CN100464347C - Vector graphics identifying method for engineering CAD drawing - Google Patents
Vector graphics identifying method for engineering CAD drawing Download PDFInfo
- Publication number
- CN100464347C CN100464347C CNB2007100379450A CN200710037945A CN100464347C CN 100464347 C CN100464347 C CN 100464347C CN B2007100379450 A CNB2007100379450 A CN B2007100379450A CN 200710037945 A CN200710037945 A CN 200710037945A CN 100464347 C CN100464347 C CN 100464347C
- Authority
- CN
- China
- Prior art keywords
- vector quantization
- image
- axial point
- data
- client
- 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.)
- Active
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
This invention relates to a vectorized idenfication system of CAD engineering blueprints including the following steps: A, applying a self-defined template filtration method based on windowns to eliminate noises of input binary data and verifying them on a platform of the customer end, B, applying an initial vectorized process based on a tilt frame covering domain to initially vectorize the binary image, C, generating a position index list of the initial vectorized data at the server end, D, applying a detection method based on the assumption to identify the vector data, E, integrating all identified results at the server and outputting them to the customer end in the standard DXF file format, which improves result of initial vector to increase the operation rate.
Description
Technical field:
The present invention relates to a kind of vector quantization process of ENGINEERING CAD drawing, particularly a kind of vector quantization pattern recognition method of ENGINEERING CAD drawing, this method can be widely used in fields such as field such as engineering drawing identification, image graphics symbol detection and identification and industrial automation detection.
Background technology:
In current information society,, still have a large amount of drawing informations to preserve, manage and be suitable for the form of papery, picture although cad technique has obtained in the industrial design field using widely.These engineering drawings often make a system or industry long-standing, complete preservation invaluable experience in the past, later design is had good use for reference of planning.Wherein the design that quite a few also can be afterwards and make in be modified and reuse.For multiplexing these drawings, the information of these drawing images is managed with computing machine, and set up corresponding database, the human resources that expend with the renewal that significantly reduces drawing and maintenance, be convenient to storage more, revise, inquire about, exchange, the development trend that is inevitable has important social reality meaning.The engineering drawing vector quantization is the sweep bitmap of engineering drawing to be expressed be converted into the pattern description entity vector that CAD system is used, and as straight line, circle, circular arc, curve and character etc., can improve the multiplexing capacity of drawing greatly.
Complete vector quantization process is divided into two classes substantially, and a kind of is the vector quantization identifying of the pre-service, image binaryzation and the binary map that include image, promptly directly carries out the vectored system of Figure recognition on raster pattern; A kind of is the two-dimensional vector system that comprises the two steps operation of preliminary vector quantization of raster pattern and graph style detection/recognition.Wherein use and comparatively it is desirable to second method, promptly earlier by the vector quantization preprocess method, utilize the output data of preprocessing process to carry out detection and Identification process based on graph style then, this process can obtain comparatively desirable cad file.The preliminary vector quantization process of image includes the preprocessing process of image, the processes such as binaryzation of image equally.The present invention relates to comprise preliminary vector quantization of image and the whole process of discerning based on the test pattern of vector quantization, be called the vector quantization pattern recognition system of ENGINEERING CAD drawing.
The researchist has proposed some relatively effectively algorithms at the image vector processing procedure both at home and abroad, mainly concentrates on the thinking of preliminary vector quantization/identification.Different preliminary vector quantization algorithms are often corresponding to different algorithm for pattern recognitions.Here have according to preliminary vector quantization algorithm classification: based on the method for refinement, based on the method for outline line, based on the method for graphic structure, the method and quadrature zig-zag type (the abbreviating OZZ as) method of discrete pixel tracking.Research at vector quantization all is to carry out under the framework of these methods basically at present, but has noise for image, the method that only has discrete picture to follow the tracks of can obtain reasonable effect, but the method that discrete picture is followed the tracks of has adopted the location index algorithm for fear of the process of full figure search in preliminary vector quantization process, the covering domain that this algorithm obtains can not be mated with former figure fully, can cause results of some mistake vector quantizations.In addition,, therefore mostly still be in conceptual phase, do not form complete system because the vector quantization of ENGINEERING CAD drawing is also had a lot of incomplete places aspect theoretical.The present invention proposes a kind of vector quantization pattern recognition system of ENGINEERING CAD drawing, the validation verification that adds data at the system data input phase, preliminary vector quantization algorithm has adopted the preliminary vector quantization algorithm based on oblique frame covering domain, classification according to figure has formed self-defining class libraries, considers that preliminary vector quantization result's characteristic has adopted a kind of algorithm for pattern recognition based on hypothesis/check.Finally formed one and overlapped the independently vector quantization pattern recognition system of ENGINEERING CAD drawing.
Summary of the invention:
The object of the present invention is to provide a kind of vector quantization pattern recognition method of ENGINEERING CAD drawing, mainly solve above-mentioned existing in prior technology technical matters, it can improve the result of vector quantization identification, improve the arithmetic speed of vector quantization identification, and have advantages such as applied widely, vector quantization accuracy of identification height, fast operation, for significant and practical values of work such as the subsequent treatment of engineering drawing vectorization system and three-dimensional reconstructions.
For solving the problems of the technologies described above, the present invention is achieved in that
A kind of vector quantization pattern recognition method of ENGINEERING CAD drawing is characterized in that it comprises the steps:
A adopts on client platform based on the algorithm of the self-defined template filtering of window input binaryzation data is carried out the image denoising line data checking of going forward side by side;
B adopts on client platform based on the preliminary vector quantization process of oblique frame covering domain binary map is carried out preliminary vector quantization;
C finishes the generation work of the location index table of preliminary vector quantization data at server end;
D has adopted the identifying of having carried out the vector quantization data based on the method for hypothesis/check at server end;
E exports to client at the comprehensive all recognition results of server end with the DXF file layout of standard.
The vector quantization pattern recognition method of described ENGINEERING CAD drawing is characterized in that this steps A further comprises:
The collection of A1 image and input: it is to obtain and send into client or providing image file by memory device obtains and deliver to client by image collecting device scanning; Wherein: image scanning is that the optoelectronic scanning device by image collecting device becomes simulating signal with drawing scanning, through A/D converter analog signal conversion is become data image signal, and this picture signal is sent to client by usb bus;
This client platform of A2 extracts its histogram to some positions of image, the histogram of gray level image provides the distribution situation of gray scale in piece image, this intensity profile information of utilizing histogram to provide is determined threshold value, pixel gray-scale value and this threshold ratio with certain position in the image comes to determine its two-value, 0 or 1 again.
This client platform of A3 adopts the algorithm based on the self-defined template filtering of window that input binaryzation data are carried out Filtering Processing; This self-defined template adopts N * N template, and N is the positive integer more than or equal to 3, each pixel in the data is scanned, and whether be noise spot to differentiate, if noise spot then is the gray-scale value identical with the drawing background with this assignment;
This client of A4 the data detection stage by calculating the counting of sweep trace institute ruler width in length and breadth, add up whether its mean breadth differentiate greater than M pixel, M is the positive integer more than or equal to 3, if greater than M pixel then by checking, otherwise it is unusual to dish out, the display abnormality reason.
The vector quantization pattern recognition method of described ENGINEERING CAD drawing is characterized in that the preliminary vector quantization process based on oblique frame covering domain among this step B further comprises:
The initial trace point of B1 is judged starting point and the directional information to obtain following the tracks of;
B2 tracing process, this tracing process are to adopt the method be similar to zig-zag type to determine the axial point of a certain line segment, comprising three conditions: unique the occupying property of the vector quantization of a axial point; B tracking direction consistance; C width retentivity;
B3 then exports the axial point chain if satisfy three conditions; Otherwise, continue to carry out B2 behind the shortening tracing step.
The vector quantization pattern recognition method of described ENGINEERING CAD drawing is characterized in that the generative process of the location index table among this step C further comprises:
C1 finishes the initialization ode table at server end: when a preliminary vector quantization result's axial point chain need join in the ode table, other is carried out the node record, promptly determine its lined position and border, the left and right sides, form the location index table of this axial point chain of record separately according to predefined lined line width;
C2 finishes the stack of node at server end: the stack ode table is that the ode table that initialization obtains is put in the middle of the overall ode table, wherein will relate to the insertion and the search procedure of ode table.
The vector quantization pattern recognition method of described ENGINEERING CAD drawing is characterized in that the identifying of the vector quantization data among this step D further comprises:
D1 finishes the generation of initial graphics element at server end, promptly suppose process: according to pre-determined certain type graphic element, system is different according to graphic element and axial point chain matching degree, and that axial point chain of selecting to meet most is as graphic element undetermined;
D2 finishes the expansion and the differentiation of graphic element at server end: the axial point chain of the conduct graphic element undetermined that finds according to the hypothesis process, it is carried out the expansion of certain rule, find its adjacent axial point chain, mate with what judgement combined whether can form the pattern classes of making in advance jointly; By continuous iterative process, to form certain figure to greatest extent.
The vector quantization pattern recognition method of described ENGINEERING CAD drawing is characterized in that in this step e that comprehensive recognition result becomes the DXF file layout of standard, has made things convenient for further editing and processing.
By technique scheme, the present invention has following useful technique effect:
Advantages such as that the inventive method is that a kind of vector quantization pattern recognition method of ENGINEERING CAD drawing has is applied widely, vector quantization precision height, fast operation are for significant and practical values of work such as the subsequent treatment of engineering drawing vectorization system and three-dimensional reconstructions.
Description of drawings:
Fig. 1 is the hardware topology structure of client/server that the inventive method adopts.
Fig. 2 is the schematic flow sheet of the inventive method.
Fig. 3 is the actual engineering drawing picture that obtains after the scanning in the embodiment of the invention;
Fig. 4 is through the image after the denoising in the embodiment of the invention;
Fig. 5 is to be that process is based on getting image after the preliminary vectorized process process of oblique frame covering domain in the embodiment of the invention;
Fig. 6 is through proposing the recognition result of number line in the inventive method.
Embodiment:
Below in conjunction with drawings and Examples technical scheme of the present invention is further described.
In the embodiments of the invention, the hardware topology structure of employing client/server as shown in Figure 1.Client can connect image scanner (as: scanner) or hardware storage device, and therefore, the source of image can be to obtain and send into client or providing image file by memory device obtains and deliver to client by image collecting device scanning; Wherein: image scanning is that the optoelectronic scanning device by image collecting device becomes simulating signal with drawing scanning, through A/D converter analog signal conversion is become data image signal, and this picture signal is sent to client by usb bus;
Wherein, the scan function by vectored system starts scanning sequence drawing is scanned, and the image after the scanning as shown in Figure 3.After the scanning through the vector quantization preprocessing process of client PC, draw image as shown in Figure 6, this image is the very high method for expressing of a kind of compressibility, be convenient to transmit in network, the data that server end receives behind the preliminary vector quantization are carried out such as the subsequent treatment such as identification that generate location index table and vector quantization figure.
Image collecting device in the present embodiment adopts the scanner of the KV-S3065CWCN of Panasonic model, and its performance is as follows:
Scanning element: CIS;
Kind of design: file scanner;
Sweep limit: 227 * 2540mm;
Optical resolution: 600 * 600;
Color figure place: black and white (two-value, shadow tone pattern), gray scale (8bit), colored (24bit);
Sweep velocity: 60ppm/110ipm;
Transmission interface: Ultra SCSI (SCSI-III) transfer rate: 20M-byte/sec, interface unit: 50 fine needles, USB2.0;
Scanned medium: file;
Light source performance: two-tube white fluorescent lamp.
Client platform performance in the present embodiment is as follows:
CPU frequency: Celon 2.66G;
Memory size: 516M;
The operation system is Windows XP;
A parallel print.er port is configured to USB port.
Server in the present embodiment adopts the ProLiant DL380 G4 (378735-AAl) of HP, and its performance is as follows:
Cpu type: Xeon DP;
Cpu frequency (MHz): 3000;
Processor is described: standard processor quantity 1;
Support the CPU number: 2;
CPU L2 cache: 2MB;
The operation system is Windows 2003 Server.
The vector quantization identification process of the two-dimentional ENGINEERING CAD drawing that adopts at client end/server end as shown in Figure 2, the detail of each step is described below:
1, based on the filtering method of self-defined window image is removed the noise processed line data checking of going forward side by side in customer end adopted:
Employing is removed image based on the filtering method of self-defined window before the processing of noise, at first will scan to obtain digitized image file drawing file, and this digitized image file also can read from memory device.The image scanning process at first scans drawing and obtains simulating signal through the optoelectronic scanning chip, then simulating signal is converted to the digitized image file through the A/D conversion chip, is sent to client platform through the USB output interface at last.
What deliver to client is the gray scale numeral engineering drawing picture of a two dimension, needing through the binary conversion treatment process is bianry image with greyscale image transitions, this process is carried out at client platform, by CPU and internal memory co-ordination to finish binaryzation work to image.At first its histogram is extracted at some positions of image, the information of utilizing histogram to provide is determined threshold value; Secondly pixel gray-scale value and this threshold ratio with certain position in the image comes to determine its two-value, 0 or 1; By being carried out above-mentioned processing, each part of image can obtain binary image at last.
After obtaining bianry image, in bianry image, can there be the pollution of a lot of noises, as shown in Figure 3.These noises can have influence on the initialization vector process and the identifying of back, are necessary to add after binary conversion treatment the processing procedure of removing noise.At this, the present invention carries out Filtering Processing at the algorithm that client has added based on the self-defined template filtering of window to input binaryzation data.Self-defined template adopts N * N template, and N is the positive integer more than or equal to 3, each pixel in the view data is scanned, to judge whether being noise spot.When certain position pixel with and the gray-scale value sum of on every side pixel only be 1, and the grey scale pixel value of this current location is 1, concludes that then this point is noise spot certainly, with its removal.The method of removing noise spot is that the gray-scale value assignment with this point is 0.Image after the denoising as shown in Figure 4.
This client the data detection stage by calculating the counting of sweep trace institute ruler width in length and breadth, pass through the width that draws is called and passes through width at every turn, add up whether its mean breadth differentiate greater than M pixel, M is the positive integer more than or equal to 3, if greater than M pixel then by checking, otherwise it is unusual to dish out, the display abnormality reason, prompting user's " the scanner performance deficiency please adopt other scanning device retries ".In implementation process, get M=3 usually, its meaning is to guarantee that the width of line of CAD drawing is more than or equal to three pixels, so that follow-up preliminary vector quantization process is stable.Here it is noted that sweep trace might just in time vertically pass through straight line, then draw to pass through width very big, we claim that this numerical value is the wild value of width.In order to address this problem, remove the wild value of width, we at first are provided with a predefined breadth extreme.When sweep length during greater than breadth extreme, be defaulted as the wild value of width, when the statistical average width, do not calculate this value.
2, based on the preliminary vector quantization process of oblique frame covering domain binary map is carried out preliminary vector quantization in customer end adopted:
Employing is carried out on client platform based on the preliminary vector quantization process of oblique frame covering domain, and it is to the improvement based on discrete pixel tracking vector method.As shown in the figure: this vector quantization process has comprised operations such as initial trace point judgement, tracing process and intersection point recovery.Initial trace point is judged starting point and the directional information to obtain following the tracks of; Tracing process is to adopt the method that is similar to zig-zag type to determine the axial point of a certain line segment, comprising three conditions, wherein unique the occupying property of the vector quantization of axial point is to utilize the method for oblique frame covering domain to obtain, and two other condition is respectively tracking direction consistance and width retentivity; The intersection point recovery is to realize by the process with tracing process associating iteration.This process is the core of whole vector quantization preprocessing process, and it is obtaining under the higher precision prerequisite, and arithmetic speed is considerably beyond based on discrete pixel tracking vector method.
The judgement of initialization axial point is to carry out on to the basis of image scanning, when a sweep trace ' bumps ' first pixel positive transition (from 0 to 1), the pixel counter begins counting, when running into the negative saltus step (from 1 to 0) of pixel once more, stop counting, the interim axial point that pixel location in the middle of calculating is differentiated as first initialization, adopt the downward scanning and counting that makes progress that uses the same method from this pixel then, calculate the axial point of the center of up-and-down boundary as second initialization differentiation, then about scanning, differ less than two pixels up to double pixel location by that analogy, it is made as stable extendible initialization axial point, if interim longitudinally axial point, then tracking direction is made as vertically, otherwise be made as laterally, direction and initialization axial point differentiated the output of process as axial point.The initialization axial point is differentiated end.
Carry out tracing process: tracing process begins to follow the tracks of with the initialization axial point, and its process is similar substantially with initialization axial point differentiation process, but it follows the tracks of on direction initialization, is made as the axial point width perpendicular to the tracking results of tracking direction.Carry out tracing process with predefined tracing step, because pixel width is very little, the tracing step here is made as 4 pixels, and actual tracing step is called dynamic step length.Carry out tracing process and need satisfy three conditions:
(1) direction consistance, the ratio of its width of the axial point that collects and dynamic tracking step-length are stabilized in greater than 1 or less than on 1.Otherwise carrying out intersection point restores.
(2) width consistance is meant that the axial point wide variety rate of being gathered remains in 50%.
(3) unique the occupying property of the vector quantization of axial point: an axial point can not be in these vector quantization lines simultaneously, is in again in the another one vector quantization lines, promptly can not be simultaneously as the axial point of two or more vector quantization lines.This especially should be noted that in the process process of carrying out.Adopted the method for location index based on the vectorization method of discrete pixel tracking, be that value with some vector quantization lines covers on the tool lined line at regular intervals, this lined line finally constitutes node one by one, the left and right sides boundary representation of node the covering domain of certain vector quantization lines.Carry out the axial point that tracing process finds afterwards and can not drop within this covering domain, restore otherwise carry out intersection point.Utilize contiguous two axial point and their dynamic width to determine an oblique frame among the present invention, utilize oblique frame to determine this covering domain, this can obtain more accurate covering domain, has avoided the leakage vector quantization phenomenon and the too small mistake vector quantization phenomenon that causes of covering domain that cause owing to covering domain is excessive.
Intersection point restores: it is a kind of operation that tracing step is shortened of carrying out under the ungratified situation of tracking condition that intersection point restores, and then carries out tracing process.This can obtain reasonable vector quantization effect in the place of line segment and line segment intersection, as shown in Figure 5.
3. generate location index at server end:
The location index table is made up of the node chain of delegation of delegation, and the node chain is another node of one composition.It is capable that node has write down the address of axial point chain and border, the left and right sides and place node.Each axial point chain has write down each axial point chain position in two-dimensional space all by the node of different rows institute index like this, as its name suggests, is referred to as location index.This process institute primary study be the generative process of location index, the generative process of location index has comprised the initialization of ode table and the additive process of node.In addition because the node of location index has write down the address information of axial point chain, therefore after the preliminary vector quantization of client is finished, if carried out the generative process of location index, then can in the long-distance transmissions process, lose the address information of axial point chain, the perhaps skew of this address information generation, can't correct indexing in follow-up use, therefore need carry out the generation work of axial point chain location index at server end.
Finish the initialization ode table at server end:, at first generate the location index table of an interim sky for the axial point chain is joined in the location index table.The lined line of location index table with the axial point chain horizontal be divided into some five equilibriums, consider the width information that lined line itself should have, then can define the border, the left and right sides of a node according to lined line intersection location and lined line width information, thereby generate a series of nodes of this axial point chain of record, then a location index table interim, the single axial point chain of record has generated.
Finish the stack of node at server end: after single location index table generates, it must be joined in the location index table of ultimate demand generation.Temporary position concordance list and finally generate and do not have essential distinction between the concordance list only is the axial point chain difference that is write down.The temporary position concordance list has write down the information of single axial point chain and the final location index table that generates is the information that has write down all axial point chains.Join at interim concordance list and to relate to a step overlap-add operation in the final concordance list, overlap-add operation is to carry out one by one according to the node in the interim concordance list.Find a node in the interim concordance list earlier, the border, the left and right sides of the node of correspondence position compares in the border, the left and right sides of this node and the final concordance list, with cutting and the retouching operation of finishing the respective nodes in the final concordance list.After the node in all interim concordance lists is all finished with final concordance list coupling, then can generate the intermediate result of a final concordance list, wait the overlap-add operation of the interim concordance list of next bar axial point chain, up to finishing.
4. finish the vector quantization identifying at server end:
Finish the generation of initial graphics element at server end, promptly suppose process: according to pre-determined certain type graphic element, system is different according to graphic element and axial point chain matching degree, and that axial point chain of selecting to meet most is as graphic element undetermined.The embodiment of the invention is according to the pairing axial point chain of straight line two end points of needs only, find have two end points and its length breadth ratio greater than that axial point chain of some numerical value as initial rectilinear figure element undetermined.
Finish the expansion and the differentiation of graphic element at server end: according to the left and right sides end points of hypothesis element, extend expansion to both sides, find those elements adjacent thereto (being called candidate's element) and basis and the distance of original hypothesis element to sort, mate with this.Coupling is considered from three aspects:
1) width consistance: suppose that promptly element should have identical or similar width with the coupling element, think under the general feelings money that width should be uniform on the straight line.
2) collinearity checking: suppose that promptly another end points of element links to each other with that end points of the distant place of candidate's element, the slope that obtains is consistent or is consistent substantially with the slope of previous hypothesis element.
3) proximity verification: promptly suppose between element and the candidate's element it is enough approaching.But in actual conditions, after intersecting, two straight lines can produce four straight lines.Straight line has often been become two parts by difference, we can couple together the line segment of these two sections parts in expectation, but in the middle of the axial point chain, the part that separates often distance is very big, adopts the method for a gray scale calculation block to calculate that the picture element density in binary map decides two elements whether enough approaching between two sections line segments here.When the degree of approach is big, two straight lines are connected to become straight line.Here it will be noted that this straight line is the entity that has write down two axial point chains, in data structure of the present invention, be defined as father's node of axial point chain, and the axial point chain is the child node of this father's node.
After finishing whole vector quantization identification, can form the data structure of some tree structures, its summit node has been represented entity attribute, as straight line or circular arc etc., the node of the bottom has write down the axial point chain.Be illustrated in figure 6 as Straight Line Identification result afterwards, omitted width information wherein.The identifying of above-mentioned straight line only is that the vector quantization of whole ENGINEERING CAD drawing is discerned a kind of of graphic element, for other graphic elements, identification as circular arc, dotted line, imaginary circle arc, dot-and-dash line etc. also can be undertaken by above-mentioned method, difference between them only is the difference of some identification coefficients, as expanded-angle, expansion spacing etc.
Being preferred embodiment of the present invention only in sum, is not to be used for limiting practical range of the present invention.Be that all equivalences of doing according to the content of the present patent application claim change and modification, all should be technology category of the present invention.
Claims (5)
1. the vector quantization pattern recognition method of an ENGINEERING CAD drawing is characterized in that it comprises the steps:
A adopts on client platform based on the algorithm of the self-defined template filtering of window input binaryzation data is carried out the image denoising line data checking of going forward side by side;
B adopts on client platform based on the preliminary vector quantization process of oblique frame covering domain binary map is carried out preliminary vector quantization;
C finishes the generation work of the location index table of preliminary vector quantization data at server end;
D has adopted the identifying of having carried out the vector quantization data based on the method for hypothesis/check at server end;
E exports to client at the comprehensive all recognition results of server end with the DXF file layout of standard.
2. the vector quantization pattern recognition method of ENGINEERING CAD drawing according to claim 1 is characterized in that this steps A further comprises:
The collection of A1 image and input: it is to obtain and send into client or providing image file by memory device obtains and deliver to client by image collecting device scanning; Wherein: image scanning is that the optoelectronic scanning device by image collecting device becomes simulating signal with drawing scanning, through A/D converter analog signal conversion is become data image signal, and this picture signal is sent to client by usb bus;
This client platform of A2 extracts its histogram to some positions of image, the histogram of gray level image provides the distribution situation of gray scale in piece image, this intensity profile information of utilizing histogram to provide is determined threshold value, pixel gray-scale value and this threshold ratio with certain position in the image comes to determine its two-value, 0 or 1 again;
This client platform of A3 adopts the algorithm based on the self-defined template filtering of window that input binaryzation data are carried out Filtering Processing; This self-defined template adopts N * N template, and N is the positive integer more than or equal to 3, each pixel in the data is scanned, and whether be noise spot to differentiate, if noise spot then is the gray-scale value identical with the drawing background with this assignment;
This client of A4 the data detection stage by calculating the counting of sweep trace institute ruler width in length and breadth, add up whether its mean breadth differentiate greater than M pixel, M is the positive integer more than or equal to 3, if greater than M pixel then by checking, otherwise it is unusual to dish out, the display abnormality reason.
3. the vector quantization pattern recognition method of ENGINEERING CAD drawing according to claim 1 is characterized in that the preliminary vector quantization process based on oblique frame covering domain among this step B further comprises:
The initial trace point of B1 is judged starting point and the directional information to obtain following the tracks of;
B2 tracing process, this tracing process are to adopt the method for zig-zag type to determine the axial point of a certain line segment, comprising three conditions: unique the occupying property of the vector quantization of a axial point; B tracking direction consistance; C width retentivity;
B3 then exports the axial point chain if satisfy three conditions; Otherwise, continue to carry out B2 behind the shortening tracing step.
4. the vector quantization pattern recognition method of ENGINEERING CAD drawing according to claim 1 is characterized in that the generative process of the location index table among this step C further comprises:
C1 finishes the initialization ode table at server end: when a preliminary vector quantization result's axial point chain need join in the ode table, other is carried out the node record, promptly determine its lined position and border, the left and right sides, form the location index table of this axial point chain of record separately according to predefined lined line width;
C2 finishes the stack of node at server end: the stack ode table is that the ode table that initialization obtains is put in the middle of the overall ode table, wherein will relate to the insertion and the search procedure of ode table.
5. the vector quantization pattern recognition method of ENGINEERING CAD drawing according to claim 1 is characterized in that the identifying of the vector quantization data among this step D further comprises:
D1 finishes the generation of initial graphics element at server end, promptly suppose process: according to pre-determined certain type graphic element, system is different according to graphic element and axial point chain matching degree, and that axial point chain of selecting to meet most is as graphic element undetermined;
D2 finishes the expansion and the differentiation of graphic element at server end: the axial point chain of the conduct graphic element undetermined that finds according to the hypothesis process, it is carried out the expansion of certain rule, find its adjacent axial point chain, mate with what judgement combined whether can form the pattern classes of making in advance jointly; By continuous iterative process, to form certain figure to greatest extent.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100379450A CN100464347C (en) | 2007-03-09 | 2007-03-09 | Vector graphics identifying method for engineering CAD drawing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100379450A CN100464347C (en) | 2007-03-09 | 2007-03-09 | Vector graphics identifying method for engineering CAD drawing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101021902A CN101021902A (en) | 2007-08-22 |
| CN100464347C true CN100464347C (en) | 2009-02-25 |
Family
ID=38709661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2007100379450A Active CN100464347C (en) | 2007-03-09 | 2007-03-09 | Vector graphics identifying method for engineering CAD drawing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100464347C (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101673347B (en) * | 2008-09-12 | 2011-07-20 | 纬衡浩建科技（深圳）有限公司 | Spitting method of electronic drawing file |
| JP4772888B2 (en) * | 2009-03-27 | 2011-09-14 | シャープ株式会社 | Image processing apparatus, image forming apparatus, image processing method, program, and recording medium thereof |
| CN101763510B (en) * | 2010-01-21 | 2012-10-17 | 上海电力学院 | Staggered line vectorization extraction and graph recognition method |
| CN101980200B (en) * | 2010-11-03 | 2013-09-04 | 东莞市高鑫机电科技服务有限公司 | Method and system for constructing Chinese element engineering database and application thereof in field of industrial design |
| CN102096102B (en) * | 2010-11-30 | 2013-01-09 | 中国石油集团川庆钻探工程有限公司 | Digital modeling method for seismic exploration |
| CN102096104B (en) * | 2010-12-10 | 2012-11-21 | 中国石油集团川庆钻探工程有限公司 | Seismic paper section interpretation horizon rapid digitalization method |
| CN102609687B (en) * | 2012-01-31 | 2013-03-13 | 华中科技大学 | Subway construction drawing and engineering parameter automatic identification method |
| CN103903287B (en) * | 2012-12-27 | 2016-10-05 | 中国移动通信集团设计院有限公司 | The generation method and device of building building CAD diagram shape |
| CN105302930B (en) * | 2014-06-30 | 2018-11-30 | 上海神机软件有限公司 | Engineering drawing management system and method, row's modular system and method based on beam in length and breadth |
| CN105302931B (en) * | 2014-06-30 | 2019-01-04 | 上海神机软件有限公司 | Construction project drawing identifying system and method, row's modular system and method |
| CN105205198B (en) * | 2014-06-30 | 2019-01-29 | 上海神机软件有限公司 | Construction project gang form fully-automatic intelligent integrally arranges modular system and method |
| CN105956147B (en) * | 2016-05-13 | 2019-08-27 | 广西骋天信息科技有限公司 | A kind of method and system according to drawing creation budget table |
| CN105847628A (en) * | 2016-05-20 | 2016-08-10 | 深圳市众力达机械有限公司 | Full-automatic digital scanner |
| CN106250932A (en) * | 2016-08-04 | 2016-12-21 | 上海华虹宏力半导体制造有限公司 | A kind of method and device of scanogram identification |
| CN108846398B (en) * | 2018-06-26 | 2021-09-07 | 北京天工矩阵信息技术有限公司 | CAD graph recognition method and device |
| CN111462258B (en) * | 2020-03-31 | 2023-09-15 | 上海大学 | Texture line image vectorization method and system for manufacturing printing film |
| CN111611936B (en) * | 2020-05-22 | 2021-05-14 | 青矩技术股份有限公司 | Automatic identification system for similar vector diagrams in CAD drawings |
| CN112325080A (en) * | 2020-11-16 | 2021-02-05 | 奥士康科技股份有限公司 | Automatic marking method for MI drawing |
| CN112613088B (en) * | 2020-12-18 | 2023-10-27 | 湖南特能博世科技有限公司 | Pattern recognition method, pattern recognition device and computer equipment |
| CN113158999B (en) * | 2021-05-26 | 2024-04-02 | 南京云阶电力科技有限公司 | Terminal jumper wire identification method and device in electrical design drawing based on template matching |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1333511A (en) * | 2000-07-14 | 2002-01-30 | 纬衡知识产权有限公司 | Raster image vector quantized computer automatic processing method |
| CN1416099A (en) * | 2002-12-05 | 2003-05-07 | 上海交通大学 | Method for fast preparing vector map of house through man-machine interactive |
| CN1581224A (en) * | 2004-05-17 | 2005-02-16 | 上海交通大学 | Vectorialization method of binary-state grating image |
-
2007
- 2007-03-09 CN CNB2007100379450A patent/CN100464347C/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1333511A (en) * | 2000-07-14 | 2002-01-30 | 纬衡知识产权有限公司 | Raster image vector quantized computer automatic processing method |
| CN1416099A (en) * | 2002-12-05 | 2003-05-07 | 上海交通大学 | Method for fast preparing vector map of house through man-machine interactive |
| CN1581224A (en) * | 2004-05-17 | 2005-02-16 | 上海交通大学 | Vectorialization method of binary-state grating image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101021902A (en) | 2007-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100464347C (en) | Vector graphics identifying method for engineering CAD drawing | |
| Liu et al. | Strokeaggregator: Consolidating raw sketches into artist-intended curve drawings | |
| CN110659644B (en) | Automatic extraction method for strokes of calligraphy single characters | |
| CN105528614A (en) | Cartoon image layout recognition method and automatic recognition system | |
| CN107031033B (en) | It is a kind of can 3D printing hollow out two dimensional code model generating method and system | |
| CN104346390B (en) | A kind of method and device for forming character library | |
| CN110766697B (en) | Method and device for identifying graphical interface control image of interface sketch | |
| CN101763510B (en) | Staggered line vectorization extraction and graph recognition method | |
| CN101840582B (en) | Boundary digitizing method of cadastral plot | |
| CN102880868A (en) | Engineering drawing vector conversion and primitive semantic extraction method | |
| Joseph | Processing of engineering line drawings for automatic input to CAD | |
| CN114693851A (en) | Real-time grid contour vectorization and rendering system based on GPU | |
| CN100555310C (en) | A kind of preprocess method of engineering drawing vectorization recognition system | |
| JPH07220090A (en) | Object recognition method | |
| Fan et al. | A run-length-coding-based approach to stroke extraction of Chinese characters | |
| Ablameyko | An introduction to interpretation of graphic images | |
| Tang et al. | Automatic structural scene digitalization | |
| CN116452826A (en) | Coal gangue contour estimation method based on machine vision under shielding condition | |
| CN111179289A (en) | Image segmentation method suitable for webpage length and width images | |
| JP2023164318A (en) | Scalable approach to converting images to sketches | |
| CN116541912A (en) | Method and device for generating wiring diagram based on CAD image recognition | |
| CN106023105A (en) | Binary image generation method and system for plant leaves | |
| CN100483448C (en) | Multiple linewidth self-adapting preliminary vectorization method in vectorization process of engineering drawing | |
| Potts et al. | A topological graph-based representation for denoising low quality binary images | |
| Ji et al. | Rapid dataset generation methods for stacked construction solid waste based on machine vision and deep learning |
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 |