CN110375645A - A kind of method and apparatus of character size detection - Google Patents
A kind of method and apparatus of character size detection Download PDFInfo
- Publication number
- CN110375645A CN110375645A CN201910600777.4A CN201910600777A CN110375645A CN 110375645 A CN110375645 A CN 110375645A CN 201910600777 A CN201910600777 A CN 201910600777A CN 110375645 A CN110375645 A CN 110375645A
- Authority
- CN
- China
- Prior art keywords
- character
- curve
- guide rail
- size detection
- contour curve
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/22—Measuring arrangements characterised by the use of optical techniques for measuring depth
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
- G01B11/2433—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures for measuring outlines by shadow casting
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of method and apparatus of character size detection, and the method for the present invention includes the following steps: obtaining the 3D outline data for carving code character surface；The data of geometric jacquard patterning unit surface where calculating character in outline data；The point cloud data for beating symbol of carving characters with depth or elevation information is extracted from outline data；Single character is extracted, the geometric dimension of each character is counted；Export result.The inventive system comprises 3D profile measurement unit, guide rail, guide rail fixed cell pedestal, motor, electric-motor drive unit, displacement sensor and processing units；The present invention is by carrying out full-automatic detection to depth or height, character boundary, the adjacent character spacing of carving code character, motor vehicle VIN code in motor vehicle manufacture and inspection field can be reduced, the artificial detection cost of motor number etc., detection accuracy and detection efficiency are improved, it is significant to the detection automation for promoting the sector.
Description
Technical field
The present invention relates to character size detection technique fields, more particularly to the method and dress of a kind of detection of character size
It sets.
Background technique
Traditional motor vehicle VIN code and motor number detection are measured mainly by artificial visual with dial gauge and ruler.Allusion quotation
Type, many vehicle enterprises detect the depth of VIN code and motor number using the dial gauge with probe.Since the tip of probe has
There is certain thickness, itself cannot detect the depth of character gully details, and artificially pressing strength can also seriously affect detection
Result.In short, there are high labor costs for this traditional detection method, inefficiency, quantified precision is poor, and there are subjectivities, holds
The problems such as easily slipping.It is substantially still manually to grasp although there is a small amount of invention to carry out certain technological improvement to this problem
Make, average detected one is carved the time that code needs a few minutes, is taken time and effort, is not changed this status fundamentally.With vapour
The increase of vehicle ownership and sales volume, the workload of automotive manufacturers and annual test mechanism detection VIN code and motor number
It increases sharply, traditional manual detection mode does not adapt to need of work.
Summary of the invention
To solve problems of the prior art, the present invention provides a kind of character size detection method and apparatus,
The present invention can be dropped by carrying out full-automatic detection to depth or height, character boundary, the adjacent character spacing of carving code character
Motor vehicle VIN code in low motor vehicle manufacture and inspection field, the artificial detection cost of motor number etc. improve detection accuracy and inspection
Efficiency is surveyed, it is significant to the detection automation for promoting the sector.
To achieve the above object, the present invention adopts the following technical scheme:
A kind of method and apparatus of character size detection, comprising the following steps:
S1, the 3D outline data for carving code character surface is obtained；
The data of S2, geometric jacquard patterning unit surface where calculating character in outline data；
S3, the point cloud data for beating symbol of carving characters with depth or elevation information is extracted from outline data；
S4, single character is extracted, counts the geometric dimension of each character；
S5, output result.
Preferably, the step S2 is further comprising the steps of:
S21, polynomial fitting curve model is established to each contour curve；
S22, pass through weighted polynomial curve fitting algorithm or RANSAC algorithm, the polynomial fitting for solving contour curve is bent
Line parameter model；
The multinomial contour curve parameter that S23, output are fitted.
Preferably, in the step S22, the fitting for solving contour curve using weighted polynomial curve fitting algorithm is multinomial
Formula parameter of curve model the following steps are included:
S2221, smooth, removal certain noise and abnormal point are carried out to contour curve；
S2222, polynomial curve fitting；
The quantity of the left point on fitting contour curve is fallen on S2223, statistics original contour curve；
Whether the quantity for the left point that S2224, judgement are fallen on fitting contour curve reaches maximum, if so, entering step
S2226, if it is not, entering step S2225；
S2225, removal fall in the point of fitting wheel hub extra curvature, return step S2222；
The multinomial contour curve parameter that S2226, output are fitted.
Preferably, the step S3 is further comprising the steps of:
Distance of each point to the contour curve polynomial fitting curve on S31, calculating scanning profile curve；
S32, convex and concave feature and character predetermined depth/altitude range according to character, filter out character point cloud data；
S33, output character point cloud data.
Preferably, further comprising the steps of between the step S32 and S33:
S321, judge whether character surface is curved surface, if so, S322 is entered step, if it is not, entering step S33；
S322, the character point cloud coordinate on curved surface is converted into the character point cloud data in plane.
Preferably, the step S4 the following steps are included:
S41, binary conversion treatment is done to point cloud data, generate binaryzation character picture；
S42, sciagraphy or character recognition algorithm are used to binaryzation character picture, extracts character, counts each character
Geometric dimension.
Preferably, further comprising the steps of after the step S41:
S411, connected domain calculating is carried out to binaryzation character picture, removes isolated point and small area connected domain.
Preferably, the sciagraphy in the step S42 the following steps are included:
S421, the binary image of affiliated character is projected respectively along x-axis and y-axis, i.e., the picture of cumulative binary image
Element value, obtains 2 width projected images；
S422, with thresholding method each character is calculated along the boundary of x-axis and y-axis in affiliated 2 width projected image.
Preferably, the geometric dimension of each character is counted in the step S42 the following steps are included:
S423, the x-axis according to the obtained character of step S422 and y-axis boundary, obtain the boundary rectangle of the character；
S424, between being calculated between the size dimension and adjacent character of the character according to the boundary rectangle of each character
Away from；
S425, in the boundary rectangle of character, according to step S3 obtain character point cloud data, count the depth of the character
Or altitude information.
A kind of device of character size detection, including 3D profile measurement unit, guide rail, guide rail fixed cell pedestal, motor,
Electric-motor drive unit, displacement sensor and processing unit；The guide rail is mounted on guide rail fixed cell pedestal, the 3D profile
Measuring unit is mounted on guide rail and can move under the drive of the motor along guide rail, 3D described in the displacement sensor
The displacement that profile measurement unit is moved along guide rail, and set every one spacing distance of movement of guide rail and just trigger the progress of 3D contourgraph
Configuration sampling, the processing unit receive the outline data result that 3D profile measurement unit issues and carry out to outline data
Processing.
Beneficial effect is:
1, the present invention is full-automatic by carrying out to depth or height, character boundary, the adjacent character spacing of carving code character
Detection can reduce the artificial detection cost of motor vehicle VIN code, motor number etc. in motor vehicle manufacture and inspection field, improve
Detection accuracy and detection efficiency, it is significant to the detection automation for promoting the sector；
2, include the information of geometric jacquard patterning unit surface where character and the geological information of character in 3D scanning gained outline data.It mentions
The geometric data for taking character needs the data of the first geometric jacquard patterning unit surface where extracting character in the outline data.For this purpose, this
The measure that inventive method is taken includes: to establish polynomial fitting curve model to each contour curve, to represent the curve
Corresponding contour surface shape can accurately obtain the geometric data of character in this way；
3, when being handled by weighted polynomial, noise and abnormal point are eliminated, it is as a result more acurrate；
4, according to the convex and concave feature of character and character predetermined depth/altitude range, character point cloud data is filtered out, this is passed through
Kind mode, can accurately filter out character point cloud data；
5, in general, VIN code and motor number are beaten and be engraved on even curface；In order to increase the applicable model of the method for the present invention
It encloses, it is assumed that character, which is also possible to beat, is engraved in curved surface, and proposes the processing mode for character surface for curved surface, further
Improve practicability of the invention；
6, by binary conversion treatment and sciagraphy or character recognition algorithm, more accurately point cloud data can be known
It does not count；
7, removal isolated point and small area connected domain are calculated by connected domain, can be improved recognition accuracy；
8, the geometric dimension obtained using sciagraphy of the invention is more accurate；
9, using the geometric dimension statistical method of character of the invention, size dimension, the phase of character can accurately be obtained
The depth or height of spacing, character between adjacent character.
10, the device of the invention full-automatic can detect motor vehicle VIN code, motor number etc., improve inspection
Survey precision and detection efficiency.
Detailed description of the invention
Fig. 1 is the implementation process diagram of method of the present invention；
Fig. 2 is the schematic diagram that the present invention extracts contour curve model parameter method；
Fig. 3 is the schematic diagram of weighted polynomial curve fitting algorithm of the present invention；
Fig. 4 is that the present invention extracts the schematic diagram for beating the point cloud data for symbol of carving characters；
Fig. 5 is the schematic diagram that the character point of the present invention by curved surface expands into character point coordinate in plane；
Fig. 6 is that character of the present invention extracts and recognizer flow chart；
Fig. 7 is the schematic diagram that sciagraphy of the present invention divides character zone；
Fig. 8 is that character boundary, distance computation illustrate schematic diagram；
Fig. 9 is the structural schematic diagram of device of the present invention.
Appended drawing reference:
10, guide rail mounting seat；20,3D profile measurement unit；30, displacement sensor；40, guide rail；50, motor.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings:
Embodiment:
As shown in Figure 1, a kind of method of character size detection, comprising the following steps:
S1, the 3D outline data for carving code character surface is obtained；
The data of S2, geometric jacquard patterning unit surface where calculating character in outline data；
S3, the point cloud data for beating symbol of carving characters with depth or elevation information is extracted from outline data；
S4, single character is extracted, counts the geometric dimension of each character, while checking adjacent character spacing；
S5, examining report is generated, exports result.
Obtain the method for carving the 3D outline data on code character surface, comprising: line laser contourgraph is used, at interval of certain micro-
Small distance triggers one-shot measurement, obtains the 3D contour curve of Current Scan, and continuous scanning character surface obtains the 3D on character surface
Outline data.Typically, at interval of 0.1mm or so, Zaser contourgraph is allowed to sample a character outline, the survey of available satisfaction
Measure result.
The present invention is by carrying out full-automatic inspection to depth or height, character boundary, the adjacent character spacing of carving code character
It surveys, the artificial detection cost of motor vehicle VIN code, motor number etc. in motor vehicle manufacture and inspection field can be reduced, improve inspection
Precision and detection efficiency are surveyed, it is significant to the detection automation for promoting the sector.
As shown in figure 9, a kind of device of character size detection, including 3D profile measurement unit 20, guide rail 40, guide rail are fixed
Unit base 10, motor 50, electric-motor drive unit, displacement sensor 30, processing unit and result reporting unit；Guide rail 40 is installed
On guide rail fixed cell pedestal 10,3D profile measurement unit 20 is mounted on guide rail 40 and can edge under the driving of motor 50
Guide rail 40 it is mobile, displacement sensor 30 measures the displacement that 3D profile measurement unit 20 is moved along guide rail 40, and sets and lead
Every one spacing distance of movement of rail 40 just triggers 3D profile measurement unit 20 and carries out a configuration sampling, and processing unit receives 3D profile
The outline data result of the sending of measuring unit 20 is simultaneously handled outline data.As a result reporting unit provides testing result；Place
Managing unit and executing includes processing step described in the method for the present invention.Fig. 9 shows apparatus of the present invention schematic diagram, wherein not including place
Manage unit, electric-motor drive unit and result reporting unit.
3D profile measurement unit 20 is Zaser contourgraph, and parameter includes: z-axis 2~10mm of range, and z-axis precision is not less than
0.01mm, 20~50mm of trunnion axis range.
Guide rail fixed cell pedestal 10 is the magnetic bases containing Magnetic circuit switch, and can be fixed on such as automobile frame has
On the object of permeance.In use, apparatus of the present invention can be placed on above character to be detected, Magnetic circuit switch is opened, makes this
Invention device can be adsorbed reliably above character.
Operation stability is scanned to improve, guide rail 40 is precision lead screw guide rail.
Displacement sensor 30 is mounted between 3D profile measurement unit 20 and guide rail 40, for measuring 3D profile measurement list
The displacement that member 20 is moved along guide rail 40.Displacement sensor 30 is chosen as grating, magnetic grid or laser displacement sensor, as one
Typical parameter, displacement detecting sensitivity are not less than 5um.
If selecting servo motor, since servo motor is per se with grating encoder, can be turned with grating encoder
Angle measurement equivalent substitution displacement sensor 30.
Every one spacing distance of movement of guide rail 40 just triggers the mobile touching that 3D profile measurement unit 20 carries out a configuration sampling
Hair interval, trigger interval are 0.01~0.25mm.
Processing unit, comprising: execute comprising algorithm process step described in the method for the present invention；Processing unit includes industry control electricity
Brain, embeded processor etc..
Include the information of geometric jacquard patterning unit surface where character and the geological information of character in 3D scanning gained outline data.It extracts
The geometric data of character needs the data of the first geometric jacquard patterning unit surface where extracting character in the outline data.For this purpose, this hair
The measure that bright method is taken includes: to establish polynomial fitting curve model to each contour curve, to represent the curve pair
The contour surface shape answered.
In one of the embodiments, as shown in Fig. 2, the step S2 is further comprising the steps of:
S21, polynomial fitting curve model is established to each contour curve；
S22, pass through weighted polynomial curve fitting algorithm or RANSAC algorithm, the polynomial fitting for solving contour curve is bent
Line parameter model, due to RANSAC algorithm relative maturity, the present invention is no longer specifically described；
The multinomial contour curve parameter that S23, output are fitted.
In one of the embodiments, in order to improve the computational accuracy of geometric jacquard patterning unit surface profile where character, this hair as far as possible
The method of the bright weighted polynomial curve fitting algorithm for solving fitting contour curve, using the algorithm of iteration, such as Fig. 3 institute
Show, in the step S22, the polynomial fitting parameter of curve mould of contour curve is solved using weighted polynomial curve fitting algorithm
Type the following steps are included:
S2221, smooth, removal certain noise and abnormal point are carried out to contour curve；
S2222, to contour curve least square method polynomial fitting curve；
S2223, calculate between the polynomial curve that all the points are fitted to step S2222 gained on contour curve away from
From removal distance is greater than the point of given threshold, i.e., these weights put is adjusted to 0, fallen on statistics original contour curve quasi-
Close the quantity of the left point on contour curve；
Whether the quantity for the left point that S2224, judgement are fallen on fitting contour curve reaches maximum, i.e., until the step is defeated
Until the quantity of the left point fallen in matched curve out is not further added by, if so, S2226 is entered step, if it is not, entering step
S2225；
It is to be appreciated that a method for the distance of curve smoothing, least square method, calculating point to curve, to this field
It is conventional general-purpose algorithm for professional, therefore the present invention be not explained in detail this.
S2225, removal fall in the point of fitting wheel hub extra curvature, return step S2222；
The multinomial contour curve parameter that S2226, output are fitted.
To the method that each contour curve establishes high order curve model, the highest number of the variable of polynomial curve is can
With preset.In general, VIN code and motor number are beaten and are engraved on even curface；In order to increase being applicable in for the method for the present invention
Range, it is assumed that character, which is also possible to beat, is engraved in curved surface.For plane surface, contour curve is therefore straight line can be set
The highest number for allocating the variable of the corresponding polynomial curve in face is 1.For curved surface, it is contemplated that setting polynomial curve
Variable highest number be 2 or 3.
In one of the embodiments, as shown in figure 4, the step S3 is further comprising the steps of:
S31, to each contour curve, calculate each point on original contour curve arrive described in the contour curve polynomial fitting
The distance of curve；
S32, the convex and concave feature according to character are chosen at curve side and the point of distance within the set range as word
The point cloud data of symbol；
S33, the point cloud that the character point cloud data extracted from all contour curves is spliced into the entire character surface of gained
Data, output character point cloud data.
It is further comprising the steps of between the step S32 and S33:
S321, judge whether character surface is curved surface, if so, S322 is entered step, if it is not, entering step S33；
S322, the character point cloud coordinate on curved surface is converted into the character point cloud data in plane.
Further above-mentioned steps are explained for beating and carve characters symbol.Beating symbol of carving characters is usually to be depressed in surface where character
, therefore when extracting the point cloud data of character, it is only necessary to consider in surface profile line point below.Under normal circumstances in conjunction with character
Reasonable depth, can quickly filter out the point set for meeting character geometrical characteristic, the point cloud data as character.
On the other hand, if geometric jacquard patterning unit surface where character is that arc-shaped curved surface needs to improve computational accuracy by arc
Doubly curved surfaces are plane, and concrete principle is as shown in Figure 5.In Fig. 5, point p originally on curve, the q point being located on straight line after being flattened.
Its corresponding relationship is that the length and straight line oq of curve op is isometric.
In one of the embodiments, as shown in fig. 6, the step S4 the following steps are included:
S41, binary conversion treatment is done to the point cloud data on entire character surface, is 1 than the position mark if any character point,
Remaining is 0, generates binaryzation character picture；
S42, sciagraphy is used to binaryzation character picture, extracts character, counts the geometric dimension of each character.
It is further comprising the steps of after the step S41:
S411, connected domain calculating is carried out to the binaryzation character picture, removal isolated point and its insufficient area are constituted
The small area connected domain of smallest point stroke.
In one of the embodiments, as shown in fig. 7, sciagraphy in the step S42 the following steps are included:
S421, the binary image of affiliated character is projected respectively along x-axis and y-axis, i.e., the picture of cumulative binary image
Element value, obtains 2 width projected images；
S422, with thresholding method each character is calculated along the boundary of x-axis and y-axis in affiliated 2 width projected image.
In one of the embodiments, in the step S4, the method for extracting single character is optional as a function
, further include character recognition algorithm, that is, extracts and identify character；
The character recognition algorithm, comprising: template matching algorithm or neural network algorithm；The two character recognition algorithms
It is the conventional characters recognizer of this field.
The geometric dimension of each character is counted in the step S42 in one of the embodiments, the following steps are included:
S423, the x-axis according to the obtained character of step S422 and y-axis boundary, obtain the boundary rectangle of the character；
S424, between being calculated between the size dimension and adjacent character of the character according to the boundary rectangle of each character
Away from；
S425, in the boundary rectangle of character, according to step S3 obtain character point cloud data, count the depth of the character
Or altitude information.The implementation diagram of this step is as shown in Figure 8.It, can using the geometric dimension statistical method of character of the invention
Accurately to obtain spacing, the depth of character or height between the size dimension of character, adjacent character.
The basic principles, main features and advantages of the invention have been shown and described above.The technical staff of the industry should
Understand, the present invention is not limited to the above embodiments, and the above embodiments and description only describe originals of the invention
Reason, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes and improvements
It all fall within the protetion scope of the claimed invention.
Claims (10)
1. a kind of method of character size detection, which comprises the following steps:
S1, the 3D outline data for carving code character surface is obtained；
The data of S2, geometric jacquard patterning unit surface where calculating character in outline data；
S3, the point cloud data for beating symbol of carving characters with depth or elevation information is extracted from outline data；
S4, single character is extracted, counts the geometric dimension of each character；
S5, output result.
2. the method for character size detection according to claim 1, which is characterized in that the step S2 further includes following step
It is rapid:
S21, polynomial fitting curve model is established to each contour curve；
S22, pass through weighted polynomial curve fitting algorithm or RANSAC algorithm, solve the polynomial fitting curve ginseng of contour curve
Exponential model；
The multinomial contour curve parameter that S23, output are fitted.
3. the method for character size detection according to claim 2, which is characterized in that in the step S22, using weighting
Polynomial curve fitting algorithm solve contour curve polynomial fitting parameter of curve model the following steps are included:
S2221, smooth, removal certain noise and abnormal point are carried out to contour curve；
S2222, polynomial curve fitting；
The quantity of the left point on fitting contour curve is fallen on S2223, statistics original contour curve；
Whether the quantity for the left point that S2224, judgement are fallen on fitting contour curve reaches maximum, if so, entering step
S2226, if it is not, entering step S2225；
S2225, removal fall in the point of fitting wheel hub extra curvature, return step S2222；
The multinomial contour curve parameter that S2226, output are fitted.
4. the method for character size detection according to claim 1, which is characterized in that the step S3 further includes following step
It is rapid:
Distance of each point to the contour curve polynomial fitting curve on S31, calculating scanning profile curve；
S32, convex and concave feature and character predetermined depth/altitude range according to character, filter out character point cloud data；
S33, output character point cloud data.
5. the method for character size detection according to claim 4, which is characterized in that between the step S32 and S33 also
The following steps are included:
S321, judge whether character surface is curved surface, if so, S322 is entered step, if it is not, entering step S33；
S322, the character point cloud coordinate on curved surface is converted into the character point cloud data in plane.
6. the method for character size detection according to claim 1, which is characterized in that the step S4 includes following step
It is rapid:
S41, binary conversion treatment is done to point cloud data, generate binaryzation character picture；
S42, sciagraphy or character recognition algorithm are used to binaryzation character picture, extracts character, counts the geometry of each character
Size.
7. the method for character size detection according to claim 6, which is characterized in that further include after the step S41
Following steps:
S411, connected domain calculating is carried out to binaryzation character picture, removes isolated point and small area connected domain.
8. the method for character size detection according to claim 6, which is characterized in that the sciagraphy in the step S42
The following steps are included:
S421, the binary image of affiliated character is projected respectively along x-axis and y-axis, i.e., the pixel value of cumulative binary image,
Obtain 2 width projected images；
S422, with thresholding method each character is calculated along the boundary of x-axis and y-axis in affiliated 2 width projected image.
9. the method for character size detection according to claim 8, which is characterized in that counted in the step S42 each
The geometric dimension of character the following steps are included:
S423, the x-axis according to the obtained character of step S422 and y-axis boundary, obtain the boundary rectangle of the character；
S424, spacing between the size dimension and adjacent character of the character is calculated according to the boundary rectangle of each character；?
In the boundary rectangle of character, according to the character point cloud data that step S3 is obtained, the depth or altitude information of the character are counted.
10. a kind of device of character size detection, which is characterized in that including 3D profile measurement unit, guide rail, guide rail fixed cell
Pedestal, motor, electric-motor drive unit, displacement sensor and processing unit；The guide rail is mounted on guide rail fixed cell pedestal,
The 3D profile measurement unit is mounted on guide rail and can move under the drive of the motor along guide rail, institute's displacement sensors
The displacement that the 3D profile measurement unit is moved along guide rail is measured, and sets every one spacing distance of movement of guide rail and just triggers 3D
Contourgraph carries out a configuration sampling, and the processing unit receives the outline data result that 3D profile measurement unit issues and to wheel
Wide data are handled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910600777.4A CN110375645B (en) | 2019-07-04 | 2019-07-04 | Character size detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910600777.4A CN110375645B (en) | 2019-07-04 | 2019-07-04 | Character size detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110375645A true CN110375645A (en) | 2019-10-25 |
| CN110375645B CN110375645B (en) | 2021-09-28 |
Family
ID=68252055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910600777.4A Active CN110375645B (en) | 2019-07-04 | 2019-07-04 | Character size detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110375645B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111259902A (en) * | 2020-01-13 | 2020-06-09 | 上海眼控科技股份有限公司 | Arc-shaped vehicle identification number detection method and device, computer equipment and medium |
| CN111401142A (en) * | 2020-02-25 | 2020-07-10 | 杭州测质成科技有限公司 | Aero-engine blade metal surface etching character recognition method based on deep learning |
| CN116052185A (en) * | 2023-01-09 | 2023-05-02 | 四川轻化工大学 | System and method for identifying and engraving depth detection of vehicle VIN (vehicle identification number) code matched with template |
| WO2023097600A1 (en) * | 2021-12-02 | 2023-06-08 | 苏州惟信易量智能科技有限公司 | Three-dimensional character recognition method and system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NL9200329A (en) * | 1992-02-21 | 1993-09-16 | Edwin Van Der Lely | Method and apparatus for reading in line-wise image information |
| CN2245211Y (en) * | 1995-10-31 | 1997-01-15 | 北京光电设备厂 | Linearity measurer |
| JPH09146691A (en) * | 1995-11-17 | 1997-06-06 | Hitachi Ltd | Information processing device |
| CN2676151Y (en) * | 2003-12-26 | 2005-02-02 | 暨南大学 | Doublesided light knife type three dimensional profile measuring device with adjustable height measurement range |
| GB2419760A (en) * | 2004-11-01 | 2006-05-03 | Citysync Ltd | Image capture system with alignment and character recognition means |
| CN101408937A (en) * | 2008-11-07 | 2009-04-15 | 东莞市微模式软件有限公司 | Character line positioning method and device |
| CN101666633A (en) * | 2009-09-23 | 2010-03-10 | 中国科学院上海光学精密机械研究所 | Non-contact detection system and detection method for hollow cylindrical parts |
| CN103226008A (en) * | 2013-04-27 | 2013-07-31 | 长春理工大学 | Synchronous acquisition method for gear pattern measuring data |
| CN106104201A (en) * | 2014-04-07 | 2016-11-09 | 横滨橡胶株式会社 | Method and device for inspecting imprint of tire mold |
| CN107292309A (en) * | 2017-06-12 | 2017-10-24 | 长春工程学院 | A kind of no color differnece marks character identifying method |
| CN107392206A (en) * | 2017-07-21 | 2017-11-24 | 武汉理工大学 | Rail pressed characters dividing method under a kind of working condition |
| CN208654813U (en) * | 2018-08-14 | 2019-03-26 | 成都佳诚弘毅科技股份有限公司 | A kind of VIN image collecting device |
-
2019
- 2019-07-04 CN CN201910600777.4A patent/CN110375645B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NL9200329A (en) * | 1992-02-21 | 1993-09-16 | Edwin Van Der Lely | Method and apparatus for reading in line-wise image information |
| CN2245211Y (en) * | 1995-10-31 | 1997-01-15 | 北京光电设备厂 | Linearity measurer |
| JPH09146691A (en) * | 1995-11-17 | 1997-06-06 | Hitachi Ltd | Information processing device |
| CN2676151Y (en) * | 2003-12-26 | 2005-02-02 | 暨南大学 | Doublesided light knife type three dimensional profile measuring device with adjustable height measurement range |
| GB2419760A (en) * | 2004-11-01 | 2006-05-03 | Citysync Ltd | Image capture system with alignment and character recognition means |
| CN101408937A (en) * | 2008-11-07 | 2009-04-15 | 东莞市微模式软件有限公司 | Character line positioning method and device |
| CN101666633A (en) * | 2009-09-23 | 2010-03-10 | 中国科学院上海光学精密机械研究所 | Non-contact detection system and detection method for hollow cylindrical parts |
| CN103226008A (en) * | 2013-04-27 | 2013-07-31 | 长春理工大学 | Synchronous acquisition method for gear pattern measuring data |
| CN106104201A (en) * | 2014-04-07 | 2016-11-09 | 横滨橡胶株式会社 | Method and device for inspecting imprint of tire mold |
| CN107292309A (en) * | 2017-06-12 | 2017-10-24 | 长春工程学院 | A kind of no color differnece marks character identifying method |
| CN107392206A (en) * | 2017-07-21 | 2017-11-24 | 武汉理工大学 | Rail pressed characters dividing method under a kind of working condition |
| CN208654813U (en) * | 2018-08-14 | 2019-03-26 | 成都佳诚弘毅科技股份有限公司 | A kind of VIN image collecting device |
Non-Patent Citations (3)
| Title |
|---|
| NARAHARI SASTRY PANYAM等: "Modeling of palm leaf character recognition system using transform based techniques", 《PATTERN RECOGNITION LETTERS》 * |
| 肖如镜: "基于结构光的无色差立体字符图像采集与识别研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 钟庆等: "基于结构光的凸凹字符采集与提取", 《计算机与数字工程》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111259902A (en) * | 2020-01-13 | 2020-06-09 | 上海眼控科技股份有限公司 | Arc-shaped vehicle identification number detection method and device, computer equipment and medium |
| CN111401142A (en) * | 2020-02-25 | 2020-07-10 | 杭州测质成科技有限公司 | Aero-engine blade metal surface etching character recognition method based on deep learning |
| WO2023097600A1 (en) * | 2021-12-02 | 2023-06-08 | 苏州惟信易量智能科技有限公司 | Three-dimensional character recognition method and system |
| CN116052185A (en) * | 2023-01-09 | 2023-05-02 | 四川轻化工大学 | System and method for identifying and engraving depth detection of vehicle VIN (vehicle identification number) code matched with template |
| CN116052185B (en) * | 2023-01-09 | 2023-10-31 | 四川轻化工大学 | Template matching vehicle VIN code identification and engraving depth detection system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110375645B (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110375645A (en) | A kind of method and apparatus of character size detection | |
| CN104359403B (en) | Planar part dimension measurement method based on sub-pixel edge algorithm | |
| KR101718752B1 (en) | System and method for analyzing tire tread parameters | |
| CN109141232A (en) | A kind of circle plate casting online test method based on machine vision | |
| US20200364849A1 (en) | Method and device for automatically drawing structural cracks and precisely measuring widths thereof | |
| CN102607977B (en) | Wear in-situ measurement device and method based on digital image processing | |
| CN105783723B (en) | Precision die surface processing accuracy detection device and method based on machine vision | |
| CN114359841B (en) | Video water level identification method based on space-time average | |
| CN106949848A (en) | A kind of high-precision laser 3D profiles phone structural detection method | |
| CN104236498B (en) | Method for measuring end size of switch rail | |
| CN109443214B (en) | A calibration method and device for structured light three-dimensional vision, and a measuring method and device | |
| CN102609712A (en) | Reading method of round-like pointer instrument used for mobile robot | |
| CN109489591A (en) | Plane scratch length non-contact measurement method based on machine vision | |
| CN109507198B (en) | Mask detection system and method based on fast Fourier transform and linear Gaussian | |
| CN109029203A (en) | A kind of semi-automatic measuring dimension of object device based on Digital Image Processing | |
| CN106289099A (en) | A kind of single camera vision system and three-dimensional dimension method for fast measuring based on this system | |
| CN115656182A (en) | Defect detection method of plate point cloud based on tensor voting principal component analysis | |
| CN104515479A (en) | Medium plate plane shape measuring system and method | |
| CN119049030B (en) | High-precision scale mark recognition method and system based on machine vision | |
| CN111882569A (en) | Machine vision-based pointer type pressure gauge automatic calibrator indication value reading method | |
| Fan et al. | Objective evaluation of pucker in three-dimensional garment seams | |
| CN102980536B (en) | Brake pad steel back flatness detection system and method | |
| CN113607058B (en) | A method and system for dimension detection of straight-edge knives based on machine vision | |
| CN118458461A (en) | Article deviation correcting method and deviation correcting device | |
| CN106841231B (en) | A visual precision measurement system and method for tiny parts |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240818 Address after: 1-2 / F, No.7, Lane 1088, Mingcheng Road, Fengxian District, Shanghai Patentee after: Shanghai Zhenzhen Upward Intellectual Property Agency Co.,Ltd. Country or region after: China Address before: No. 259, floor 2, building 1, No. 1388, middle section of Tianfu Avenue, hi tech Zone, Chengdu, Sichuan 610000 Patentee before: Chengdu Juying Intelligent Technology Co.,Ltd. Country or region before: China |