CN102542555A - Method and system for generating edge seam path and edge seam topological structure of raster image - Google Patents
Method and system for generating edge seam path and edge seam topological structure of raster image Download PDFInfo
- Publication number
- CN102542555A CN102542555A CN2010106091241A CN201010609124A CN102542555A CN 102542555 A CN102542555 A CN 102542555A CN 2010106091241 A CN2010106091241 A CN 2010106091241A CN 201010609124 A CN201010609124 A CN 201010609124A CN 102542555 A CN102542555 A CN 102542555A
- Authority
- CN
- China
- Prior art keywords
- limit
- point
- seam
- path
- crossing
- 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
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a method and a system for generating edge seam path and edge seam topological structure of raster image, which belongs to technical field of image edge detection. The method comprises S1, selecting a raster image, and carrying out edge detection calculation by calculating a gradient magnitude diagram to obtain boundary points of the image; S2, selecting a boundary point of step S1, and carrying out neighborhood tracing according to gradient magnitude of pixels to obtain the second boundary point; S3, converting the edge seam gradient of the second boundary point in the vertical direction in reference to the first boundary point to the edge seam path; and S4, repeating the steps of S2 and S3 until the edge seam path of the whole raster image is completed; and recording information of the edge seam path and intersection points to generate the edge seam topological structure. The boundary generated by the method has high location accuracy, good continuity and abundant boundary information, and can meet the application requirement for boundary detection in each hot field of image processing.
Description
Technical field
The present invention relates to image processing field, relate in particular to the generation method and system of seam path, a kind of grating image limit and limit seam topological structure.
Background technology
In Flame Image Process, the coloured image bound test technology has extremely wide application prospect, in many hot fields such as image recognition, coupling, three-dimensional reconstruction, image retrieval, image segmentation important effect is arranged all.
Border detection algorithm is a lot, but after the candidate pixel dot generation of border, and effect has two kinds of limit seam tracing algorithm (tracking of neighbours territory) and eight neighborhood tracing algorithms preferably on the chained list tracing algorithm of border.Limit seam tracing algorithm (tracking of neighbours territory) generally adopts the limit seam gradient on direct calculated level, the vertical direction to follow the trail of the border; Locate comparatively accurate; But owing to have only four neighborhood directions, and limit seam gradient has instability, and limit tape edge circle of generation very easily ruptures; Eight neighborhood tracing algorithms generally adopt calculating pixel point gradient amplitude, on eight directions, follow the trail of gradient amplitude and follow the trail of the border, have continuity preferably, but bearing accuracy can only reach Pixel-level, and are accurate inadequately.
Summary of the invention
The objective of the invention is to defective, the generation method and system of seam path, a kind of grating image limit and limit seam topological structure are provided, make the border of generation have bearing accuracy, better continuity and abundanter boundary information more accurately to prior art.
The present invention provides the generation method of seam path, a kind of grating image limit and limit seam topological structure, and this method comprises the steps:
S1: selected grating image, through the calculating of gradient amplitude figure, carry out boundary detection calculations, obtain the frontier point of said image;
S2: choose frontier point among the step S1, carry out neighborhood according to the pixel gradient amplitude and follow the trail of, obtain next frontier point;
S 3: said next frontier point combines the limit seam gradient of previous frontier point reference level, vertical direction to be converted into seam path, limit;
S4: to all frontier points, repeating step S2～S3 is until the seam path, limit of accomplishing the view picture grating image.
Further; The generation method of seam path, aforesaid grating image limit and limit seam topological structure; This method also comprises, seam routing information in limit among recording step S2～S4, and the information of point of crossing; Generate limit seam topological structure, wherein seam topological structure in limit is made up of boundary information group and point of crossing message block.
Further, the generation method of seam path, aforesaid grating image limit and limit seam topological structure, the boundary information group comprises that border chained list, position, initial point of crossing, border and border stop position, point of crossing three parts; The point of crossing message block comprises two parts of border pointer that point of crossing coordinate position and point of crossing connect.
Further, the generation method of seam path, aforesaid grating image limit and limit seam topological structure is in the step (S1); Both direction gradient to grating image merges; Obtain the gradient amplitude figure of said image,, obtain frontier point candidate image again through non-largest inhibition algorithm and magnetic hysteresis algorithm.
Further; The generation method of seam path, aforesaid grating image limit and limit seam topological structure is in the step (S2), when carrying out the neighborhood tracking according to frontier point contrast pixel gradient amplitude; Run into the situation that has non-conterminous frontier point more than three or three on four of a frontier point or eight the adjacent directions; This finish on the border, and record point of crossing information remains direction and generates new border continuation tracking outside this border.
Further, the generation method of seam path, aforesaid grating image limit and limit seam topological structure in the step (S3), transforms seam path, limit and comprises:
(I) limit seam start position chooses;
(II) conversion in limit seam path;
(III) repeating step (II) is until running into next point of crossing, or finish in seam path, whole piece limit.
Further, the generation method of seam path, aforesaid grating image limit and limit seam topological structure, in the step (I), limit choosing of start position of seam comprises:
(a) first frontier point for the limit of point of crossing seam start position for the total maximum limit seam gradient of second frontier point be the center with first frontier point, the limit seam point on the counter clockwise direction at seam center, seam gradient limit, maximum limit stitches starting point for the limit;
(b) first frontier point is that the limit seam start position of point of crossing is to sew in two points with the total limit of second frontier point, the bigger point of another limit seam gradient except that the seam of total limit.
Further, the generation method of seam path, aforesaid grating image limit and limit seam topological structure, in the step (II), the conversion in seam path, limit comprises:
(a) calculating from the limit seam starting point just stops along being rotated with both direction counterclockwise clockwise, running into the total limit seam point of second frontier point around pixel center;
(b) seek in two paths and be not labeled the path of passing by, if unmarked passing by all selected the bigger path of seam intensity, average limit, path;
(c) path tag of passing by outside the upper pathway of point of crossing is for passing by.
Further, the generation method of seam path, aforesaid grating image limit and limit seam topological structure, this method also comprises; After seam path, image limit generates; Place, point of crossing limit seam position of intersecting point and seam path, limit are revised in the traversal point of crossing, and the point of crossing has following two kinds of situation:
When 1. the point of crossing is isolated point, give up the most weak path, a border in four limit seam gradients, be about to this point and be assigned to the zone the most close with its color, can not be from this fillet seam path, limit;
When 2. the point of crossing was adhesion point, the path, border that gradient is stitched on a limit the most weak was given up in outline fillet seam path along the point of crossing.
Further, the generation method of seam path, aforesaid grating image limit and limit seam topological structure when the point of crossing is isolated point, also comprises:
(a) limit seam path branches number is 3 o'clock, and intersection point is not stitched as the limit in one of them branch summit of recurring rule selection in the path during according to connection;
(b) limit seam path branches number is 4 o'clock; Select two summits of the opposite side of the most weak limit seam of gradient to stitch intersection point as the limit; Revise the position, point of crossing and increase a point of crossing; When connecting the path not recurring rule will remain seam path, two limits and extend to a summit separately, be starting point with two point of crossing, increase a fillet and stitch the path.
The generation system of seam path, a kind of grating image limit and limit seam topological structure comprises:
The sharp point generating apparatus is used for the calculating through gradient amplitude figure, carries out boundary detection calculations, obtains the frontier point of said image;
Seam path, limit generating apparatus is used to choose a frontier point, carries out neighborhood according to frontier point pixel gradient amplitude and follows the trail of, and obtains second frontier point, combines the limit seam gradient of previous frontier point reference level, vertical direction to be converted into seam path, limit again;
The point of crossing correcting device is used to travel through the point of crossing, revises limit, place, point of crossing seam position of intersecting point;
Limit seam topological structure generating apparatus, routing information is stitched on the limit that is used for writing edge seam path generating apparatus, and the point of crossing information in the correcting device of point of crossing, generates limit seam topological structure.
Beneficial effect of the present invention is following: the border that utilizes method and system of the present invention to generate has more accurately bearing accuracy, better continuity and abundanter boundary information, thereby can adapt to each hot fields of present Flame Image Process to the application requirements on the increasingly high precision of border detection and the continuity of becoming better and better.That is to say that the border chained list that generates through this method can guarantee on the successional basis, border the border accurate localization to be stitched precision to the limit; Simultaneously, the limit seam topological structure that is generated has abundant boundary information, can between border and point of crossing, realize fast query, thereby can realize the quick tracking and the searching on border, optional position.
Description of drawings
Fig. 1 is the generation method flow diagram in seam path in a kind of grating image limit in the embodiment of the invention;
Fig. 2 a is colour original in the embodiment of the invention, and Fig. 2 b carries out the frontier point of the said image that boundary detection calculations obtains through the calculating of gradient amplitude figure for Fig. 2 a;
Fig. 3 a is that pixel is changeed limit seam synoptic diagram in the embodiment of the invention, and Fig. 3 b is three limit intersect edges correction figure, and Fig. 3 c is many point of crossing adhesion border correction figure;
Fig. 4 is limit seam topological structure in the embodiment of the invention;
Fig. 5 a is a colour original in the embodiment of the invention, and Fig. 5 b is a Pixel-level boundary tracking synoptic diagram as a result, and Fig. 5 c is boundary tracking limit seam route result synoptic diagram;
Fig. 6 is the boundary information in the complete grating image in the embodiment of the invention;
Fig. 7 is the generation system structural drawing of seam topological structure in a kind of grating image limit in the embodiment of the invention.
Embodiment
Be elaborated below in conjunction with the Figure of description specific embodiments of the invention.
As shown in Figure 7, the invention provides the generation system that topological structure is stitched on seam path, a kind of grating image limit and limit, comprising:
Sharp point generating apparatus 1 is used for the calculating through gradient amplitude figure, carries out boundary detection calculations, obtains the frontier point of said image;
Seam path, limit generating apparatus 2 is used to choose a frontier point, carries out neighborhood according to frontier point pixel gradient amplitude and follows the trail of, and obtains second frontier point, combines the limit seam gradient of previous frontier point reference level, vertical direction to be converted into seam path, limit again;
Point of crossing correcting device 3 is used to travel through the point of crossing, revises limit, place, point of crossing seam position of intersecting point;
Limit seam topological structure generating apparatus 4, routing information is stitched on the limit that is used for writing edge seam path generating apparatus 2, and the point of crossing information in the point of crossing correcting device 3, generates limit seam topological structure.
The generation method of seam path, grating image limit that said system realized and limit seam topological structure is as shown in Figure 1, and this method comprises the steps:
S1: selected grating image, through the calculating of gradient amplitude figure, carry out boundary detection calculations, obtain the frontier point of said image;
In the embodiment of the invention, the both direction gradient of grating image is merged, obtain the gradient amplitude figure of said image,, obtain frontier point candidate image again through non-largest inhibition algorithm and magnetic hysteresis algorithm.
S2: choose frontier point among the step S1, carry out neighborhood according to the pixel gradient amplitude and follow the trail of, obtain next frontier point;
In the embodiment of the invention; When carrying out the neighborhood tracking according to frontier point contrast pixel gradient amplitude; Run into the situation that has non-conterminous frontier point more than three or three on four of a frontier point or eight the adjacent directions; This finish on the border, and record point of crossing information remains direction and generates new border continuation tracking outside this border.
S3: said next frontier point combines the limit seam gradient of previous frontier point reference level, vertical direction to be converted into seam path, limit;
In the embodiment of the invention, transform seam path, limit and also comprise:
(1) choosing of limit seam start position comprises:
A) first frontier point for the limit of point of crossing seam start position for the total maximum limit seam gradient of second frontier point be the center with first frontier point, the limit seam point on the counter clockwise direction at seam gradient wing center, maximum limit stitches starting point for the limit;
B) first frontier point is that the limit seam start position of point of crossing is to sew in two points with the total limit of second frontier point, the bigger point of another limit seam gradient except that the seam of total limit.
(2) conversion in limit seam path comprises:
A) calculating from the limit seam starting point just stops along being rotated with both direction counterclockwise clockwise, running into the total limit seam point of second frontier point around pixel center;
B) seek in two paths and be not labeled the path of passing by, if unmarked passing by all selected the bigger path of seam intensity, average limit, path;
C) path tag of passing by outside the upper pathway of point of crossing is for passing by.
(3) repeating step (2) is until running into next point of crossing, or finish in seam path, whole piece limit.
S4: repeating step S2～S3, until the seam path, limit of accomplishing the view picture grating image.
In the embodiment of the invention, this method comprises that also seam routing information in limit among recording step S2～S4, and the information of point of crossing generate limit seam topological structure, and wherein seam topological structure in limit is made up of boundary information group and point of crossing message block.
In the embodiment of the invention, the boundary information group comprises that border chained list, position, initial point of crossing, border and border stop position, point of crossing three parts; The point of crossing message block comprises two parts of border pointer that point of crossing coordinate position and point of crossing connect.
In the embodiment of the invention, this method comprises that also after seam path, image limit generated, place, point of crossing limit seam position of intersecting point and seam path, limit were revised in the traversal point of crossing, and the point of crossing has following two kinds of situation:
When (1) point of crossing is isolated point, give up the most weak path, a border in four limit seam gradients, be about to this point and be assigned to the zone the most close with its color, can not be from this fillet seam path, limit;
When (2) point of crossing was adhesion point, the path, border that gradient is stitched on a limit the most weak was given up in outline fillet seam path along the point of crossing.
In the embodiment of the invention, when the point of crossing is isolated point, also comprise:
(a) limit seam path branches number is 3 o'clock, and intersection point is not stitched as the limit in one of them branch summit of recurring rule selection in the path during according to connection;
(b) limit seam path branches number is 4 o'clock; Select two summits of the opposite side of the most weak limit seam of gradient to stitch intersection point as the limit; Revise the position, point of crossing and increase a point of crossing; When connecting the path not recurring rule will remain seam path, two limits and extend to a summit separately, be starting point with two point of crossing, increase a fillet and stitch the path.
Be the concrete embodiment description of the present invention, the concrete ins and outs when generating grating image limit seam topological structure below to be described in detail in.
Fig. 2 a is grating image in the embodiment of the invention, and Fig. 2 b carries out the frontier point of the said image that boundary detection calculations obtains through the calculating of gradient amplitude figure for Fig. 2 a.Grating image in the present embodiment is selected the cmyk color pattern for use; Total C, M, Y, four color channels of K; But range of application of the present invention is not limited to the grating image of cmyk color pattern, and the grating image of other color mode (like RGB etc.) is equally applicable to this method.The grating image of selecting to Fig. 2; Calculate the level and vertical both direction gradient of each passage respectively; Adopt gradient maximal value fusion method or hyperchannel gradient fusion method, pass through non-largest inhibition algorithm again after, enhancing in the same way, thinning algorithm and magnetic hysteresis algorithm, obtain the frontier point of image.
Fig. 3 a is that pixel is changeed limit seam synoptic diagram in the embodiment of the invention, and Fig. 3 b is three limit intersect edges correction figure, and Fig. 3 c is many point of crossing adhesion border correction figure.
Limit tape edge circle is meant that frontier point is positioned at the centre position of neighbor, and limit tape edge circle tracing process is: choose a frontier point in the image, carry out neighborhood according to the pixel gradient amplitude and follow the trail of, obtain second frontier point; Second frontier point combines the limit seam gradient of first frontier point reference level, vertical direction to be converted into seam path, limit.So-called Pixel-level border is just shown in Fig. 5 b; Limit tape edge circle is just shown in Fig. 5 c.
When carrying out the neighborhood tracking on the border; Run into when having more than three or three non-conterminous frontier point on four of a frontier point or eight the adjacent directions; This finish on the border, and record point of crossing information generates new border continuation tracking with remaining direction outside this border.
In the embodiment of the invention, transform seam path, limit and also comprise:
Choosing of frontier point limit seam start position; Frontier point for the limit seam start position of point of crossing for the total maximum limit seam gradient of second frontier point be the center with a frontier point, the limit seam point on the counter clockwise direction at seam center, seam gradient limit, maximum limit stitches starting point for the limit; Frontier point be the limit seam start position of point of crossing for sewing in two points with the total limit of second frontier point, the bigger point of gradient is stitched on another limit except that the seam of total limit.
When tracking second frontier point, each point all combines previous frontier point to transfer seam path, limit to, calculates from the limit seam starting point and just stops along being rotated with both direction counterclockwise clockwise, running into the total limit seam point of second frontier point around pixel center; Seek and be not labeled the path of passing by in two paths, if unmarked passing by all selected the bigger path of seam intensity, average limit, path; The path tag of passing by outside the upper pathway of point of crossing is for passing by.
Shown in Fig. 3 a, it is to run into the total limit seam point of next pixel just to stop that frontier point path, two non-point of crossing transfers limit seam point route method to, and instance is shown in the following figure:
If the summit in the upper left corner is seam point position, last one side, X0 is for to work as fore boundary point, and X1 is next frontier point position; So, from the frontier point in the upper left corner clockwise (0 ,-1) and counterclockwise (1 is just arranged to the path that X1 is ordered; 0), (0,1) two kinds maybe; In two paths, calculate its limit seam amplitude equalizing value Mean
Mag, N is the limit seam number of passing by, Mag is a limit seam amplitude:
After seam path, image limit generates, the traversal point of crossing, revise place, point of crossing limit seam position of intersecting point and seam path, limit:
When the point of crossing is isolated point, give up path, a border the most weak in four limit seam amplitudes (be about to this point and be assigned to the zone the most close, can not stitch the path) from this limit fillet with its color.Shown in Fig. 3 b; If limit seam path branches number is three, intersection point is not stitched as the limit in one of them branch summit of recurring rule selection in the path during according to connection, and three branch summits all can be used as limit seam intersection point among Fig. 3 b; So give up the most weak path, a border of amplitude in four limits of this pixel; For example be exactly the top (dotted line) of this pixel, this side given up (mean and can not stitch the path from this limit fillet), seam path in the limit of three directions just can only be aggregated in the left inferior division summit of this pixel so; If branches is four; Selection is opened two summits of limit seam opposite side and is stitched intersection point as the limit; Revise the position, point of crossing and increase a point of crossing; When connecting the path not recurring rule will remain seam path, two limits and extend to a summit separately, be starting point with two point of crossing, increase a fillet and stitch the path.
Shown in Fig. 3 c, the point of crossing is the adhesion point, and seam path branches summit, five limits is outline fillet seam path along the point of crossing, and the inner edge of point of crossing is given up automatically, and the most weak one of the amplitude in the outline calculated then for example is exactly leftmost vertical edges, and this side is given up.
Fig. 4 is limit seam topological structure in the embodiment of the invention, comprising boundary information group and point of crossing message block.The boundary information group comprises that border chained list, position, initial point of crossing, border and border stop position, point of crossing three parts; The point of crossing message block comprises two parts of border pointer that point of crossing coordinate position and point of crossing connect.
Fig. 5 a is a colour original in the embodiment of the invention, and Fig. 5 b is a Pixel-level boundary tracking synoptic diagram as a result, and Fig. 5 c is boundary tracking limit seam route result synoptic diagram.Can find out that by figure the demand not too high to the boundary alignment accuracy requirement can be satisfied in the Pixel-level border, advantage is that the border is continuous, and shortcoming is that the location is not accurate enough; Limit tape edge circle is meant that frontier point is positioned at the centre position of neighbor, than Pixel-level boundary accurate, adopts method of the present invention, can take into account the continuity on Pixel-level border and the accuracy in seam path, limit.
Fig. 6 is the boundary information in the complete grating image in the embodiment of the invention.Comprised n group limit seam topological structure among the figure, every group of limit seam topological structure all is made up of boundary information group and point of crossing message block.
Obviously, those skilled in the art can carry out various changes and modification to the present invention and not break away from the spirit and scope of the present invention.Like this, belong within the scope of claim of the present invention and equivalent technologies thereof if of the present invention these are revised with modification, then the present invention also is intended to comprise these changes and modification interior.
Claims (11)
1. the generation method of seam path, a grating image limit and limit seam topological structure comprises the steps:
S1: selected grating image, through the calculating of gradient amplitude figure, carry out boundary detection calculations, obtain the frontier point of said image;
S2: choose frontier point among the step S1, carry out neighborhood according to the pixel gradient amplitude and follow the trail of, obtain next frontier point;
S3: said next frontier point combines the limit seam gradient of previous frontier point reference level, vertical direction to be converted into seam path, limit;
S4: to all frontier points, repeating step S2～S3 is until the seam path, limit of accomplishing the view picture grating image.
2. the generation method of seam path, grating image as claimed in claim 1 limit and limit seam topological structure; It is characterized in that; This method also comprises, seam routing information in limit among recording step S2～S4, and the information of point of crossing; Generate limit seam topological structure, wherein seam topological structure in limit is made up of boundary information group and point of crossing message block.
3. the generation method of seam path, grating image as claimed in claim 2 limit and limit seam topological structure is characterized in that the boundary information group comprises that border chained list, position, initial point of crossing, border and border stop position, point of crossing three parts; The point of crossing message block comprises two parts of border pointer that point of crossing coordinate position and point of crossing connect.
4. the generation method of seam path, grating image as claimed in claim 1 limit and limit seam topological structure; It is characterized in that; In the step (S1), the both direction gradient of grating image is merged, obtain the gradient amplitude figure of said image; Through non-largest inhibition algorithm and magnetic hysteresis algorithm, obtain frontier point candidate image again.
5. the generation method of seam path, grating image as claimed in claim 1 limit and limit seam topological structure; It is characterized in that, in the step (S2), when carrying out the neighborhood tracking according to frontier point contrast pixel gradient amplitude; Run into the situation that has non-conterminous frontier point more than three or three on eight adjacent directions of a frontier point; This finish on the border, and record point of crossing information remains direction and generates new border continuation tracking outside this border.
6. the generation method of seam path, grating image as claimed in claim 1 limit and limit seam topological structure is characterized in that, in the step (S3), transforms seam path, limit and comprises:
(I) limit seam start position chooses;
(II) conversion in limit seam path;
(III) repeating step (II) is until running into next point of crossing, or finish in seam path, whole piece limit.
7. the generation method of seam path, grating image as claimed in claim 6 limit and limit seam topological structure is characterized in that, in the step (I), limit choosing of start position of seam comprises:
(a) first frontier point for the limit of point of crossing seam start position for the total maximum limit seam gradient of second frontier point be the center with first frontier point, the limit seam point on the counter clockwise direction at seam center, seam gradient limit, maximum limit stitches starting point for the limit;
(b) first frontier point is that the limit seam start position of point of crossing is to sew in two points with the total limit of second frontier point, the bigger point of another limit seam gradient except that the seam of total limit.
8. the generation method of seam path, grating image as claimed in claim 6 limit and limit seam topological structure is characterized in that, in the step (II), the conversion in seam path, limit comprises:
(a) calculating from the limit seam starting point just stops along being rotated with both direction counterclockwise clockwise, running into the total limit seam point of second frontier point around pixel center;
(b) seek in two paths and be not labeled the path of passing by, if unmarked passing by all selected the bigger path of seam intensity, average limit, path;
(c) path tag of passing by outside the upper pathway of point of crossing is for passing by.
9. the generation method of seam path, grating image as claimed in claim 1 limit and limit seam topological structure is characterized in that this method also comprises; After seam path, image limit generates; Place, point of crossing limit seam position of intersecting point and seam path, limit are revised in the traversal point of crossing, and the point of crossing has following two kinds of situation:
When 1. the point of crossing is isolated point, give up the most weak path, a border in four limit seam gradients, be about to this point and be assigned to the zone the most close with its color, can not be from this fillet seam path, limit;
When 2. the point of crossing was adhesion point, the path, border that gradient is stitched on a limit the most weak was given up in outline fillet seam path along the point of crossing.
10. the generation method of seam path, grating image as claimed in claim 9 limit and limit seam topological structure is characterized in that, when the point of crossing is isolated point, also comprises:
(a) limit seam path branches number is 3 o'clock, and intersection point is not stitched as the limit in one of them branch summit of recurring rule selection in the path during according to connection;
(b) limit seam path branches number is 4 o'clock; Select two summits of the opposite side of the most weak limit seam of gradient to stitch intersection point as the limit; Revise the position, point of crossing and increase a point of crossing; When connecting the path not recurring rule will remain seam path, two limits and extend to a summit separately, be starting point with two point of crossing, increase a fillet and stitch the path.
11. the generation system of seam path, a grating image limit and limit seam topological structure comprises:
Sharp point generating apparatus (1) is used for the calculating through gradient amplitude figure, carries out boundary detection calculations, obtains the frontier point of said image;
Limit seam path generating apparatus (2) is used to choose a frontier point, carries out neighborhood according to frontier point pixel gradient amplitude and follows the trail of, and obtains second frontier point, combines the limit seam gradient of previous frontier point reference level, vertical direction to be converted into seam path, limit again;
Point of crossing correcting device (3) is used to travel through the point of crossing, revises limit, place, point of crossing seam position of intersecting point;
Limit seam topological structure generating apparatus (4), routing information is stitched on the limit that is used for writing edge seam path generating apparatus (2), and the point of crossing information in the point of crossing correcting device (3), generates limit seam topological structure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010609124.1A CN102542555B (en) | 2010-12-17 | 2010-12-17 | Method and system for generating edge seam path and edge seam topological structure of raster image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010609124.1A CN102542555B (en) | 2010-12-17 | 2010-12-17 | Method and system for generating edge seam path and edge seam topological structure of raster image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102542555A true CN102542555A (en) | 2012-07-04 |
| CN102542555B CN102542555B (en) | 2015-06-03 |
Family
ID=46349378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010609124.1A Active CN102542555B (en) | 2010-12-17 | 2010-12-17 | Method and system for generating edge seam path and edge seam topological structure of raster image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102542555B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544488A (en) * | 2013-11-07 | 2014-01-29 | 湖南创合制造有限公司 | Face recognition method and device |
| CN104778736A (en) * | 2015-04-03 | 2015-07-15 | 北京航空航天大学 | Three-dimensional garment animation generation method driven by single video content |
| CN108154516A (en) * | 2018-01-30 | 2018-06-12 | 北京进化者机器人科技有限公司 | Towards the point cloud topology dividing method and device of enclosure space |
| US20180260943A1 (en) * | 2017-03-07 | 2018-09-13 | Fujitsu Limited | Apparatus and method for image processing |
| CN115272381A (en) * | 2022-09-28 | 2022-11-01 | 无锡日联科技股份有限公司 | Metal wire segmentation method and device, electronic equipment and storage medium |
| CN117058358A (en) * | 2023-10-12 | 2023-11-14 | 之江实验室 | Scene boundary detection method and mobile platform |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1852389A (en) * | 2006-04-29 | 2006-10-25 | 北京北大方正电子有限公司 | Image crisperding method during composing process |
-
2010
- 2010-12-17 CN CN201010609124.1A patent/CN102542555B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1852389A (en) * | 2006-04-29 | 2006-10-25 | 北京北大方正电子有限公司 | Image crisperding method during composing process |
Non-Patent Citations (2)
| Title |
|---|
| 周丽娟 等: "图像边界自动跟踪的边缘提取算法", 《哈尔滨理工大学学报》, vol. 2, no. 05, 25 October 1997 (1997-10-25), pages 50 - 53 * |
| 张宏志 等: "一种基于边界分析的图像陷印方法", 《中国印刷与包装研究》, vol. 2, 4 November 1923 (1923-11-04), pages 161 - 165 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544488A (en) * | 2013-11-07 | 2014-01-29 | 湖南创合制造有限公司 | Face recognition method and device |
| CN103544488B (en) * | 2013-11-07 | 2016-04-13 | 湖南创合制造有限公司 | A kind of face identification method and device |
| CN104778736A (en) * | 2015-04-03 | 2015-07-15 | 北京航空航天大学 | Three-dimensional garment animation generation method driven by single video content |
| CN104778736B (en) * | 2015-04-03 | 2017-10-20 | 北京航空航天大学 | The clothes three-dimensional animation generation method of single video content driven |
| US20180260943A1 (en) * | 2017-03-07 | 2018-09-13 | Fujitsu Limited | Apparatus and method for image processing |
| US10614560B2 (en) * | 2017-03-07 | 2020-04-07 | Fujitsu Limited | Apparatus and method for image processing |
| CN108154516A (en) * | 2018-01-30 | 2018-06-12 | 北京进化者机器人科技有限公司 | Towards the point cloud topology dividing method and device of enclosure space |
| CN108154516B (en) * | 2018-01-30 | 2020-06-09 | 北京进化者机器人科技有限公司 | Point cloud topological segmentation method and device for closed space |
| CN115272381A (en) * | 2022-09-28 | 2022-11-01 | 无锡日联科技股份有限公司 | Metal wire segmentation method and device, electronic equipment and storage medium |
| CN115272381B (en) * | 2022-09-28 | 2023-02-03 | 无锡日联科技股份有限公司 | Metal wire segmentation method and device, electronic equipment and storage medium |
| CN117058358A (en) * | 2023-10-12 | 2023-11-14 | 之江实验室 | Scene boundary detection method and mobile platform |
| CN117058358B (en) * | 2023-10-12 | 2024-03-22 | 之江实验室 | Scene boundary detection method and mobile platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102542555B (en) | 2015-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102542555A (en) | Method and system for generating edge seam path and edge seam topological structure of raster image | |
| CN103759648B (en) | A kind of complicated angle welding method for detecting position based on Binocular stereo vision with laser | |
| CN102800052B (en) | Semi-automatic digital method of non-standard map | |
| CN102867311B (en) | Method for tracking target and target following equipment | |
| CN102368810B (en) | Semi-automatic aligning video fusion system and method thereof | |
| CN101645091B (en) | Image data compression method, pattern model positioning method in image processing, image processing apparatus | |
| CN104867137B (en) | A kind of method for registering images based on improvement RANSAC algorithms | |
| CN102436670B (en) | Computer system and position alignment method | |
| CN102609934A (en) | Multi-target segmenting and tracking method based on depth image | |
| CN109711242A (en) | Modification method, device and the storage medium of lane line | |
| CN109584300A (en) | A kind of method and device of determining headstock towards angle | |
| CN110119679A (en) | Object dimensional information estimating method and device, computer equipment, storage medium | |
| CN103512558A (en) | Binocular video pose measuring method for conical target and target patterns | |
| CN106295491A (en) | Track line detection method and device | |
| Huang et al. | Vision-based semantic mapping and localization for autonomous indoor parking | |
| CN110533716A (en) | A kind of semantic SLAM system and method based on 3D constraint | |
| CN102136133B (en) | A kind of image processing method and image processing apparatus | |
| CN104317793A (en) | Different-period spatial entity hierarchical matching method and system based on multi-source information | |
| CN104217414A (en) | Method and device for extracting mosaicing line for image mosaic | |
| Yang et al. | Grounding 3d object affordance from 2d interactions in images | |
| CN101847165A (en) | Layout drawing method and device of memory part | |
| CN107133260A (en) | The matching and recognition method and device of a kind of landmark image | |
| Sun et al. | Decoupled feature pyramid learning for multi-scale object detection in low-altitude remote sensing images | |
| Yang et al. | Rethinking the misalignment problem in dense object detection | |
| Messom et al. | Hough transform run length encoding for real-time image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |