 includes: according to the known pixels point information architecture architectural difference matrix of extraction
Breakage image is accordingly divided into three layers on tri- Color Channels of R, B, G by S31, extracts each known picture in target area respectively
The pixel value of vegetarian refreshments;
S32 calculates separately each layer pixel value standard deviation S in target aream(i, j), calculation formula are as follows:
Wherein, Pm(i, j) is m layers of target area image, the i-th row, and jth column point pixel value, n is known in target area image
The number of pixel, Em(i, j) is the pixel expectation of m layers of corresponding position, it may be assumed that
Each layer pixel value standard deviation of S33 integration objective area image is calculated architectural difference matrix and corresponds to each pixel position
Value S (i, j), calculation formula is as follows:
S4 calculates the marginal texture coefficient T (p) of area to be repaired boundary complex point p to be repaired, including calculates according to the following formula to be repaired
Multiple edges of regions structural coefficient T (p):
Wherein, NsIt (p) is window area, | Ns(p) | for known element number in window area, Vp,kIt is neighborhood of a point point to be repaired
Normalization as a result, is defined as:
Wherein Z (p) is normaliztion constant, is defined as:
S5 calculates standard deviation criteria S of the complex point p to be repaired in the window area centered on itp(p) and confidence level parameter C
(p);
S6 calculates this complex point to be repaired according to marginal texture coefficient, complex point standard deviation criteria to be repaired and pixel confidence parameter to be repaired
Priority valve P (p), calculation formula are P (p)=T (p) C (p) Sp(p);
S7 repeats step S5-S6, until all complex points to be repaired on traversal area to be repaired boundary, obtain corresponding priority collection
It closes;
S8 repairs the window area centered on the maximum complex point to be repaired of priority valve, and updates area to be repaired boundary and structure
Difference matrix;
S9 repeats step S4-S8, until area to be repaired is repaired completely.
2. the precedence algorithm according to claim 1 based on architectural difference Yu marginal texture coefficient to be repaired, feature
It is, the step S5 Plays difference parameter Sp(p) calculation formula are as follows:
3. the precedence algorithm according to claim 1 based on architectural difference Yu marginal texture coefficient to be repaired, feature
It is, confidence level parameter C (p) is the ratio of known pixels point number and whole pixel numbers in window area in the step S5
Value.
4. a kind of image repair method based on precedence algorithm described in claim 1, which is characterized in that its step includes:
Step 1 reads restored image to be repaired, and determines area to be repaired boundary point;
Step 2 calculates each corresponding priority valve of complex point to be repaired in area to be repaired boundary;
Step 3 searches the maximum complex point to be repaired of priority valve, and repairs the target area image centered on this complex point to be repaired
Block;
Step 4 refreshes architectural difference matrix, judges whether that there are also the regions that do not repair, if so, 2- step 3 is thened follow the steps,
Until image repair is complete.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710438763.8A CN107194897B (en) | 2017-06-12 | 2017-06-12 | A kind of precedence algorithm and image repair method based on architectural difference Yu marginal texture coefficient to be repaired |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710438763.8A CN107194897B (en) | 2017-06-12 | 2017-06-12 | A kind of precedence algorithm and image repair method based on architectural difference Yu marginal texture coefficient to be repaired |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107194897A CN107194897A (en) | 2017-09-22 |
CN107194897B true CN107194897B (en) | 2019-07-23 |
Family
ID=59876451
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710438763.8A Expired - Fee Related CN107194897B (en) | 2017-06-12 | 2017-06-12 | A kind of precedence algorithm and image repair method based on architectural difference Yu marginal texture coefficient to be repaired |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107194897B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111915507B (en) * | 2020-06-19 | 2023-10-17 | 西安理工大学 | Repairing method for wall painting falling off |
CN112330643B (en) * | 2020-11-10 | 2023-02-07 | 国网湖北省电力有限公司宜昌供电公司 | Secondary equipment state identification method based on sparse representation image restoration |
CN116153476B (en) * | 2023-01-04 | 2024-01-26 | 英德市优越义齿技术有限公司 | Digital false tooth intelligent processing system and method based on medical internet of things |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20050028741A (en) * | 2003-09-19 | 2005-03-23 | 한국전자통신연구원 | Apparatus and method for yielding wavelets coefficient |
CN101504764A (en) * | 2009-01-19 | 2009-08-12 | 西安交通大学 | Ancient architecture oil-decorative painting virtual repairing system and method |
CN106023089A (en) * | 2016-01-19 | 2016-10-12 | 河南理工大学 | Image restoration method based on block matching |
CN106504203A (en) * | 2016-09-29 | 2017-03-15 | 河南理工大学 | A kind of Block- matching image repair method of application screening strategy |
CN106530247A (en) * | 2016-11-04 | 2017-03-22 | 天津大学 | Multi-scale image restoring algorithm based on structure information |
-
2017
- 2017-06-12 CN CN201710438763.8A patent/CN107194897B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20050028741A (en) * | 2003-09-19 | 2005-03-23 | 한국전자통신연구원 | Apparatus and method for yielding wavelets coefficient |
CN101504764A (en) * | 2009-01-19 | 2009-08-12 | 西安交通大学 | Ancient architecture oil-decorative painting virtual repairing system and method |
CN106023089A (en) * | 2016-01-19 | 2016-10-12 | 河南理工大学 | Image restoration method based on block matching |
CN106504203A (en) * | 2016-09-29 | 2017-03-15 | 河南理工大学 | A kind of Block- matching image repair method of application screening strategy |
CN106530247A (en) * | 2016-11-04 | 2017-03-22 | 天津大学 | Multi-scale image restoring algorithm based on structure information |
Non-Patent Citations (1)
Title |
---|
基于几何距离的Criminisi图像修复算法;王新年 等;《计算机工程与设计》;20150731;第36卷(第7期);第1835-1839页 |
Also Published As
Publication number | Publication date |
---|---|
CN107194897A (en) | 2017-09-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107194897B (en) | A kind of precedence algorithm and image repair method based on architectural difference Yu marginal texture coefficient to be repaired | |
Lafarge et al. | Creating large-scale city models from 3D-point clouds: a robust approach with hybrid representation | |
Mei et al. | 3D tree modeling from incomplete point clouds via optimization and L 1-MST | |
CN103310421B (en) | The quick stereo matching process right for high-definition image and disparity map acquisition methods | |
CN100458846C (en) | A method of image restoration | |
CN103544711B (en) | The autoegistration method of remote sensing image | |
US20110310101A1 (en) | Pillar grid conversion | |
CN109493320A (en) | Method for extracting remote sensing image road and system, storage medium, electronic equipment based on deep learning | |
CN105069843A (en) | Rapid extraction method for dense point cloud oriented toward city three-dimensional modeling | |
CN103646396A (en) | Matching cost algorithm of binocular stereo matching algorithm, and non-local stereo matching algorithm | |
CN108629809B (en) | Accurate and efficient stereo matching method | |
CN109271928A (en) | A kind of road network automatic update method based on the fusion of vector road network with the verifying of high score remote sensing image | |
TW201022708A (en) | Method of change detection for building models | |
CN109859114A (en) | Three-dimensional point cloud restorative procedure based on local flatness and non-local similitude | |
CN105139379A (en) | Airborne Lidar point cloud building top surface gradual extraction method based on classifying and laying | |
KR20120005654A (en) | Method of establishing information of cloud data and establishing system of information of cloud data | |
Borovec et al. | Registration of multiple stained histological sections | |
CN103544695A (en) | Efficient medical image segmentation method based on game framework | |
CN103440672A (en) | Flowering plant flower image division extracting method | |
CN105913378A (en) | Layered task dependence-based remote sensing image parallel splicing method | |
CN106339985B (en) | A method of selection is inlayed line and is inlayed to aviation image from vector house data | |
CN103020964B (en) | A kind of based on the figure in the self adaptation watershed binocular solid matching process cut | |
Sun et al. | Building outline extraction from aerial imagery and digital surface model with a frame field learning framework | |
CN111046884A (en) | Slope geological disaster extraction method of multi-feature auxiliary watershed algorithm | |
CN103258344A (en) | Method for automatically extracting texture in plant three-dimensional reconstruction |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190723 Termination date: 20200612 |