CN108171771A - The line drawing in a kind of combination external margin information and interior polymeric road draws generating algorithm - Google Patents
The line drawing in a kind of combination external margin information and interior polymeric road draws generating algorithm Download PDFInfo
- Publication number
- CN108171771A CN108171771A CN201711418454.0A CN201711418454A CN108171771A CN 108171771 A CN108171771 A CN 108171771A CN 201711418454 A CN201711418454 A CN 201711418454A CN 108171771 A CN108171771 A CN 108171771A
- Authority
- CN
- China
- Prior art keywords
- road
- line drawing
- image
- edge
- external margin
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 19
- 238000010422 painting Methods 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 230000004927 fusion Effects 0.000 claims abstract description 7
- 230000001629 suppression Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000205 computational method Methods 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims description 2
- 238000013461 design Methods 0.000 abstract description 4
- 238000000605 extraction Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007591 painting process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to the line drawings in a kind of combination external margin information and interior polymeric road to draw generating algorithm, and technical characteristics are:For the mural painting image I of input, carry out gray processing and handle to obtain the gray level image I after denoising0;To I0Edge extracting is carried out, obtains a road external margin figure I1;Using High frequency filter to I0It is promoted to obtain a road interior details figure I2;Comprehensive I1And I2Information carry out the fusion of road, generate a complete road I3;Road repairing based on Threshold segmentation and information superposition, obtains the line drawing figure I of integrality enhancing4;Using Portace methods to I4Vectorized process is carried out, obtains smooth consistent result line drawing figure.Colored mural painting image procossing can be generated the line drawing polar plot that can retain mural painting main structure and artistic style, can accurately describe edge feature, while processing speed is quickly by reasonable design of the present invention.
Description
Technical field
The invention belongs to technical field of image processing, especially a kind of combination external margin information and interior polymeric road
Line drawing draws generating algorithm.
Background technology
Mural painting is one of cultural heritage of China's preciousness, and the line drawing for playing bottom in Dunhuang frescoes is drawn, and is both that Chinese tradition is painted
A kind of distinctive painting mode is drawn, and is a kind of special mural painting salvo, there is important researching value.Traditional line drawing
Drafting relies primarily on manual operations.Due to the particularity of mural painting, painter can only rely on local light to be drawn;With multimedia
The popularization of technology can be taken pictures or recorded to grottoes mural painting, and painter against digital mural painting again than carrying out line drawing drawing.According to
The process for carrying out line drawing drafting by hand is sufficiently complex and very time-consuming, compared with the speed of threat sprawling that mural painting faces,
Achieve the purpose that protect mural painting very small with this, and utilize computer and image processing techniques, line drawing generation is carried out to mural painting
Process will not both damage historical relic, it may have the characteristics of conventional methods such as efficient, reusable do not have, it is therefore necessary to needle
Line drawing figure Generation Technology is carried out to digitlization mural painting.
Carry out the key technology edge extracting of line drawing figure to digitlization mural painting, typical arithmetic operators there are Canny calculations
Method etc., but when these operators are directly applied to the extraction of line drawing picture, response can be generated to road both sides, so as to same pen occur
Road corresponds to the situation at 2 edges.Global marginal probability detective operators (Glabalized Probability of a
Boundary, gPb) there is higher accuracy rate, and one edge only generated compared with Xi Bi roads for some, but its width
It is also poor for single pixel, continuity, if without skeletal extraction processing, although the result of gPb operators can embody a road
Width, but can not the intensive road of extraction comparison.
By patent retrieval, domestic patent of invention related with mural painting image procossing at present is concentrated mainly on mural painting image
Digital repair, mural painting Image Acquisition and mural painting Classification and Identification etc., more than patent do not relate to the line of colored mural painting image
Tracing extraction or generating process can not generate accurate line drawing figure to mural painting.
Invention content
It is an object of the invention to overcome the deficiencies in the prior art, propose that a kind of reasonable design, speed are fast and can retain wall
The main structure of picture and the line drawing in the combination external margin information of artistic style and interior polymeric road draw generating algorithm.
The present invention solves its technical problem and following technical scheme is taken to realize:
The line drawing in a kind of combination external margin information and interior polymeric road draws generating algorithm, includes the following steps:
Step 1, the mural painting image I for input remove noise using Gaussian filter and carry out gray processing and handle to obtain
Gray level image I after denoising0;
Step 2, to gray level image I0Edge extracting is carried out, obtains a road external margin figure I1;
Step 3, using High frequency filter to gray level image I0It is promoted to obtain a road interior details figure I2;
Step 4, comprehensive road external margin figure I1With a road interior details figure I2Information carry out the fusion of road, generation one
Complete road I of item3;
Step 5, the road repairing based on Threshold segmentation and information superposition, obtain the line drawing figure I of integrality enhancing4;
Step 6, using Portace methods to line drawing figure I4Vectorized process is carried out, obtains smooth consistent result line drawing
Figure.
Further, the concrete processing procedure of the step 2 is as follows:
(1) the Grad of each pixel is calculated using Sobel operators to obtain gray level image I0Gradient magnitude, ladder
The computational methods for spending amplitude G are as follows:
Wherein GxAnd GyThe gradient of pixel (x, y) both horizontally and vertically is represented respectively;
(2) the horizontal gradient G of arctan function compared pixels point is utilizedxWith vertical gradient GySize obtain edge direction
D, calculation formula are as follows:
D [x, y]=arctan (Gx/Gy)
(3) non-maxima suppression is carried out to gradient magnitude:It, will be terraced using the direction finding pixel local maximum of gradient
Gray value in degree amplitude G corresponding to non-maximum point is set to 0, so as to weed out the point of most non-edge, obtains non-pole
Big value inhibits image G1;
(4) to non-maxima suppression image G1Two threshold values th1 and th2 are acted on, Grad is less than to the pixel of threshold value th1
Gray value be set as 0, obtain edge image N1, the gray value of pixel of the Grad less than threshold value th2 is then set as 0, is obtained
Edge image N2, with edge image N2Based on, by edge link into profile, when the endpoint for reaching profile, end-on 8 is adjacent
The point for meeting Low threshold is found in the point of domain, new edge is collected further according to this point, until whole image edge closure, is consequently formed
Road external margin figure I1。
Further, the relationship between the threshold value th1 and th2 is:Th1=0.4th2.
Further, the concrete processing procedure of the step 3 is:
(1) the increment of gray-scale map is calculated using following formula, as a result with Δ I0It represents:
(2) high boost is carried out, is calculated as follows to obtain a road interior details figure I2:
I2(x, y)=min (255, I0(x,y)+ΔI0(x,y))。
Further, the step 4 carries out a road fusion using equation below:
Wherein, (x ', y ') is some pixel in 8 neighborhoods of (x, y).
Further, the specific processing method of the step 5 is:
(1) using Otsu methods to filter result I2Into row threshold division, the larger pixel of gray value, Threshold segmentation are rejected
As a result it is denoted as I '2;
(2) I is superimposed using equation below3With I '2, I is drawn to generate complete line drawing4:
I4(x, y)=I3(x,y)&I2′(x,y)。
The advantages and positive effects of the present invention are:
Significant marginal point is attached by reasonable design of the present invention using heuristic routing algorithm, completes mural painting figure
Road external margin detection, road internal information extraction and the repairing optimization function of picture, energy is generated by colored mural painting image procossing
Retain the line drawing polar plot of mural painting main structure and artistic style, can accurately describe edge feature, so as to generate clean, company
Continuous single pixel side, meets archaeology drawing requirements;Entire processing procedure is without further contour connection process simultaneously, when consume
Aspect also has advantage, therefore processing speed is quickly.
Description of the drawings
Fig. 1 is the process chart of the present invention;
Fig. 2 is respectively to walk intermediate result displaying figure in processing procedure of the present invention;
Fig. 3 is the effect displaying figure of different mural painting styles;
Fig. 4 is the handling result schematic diagram of the present invention;
Fig. 5 be Canny algorithms, gPb algorithms be directed to mural painting image comparative result figure.
Specific embodiment
The embodiment of the present invention is further described below in conjunction with attached drawing.
The present invention proposes a kind of combination external margin information and the line drawing in interior polymeric road draws generating algorithm, including pre-
Processing, edge detection, high boost filtering, Threshold segmentation, information fusion and vector quantization and etc..First to artwork mural painting image
Gaussian filtering and gray proces are carried out, reject unnecessary detailed information, recycle the external margin in Canny operator extractions road
Then figure carries out High frequency filter and is promoted to extract a road internal information, next merges the two information, and utilize threshold value
Divide and obtain smooth consistent abstract lines figure with measures such as details compensation, finally result is optimized using vector.
The line drawing of the present invention draws generating algorithm, as shown in Figure 1, including the following steps:
Step 1, the mural painting image I for input remove noise using gaussian filtering, then carry out gray processing processing, obtain
Gray level image I after to denoising0。
In the present embodiment, Gaussian filter is set as 1 using the Gaussian kernel of one 5 × 5, parameter σ.
Step 2, to gray level image I0Edge extracting is carried out, the external margin figure in mural painting road is obtained, as a result remembers I1.Specifically
Processing procedure is as follows:
(1) Grad of each pixel is calculated using Sobel operators to obtain I0Gradient magnitude, the calculating side of G
Method is as follows:
Wherein GxAnd GyThe gradient of pixel (x, y) both horizontally and vertically is represented respectively.In order to obtain faster
Computational efficiency, Grad can use G [x, y]=| Gx|+|Gy| to replace, thus form gradient amplitude figure G.
(2) edge orientation map D is calculated, utilizes the horizontal gradient G of arctan function compared pixels pointxWith vertical gradient Gy's
Size obtains.So that the deflection D [x, y] of G [x, y] acquirement local maximas has just reacted the direction at edge.
D [x, y]=arctan (Gx/Gy)
(3) non-maxima suppression is carried out to gradient magnitude.
Using the direction finding pixel local maximum of gradient, the gray value corresponding to maximum point non-in G is set to
0, the point of most non-edge can be weeded out in this way.Image after non-maxima suppression is denoted as G1。
(4) to non-maxima suppression image G1Effect two threshold value th1 and th2, both sides relation th1=0.4th2.Ladder
The gray value of pixel of the angle value less than th1 is set as 0, obtains edge image N1.Then the gray scale of pixel of the Grad less than th2
Value is set as 0, obtains edge image N2.Due to image N2Threshold value it is higher, remove most of noise, but also have lost simultaneously useful
Marginal information.And image N1Threshold value it is relatively low, more information is remained, with image N2Based on, edge link into wheel
Exterior feature, when the endpoint for reaching profile, which can find the point for meeting Low threshold in end-on 8 neighborhood point, further according to this point
New edge is collected, until whole image edge closure, binary edge figure I is consequently formed1。
Step 3 is promoted to obtain a road interior details figure I using High frequency filter2。
The road edge obtained in step 2 is single pixel width, and a complete road can respond into two sides, inside road
Details lacks.For this purpose, this step is based on Gaussian Blur to I0Carry out High frequency filter promotion, handling result I2It represents.Specific processing
Process is as follows:
(1) increment of gray-scale map is calculated using following formula, as a result with Δ I0It represents, that is, has
(2) high boost is carried out.As a result I is used2It represents, that is, has
I2(x, y)=min (255, I0(x,y)+ΔI0(x,y))
Step 4, road fusion.Comprehensive road edge graph I1With inside road figure I2Information, generate a complete road
I3, formula is as follows:
Wherein, (x ', y ') is some pixel in (x, y) 8 neighborhood.
Step 5, road repairing.
Road interior details figure I2After being filtered through high boost, the gray value of image background pixels is generally larger than a road picture
Element, the larger pixel of gray value have it is larger be likely located at background, so, this step using Otsu methods to filter result I2It carries out
Threshold segmentation rejects the larger pixel of gray value.Threshold segmentation result is denoted as I '2。
I1Zhong Bi roads continuity is preferable, and eliminates gray value and the close pixel in road in background, however simultaneously
It eliminates inside a road from the pixel of road edge farther out.I3The knot that the middle road pixel rejected by mistake is generated in Threshold segmentation
Fruit I '2In retained, so, this step using equation below be superimposed I3With I '2, I is drawn to generate complete line drawing4。
I4(x, y)=I3(x,y)&I′2(x,y)
Step 6, road optimization.Using Portace methods to I4Vectorized process is carried out, obtains smooth consistent line drawing effect
Fruit, available for imitation or industrial design.
The present invention completes the extraction of line drawing figure or the generating process of colored mural painting image by above step, generates accurate line
Tracing.Intermediate result such as (a), (b), (c), (d) (d), (e), (f), (g), (h) institute in Fig. 2 are respectively walked in above-mentioned processing procedure
Show.Fig. 3 gives the effect displaying figure of different mural painting styles, wherein, left side (a) is artwork, other are different mural painting wind
The effect displaying figure of lattice.
In order to verify the effect of the present invention, following contrast test is carried out:
Using the Visual C++2010 under Windows7 systems as experiment simulation platform.Mural painting sinking shaft image is selected to make
For test set, 100 width image altogether.Horizontal/vertical resolution is 300dpi, and pixel number is 800 × 680.Using this patent institute
Extracting method handles test image, has obtained good treatment effect, by adjusting parameter, can also generate different width
Degree response, and then embody different mural painting line drawing styles.Fig. 4 gives the handling result of the present invention, and left side is mural painting in figure,
The line drawing figure that right side is generated for the present invention, average treatment speed are 14ms, and processing speed is substantially real-time, disclosure satisfy that requirement.And
Fig. 5 gives the line drawing figure obtained using Canny, gPb algorithm, and comparison diagram 4 and Fig. 5 can be seen that the line drawing that the present invention generates
Figure is more more life-like than the line drawing figure that Canny, gPb algorithm generate.
It is emphasized that embodiment of the present invention is illustrative rather than limited, therefore present invention packet
Include the embodiment being not limited to described in specific embodiment, it is every by those skilled in the art according to the technique and scheme of the present invention
The other embodiment obtained, also belongs to the scope of protection of the invention.
Claims (6)
1. the line drawing in a kind of combination external margin information and interior polymeric road draws generating algorithm, it is characterised in that including following step
Suddenly:
Step 1, the mural painting image I for input remove noise using Gaussian filter and carry out gray processing and handle to obtain denoising
Gray level image I afterwards0;
Step 2, to gray level image I0Edge extracting is carried out, obtains a road external margin figure I1;
Step 3, using High frequency filter to gray level image I0It is promoted to obtain a road interior details figure I2;
Step 4, comprehensive road external margin figure I1With a road interior details figure I2Information carry out the fusion of road, generation one is complete
Lump-sum road I3;
Step 5, the road repairing based on Threshold segmentation and information superposition, obtain the line drawing figure I of integrality enhancing4;
Step 6, using Portace methods to line drawing figure I4Vectorized process is carried out, obtains smooth consistent result line drawing figure.
2. the line drawing in a kind of combination external margin information according to claim 1 and interior polymeric road draws generating algorithm,
It is characterized in that:The concrete processing procedure of the step 2 is as follows:
(1) the Grad of each pixel is calculated using Sobel operators to obtain gray level image I0Gradient magnitude, gradient magnitude
The computational methods of G are as follows:
Wherein GxAnd GyThe gradient of pixel (x, y) both horizontally and vertically is represented respectively;
(2) the horizontal gradient G of arctan function compared pixels point is utilizedxWith vertical gradient GySize obtain edge direction D,
Calculation formula is as follows:
D [x, y]=arctan (Gx/Gy)
(3) non-maxima suppression is carried out to gradient magnitude:Using the direction finding pixel local maximum of gradient, by gradient width
Gray value in value G corresponding to non-maximum point is set to 0, so as to weed out the point of most non-edge, obtains non-maximum
Inhibit image G1;
(4) to non-maxima suppression image G1Two threshold values th1 and th2 are acted on, by the gray scale of pixel of the Grad less than threshold value th1
Value is set as 0, obtains edge image N1, the gray value of pixel of the Grad less than threshold value th2 is then set as 0, obtains edge graph
As N2, with edge image N2Based on, by edge link into profile, when the endpoint for reaching profile, in end-on 8 neighborhood point
The point for meeting Low threshold is found, new edge is collected further according to this point, until whole image edge closure, is consequently formed outside a road
Portion edge graph I1。
3. the line drawing in a kind of combination external margin information according to claim 2 and interior polymeric road draws generating algorithm,
It is characterized in that:Relationship between the threshold value th1 and th2 is:Th1=0.4th2.
4. the line drawing in a kind of combination external margin information according to claim 1 and interior polymeric road draws generating algorithm,
It is characterized in that:The concrete processing procedure of the step 3 is:
(1) the increment of gray-scale map is calculated using following formula, as a result with Δ I0It represents:
(2) high boost is carried out, is calculated as follows to obtain a road interior details figure I2:
I2(x, y)=min (255, I0(x,y)+ΔI0(x,y))。
5. the line drawing in a kind of combination external margin information according to claim 1 and interior polymeric road draws generating algorithm,
It is characterized in that:The step 4 carries out a road fusion using equation below:
Wherein, (x ', y ') is some pixel in 8 neighborhoods of (x, y).
6. the line drawing in a kind of combination external margin information according to claim 1 and interior polymeric road draws generating algorithm,
It is characterized in that:The specific processing method of the step 5 is:
(1) using Otsu methods to filter result I2Into row threshold division, the larger pixel of gray value, Threshold segmentation result note are rejected
For I '2;
(2) I is superimposed using equation below3With I '2, I is drawn to generate complete line drawing4:
I4(x, y)=I3(x,y)&I2′(x,y)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711418454.0A CN108171771A (en) | 2017-12-25 | 2017-12-25 | The line drawing in a kind of combination external margin information and interior polymeric road draws generating algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711418454.0A CN108171771A (en) | 2017-12-25 | 2017-12-25 | The line drawing in a kind of combination external margin information and interior polymeric road draws generating algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108171771A true CN108171771A (en) | 2018-06-15 |
Family
ID=62520436
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711418454.0A Pending CN108171771A (en) | 2017-12-25 | 2017-12-25 | The line drawing in a kind of combination external margin information and interior polymeric road draws generating algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108171771A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110689016A (en) * | 2018-07-05 | 2020-01-14 | 山东华软金盾软件股份有限公司 | License plate image coarse positioning method |
CN115409914A (en) * | 2022-11-02 | 2022-11-29 | 天津恒达文博科技股份有限公司 | Method and device for generating cultural relic line drawing, storage medium and electronic equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7119924B2 (en) * | 2001-09-28 | 2006-10-10 | Xerox Corporation | Detection and segmentation of sweeps in color graphics images |
CN101488223A (en) * | 2008-01-16 | 2009-07-22 | 中国科学院自动化研究所 | Image curve characteristic matching method based on average value standard deviation descriptor |
CN104766095A (en) * | 2015-04-16 | 2015-07-08 | 成都汇智远景科技有限公司 | Mobile terminal image identification method |
US20170076174A1 (en) * | 2014-05-06 | 2017-03-16 | Nant Holdings Ip, Llc | Image-based feature detection using edge vectors |
-
2017
- 2017-12-25 CN CN201711418454.0A patent/CN108171771A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7119924B2 (en) * | 2001-09-28 | 2006-10-10 | Xerox Corporation | Detection and segmentation of sweeps in color graphics images |
CN101488223A (en) * | 2008-01-16 | 2009-07-22 | 中国科学院自动化研究所 | Image curve characteristic matching method based on average value standard deviation descriptor |
US20170076174A1 (en) * | 2014-05-06 | 2017-03-16 | Nant Holdings Ip, Llc | Image-based feature detection using edge vectors |
CN104766095A (en) * | 2015-04-16 | 2015-07-08 | 成都汇智远景科技有限公司 | Mobile terminal image identification method |
Non-Patent Citations (1)
Title |
---|
许迪: "面向中国古代壁画的线描画生成方法", 《计算机工程》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110689016A (en) * | 2018-07-05 | 2020-01-14 | 山东华软金盾软件股份有限公司 | License plate image coarse positioning method |
CN110689016B (en) * | 2018-07-05 | 2023-04-18 | 山东华软金盾软件股份有限公司 | License plate image coarse positioning method |
CN115409914A (en) * | 2022-11-02 | 2022-11-29 | 天津恒达文博科技股份有限公司 | Method and device for generating cultural relic line drawing, storage medium and electronic equipment |
CN115409914B (en) * | 2022-11-02 | 2023-01-06 | 天津恒达文博科技股份有限公司 | Method and device for generating cultural relic line drawing, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110866924B (en) | Line structured light center line extraction method and storage medium | |
CN110264448B (en) | Insulator fault detection method based on machine vision | |
CN108898610A (en) | A kind of object contour extraction method based on mask-RCNN | |
CN105719306B (en) | A kind of building rapid extracting method in high-resolution remote sensing image | |
Cheng et al. | Building region derivation from LiDAR data using a reversed iterative mathematic morphological algorithm | |
CN108280823A (en) | The detection method and system of the weak edge faults of cable surface in a kind of industrial production | |
CN105913415A (en) | Image sub-pixel edge extraction method having extensive adaptability | |
CN104463814B (en) | Image enhancement method based on local texture directionality | |
CN109961416B (en) | Business license information extraction method based on morphological gradient multi-scale fusion | |
CN109559324A (en) | A kind of objective contour detection method in linear array images | |
CN110544300B (en) | Method for automatically generating three-dimensional model based on two-dimensional hand-drawn image characteristics | |
CN109166125A (en) | A kind of three dimensional depth image partitioning algorithm based on multiple edge syncretizing mechanism | |
CN105809673A (en) | SURF (Speeded-Up Robust Features) algorithm and maximal similarity region merging based video foreground segmentation method | |
CN112861654A (en) | Famous tea picking point position information acquisition method based on machine vision | |
CN110276747B (en) | Insulator fault detection and fault rating method based on image analysis | |
CN108171771A (en) | The line drawing in a kind of combination external margin information and interior polymeric road draws generating algorithm | |
CN110751680A (en) | Image processing method with fast alignment algorithm | |
CN104809733A (en) | Ancient building wall polluted inscription character image edge extraction method | |
Omidalizarandi et al. | Segmentation and classification of point clouds from dense aerial image matching | |
CN102679871B (en) | Rapid detection method of sub-pixel precision industrial object | |
CN105374024B (en) | The method of high-resolution satellite image on-water bridge extraction | |
CN106203440A (en) | A kind of gray level image recognition methods based on complex network | |
Pooja et al. | Image segmentation: A survey | |
CN105354823A (en) | Tree-ring image edge extraction and segmentation system | |
CN115841618A (en) | Remote sensing image coastline extraction method based on clustering and edge detection |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180615 |