CN104200479A - Method for extracting cloud heads and tails from cloud cultural elements in Dunhuang murals - Google Patents
Method for extracting cloud heads and tails from cloud cultural elements in Dunhuang murals Download PDFInfo
- Publication number
- CN104200479A CN104200479A CN201410467807.6A CN201410467807A CN104200479A CN 104200479 A CN104200479 A CN 104200479A CN 201410467807 A CN201410467807 A CN 201410467807A CN 104200479 A CN104200479 A CN 104200479A
- Authority
- CN
- China
- Prior art keywords
- cloud
- point
- auspicious
- circle
- maximum inscribed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method for extracting cloud heads and tails from cloud cultural elements in Dunhuang murals. According to the method, an outline sequence of clouds is searched for by an outline extraction method in image processing; cloud heads and tails are cut by a maximum inscribed circle method. The problems such that manual distinguishing of cloud heads and tails is subjective and low in efficiency are avoided; feature extraction of mass clouds and quantitative analysis by a computer are facilitated. The method has the advantages that the loopback problem can be solved, the maximum inscribed circle method is assistant in establishing framework structures of clouds, basis is provided for the analysis on framework features of clouds, and the use of the automatic cutting method of cloud heads and tails provide important technical support for the analysis on quantitative features of clouds and the research on evolution law of clouds.
Description
Technical field
The present invention relates to image-region and process, be specifically related to a kind of cloud cluster cloud tail extracting method of Dunhuang frescoes auspicious cloud Cultural Elements.
Background technology
As an important Cultural Elements of Dunhuang frescoes, auspicious cloud pattern is the cultural Symbol of representative of China's property, lasts thousand, uses very extensively, at aspects such as dress ornament, picture, vessel, furniture, building, advertisement designs, can see its figure.The design of torch in the 2008 Beijing Olympic Games, its creation inspiration is based on auspicious cloud pattern.Research auspicious cloud, can excavate a lot of information: from historical point view, can work out its development and evolution rule, be to historical dynasty side reflection; From utilization aspect, can obtain the potential information of grain pattern, commercialization is designed with to good reference value.
From Sui-Tang bines, auspicious cloud form has significantly " cloud cluster " and " cloud tail " two regions, is cloudlet shape; " cloud cluster " is irregular ellipticity, and " cloud tail " is thin by thick gradual change, in the inner side of cloud, by another kind of color, sketches the contours its profile.Sheng Tang period, " cloud cluster " is more regular, in auspicious cloud, by color, forms the form that hooks volume.Also having a kind of is without " cloud tail ", only has " cloud cluster ", and " cloud cluster " both sides grow the similar shape of multilayer, and the profile of each layer is described with other color fine rules.
There is no at present the concrete grammar that uses computer image processing technology to analyze to auspicious cloud pattern.
Summary of the invention:
The object of the invention is the deficiency existing in order to solve above-mentioned background technology, and propose a kind of cloud cluster cloud tail extracting method of Dunhuang frescoes auspicious cloud Cultural Elements.
To achieve these goals, the technical solution adopted in the present invention is:
A cloud cluster cloud tail extracting method for Dunhuang frescoes auspicious cloud Cultural Elements, the method comprises the steps: step 1, extracts the profile sequence of auspicious cloud Cultural Elements image; Step 2, finds the maximum inscribed circle of each point and the skeleton of auspicious cloud Cultural Elements image in auspicious cloud Cultural Elements image; Step 3, classifies to all maximum inscribed circles in auspicious cloud Cultural Elements image according to the mean value of take on skeleton a little as the maximum inscribed circle radius in the center of circle, filters out and belongs to cloud cluster maximum inscribed circle partly; Maximum inscribed circle according to cloud cluster part calculates and marks cloud cluster central point and cloud cluster line, on skeleton, distance cloud cluster central point point is farthest cloud tail point and starting point, according to starting point and cloud cluster line, adopt diffusion to spread method and mark all cloud tail points, the unlabelled point of all the other auspicious cloud Cultural Elements images is cloud cluster point.
Preferably, the profile sequence that step 1 is extracted auspicious cloud Cultural Elements image is that auspicious cloud image is converted into bianry image, and auspicious cloud regional value is 1, and other value is 0; Then any point in auspicious cloud region being analyzed, judged whether the value upper, left, down, right adjoint point of this point is all 1, is if so, the point of auspicious cloud intra-zone, is the frontier point of auspicious cloud profile if not, deposits this frontier point in profile sequence array; Contour tracing method to bianry image employing based on first search direction obtains the profile sequence of orderly auspicious cloud Cultural Elements image.
Preferably, when the frontier point of step 1 search auspicious cloud profile, if while running into winding, from causing that point of ring to date back to a some P, 8 neighborhoods to a P are searched for clockwise successively since 0 direction, using the not searched mistake searching first be frontier point as next point, complete to ring release.
Preferably, in step 2, finding maximum inscribed circle is to travel through successively inner each point of auspicious cloud Cultural Elements image, filter out the center of circle of each maximum inscribed circle, take this point does circle as the center of circle, make circle with auspicious cloud Cultural Elements image image border being tangential on two points, and circle in a little all within the image of auspicious cloud Cultural Elements;
The skeleton of finding auspicious cloud Cultural Elements image is successively the center of circle of immediate each maximum inscribed circle to be connected, and obtains the skeleton of auspicious cloud Cultural Elements.
Preferably, the method of finding the maximum inscribed circle center of circle of each point in auspicious cloud Cultural Elements image is: in auspicious cloud Cultural Elements image, appoint and get 1 A, the distance of calculating A point and all point, sorts all range data from small to large, is designated as apart from array r[n]; Will be apart from array r[n] in three minimum range data as two groups, analyze, first group of r[0] and r[1], second group of r[0] and r[2], when first group and second group any one group while meeting the following conditions, judge that A point is the center of circle of maximum inscribed circle, when all meeting the following conditions for first group and second group, judge that A point is not the center of circle of maximum inscribed circle, condition is: r[0] and r[1] or r[0] and r[2] profile distance between corresponding point is greater than assign thresholds and r[0] and r[1] or r[0] and r[2] difference be less than 0.5.
Preferably, the concrete steps of step 3 comprise: 31) ask the radius mean value that has a maximum inscribed circle on skeleton, and adjust mean value with cloud neck parameter k, and filter out the maximum inscribed circle that radius is greater than the mean value after adjusting, what screen is the maximum inscribed circle of cloud cluster part; 32) mean value that solves each cloud cluster part maximum inscribed circle center of circle is as cloud cluster central point, and on skeleton, distance center point point is farthest cloud tail point, and this cloud tail point of mark is diffusion starting point; 33) each cloud cluster part maximum inscribed circle and tangent two points of auspicious cloud edges of regions are coupled together respectively and form several cloud cluster lines; 34) from starting point, start to both sides diffusion, to spread in profile, until diffusion spreads to immediate cloud cluster line, diffusion spreads and stops, and the point of diffusion process is labeled as the point in territory, cloud tail region; The point that is not marked as territory, cloud tail region is the point in cloud cluster region.
Preferably, the span of cloud neck parameter k is 0.8-1.2.
Beneficial effect of the present invention is: the present invention utilizes the contour extraction method in image processing to find the profile sequence of auspicious cloud, by maximum inscribed circle method, carrying out cloud cluster cloud tail cuts apart, having avoided people is the problems such as the subjectivity of carrying out dividing cloud cluster cloud tail region, poor efficiency, is convenient to computing machine a large amount of auspicious cloud features are extracted and quantitative analysis.The contour extraction method that the present invention chooses has solved winding problem, maximum inscribed circle heart method can assisting building auspicious cloud framework characteristic, for the framework characteristic analysis of auspicious cloud provides basis, the automatic division method of cloud cluster cloud tail is also for analyzing auspicious cloud quantization characteristic, the Evolution of research auspicious cloud, provides important technical support.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of embodiment of the present invention point,
Fig. 2 is 8 neighborhood directions of embodiment of the present invention point,
Fig. 3 is that embodiment of the present invention profile is followed the tracks of schematic diagram,
Fig. 4 is the invention process winding schematic diagram,
Fig. 5 is that the invention process winding is processed schematic diagram,
Fig. 6 is the bianry image of the invention process auspicious cloud and the figure of profile sequence stack,
Fig. 7 is the invention process auspicious cloud maximum inscribed circle,
Fig. 8 is the center of circle of the maximum inscribed circle after the invention process screening,
Fig. 9 is maximum inscribed circle after the invention process screening and the line of profile points of tangency,
Figure 10 is " cloud cluster " image that the invention process auspicious cloud culture image extracts,
Figure 11 is " cloud tail " image that the invention process auspicious cloud culture image extracts.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described further.
As shown in Figure 1, a kind of cloud cluster cloud tail extracting method of Dunhuang frescoes auspicious cloud Cultural Elements, the method comprises the steps:
Step 1, the profile sequence of extraction auspicious cloud Cultural Elements image;
The profile sequence of extracting auspicious cloud Cultural Elements image is that auspicious cloud image is converted into bianry image, and auspicious cloud regional value is 1, and other value is 0; Then any point in auspicious cloud region being analyzed, judged whether the value upper, left, down, right adjoint point of this point is all 1, is if so, the point of auspicious cloud intra-zone, is the frontier point of auspicious cloud profile if not, deposits this frontier point in profile sequence array; Contour tracing method to bianry image employing based on first search direction obtains the profile sequence of orderly auspicious cloud Cultural Elements image.
The concrete steps that the present embodiment profile extracts are as follows:
11) determine initial search point Start
According to direction from top to bottom, from left to right, the point that is 1 by first value searching (being first point in auspicious cloud region), as the starting point Start of profile.
12) the next point of search Start
As shown in Figure 3, if the next point of Start exists, must be in upper right in its 8 neighborhood, the right side, bottom right, lower direction (corresponding respectively to 7 in Fig. 2,0,1,2).By upper right, the right side, bottom right, lower direction, search for successively, finding first value is 1 point, is next point N.Be that Start is a upper point, N is current point.
13) search for next point
Start is Pre assignment, and N is Curr assignment, and Pre is a upper point, and Curr is current point, and Dir is the direction of search (for example put Curr on the 3 neighborhood positions of a Pre, Dir is 3 so) from a upper point to current point.The initial direction of search using Dir as Curr, then search successively in the direction of the clock in 8 neighborhoods of a Curr, finding first value is 1, and not searched mistake, and is the point of frontier point, is the next point Tmp of a Curr.Current point becomes a upper point, and Tmp becomes current point.
14) if current some Curr is exactly starting point Start, again got back to starting point, profile is followed the tracks of complete; Otherwise, jump to the 3rd step and continue search.
Winding refers to and causes endless loop and cannot get back to starting point, and as shown in Figure 4, according to first search direction algorithm, the next point of A is P, and the next point of P is B, and the next point of B is A, and this has just caused winding; When the frontier point of search auspicious cloud profile, if run into winding,, from causing that point of ring to date back to a some P, 8 neighborhoods of a P are searched for clockwise successively since 0 direction, using the not searched mistake searching first be frontier point as next point, complete to ring release.For winding problem, causing that B of ring, date back to a some P, 8 neighborhoods to a P, since 0 direction, search for successively clockwise, using first running into be frontier point and not searched mistake and be not the some C of a B as the next point of a P, so just can to ring carry out release, be as shown in Figure 5 the winding release in Fig. 4.
Step 2, finds the maximum inscribed circle of each point and the skeleton of auspicious cloud Cultural Elements image in auspicious cloud Cultural Elements image;
Finding maximum inscribed circle is to travel through successively inner each point of auspicious cloud Cultural Elements image, filter out the center of circle of each maximum inscribed circle, its method is: in auspicious cloud Cultural Elements image, appoint and get 1 A, calculate the distance of A point and all point, all range data are sorted from small to large, be designated as apart from array r[n]; Will be apart from array r[n] in three minimum range data as two groups, analyze, first group of r[0] and r[1], second group of r[0] and r[2], when first group and second group any one group while meeting the following conditions, judge that A point is the center of circle of maximum inscribed circle, when all meeting the following conditions for first group and second group, judge that A point is not the center of circle of maximum inscribed circle, condition is: r[0] and r[1] or r[0] and r[2] profile distance between corresponding point is greater than assign thresholds and r[0] and r[1] or r[0] and r[2] difference be less than 0.5.
Take the center of circle of each maximum inscribed circle of being found does circle as the center of circle, make circle be tangential on two points of image border, and in circle institute a little all within the image of auspicious cloud Cultural Elements, the maximum inscribed circle that circle is auspicious cloud Cultural Elements image of doing.
The skeleton of finding auspicious cloud Cultural Elements image is successively the center of circle of immediate each maximum inscribed circle to be connected, and can obtain the skeleton of auspicious cloud Cultural Elements.The center of circle of note maximum inscribed circle is (x
i, y
i), radius is r
i, in auspicious cloud Cultural Elements image, the number of maximum inscribed circle is N, the skeleton representation of the auspicious cloud extracting with maximum inscribed circle is:
S＝{(x
i,y
i,r
i)|i＝1,2,…,N}
Step 3, the maximum inscribed circle that filters out cloud cluster part, calculates cloud cluster central point, finds out on skeleton distance cloud cluster central point point farthest as starting point, from starting point, start to adopt diffusion to spread the point that method marks all territories, cloud tail region, the unlabelled point that is cloud cluster region.
Concrete steps are as follows:
31) ask the radius mean value that has a maximum inscribed circle on skeleton,
Central point (the x in the center of circle of calculating sifting maximum inscribed circle out
c, y
c), the number of note circle is M,
m is the number of the incircle of the cloud cluster part that screens.
And adjust mean value with cloud neck parameter k, and k is empirical value, represents that Yun Jing departs from the degree of cloud cluster, and k is larger, and the place of cutting apart more departs from cloud cluster, and the general value of k is 1, span is 0.8-1.2, obtains mean value after adjusting and cuts apart formula and be
Filter out radius and be greater than the mean value after adjusting
maximum inscribed circle, what screen is the maximum inscribed circle of cloud cluster part;
32) mean value that solves each cloud cluster part maximum inscribed circle center of circle is as cloud cluster central point, and on skeleton, distance cloud cluster central point point is farthest cloud tail point, and this cloud tail point of mark is diffusion starting point;
33) each cloud cluster part maximum inscribed circle and tangent two points of auspicious cloud edges of regions are coupled together respectively and form several cloud cluster lines, as shown in Figure 9;
34) from starting point, start to both sides diffusion, to spread in profile, until diffusion spreads to immediate cloud cluster line, diffusion spreads and stops, and the point of diffusion process is labeled as the point in territory, cloud tail region; The point that is not marked as territory, cloud tail region is the point in cloud cluster region.As shown in Figure 10 and Figure 11, be and extract cloud cluster and cloud tail.
Should be understood that, for those of ordinary skills, can be improved according to the above description or convert, and all these improvement and conversion all should belong to the protection domain of claims of the present invention.
Claims (7)
1. a cloud cluster cloud tail extracting method for Dunhuang frescoes auspicious cloud Cultural Elements, is characterized in that, the method comprises the steps:
Step 1, extracts the profile sequence of described auspicious cloud Cultural Elements image;
Step 2, finds the maximum inscribed circle of each point and the skeleton of auspicious cloud Cultural Elements image in described auspicious cloud Cultural Elements image;
Step 3, classifies to all maximum inscribed circles in described auspicious cloud Cultural Elements image according to the mean value of take on described skeleton a little as the maximum inscribed circle radius in the center of circle, filters out and belongs to cloud cluster maximum inscribed circle partly; Maximum inscribed circle according to described cloud cluster part calculates and marks cloud cluster central point and cloud cluster line, on described skeleton, described in distance, cloud cluster central point point is farthest cloud tail point and starting point, according to described starting point and cloud cluster line, adopt diffusion to spread method and mark all cloud tail points, described in all the other, the unlabelled point of auspicious cloud Cultural Elements image is cloud cluster point.
2. the cloud cluster cloud tail extracting method of a kind of Dunhuang frescoes auspicious cloud Cultural Elements according to claim 1, it is characterized in that: the profile sequence that described step 1 is extracted described auspicious cloud Cultural Elements image is that auspicious cloud image is converted into bianry image, auspicious cloud regional value is 1, and other value is 0; Then any point in auspicious cloud region being analyzed, judged whether the value upper, left, down, right adjoint point of this point is all 1, is if so, the point of auspicious cloud intra-zone, is the frontier point of auspicious cloud profile if not, deposits this frontier point in profile sequence array; Contour tracing method to described bianry image employing based on first search direction obtains the profile sequence of orderly described auspicious cloud Cultural Elements image.
3. the cloud cluster cloud tail extracting method of a kind of Dunhuang frescoes auspicious cloud Cultural Elements according to claim 1 and 2, it is characterized in that: when the frontier point of step 1 search auspicious cloud profile, if while running into winding, from causing that point of ring to date back to a some P, 8 neighborhoods to a P are searched for clockwise successively since 0 direction, using the not searched mistake searching first be frontier point as next point, complete to ring release.
4. the cloud cluster cloud tail extracting method of a kind of Dunhuang frescoes auspicious cloud Cultural Elements according to claim 1, is characterized in that:
Described in described step 2, finding maximum inscribed circle is to travel through successively inner each point of described auspicious cloud Cultural Elements image, filter out the center of circle of each maximum inscribed circle, take this point does circle as the center of circle, make described circle and auspicious cloud Cultural Elements image image border be tangential on two points, and described circle in a little all within the image of described auspicious cloud Cultural Elements;
The skeleton of finding described auspicious cloud Cultural Elements image is successively the center of circle of immediate each maximum inscribed circle to be connected, and obtains the described skeleton of described auspicious cloud Cultural Elements.
5. the cloud cluster cloud tail extracting method of a kind of Dunhuang frescoes auspicious cloud Cultural Elements according to claim 4, is characterized in that: the method for finding the maximum inscribed circle center of circle of each point in described auspicious cloud Cultural Elements image is:
In auspicious cloud Cultural Elements image, appoint and get 1 A, calculate the distance of A point and all point, all range data are sorted from small to large, be designated as apart from array r[n];
Using described apart from array r[n] in three minimum range data as two groups, analyze, first group of r[0] and r[1], second group of r[0] and r[2], when first group and second group any one group while meeting the following conditions, judge that A point is the center of circle of maximum inscribed circle, when all meeting the following conditions for first group and second group, judge that A point is not the center of circle of maximum inscribed circle, described condition is: r[0] and r[1] or r[0] and r[2] profile distance between corresponding point is greater than assign thresholds and r[0] and r[1] or r[0] and r[2] difference be less than 0.5.
6. the cloud cluster cloud tail extracting method of a kind of Dunhuang frescoes auspicious cloud Cultural Elements according to claim 1, is characterized in that, the concrete steps of described step 3 comprise:
31) ask on described skeleton have the radius mean value of a maximum inscribed circle, and adjust described mean value with cloud neck parameter k, filter out the maximum inscribed circle that radius is greater than the described mean value after adjusting, what screen is the maximum inscribed circle of cloud cluster part;
32) mean value that solves each cloud cluster part maximum inscribed circle center of circle is as cloud cluster central point, and on skeleton, described in distance, central point point is farthest cloud tail point, and this cloud tail point of mark is diffusion starting point;
33) each cloud cluster part maximum inscribed circle and tangent two points of auspicious cloud edges of regions are coupled together respectively and form several cloud cluster lines;
34) from described starting point, start to both sides diffusion, to spread in described profile, until diffusion spreads to immediate cloud cluster line, diffusion spreads and stops, and the point of diffusion process is labeled as the point in territory, cloud tail region; The point that is not marked as territory, cloud tail region is the point in cloud cluster region.
7. the cloud cluster cloud tail extracting method of a kind of Dunhuang frescoes auspicious cloud Cultural Elements according to claim 6, is characterized in that: the span of described cloud neck parameter k is 0.8-1.2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410467807.6A CN104200479B (en) | 2014-09-15 | 2014-09-15 | A kind of cloud cluster cloud tail extracting method of Dunhuang frescoes auspicious cloud Cultural Elements |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410467807.6A CN104200479B (en) | 2014-09-15 | 2014-09-15 | A kind of cloud cluster cloud tail extracting method of Dunhuang frescoes auspicious cloud Cultural Elements |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104200479A true CN104200479A (en) | 2014-12-10 |
| CN104200479B CN104200479B (en) | 2017-03-29 |
Family
ID=52085765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410467807.6A Active CN104200479B (en) | 2014-09-15 | 2014-09-15 | A kind of cloud cluster cloud tail extracting method of Dunhuang frescoes auspicious cloud Cultural Elements |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104200479B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004759A (en) * | 2010-11-03 | 2011-04-06 | 东莞市冠辉五金有限公司 | Chinese culture element engineering database system and application thereof in manufacture filed of hardware |
| US20120189176A1 (en) * | 2010-11-26 | 2012-07-26 | Giger Maryellen L | Method, system, software and medium for advanced intelligent image analysis and display of medical images and information |
| CN103714537A (en) * | 2013-12-19 | 2014-04-09 | 武汉理工大学 | Image saliency detection method |
-
2014
- 2014-09-15 CN CN201410467807.6A patent/CN104200479B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004759A (en) * | 2010-11-03 | 2011-04-06 | 东莞市冠辉五金有限公司 | Chinese culture element engineering database system and application thereof in manufacture filed of hardware |
| US20120189176A1 (en) * | 2010-11-26 | 2012-07-26 | Giger Maryellen L | Method, system, software and medium for advanced intelligent image analysis and display of medical images and information |
| CN103714537A (en) * | 2013-12-19 | 2014-04-09 | 武汉理工大学 | Image saliency detection method |
Non-Patent Citations (1)
| Title |
|---|
| 方建文: "计算机生成中国传统祥云动画", 《中国图像图形学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104200479B (en) | 2017-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105930159B (en) | A kind of method and system that the GUI code based on image generates | |
| CN101777060B (en) | Webpage classification method and system based on webpage visual characteristics | |
| CN110210387B (en) | Method, system and device for detecting insulator target based on knowledge graph | |
| CN108198244A (en) | A kind of Apple Leaves point cloud compressing method and device | |
| CN104299004B (en) | A kind of gesture identification method based on multiple features fusion and finger tip detection | |
| CN105046287B (en) | A kind of online more strokes repeat the cluster and approximating method of skeletonizing | |
| CN104077806B (en) | Automatic split extracting method based on urban architecture threedimensional model | |
| CN102663382A (en) | Video image character recognition method based on submesh characteristic adaptive weighting | |
| CN101216943B (en) | A method for video moving object subdivision | |
| CN103295013A (en) | Pared area based single-image shadow detection method | |
| CN105894044A (en) | Single-plant tree point cloud automatic extraction method based on vehicle-mounted laser scanning data | |
| CN102945567A (en) | Method and system for classifying and reconstructing indoor scene | |
| CN105808665A (en) | Novel hand-drawn sketch based image retrieval method | |
| CN109086772A (en) | A kind of recognition methods and system distorting adhesion character picture validation code | |
| CN109685788A (en) | A kind of flooring defect image automatic testing method based on morphological feature | |
| CN105303587A (en) | Automated and intelligent figure color-matching method | |
| CN103729621B (en) | Plant leaf image automatic recognition method based on leaf skeleton model | |
| CN105654099A (en) | Sugarcane segmentation and identification method based on improved vision | |
| CN103976468A (en) | Tobacco leaf grading method | |
| CN109766892A (en) | A kind of ray detection image tagged information character dividing method based on edge detection | |
| CN103824325A (en) | Fruit tree branch interactive three-dimensional reconstruction method and system | |
| CN109102538A (en) | Method, the synoptic analysis method of piston ring land characteristic point and land features line are extracted using isopleth data | |
| CN107292898A (en) | A kind of car plate shadow Detection and minimizing technology based on HSV | |
| CN104200479A (en) | Method for extracting cloud heads and tails from cloud cultural elements in Dunhuang murals | |
| CN102938052A (en) | Sugarcane segmentation and recognition method based on computer vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210205 Address after: 850030 1st floor, unit 1, building 12, international headquarters city, Liuwu New District, Lhasa City, Tibet Autonomous Region Patentee after: Tibet Zhumuyalu Digital Science and Technology Culture Co.,Ltd. Address before: 430070 Wuhan University of technology, 122 Luoshi Road, Wuhan City, Hubei Province Patentee before: WUHAN University OF TECHNOLOGY |