CN109029203A - A kind of semi-automatic measuring dimension of object device based on Digital Image Processing - Google Patents
A kind of semi-automatic measuring dimension of object device based on Digital Image Processing Download PDFInfo
- Publication number
- CN109029203A CN109029203A CN201811008960.7A CN201811008960A CN109029203A CN 109029203 A CN109029203 A CN 109029203A CN 201811008960 A CN201811008960 A CN 201811008960A CN 109029203 A CN109029203 A CN 109029203A
- Authority
- CN
- China
- Prior art keywords
- image
- graduated scale
- scale
- pixel
- digital image
- 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.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 53
- 238000012360 testing method Methods 0.000 claims abstract description 37
- 238000005259 measurement Methods 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims description 17
- 238000013178 mathematical model Methods 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 14
- 235000013399 edible fruits Nutrition 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005266 casting Methods 0.000 description 1
- 238000011840 criminal investigation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B5/00—Measuring arrangements characterised by the use of mechanical techniques
- G01B5/02—Measuring arrangements characterised by the use of mechanical techniques for measuring length, width or thickness
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of semi-automatic measuring dimension of object device based on Digital Image Processing, belongs to technical field of image processing.The present invention around object under test by placing one graduated scale, and it is shot or is scanned to obtain respective digital image, effectively actual object size is linked together with Pixel of Digital Image, pass through respective digital image procossing again, identify the graduation mark in image on graduated scale, then the minimum scale indicated as unit of pixel is obtained by calculation, calculates object under test size automatically finally by setting-out measurement.Since image can scale, straight line can repeatedly draw lines, dimension of object is measured using the present apparatus, measurement result is more accurate.Digital Image Processing is applied to fields of measurement by the present invention, preferably solves the problems, such as to measure certain objects (footprint or impression of the hand in such as scene of a crime) that should not be moved and need repeatedly to measure, has certain practical application value.
Description
Technical field
The present invention relates to a kind of semi-automatic measuring dimension of object device based on Digital Image Processing, in particular to a kind of base
The scale in one width graduated scale image is identified in Digital Image Processing, is calculated and is carved by Correlation method for data processing mathematical model
It spends minimum scale on ruler, calculate setting-out length by the way that measuring targets setting-out is automatic, belong to Digital Image Processing, measuring technique neck
Domain.
Background technique
Image plays an important role in human perception external information, and for the ease of storage and processing, computer is with number
The form of image indicates image.Much measurement scenes in, due to the particularity of object under test, for example, should not move, need it is more
Secondary measurement, not directly contact etc., measurement method is often based on computer vision and carries out a series of processing to image, then passes through
Object under test size is calculated.For example, in certain scene of a crime, technique of criminal investigation personnel in order to retain footprint that suspect leaves or
On the one hand the information such as impression of the hand simulate corresponding footprint or impression of the hand by particular technology, then by measuring or marking to model,
To obtain suspect's relevant information, on the other hand due to needing repeatedly to measure and save data or carrying out database comparison, this
Class object under test is saved in the form of digital picture and measurement is particularly important.
It is measured based on digital picture measuring targets size, the most key is by the pixel and reality in digital picture
Border dimension of object effectively docks, that is, the unit sizes of actual object be in certain width digital picture how many pixel or certain
Does is the actual object size that unit pixel in width digital picture represents how many? this is solved by the way of a kind of simple low cost
One problem has important practical significance and higher practical value.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of semi-automatic measuring dimension of object based on Digital Image Processing
Device, first measuring targets are shot or are scanned with graduated scale, then the Mathematic Model of Digital Image Processing by establishing, right
Associated picture carries out a series of Digital Image Processing, identifies all graduation marks of graduated scale in image, then the quarter by establishing
Line coordinates data processing mathematical model is spent, the minimum scale on the graduated scale indicated as unit of pixel is calculated, finally by
Scaling and repeatedly setting-out relatively accurately measure object under test size.The device is more effectively measuring should not to be moved and need more
The dimension of object of secondary measurement, by the way that object under test and graduated scale are converted an image, reduce encountered in actual measurement it is tired
Difficulty is equally beneficial for application and popularization in Digital Image Processing to graduated scale identification problem.
The technical solution adopted by the present invention is that: a kind of semi-automatic measuring dimension of object device based on Digital Image Processing,
Include the following steps:
Step1: image is obtained, that is, obtains the image comprising object under test and graduated scale；
Step2: advanced row Digital Image Processing and corresponding data processing pass through the respective digital image procossing mathematics of foundation
Model identifies all graduation marks on graduated scale, then handles mathematical model by the graduation mark coordinate data established, calculates
Minimum scale on the graduated scale indicated as unit of pixel out；
Step3: carrying out setting-out measurement, measures and calculate the length of drawn straight line according to the minimum scale on graduated scale,
Obtain object actual size.
Specifically, the Step1 specifically: place one around object under test and shot graduated scale, and to it
Or scanning, to obtain the image comprising object under test and graduated scale.
Specifically, specific step is as follows by the Step2:
Step2.1: the image comprising object under test and graduated scale is successively smoothed, threshold process, morphology
Processing, contour detecting, image rotation, image segmentation, upright projection operation, identify the graduation mark on graduated scale；
Step2.2: according to the coordinate of the graduation mark on the graduated scale of identification, by Correlation method for data processing computing scale ruler
Minimum scale, i.e., the graduated scale minimum scale indicated with pixel.
Specifically, the Step3 specifically:
Measuring targets image zooms in and out to sight object under test endpoint, draws the line of two endpoints, passes through scale
Ruler minimum scale calculates drawn straight length, that is, object under test actual size.
More specifically, specific step is as follows by the Step2.1:
Cv.imread () function in the library OpenCV is called first, reads the image comprising object under test and graduated scale, and
It is converted into gray level image；
Then the noise in cv2.GaussianBlur () the function removal image in the library OpenCV is called, using OpenCV
In gaussian filtering, by giving different weights to the pixel around a pixel, weight size is according to its distance center picture
Depending on the distance of element, all pixels weight distribution is in Gaussian function, and the pixel value of certain pixel is equal to original image with the pixel
Multiplied by the Gaussian function centered on point, original image is smoothed with this；
Then cv2.threshold () function in the library OpenCV is called, after a threshold value is set to smoothing processing
Image carry out threshold process, gray level image is converted to bianry image, to extract graduated scale boundary；
Then cv2.morphologyEx () function in the library OpenCV is called, by being set on operation, to binary map
As carrying out Morphological scale-space, i.e., first corrodes reflation, remove borderline noise, keep boundary more smooth；
Then cv2.findContours () function in the library OpenCV is called, the boundary in image is searched, detects to carve
It is wide to spend foot wheel, in particular, the rectangular profile in graduated scale, and return graduated scale minimum circumscribed rectangle four vertex, length and width,
Center point coordinate and rotation angle:
Then the cv2.getRotationMatrix2D () and cv2.warpAffine () letter in the library OpenCV are called
Number rotate without scaling to original image, makes graduated scale according to the centre coordinate and rotation angle of appeal minimum circumscribed rectangle
Boundary parallel or perpendicular to reference axis, at this point, rotation angle is 0, then according to four vertex of minimum circumscribed rectangle and length
And width, it is partitioned into the part graduated scale containing graduation mark；
Then to the graduation mark being partitioned into, upright projection is carried out, that is, counts of its non-zero pixel in vertical direction
Number, in which: black pixel value is 0 in bianry image, and white pixel value is non-zero, and is stored in the column for being named as count [i]
In table, wherein i indicates image abscissa, and due to there is one section of interval between the adjacent graduation mark on graduated scale, these intervals are hung down
The number for delivering directly the non-zero pixel of movie queen is 0, i.e., count value is 0 at these points, and count value is not 0 at graduation mark position.
More specifically, specific step is as follows by the Step2.2:
One graduation mark tends to take up multiple pixels, if count [i] is equal to 0 and count [i+1] no at i-th point
Equal to 0, be approximately considered i-th point be certain graduation mark starting point, if at i-th point count [i] be not equal to 0 and count
[i+1] is equal to 0, be approximately considered i-th point be certain graduation mark terminating point, certain graduation mark includes one from for image
Initial point and a terminating point are approximately considered the center that certain scale line coordinates is starting point and ending point, and so on, system
All scale line coordinates are counted, calculate the interval between all adjacent graduation marks, and be stored in the list for being named as gap [i]
In, wherein i indicates which minimum scale on graduated scale, a pretreatment done to list gap, rejecting abnormalities interval data, such as
Some value is significantly greater or less than the mean value of list gap in fruit gap, then it is assumed that the gap value is not a normal value, needs to pick
It removes, after the completion of pretreatment, then averages to list gap, the mean value is as the minimum scale on graduated scale.
The beneficial effects of the present invention are: the present invention effectively docks the pixel of digital picture with actual object size, pass through
Graduation mark on image processing flow identification graduated scale appropriate, then corresponding data processing, meter are carried out to all scale line coordinates
Calculation obtains minimum scale on the graduated scale indicated as unit of pixel, which is all adjacent graduation marks on graduated scale
The average value at interval effectively reduces the error of Digital Image Processing introducing, by scaling and repeatedly setting-out, measurement can be made to tie
Fruit is more accurate, effectively reduces the error of manual measurement introducing, and then allow to preferably be applied to based on digital picture
Processing is in the measurement of dimension of object.
Detailed description of the invention
Fig. 1 is a kind of overview flow chart of the semi-automatic measuring dimension of object device based on Digital Image Processing of the present invention；
Fig. 2 is the test image after measuring targets and graduated scale are shot in the present invention；
Fig. 3 is the image after being smoothed in the present invention to test image；
Fig. 4 is to carry out the image after threshold process in the present invention to the image after smoothing processing；
Fig. 5 is to carry out the image after Morphological scale-space in the present invention to the image after threshold process；
Fig. 6 is to carry out the image after contour detecting in the present invention to the image after Morphological scale-space；
Fig. 7 is to carry out postrotational image to test image in the present invention；
Fig. 8 is to carry out the image after image segmentation in the present invention to postrotational image；
Fig. 9 is to carry out the image after upright projection in the present invention to the image after image segmentation；
Figure 10 is connected between graduation mark on graduated scale apart from schematic diagram in the present invention；
Figure 11 is in the present invention by the result figure of setting-out measurement dimension of object.
Specific embodiment
Gather the drawings and specific embodiments below, the present invention is further illustrated.
Embodiment 1: as shown in figs. 1-11, a kind of semi-automatic measuring dimension of object device based on Digital Image Processing, packet
Include following steps:
Step1, placed around object under test and one shot or scanned graduated scale, then to it, with obtain include to
Survey the image of object and graduated scale；It is specific:
Selection one is common graduated scale first, and is arbitrarily placed on around object under test and (does not need to contact), preferably will
Graduated scale and object under test are placed on same level, reuse filming instrument or scanner perpendicular to horizontal plane to determinand
Body and graduated scale are shot or are scanned, and the image comprising object under test and graduated scale is obtained；
Footprint or impression of the hand to the object for being inconvenient to move and need repeatedly to measure, such as in scene of a crime, around it
One is placed graduated scale, is shot or scanned to obtain the image, realizes measuring targets size by carrying out setting-out to image
Semi-automatic measuring.
Step2: advanced row Digital Image Processing and corresponding data processing pass through the respective digital image procossing mathematics of foundation
Model identifies all graduation marks on graduated scale, then handles mathematical model by the graduation mark coordinate data established, calculates
Minimum scale on the graduated scale indicated as unit of pixel out；Specifically:
Step2.1, the image comprising object under test and graduated scale is successively smoothed, threshold process, morphology
The operation such as processing, contour detecting, image rotation, image segmentation, upright projection, identifies the graduation mark on graduated scale；It is specific:
Cv.imread () function in the library OpenCV is called first, reads the image comprising object under test and graduated scale, and
It is converted into gray level image；
Then the noise in cv2.GaussianBlur () the function removal image in the library OpenCV is called, using OpenCV
In gaussian filtering, by giving different weights to the pixel around a pixel, weight size is according to its distance center picture
Depending on the distance of element, all pixels weight distribution is in Gaussian function, and the pixel value of certain pixel is equal to original image with the pixel
Multiplied by the Gaussian function centered on point, original image is smoothed with this；
Then cv2.threshold () function in the library OpenCV is called, after a threshold value is set to smoothing processing
Image carry out threshold process, gray level image is converted to bianry image, to extract graduated scale boundary；
Preferably ruler profile can be detected by the threshold process in Digital Image Processing, then be based on the profile
In straight line, image rotate without scaling, image is split and upright projection so as to subsequent, it is last to be thrown according to vertical
Shadow identifies scale line coordinates；
Then cv2.morphologyEx () function in the library OpenCV is called, by being set on operation, to binary map
As carrying out Morphological scale-space, i.e., first corrodes reflation, remove borderline noise, keep boundary more smooth；
Then cv2.findContours () function in the library OpenCV is called, the boundary in image is searched, detects to carve
It is wide to spend foot wheel, in particular, the rectangular profile in graduated scale, and return graduated scale minimum circumscribed rectangle four vertex, length and width,
Center point coordinate and rotation angle:
Four apex coordinates of graduated scale minimum circumscribed rectangle are as follows:
(119.04187012,826.31030273), (37.02392578,608.75817871),
(1586.30480957,24.67382812), (1668.32275391,242.22595215)
Graduated scale minimum circumscribed rectangle is long and wide are as follows:
Width=1655.72521973, height=232.499206543
Graduated scale minimum circumscribed rectangle center point coordinate and rotation angle are as follows:
(852.673339844,425.49206543), angle=-20.6566162109
Then the cv2.getRotationMatrix2D () and cv2.warpAffine () letter in the library OpenCV are called
Number rotate without scaling to original image, makes graduated scale according to the centre coordinate and rotation angle of appeal minimum circumscribed rectangle
Boundary parallel or perpendicular to reference axis, graduated scale minimum circumscribed rectangle parameter information after rotation are as follows:
Four apex coordinates of graduated scale minimum circumscribed rectangle are as follows:
(149., 719.), (149., 489.), (1801.99975586,489.), (1801.99975586,719.)
Graduated scale minimum circumscribed rectangle is long and wide are as follows:
Width=1652.99975586, height=229.999969482
Graduated scale minimum circumscribed rectangle center point coordinate and rotation angle are as follows:
(975.49987793,604.0), angle=0.0
At this point, rotation angle is 0, then according to four vertex of minimum circumscribed rectangle and length and width, it is partitioned into containing quarter
Spend the part graduated scale of line；
Then to the graduation mark being partitioned into, upright projection is carried out, that is, counts its non-zero pixel (two-value in vertical direction
Black pixel value is 0 in image, and white pixel value is non-zero) number, and be stored in one and be named as in the list of count [i],
Wherein i indicates image abscissa.Due to having one section of interval, these interval upright projections between the adjacent graduation mark on graduated scale
The number of non-zero pixel is 0 afterwards, i.e., count value is 0 at these points, and count value is not 0 at graduation mark position.
Step2.2, according to the coordinate of the graduation mark on the graduated scale of identification, by Correlation method for data processing computing scale ruler
Minimum scale, i.e., the graduated scale minimum scale indicated with pixel；It is specific:
One graduation mark tends to take up multiple pixels, if count [i] is equal to 0 and count [i+1] no at i-th point
Equal to 0, be approximately considered i-th point be certain graduation mark starting point, if at i-th point count [i] be not equal to 0 and count
[i+1] is equal to 0, be approximately considered i-th point be certain graduation mark terminating point, certain graduation mark includes one from for image
Initial point and a terminating point are approximately considered the center that certain scale line coordinates is starting point and ending point.And so on, system
All scale line coordinates are counted, calculate the interval between all adjacent graduation marks, and be stored in the list for being named as gap [i]
In, wherein i indicates which minimum scale on graduated scale, a pretreatment done to list gap, rejecting abnormalities interval data, such as
Some value is significantly greater or less than the mean value of list gap in fruit gap, then it is assumed that the gap value is not a normal value, needs to pick
It removes, after the completion of pretreatment, then averages to list gap, which calculates to obtain gap mean value as the minimum scale on graduated scale
It is 7.84422110553, i.e., minimum scale (1mm) is 7.84422110553pixels on graduated scale；
Step3, measuring targets image zoom in and out to sight object under test endpoint, draw the line of two endpoints, lead to
Scaleover ruler minimum scale calculates drawn straight length, that is, object under test actual size, specific:
Two endpoints of determining coin are zoomed in and out to coin, the two endpoints is connected, draws straight line, straight length is
194.537914pixels, according to 1mm=7.84422110553pixels, calculating drawn straight length automatically is
24.800157mm, i.e. coin dimensions are 24.800157mm, by inquiring related data, the gauge of country's casting unitary coin
Very little is 25mm, and since the minimum scale of graduated scale in figure is 1mm, the measurement result of the present apparatus is acceptable.
It can be amplified with measuring targets, be drawn lines to find object under test endpoint accurately, it can also be with measuring targets
Repeatedly drawn lines, it is more accurate to measure size.
The present invention relates to a kind of semi-automatic measuring dimension of object device based on Digital Image Processing, first by to be measured
Object and graduated scale are shot or are scanned, and are obtained the image comprising object under test and graduated scale, are then established to comprising to be measured
Object and graduated scale image carry out the mathematical model of respective image processing, identify in image all graduation marks on graduated scale, then
The mathematical model for carrying out corresponding data processing to scale line coordinates is established, it is minimum to calculate the graduated scale indicated as unit of pixel
Scale carries out picture straight line finally by the object under test in image, and it is single for being calculated according to the pixel of minimum scale with distance
The straight length that position indicates, to realize the measurement of measuring targets size.Since image can scale, straight line can repeatedly be drawn
Line measures dimension of object using the present apparatus, and measurement result is more accurate.Digital Image Processing is applied to survey by the present invention
Amount field is preferably solved to certain object (footprints or hand in such as scene of a crime that should not be moved and need repeatedly to measure
Print etc.) the problem of measuring, have certain practical application value.
This mode measured based on Digital Image Processing measuring targets size, there is an urgent need to digitized maps appropriate
As processing operation process and corresponding data processing method, to identify graduation mark in image on graduated scale and calculate quarter
Minimum scale on ruler is spent, object under test size is further measured and calculate.With the development and application of computer vision, for
Digital picture comprising object under test and graduated scale measures with certain reality dimension of object by Digital Image Processing
Border application value.
The device of the invention can be not only used for can be used for manual measurement in the identification problem to graduated scale graduation mark
Objects in images size constitutes a kind of semi-automatic measuring dimension of object dress based on Digital Image Processing of the present invention in conjunction with the two
It sets.
Above in conjunction with attached drawing, the embodiment of the present invention is explained in detail, but the present invention is not limited to above-mentioned
Embodiment within the knowledge of a person skilled in the art can also be before not departing from present inventive concept
Put that various changes can be made.
Claims (6)
1. a kind of semi-automatic measuring dimension of object device based on Digital Image Processing, characterized by the following steps:
Step1: image is obtained, that is, obtains the image comprising object under test and graduated scale；
Step2: advanced row Digital Image Processing and corresponding data processing pass through the respective digital image procossing mathematical modulo of foundation
Type identifies all graduation marks on graduated scale, then handles mathematical model by the graduation mark coordinate data established, calculates
Minimum scale on the graduated scale indicated as unit of pixel；
Step3: carrying out setting-out measurement, measures and calculates the length of drawn straight line according to the minimum scale on graduated scale, obtain
Object actual size.
2. the semi-automatic measuring dimension of object device according to claim 1 based on Digital Image Processing, it is characterised in that:
The Step1 specifically: place one around object under test and shot or scanned graduated scale, and to it, to obtain
Image comprising object under test and graduated scale.
3. the semi-automatic measuring dimension of object device according to claim 1 based on Digital Image Processing, it is characterised in that:
Specific step is as follows by the Step2:
Step2.1: the image comprising object under test and graduated scale is successively smoothed, threshold process, Morphological scale-space,
Contour detecting, image rotation, image segmentation, upright projection operation, identify the graduation mark on graduated scale；
Step2.2: according to the coordinate of the graduation mark on the graduated scale of identification, by minimum on Correlation method for data processing computing scale ruler
Scale, i.e., the graduated scale minimum scale indicated with pixel.
4. the semi-automatic measuring dimension of object device according to claim 1 based on Digital Image Processing, it is characterised in that:
The Step3 specifically:
Measuring targets image zooms in and out to sight object under test endpoint, draws the line of two endpoints, most by graduated scale
Down scale calculates drawn straight length, that is, object under test actual size.
5. the semi-automatic measuring dimension of object device according to claim 3 based on Digital Image Processing, it is characterised in that:
Specific step is as follows by the Step2.1:
Call cv.imread () function in the library OpenCV first, read the image comprising object under test and graduated scale, and by its
Be converted to gray level image；
Then the noise in cv2.GaussianBlur () the function removal image in the library OpenCV is called, using in OpenCV
Gaussian filtering, by giving different weights to the pixel around a pixel, weight size is according to its distance center pixel
Depending on distance, all pixels weight distribution is in Gaussian function, and the pixel value of certain pixel is equal to original image with the pixel and is
Center is smoothed original image with this multiplied by the Gaussian function；
Then cv2.threshold () function in the library OpenCV is called, by one threshold value of setting to the figure after smoothing processing
As carrying out threshold process, gray level image is converted to bianry image, to extract graduated scale boundary；
Then call the library OpenCV in cv2.morphologyEx () function, by being set on operation, to bianry image into
Row Morphological scale-space, i.e., first corrode reflation, removes borderline noise, keeps boundary more smooth；
Then cv2.findContours () function in the library OpenCV is called, the boundary in image is searched, detects graduated scale
Profile, in particular, the rectangular profile in graduated scale, and return to four vertex, length and the width, center of graduated scale minimum circumscribed rectangle
Point coordinate and rotation angle:
Then the cv2.getRotationMatrix2D () and cv2.warpAffine () function in the library OpenCV are called, according to
According to the centre coordinate and rotation angle of appeal minimum circumscribed rectangle, original image rotate without scaling, the side of graduated scale is made
Boundary is parallel or perpendicular to reference axis, at this point, rotation angle is 0, then according to four vertex of minimum circumscribed rectangle and length and width,
It is partitioned into the part graduated scale containing graduation mark；
Then to the graduation mark being partitioned into, upright projection is carried out, that is, counts the number of its non-zero pixel in vertical direction,
In: black pixel value is 0 in bianry image, and white pixel value is non-zero, and is stored in one and is named as in the list of count [i],
Wherein i indicates image abscissa, due to having one section of interval, these interval upright projections between the adjacent graduation mark on graduated scale
The number of non-zero pixel is 0 afterwards, i.e., count value is 0 at these points, and count value is not 0 at graduation mark position.
6. the semi-automatic measuring dimension of object device according to claim 5 based on Digital Image Processing, it is characterised in that:
Specific step is as follows by the Step2.2:
One graduation mark tends to take up multiple pixels, if count [i] is not equal to equal to 0 and count [i+1] at i-th point
0, be approximately considered i-th point be certain graduation mark starting point, if at i-th point count [i] be not equal to 0 and count [i+
1] be equal to 0, be approximately considered i-th point be certain graduation mark terminating point, certain graduation mark includes a starting from for image
Point and a terminating point are approximately considered the center that certain scale line coordinates is starting point and ending point, and so on, statistics
All scale line coordinates calculate the interval between all adjacent graduation marks, and are stored in one and are named as in the list of gap [i],
Wherein i indicates which minimum scale on graduated scale, does a pretreatment to list gap, rejecting abnormalities interval data, if
Some value is significantly greater or less than the mean value of list gap in gap, then it is assumed that the gap value is not a normal value, needs to pick
It removes, after the completion of pretreatment, then averages to list gap, the mean value is as the minimum scale on graduated scale.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811008960.7A CN109029203A (en) | 2018-08-31 | 2018-08-31 | A kind of semi-automatic measuring dimension of object device based on Digital Image Processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811008960.7A CN109029203A (en) | 2018-08-31 | 2018-08-31 | A kind of semi-automatic measuring dimension of object device based on Digital Image Processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109029203A true CN109029203A (en) | 2018-12-18 |
Family
ID=64626037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811008960.7A Pending CN109029203A (en) | 2018-08-31 | 2018-08-31 | A kind of semi-automatic measuring dimension of object device based on Digital Image Processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109029203A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246124A (en) * | 2019-05-24 | 2019-09-17 | 西安交通大学 | Target size measurement method and system based on deep learning |
| CN110674745A (en) * | 2019-09-24 | 2020-01-10 | 山东省计算中心（国家超级计算济南中心） | Fingerprint restoration method and system based on field legacy fingerprints |
| CN110986789A (en) * | 2019-11-21 | 2020-04-10 | 海南中航特玻科技有限公司 | Multi-point image identification measurement control method for glass ribbon in float glass tin bath |
| CN114494017A (en) * | 2022-01-25 | 2022-05-13 | 北京至简墨奇科技有限公司 | Method, device, equipment and medium for adjusting DPI (deep packet inspection) image according to scale |
| CN114581507A (en) * | 2022-04-24 | 2022-06-03 | 浙江托普云农科技股份有限公司 | Seed size calibration method, system and device based on image seed test and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0464004A (en) * | 1990-07-02 | 1992-02-28 | Toshiba Corp | Image pickup device |
| CN101288589A (en) * | 2008-04-25 | 2008-10-22 | 浙江省淡水水产研究所 | Non-invasive rapid detection device of aquatic animal morphological feature |
| CN102445239A (en) * | 2010-09-29 | 2012-05-09 | 联宇工程技术(武汉)有限公司 | Novel water metering method for open channel based on multi-point water level |
| CN102445153A (en) * | 2011-09-23 | 2012-05-09 | 联宇工程技术(武汉)有限公司 | Gatage measuring method based on digital image processing |
| CN102809347A (en) * | 2011-06-01 | 2012-12-05 | 鸿富锦精密工业（深圳）有限公司 | Multiplying-power multi-form scale marking system and method |
| CN105403146A (en) * | 2015-11-05 | 2016-03-16 | 上海卓易科技股份有限公司 | Object size measurement method and system and intelligent terminal |
| CN106918312A (en) * | 2017-03-30 | 2017-07-04 | 招商局重庆交通科研设计院有限公司 | Pavement strip based on computer vision peels off area detecting device and method |
-
2018
- 2018-08-31 CN CN201811008960.7A patent/CN109029203A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0464004A (en) * | 1990-07-02 | 1992-02-28 | Toshiba Corp | Image pickup device |
| CN101288589A (en) * | 2008-04-25 | 2008-10-22 | 浙江省淡水水产研究所 | Non-invasive rapid detection device of aquatic animal morphological feature |
| CN102445239A (en) * | 2010-09-29 | 2012-05-09 | 联宇工程技术(武汉)有限公司 | Novel water metering method for open channel based on multi-point water level |
| CN102809347A (en) * | 2011-06-01 | 2012-12-05 | 鸿富锦精密工业（深圳）有限公司 | Multiplying-power multi-form scale marking system and method |
| CN102445153A (en) * | 2011-09-23 | 2012-05-09 | 联宇工程技术(武汉)有限公司 | Gatage measuring method based on digital image processing |
| CN105403146A (en) * | 2015-11-05 | 2016-03-16 | 上海卓易科技股份有限公司 | Object size measurement method and system and intelligent terminal |
| CN106918312A (en) * | 2017-03-30 | 2017-07-04 | 招商局重庆交通科研设计院有限公司 | Pavement strip based on computer vision peels off area detecting device and method |
Non-Patent Citations (1)
| Title |
|---|
| 李国军: "数字图像处理的一种新方法", 《鞍山师范学院学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246124A (en) * | 2019-05-24 | 2019-09-17 | 西安交通大学 | Target size measurement method and system based on deep learning |
| CN110674745A (en) * | 2019-09-24 | 2020-01-10 | 山东省计算中心（国家超级计算济南中心） | Fingerprint restoration method and system based on field legacy fingerprints |
| CN110674745B (en) * | 2019-09-24 | 2022-11-04 | 山东省计算中心（国家超级计算济南中心） | Fingerprint restoration method and system based on field legacy fingerprints |
| CN110986789A (en) * | 2019-11-21 | 2020-04-10 | 海南中航特玻科技有限公司 | Multi-point image identification measurement control method for glass ribbon in float glass tin bath |
| CN114494017A (en) * | 2022-01-25 | 2022-05-13 | 北京至简墨奇科技有限公司 | Method, device, equipment and medium for adjusting DPI (deep packet inspection) image according to scale |
| CN114581507A (en) * | 2022-04-24 | 2022-06-03 | 浙江托普云农科技股份有限公司 | Seed size calibration method, system and device based on image seed test and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109029203A (en) | A kind of semi-automatic measuring dimension of object device based on Digital Image Processing | |
| CN110095062A (en) | A kind of object volume measurement method of parameters, device and equipment | |
| CN109443480A (en) | Gauge positioning and water level measurement method based on image procossing | |
| CN107358628B (en) | Linear array image processing method based on target | |
| CN107392849B (en) | Target identification and positioning method based on image subdivision | |
| CN108764234B (en) | Liquid level meter reading identification method based on inspection robot | |
| CN109376740A (en) | A kind of water gauge reading detection method based on video | |
| CN111307039A (en) | Object length identification method and device, terminal equipment and storage medium | |
| CN114627080B (en) | Vehicle stamping accessory defect detection method based on computer vision | |
| CN112907506A (en) | Water gauge color information-based indefinite-length water gauge water level detection method and device and storage medium | |
| CN110211178A (en) | A kind of pointer instrument recognition methods calculated using projection | |
| CN115761563A (en) | River surface flow velocity calculation method and system based on optical flow measurement and calculation | |
| CN113378663B (en) | Inspection pointer type circular instrument identification method and device | |
| CN106340062B (en) | A kind of generation method and device of three-D grain model file | |
| Ying et al. | Research on an automatic counting method for steel bars' image | |
| CN115760860B (en) | Multi-type workpiece dimension visual measurement method based on DXF file import | |
| CN111862082A (en) | Train brake pad thickness rechecking method and system thereof | |
| CN112836726A (en) | Pointer instrument indication reading method and device based on video information | |
| CN115880643B (en) | Social distance monitoring method and device based on target detection algorithm | |
| JP3071956B2 (en) | Vickers hardness automatic reading device | |
| CN112233063B (en) | Circle center positioning method for large-size round object | |
| CN115018735A (en) | Fracture width identification method and system for correcting two-dimensional code image based on Hough transform | |
| CN112184790B (en) | Object size high-precision measurement method based on depth camera | |
| CN114882095A (en) | Object height online measurement method based on contour matching | |
| CN113048899A (en) | Thickness measuring method and system based on line structured light |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |