CN113392913A - Plane graph matching degree evaluation method, device and system based on boundary feature point set - Google Patents
Plane graph matching degree evaluation method, device and system based on boundary feature point set Download PDFInfo
- Publication number
- CN113392913A CN113392913A CN202110686670.3A CN202110686670A CN113392913A CN 113392913 A CN113392913 A CN 113392913A CN 202110686670 A CN202110686670 A CN 202110686670A CN 113392913 A CN113392913 A CN 113392913A
- Authority
- CN
- China
- Prior art keywords
- boundary
- straight
- plane
- matching degree
- feature point
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a plane graph matching degree evaluation method, a device and a system based on a boundary feature point set, wherein the method comprises the steps of collecting boundary feature points of two straight-edge plane graphs to be matched; based on the boundary characteristic points, calculating and obtaining graph transformation parameters after translating and rotating the straight-edge plane graphs by taking the maximum coincidence of the two straight-edge plane graphs to be matched as a target, and further obtaining the non-coincident area of the two straight-edge plane graphs; and determining a pattern matching degree value according to the relation between the misaligned area and the average area of the two straight-edge plane patterns, and finishing the evaluation of the plane pattern matching degree. The method is based on the overall matching principle with the average effect, does not need to consider the specific corresponding situation between the acquired boundary characteristic points, only adopts the contour information of the plane graph with the straight line boundary for matching, has the advantages of high calculation efficiency, robustness and accuracy, and is particularly suitable for the application occasions of identification and classification of sheet metal parts with straight-edge contours, mapping and splicing of inner space planes and the like.
Description
Technical Field
The invention belongs to the technical field of computer image processing, and particularly relates to a plane graph matching degree evaluation method, device and system based on a boundary feature point set.
Background
Plane graph matching and matching degree evaluation are commonly used for graph splicing, comparison, identification and the like, and can be further used for complex application development in the fields of automatic mapping, machine vision and the like. Patent CN201610102703.4 provides an image matching method and device, which calculate a pair of feature matching points between a screenshot to be matched and the source image through SIFT feature points and SIFT feature vectors of an image, and perform image matching by combining with an SIFT algorithm. The method needs to acquire area information of the whole image and perform feature point and feature vector operation, and needs the support of high-performance data processing hardware for use occasions such as real-time inner space measurement, rapid outline identification and the like. The matching operation using feature points is an effective method for avoiding processing a large amount of image data, but some technical difficulties still exist under some non-ideal conditions, such as: collecting characteristic points without reference; the patterns used for matching are not exactly the same; even in the same pattern, the feature point data scale differs depending on the sampling frequency. Therefore, it is very meaningful to find a mature and efficient method suitable for computer processing.
Disclosure of Invention
Aiming at the problems, the invention provides a plane graph matching degree evaluation method, device and system based on a boundary feature point set, based on the overall matching principle with average effect, without considering the specific corresponding situation between the acquired boundary feature points, only adopting the contour information of the plane graph with a straight line boundary for matching, having the advantages of high calculation efficiency, robustness and accuracy, and being particularly suitable for the application occasions of identification and classification of sheet metal parts with straight-edge contours, surveying and splicing of inner space planes and the like.
In order to achieve the technical purpose and achieve the technical effects, the invention is realized by the following technical scheme:
in a first aspect, the present invention provides a planar graph matching degree evaluation method based on a boundary feature point set, including:
collecting boundary characteristic points of two straight-edge plane graphs to be matched;
based on the boundary characteristic points, calculating and obtaining graph transformation parameters after translating and rotating the straight-edge plane graphs by taking the maximum coincidence of the two straight-edge plane graphs to be matched as a target, and further obtaining the non-coincident area of the two straight-edge plane graphs;
and determining a pattern matching degree value according to the relation between the misaligned area and the average area of the two straight-edge plane patterns, and finishing the evaluation of the plane pattern matching degree.
Optionally, the method for acquiring boundary feature points includes:
and respectively establishing a rectangular coordinate system in the planes of the two straight-edge plane figures to be matched, and extracting the position coordinates of the boundary characteristic points of the two straight-edge plane figures to be matched.
Optionally, the position of the boundary feature point of the first straight-sided planar graph is marked as (x)1i,y1i) I is the total number of the boundary characteristic points from 1 to the first straight-edge plane figure; the position of the boundary feature point of the second plane figure is expressed as (x)2i,y2i) I is the total number of boundary feature points from 1 to the second straight-sided planar figure.
Optionally, the method for calculating the non-overlapping area of the two straight-sided plane patterns includes:
identifying a linear boundary formed by a boundary discrete boundary characteristic point set, respectively determining intersection points of adjacent linear boundaries in a rectangular coordinate system, and sequentially connecting the adjacent intersection points to form a linear boundary section; connecting the straight line boundary segments of the first plane figure end to end in sequence, and recording the straight line boundary segments as l in sequence1iWherein, i is the total number of straight line boundary segments from 1 to the first plane figure; connecting the straight line boundary segments of the second plane figure end to end in sequenceSequence is given as2iWherein, i is the total number of straight line boundary segments from 1 to the second plane figure;
for all l1iAnd l2iPerforming equidistant interpolation point extraction, wherein the distance between the interpolation points is d, and respectively obtaining equidistant boundary points (x) of two straight-edge plane graphsd1k,yd1k) And (x)d2k,yd2k) K is the number of the boundary points with equal spacing, and is respectively 1 to the total number N of the boundary points with equal spacing of the two plane figuresd1And Nd2；
Respectively calculate out
ΔX＝X2-X1，ΔY＝Y2-Y1；
Integrally translating (-DeltaX, -DeltaY) the second straight-sided planar pattern, and recording boundary feature point (X ') of the translated second straight-sided planar pattern'2i,y’2i) And the straight line boundary segment is l'2i；
With (X)1，Y1) Making 0-360 degree equiangular radiation line as the center, recording the included angle of adjacent equiangular radiation lines as theta, obtaining the equiangular radiation line and the straight line boundary section l of the first plane figure1iCross point (x) ofθ1j，yθ1j) Wherein j is from 1 to the total number N of intersections on the straight boundary segment of the first plane figureθ1(ii) a Similarly, the set of equiangular radiation lines is aligned with the linear boundary segment l 'of the second straight-sided planar pattern'2iThe intersection of (A) and (B) is expressed as (x)θ2j，yθ2j) (ii) a Wherein j is from 1 to the total number N of intersections on the straight boundary segment of the second plane figureθ2；
According to the point of intersection (x)θ1j，yθ1j) Straight boundary segment l connected end to end in sequence1iThe above sequence, respectively calculate (x) in a clockwise directionθ1j，yθ1j) And a center point (X)1，Y1) A distance d between1jSequentially calculating (x) in the same direction and orderθ2j，yθ2j) And a center point (X)1，Y1) BetweenDistance d of2j. To d2jAnd d1jPerforming cross-correlation analysis to obtain a time delay parameter delta when the cross-correlation function reaches a maximum value; rotating the translated second plane figure counterclockwise according to the angle delta multiplied by theta, and recording the boundary characteristic point (x) of the rotated second plane figure "2i,y”2i) The straight line boundary segment is l "2i；
Calculating the straight boundary segment l1iAnd a straight boundary segment l "2iThe enclosed area Δ S, i.e., the non-overlapping area of the two straight-sided planar patterns.
Optionally, the graph matching degree value is calculated by the following formula:
where eta is the matching value of two plane figures, S1Is a straight boundary segment l1iArea enclosed, S2Is a straight boundary segment l "2iThe enclosed area, Delta S is a straight boundary section l1iAnd a straight boundary segment l "2iThe area enclosed.
Optionally, after the step of calculating two plane graph matching values η, the method further includes:
the boundary feature point (x) of the second plane figure2i,y2i) Is replaced by (x) "2i,y”2i) Taking half of the original value of d and theta respectively;
re-collecting boundary characteristic points of two straight-edge plane graphs to be matched;
based on the boundary characteristic points again, calculating and obtaining graph transformation parameters after translating and rotating the straight-edge plane graphs by taking the maximum coincidence of the two straight-edge plane graphs to be matched as a target, and further obtaining the non-coincident area of the two straight-edge plane graphs;
until the variation of the matching degree eta of the two plane graphs is smaller than an expected threshold value, the mean value of the eta values calculated for the last two times
I.e. the final matching value of the two plane graphs.
Optionally, the desired threshold for variation of η is 1%.
Optionally, the straight line boundary is formed after a discrete boundary feature point set is identified by a hough transform algorithm.
In a second aspect, the present invention provides a planar graph matching degree evaluation device based on a boundary feature point set, including:
the acquisition unit is used for acquiring boundary characteristic points of two straight-edge plane graphs to be matched;
the calculation unit is used for calculating and obtaining the graph transformation parameters after the translation and rotation of the straight-edge plane graphs by taking the maximum superposition of the two straight-edge plane graphs to be matched as a target based on the boundary characteristic points so as to obtain the non-superposed area of the two straight-edge plane graphs;
and the evaluation unit is used for determining a pattern matching degree value according to the relation between the non-coincident area and the average area of the two straight-edge plane patterns to finish the evaluation of the plane pattern matching degree.
In a third aspect, the invention provides a planar graph matching degree evaluation system based on a boundary feature point set, which comprises a storage medium and a processor;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the method according to any one of the first aspects.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method only adopts the contour information of the plane figure with the straight line boundary for matching, evaluates the figure matching degree by means of a limited number of characteristic points on the straight line boundary of the figure, can exponentially reduce the calculated amount compared with the method of matching by utilizing the whole image information (such as information of pixels, textures and the like), thereby obtaining very high calculating efficiency, and is particularly suitable for application occasions of identifying and classifying sheet metal parts with straight-side contours, surveying and splicing inner space planes and the like.
(2) The method is based on the overall matching principle with the average effect, and does not need to consider the one-to-one correspondence condition between the acquired boundary feature points or key points on the two plane graphs, thereby effectively reducing the influence of individual bad point data in the acquired boundary feature points on the matching result and improving the robustness and the accuracy of the method. In addition, the reference is not needed when the boundary characteristic points of the plane graph are collected, only the relative coordinates of the boundary point sets are obtained, and the method can be applied even if the number of the boundary characteristic points of the two plane graphs is different.
Drawings
In order that the present disclosure may be more readily and clearly understood, reference is now made to the following detailed description of the present disclosure taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flow chart of a plane graph matching degree evaluation method based on a boundary feature point set according to the present invention;
FIG. 2 is a schematic diagram of a first plane graph boundary feature point, a straight line boundary, and an intersection point;
FIG. 3 is a schematic diagram of a second plane graph boundary feature point, a straight line boundary, and an intersection point;
FIG. 4 is a schematic diagram of a first plane graph line boundary equidistant interpolation point-taking;
FIG. 5 is a schematic diagram of a second plane graph line boundary equal-spacing interpolation point-taking;
FIG. 6 is a second plan view translation diagram;
FIG. 7 is a schematic view of the intersection of the first plane pattern isogonic radial line with the straight boundary segment;
FIG. 8 is a schematic diagram of the intersection of the second plane pattern isogonic radial line with the straight boundary segment;
FIG. 9 is d2jAnd d1jA cross-correlation analysis result;
FIG. 10 is a schematic view of a second plane graph of rotated boundary feature points and straight line boundaries;
FIG. 11 l1iAnd l'2iThe enclosed area deltaS is shown schematically.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of the invention.
The following detailed description of the principles of the invention is provided in connection with the accompanying drawings.
Example 1
As shown in fig. 1, the embodiment of the present invention provides a planar graph matching degree evaluation method based on a boundary feature point set, and as shown in fig. 1, the method specifically includes the following steps:
(1) and respectively establishing a rectangular coordinate system in the planes of the two straight-side plane figures to be matched, and extracting the position coordinates of the boundary characteristic points of the two plane figures to be matched. As shown in FIG. 2, the position of the boundary feature point of the first plane figure is expressed as (x)1i,y1i). Where i is from 1 to the total number of boundary feature points 18 of the first plane figure. As shown in FIG. 3, the position of the boundary feature point of the second plane figure is expressed as (x)2i,y2i). Wherein i is from 1 to 20 total number of boundary feature points of the second plane figure.
(2) And recognizing a straight line boundary formed by the boundary discrete point set by utilizing a Hough transform algorithm, and respectively determining the intersection points of adjacent straight line boundaries in the rectangular coordinate system. As shown in FIG. 2, for the first plane graph, the intersection point is denoted as (x)c1i,yc1i). Wherein, i is from 1 to 3 in total number of the intersections of the adjacent straight line boundaries of the first plane figure. As shown in FIG. 3, for the second plane graph, the intersection point is denoted as (x)c2i,yc2i). Wherein i is from 1 to 3 in total of the intersections of the adjacent straight line boundaries of the second plane figure. And sequentially connecting adjacent intersection points to form a straight boundary section. Connecting the straight line boundary segments of the first plane figure end to end in sequence, and recording the straight line boundary segments as l in sequence1iWherein i is from 1 to 3 in total number of straight line boundary segments of the first plane figure. Connecting the straight line boundary segments of the second plane figure end to end in sequence, and recording the straight line boundary segments as l in sequence2iWherein i is from 1 to the total number of straight line boundary segments of the second plane figure 3.
(3) As shown in fig. 4 and 5, for all l1iAnd l2iPerforming equidistant interpolation to obtain points, wherein the distance between the interpolation points is d-32, and obtaining equidistant boundary points (x) of the two plane graphs respectivelyd1k,yd1k) And (x)d2k,yd2k). K is the serial number of the boundary points with equal spacing, and is respectively 1 to the total number N of the boundary points with equal spacing of the two plane graphs d124 and Nd2＝24。
(4) Respectively calculate out
ΔX＝X2-X1＝-6，ΔY＝Y2-Y1＝-5。
(5) The second plane figure is translated as a whole (- Δ X, - Δ Y), i.e., (6, 5). As shown in FIG. 6, the boundary feature point (x ') of the translated second plane figure is recorded'2i,y’2i) And the straight line boundary segment is l'2i。
(6) With (X)1，Y1) The included angle between adjacent equiangular radiation lines is recorded as theta 15 degrees. As shown in FIG. 7, a straight boundary segment l of the equal angle radial line and the first plane figure is obtained1iCross point (x) ofθ1j， yθ1j) Wherein j is from 1 to the total number N of intersections on the straight boundary segment of the first plane figureθ124. Similarly, the set of equiangular radial lines is in line with the straight boundary segment l 'of the second plane pattern'2iThe intersection of (A) and (B) is expressed as (x)θ2j，yθ2j) As shown in fig. 8. Wherein j is from 1 to the total number N of intersections on the straight boundary segment of the second plane figureθ2＝24。
(7) According to the point of intersection (x)θ1j，yθ1j) Straight boundary segment l connected end to end in sequence1iThe above sequence, respectively calculate (x) in turnθ1j， yθ1j) And a center point (X)1，Y1) A distance d between1jClockwise in the positive X-axis direction of the rectangular coordinate system, d11To d124Respectively as follows: 93. 103, 65, 49, 42, 39, 42, 49, 63, 101, 104, 71, 57, 51, 49, 50, 55, 66, 63, 58, 62, 72. Respectively calculating (x) in sequence according to the same direction and sequenceθ2j，yθ2j) And a center point (X)1，Y1) A distance d between2j，d21To d224Respectively as follows: 99. 63, 49, 42, 39, 42, 50, 65, 104, 106, 73, 59, 53, 50, 52, 58, 69, 64, 69, 80, 105. To d2jAnd d1jThe cross-correlation analysis was performed and the results are shown in fig. 9. From fig. 9, the peak abscissa position determines the delay parameter Δ 24. Rotating the translated second plane pattern counterclockwise according to the angle of 360 degrees (the angle error of the two plane patterns is less than 15 degrees, and further reducing the angle to accurately match the two plane patterns), and recording the boundary characteristic point (x) of the rotated second plane pattern as shown in fig. 10 "2i,y”2i) The straight line boundary segment is l "2i。
(8) Respectively calculating the linear boundary segments l1iEnclosed area S1，l”2iEnclosed area S2，l1iAnd l'2iThe enclosed area deltaS (figure 11) and the matching degree of the two plane figures are calculated
(9) The boundary characteristic point (x) of the second plane figure in the step (1)2i,y2i) Is replaced by (x) "2i,y”2i) Respectively taking half of the original value of d and theta, repeating the steps (1) to (8) until the change of the matching degree eta of the two plane graphs is less than an expected threshold value, and calculating the mean value of eta values for the last two times
I.e. the final matching value of the two plane graphs. The expected threshold for the variation of η in this example is 1% and the final match value calculated is 93%.
Example 2
Based on the same inventive concept as embodiment 1, an embodiment of the present invention provides a planar graph matching degree evaluation device based on a boundary feature point set, including:
the acquisition unit is used for acquiring boundary characteristic points of two straight-edge plane graphs to be matched;
the calculation unit is used for calculating and obtaining the graph transformation parameters after the translation and rotation of the straight-edge plane graphs by taking the maximum superposition of the two straight-edge plane graphs to be matched as a target based on the boundary characteristic points so as to obtain the non-superposed area of the two straight-edge plane graphs;
and the evaluation unit is used for determining a pattern matching degree value according to the relation between the non-coincident area and the average area of the two straight-edge plane patterns to finish the evaluation of the plane pattern matching degree.
The rest of the process was the same as in example 1.
Example 3
The embodiment of the invention provides a plane graph matching degree evaluation system based on a boundary characteristic point set, which comprises a storage medium and a processor, wherein the storage medium is used for storing a plurality of plane graph matching degrees;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the method of any of embodiment 1.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A plane graph matching degree evaluation method based on a boundary feature point set is characterized by comprising the following steps:
collecting boundary characteristic points of two straight-edge plane graphs to be matched;
based on the boundary characteristic points, calculating and obtaining graph transformation parameters after translating and rotating the straight-edge plane graphs by taking the maximum coincidence of the two straight-edge plane graphs to be matched as a target, and further obtaining the non-coincident area of the two straight-edge plane graphs;
and determining a pattern matching degree value according to the relation between the misaligned area and the average area of the two straight-edge plane patterns, and finishing the evaluation of the plane pattern matching degree.
2. The planar graph matching degree evaluation method based on the boundary feature point set according to claim 1, wherein the boundary feature point collection method comprises the following steps:
and respectively establishing a rectangular coordinate system in the planes of the two straight-edge plane figures to be matched, and extracting the position coordinates of the boundary characteristic points of the two straight-edge plane figures to be matched.
3. The method for evaluating the matching degree of plane graphics based on the boundary feature point set according to claim 2, wherein the position of the boundary feature point of the first straight-sided plane graphics is marked as (x)1i,y1i) I is the total number of the boundary characteristic points from 1 to the first straight-edge plane figure; the position of the boundary feature point of the second plane figure is expressed as (x)2i,y2i) I is the total number of boundary feature points from 1 to the second straight-sided planar figure.
4. The method for evaluating the matching degree of the plane graphs based on the boundary feature point set according to claim 3, wherein the method for calculating the non-overlapping area of the two straight-edge plane graphs comprises the following steps:
identifying a linear boundary formed by a boundary discrete boundary characteristic point set, respectively determining intersection points of adjacent linear boundaries in a rectangular coordinate system, and sequentially connecting the adjacent intersection points to form a linear boundary section; connecting the straight line boundary segments of the first plane figure end to end in sequence, and recording the straight line boundary segments as l in sequence1iWherein, i is the total number of straight line boundary segments from 1 to the first plane figure; a second plan viewThe linear boundary segments of the shape are connected end to end in sequence and are marked as l in sequence2iWherein, i is the total number of straight line boundary segments from 1 to the second plane figure;
for all l1iAnd l2iPerforming equidistant interpolation point extraction, wherein the distance between the interpolation points is d, and respectively obtaining equidistant boundary points (x) of two straight-edge plane graphsd1k,yd1k) And (x)d2k,yd2k) K is the number of the boundary points with equal spacing, and is respectively 1 to the total number N of the boundary points with equal spacing of the two plane figuresd1And Nd2；
Respectively calculate out
ΔX＝X2-X1，ΔY＝Y2-Y1；
Integrally translating (-DeltaX, -DeltaY) the second straight-sided planar pattern, and recording boundary feature point (X ') of the translated second straight-sided planar pattern'2i,y’2i) And the straight line boundary segment is l'2i；
With (X)1，Y1) Making 0-360 degree equiangular radiation line as the center, recording the included angle of adjacent equiangular radiation lines as theta, obtaining the equiangular radiation line and the straight line boundary section l of the first plane figure1iCross point (x) ofθ1j，yθ1j) Wherein j is from 1 to the total number N of intersections on the straight boundary segment of the first plane figureθ1(ii) a Similarly, the set of equiangular radiation lines is aligned with the linear boundary segment l 'of the second straight-sided planar pattern'2iThe intersection of (A) and (B) is expressed as (x)θ2j，yθ2j) (ii) a Wherein j is from 1 to the total number N of intersections on the straight boundary segment of the second plane figureθ2；
According to the point of intersection (x)θ1j，yθ1j) Straight boundary segment l connected end to end in sequence1iThe above sequence, respectively calculate (x) in a clockwise directionθ1j，yθ1j) And a center point (X)1，Y1) A distance d between1jSequentially calculating (x) in the same direction and orderθ2j，yθ2j) And a center point (X)1，Y1) A distance d between2jTo d is paired2jAnd d1jPerforming cross-correlation analysis to obtain a time delay parameter delta when the cross-correlation function reaches a maximum value; rotating the translated second plane figure counterclockwise according to the angle delta multiplied by theta, and recording the boundary characteristic point (x) of the rotated second plane figure "2i,y”2i) The straight line boundary segment is l "2i(ii) a Calculating the straight boundary segment l1iAnd a straight boundary segment l "2iThe enclosed area Δ S, i.e., the non-overlapping area of the two straight-sided planar patterns.
5. The planar graph matching degree evaluation method based on the boundary feature point set according to claim 4, wherein the graph matching degree value is calculated by the following formula:
where eta is the matching value of two plane figures, S1Is a straight boundary segment l1iArea enclosed, S2Is a straight boundary segment l "2iThe enclosed area, Delta S is a straight boundary section l1iAnd a straight boundary segment l "2iThe area enclosed.
6. The method for evaluating the degree of matching of planar graphs based on a boundary feature point set according to claim 5, further comprising, after the step of calculating the degree of matching η between two planar graphs:
the boundary feature point (x) of the second plane figure2i,y2i) Is replaced by (x) "2i,y”2i) Taking half of the original value of d and theta respectively;
re-collecting boundary characteristic points of two straight-edge plane graphs to be matched;
based on the boundary characteristic points again, calculating and obtaining graph transformation parameters after translating and rotating the straight-edge plane graphs by taking the maximum coincidence of the two straight-edge plane graphs to be matched as a target, and further obtaining the non-coincident area of the two straight-edge plane graphs;
until the variation of the matching degree eta of the two plane graphs is smaller than an expected threshold value, the mean value of the eta values calculated for the last two times
I.e. the final matching value of the two plane graphs.
7. The planar graph matching degree evaluation method based on the boundary feature point set according to claim 6, characterized in that: the desired threshold for variation of said η is 1%.
8. The planar graph matching degree evaluation method based on the boundary feature point set according to claim 4, characterized in that: the straight line boundary is formed by identifying a boundary discrete boundary feature point set through a Hough transform algorithm.
9. A planar graph matching degree evaluation device based on a boundary feature point set is characterized by comprising the following steps:
the acquisition unit is used for acquiring boundary characteristic points of two straight-edge plane graphs to be matched;
the calculation unit is used for calculating and obtaining the graph transformation parameters after the translation and rotation of the straight-edge plane graphs by taking the maximum superposition of the two straight-edge plane graphs to be matched as a target based on the boundary characteristic points so as to obtain the non-superposed area of the two straight-edge plane graphs;
and the evaluation unit is used for determining a pattern matching degree value according to the relation between the non-coincident area and the average area of the two straight-edge plane patterns to finish the evaluation of the plane pattern matching degree.
10. A plane graph matching degree evaluation system based on a boundary feature point set is characterized by comprising a storage medium and a processor;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110686670.3A CN113392913B (en) | 2021-06-21 | 2021-06-21 | Planar graph matching degree evaluation method, device and system based on boundary feature point set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110686670.3A CN113392913B (en) | 2021-06-21 | 2021-06-21 | Planar graph matching degree evaluation method, device and system based on boundary feature point set |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113392913A true CN113392913A (en) | 2021-09-14 |
| CN113392913B CN113392913B (en) | 2023-09-29 |
Family
ID=77623328
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110686670.3A Active CN113392913B (en) | 2021-06-21 | 2021-06-21 | Planar graph matching degree evaluation method, device and system based on boundary feature point set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392913B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4183013A (en) * | 1976-11-29 | 1980-01-08 | Coulter Electronics, Inc. | System for extracting shape features from an image |
| JPH0281186A (en) * | 1988-09-17 | 1990-03-22 | Brother Ind Ltd | Hatching plotting method |
| CN102117412A (en) * | 2009-12-31 | 2011-07-06 | 北大方正集团有限公司 | Method and device for image recognition |
| CN102254179A (en) * | 2010-05-21 | 2011-11-23 | 株式会社其恩斯 | Image processing apparatus, image processing method, and computer program |
| CN103279763A (en) * | 2013-05-25 | 2013-09-04 | 中北大学 | Method for automatically identifying wheel hub types based on structural features |
| CN105205439A (en) * | 2015-02-13 | 2015-12-30 | 比亚迪股份有限公司 | Method for calculating area of fingerprint overlapping region and electronic device |
| US20160012311A1 (en) * | 2014-07-09 | 2016-01-14 | Ditto Labs, Inc. | Systems, methods, and devices for image matching and object recognition in images |
| WO2017076106A1 (en) * | 2015-11-06 | 2017-05-11 | 杭州海康威视数字技术股份有限公司 | Method and device for image splicing |
| US20180188026A1 (en) * | 2016-12-30 | 2018-07-05 | DeepMap Inc. | Visual odometry and pairwise alignment for high definition map creation |
| CN110210565A (en) * | 2019-06-05 | 2019-09-06 | 中科新松有限公司 | Normalized crosscorrelation image template matching implementation method |
| CN110516734A (en) * | 2019-08-23 | 2019-11-29 | 腾讯科技（深圳）有限公司 | A kind of image matching method, device, equipment and storage medium |
| CN110751682A (en) * | 2019-10-28 | 2020-02-04 | 普联技术有限公司 | Method, device, terminal equipment and storage medium for extracting and identifying image |
| CN111553395A (en) * | 2020-04-21 | 2020-08-18 | 江苏航空职业技术学院 | Pose estimation method based on characteristic point combination matching of calibration area |
-
2021
- 2021-06-21 CN CN202110686670.3A patent/CN113392913B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4183013A (en) * | 1976-11-29 | 1980-01-08 | Coulter Electronics, Inc. | System for extracting shape features from an image |
| JPH0281186A (en) * | 1988-09-17 | 1990-03-22 | Brother Ind Ltd | Hatching plotting method |
| CN102117412A (en) * | 2009-12-31 | 2011-07-06 | 北大方正集团有限公司 | Method and device for image recognition |
| CN102254179A (en) * | 2010-05-21 | 2011-11-23 | 株式会社其恩斯 | Image processing apparatus, image processing method, and computer program |
| CN103279763A (en) * | 2013-05-25 | 2013-09-04 | 中北大学 | Method for automatically identifying wheel hub types based on structural features |
| US20160012311A1 (en) * | 2014-07-09 | 2016-01-14 | Ditto Labs, Inc. | Systems, methods, and devices for image matching and object recognition in images |
| CN105205439A (en) * | 2015-02-13 | 2015-12-30 | 比亚迪股份有限公司 | Method for calculating area of fingerprint overlapping region and electronic device |
| WO2017076106A1 (en) * | 2015-11-06 | 2017-05-11 | 杭州海康威视数字技术股份有限公司 | Method and device for image splicing |
| US20180188026A1 (en) * | 2016-12-30 | 2018-07-05 | DeepMap Inc. | Visual odometry and pairwise alignment for high definition map creation |
| CN110210565A (en) * | 2019-06-05 | 2019-09-06 | 中科新松有限公司 | Normalized crosscorrelation image template matching implementation method |
| CN110516734A (en) * | 2019-08-23 | 2019-11-29 | 腾讯科技（深圳）有限公司 | A kind of image matching method, device, equipment and storage medium |
| CN110751682A (en) * | 2019-10-28 | 2020-02-04 | 普联技术有限公司 | Method, device, terminal equipment and storage medium for extracting and identifying image |
| CN111553395A (en) * | 2020-04-21 | 2020-08-18 | 江苏航空职业技术学院 | Pose estimation method based on characteristic point combination matching of calibration area |
Non-Patent Citations (2)
| Title |
|---|
| SHANMING LIN; XIAOYAN ZHU COMPUTER AND INFORMATION ENGINEERING COLLEGE, HOHAI UNIVERSITY, HHU, CHANGZHOU, JIANGSU, CHINA: "A novel registration method that incorporates template matching and mutual information", 《 2009 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION AND LOGISTICS》 * |
| 蔡慧英;朱枫;: "仿射变换下基于凸包和多尺度积分特征的形状匹配方法", 计算机辅助设计与图形学学报, no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113392913B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Aldoma et al. | Multimodal cue integration through hypotheses verification for rgb-d object recognition and 6dof pose estimation | |
| CN109241901B (en) | A kind of detection and recognition methods to the three-dimensional point cloud with hole | |
| CN110287873B (en) | Non-cooperative target pose measurement method and system based on deep neural network and terminal equipment | |
| CN111080684B (en) | Point cloud registration method for point neighborhood scale difference description | |
| CN105740899A (en) | Machine vision image characteristic point detection and matching combination optimization method | |
| CN108830888B (en) | Coarse matching method based on improved multi-scale covariance matrix characteristic descriptor | |
| CN104298990B (en) | A kind of Fast Graphics matching based on skeleton drawing is with knowing method for distinguishing | |
| CN114743259A (en) | Pose estimation method, pose estimation system, terminal, storage medium and application | |
| CN109508709B (en) | Single pointer instrument reading method based on machine vision | |
| CN110930456A (en) | Three-dimensional identification and positioning method of sheet metal part based on PCL point cloud library | |
| CN110222661B (en) | Feature extraction method for moving target identification and tracking | |
| CN110472651B (en) | Target matching and positioning method based on edge point local characteristic value | |
| CN117132630A (en) | Point cloud registration method based on second-order spatial compatibility measurement | |
| CN111507297B (en) | Radar signal identification method and system based on measurement information matrix | |
| CN111199558A (en) | Image matching method based on deep learning | |
| CN111709426B (en) | Diatom recognition method based on contour and texture | |
| CN115797418A (en) | Complex mechanical part measurement point cloud registration method and system based on improved ICP | |
| CN109840529B (en) | Image matching method based on local sensitivity confidence evaluation | |
| Cai | Robust filtering-based thinning algorithm for pattern recognition | |
| CN110793437A (en) | Positioning method and device of manual operator, storage medium and electronic equipment | |
| CN102201060B (en) | Method for tracking and evaluating nonparametric outline based on shape semanteme | |
| CN116823827B (en) | Ore crushing effect evaluation method based on image processing | |
| Zhou et al. | Histograms of Gaussian normal distribution for 3D feature matching in cluttered scenes | |
| CN115147433A (en) | Point cloud registration method | |
| Arora et al. | An algorithm to straighten the bent human chromosomes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |