CN106841231B - Visual precision measurement system and method for tiny parts - Google Patents
Visual precision measurement system and method for tiny parts Download PDFInfo
- Publication number
- CN106841231B CN106841231B CN201710153437.2A CN201710153437A CN106841231B CN 106841231 B CN106841231 B CN 106841231B CN 201710153437 A CN201710153437 A CN 201710153437A CN 106841231 B CN106841231 B CN 106841231B
- Authority
- CN
- China
- Prior art keywords
- image
- measurement
- input picture
- edge detection
- threshold value
- 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.)
- Expired - Fee Related
Links
- 238000005259 measurement Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000000007 visual effect Effects 0.000 title claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000003708 edge detection Methods 0.000 claims description 37
- 238000000691 measurement method Methods 0.000 claims description 25
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000005496 tempering Methods 0.000 claims description 3
- 239000004744 fabric Substances 0.000 claims description 2
- 230000001678 irradiating effect Effects 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 15
- 238000004422 calculation algorithm Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 230000008901 benefit Effects 0.000 description 6
- 230000010339 dilation Effects 0.000 description 6
- 230000003628 erosive effect Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000009499 grossing Methods 0.000 description 4
- 238000004321 preservation Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000009514 concussion Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a visual precision measurement system and a method for a tiny part, wherein the measurement system comprises: the image acquisition device is used for acquiring a backlight image of the micro part to be detected as an input image and outputting the input image, and comprises a camera, a telecentric lens, an object stage and a parallel light source which are sequentially arranged on a guide rail and adjustable in position, wherein the parallel light source is used for irradiating the micro part to be detected on the object stage, and the camera acquires the backlight image of the micro part to be detected as the input image through the telecentric lens and outputs the input image; and the characteristic analysis and parameter measurement device is connected with the image acquisition device and is used for receiving the input image, performing characteristic analysis and extraction on the input image, and acquiring and outputting measurement parameters. The parameter measurement for tiny parts such as the escape pinion can be realized quickly and accurately.
Description
Technical field
The present invention relates to micro parts detection fields, a kind of precision visual measuring system more particularly to micro parts and
Method.
Background technique
Escapement is the core of modern mechanical clock and watch, and initial escapement is born in the 15th century, gradually evolves later
Various appearance till now.More specifically, escapement be it is a kind of transmit mechanical energy switching device, this switching device by
The control of time base, with the main drive chain of certain frequency switching clock and watch, so that it is alternate and with certain to stop mechanical clock
Average speed rotation, to indicate correct time.The function of escapement can understand in terms of two: catch, by main transmission
Motion locking (getting), at this point, what the main drive chain of clock and watch was locked out;It is vertical, exactly with a part of potential energy for the system of shaking, open
The movement of (relieving) main drive chain is opened, while fetching certain energy from main drive chain to maintain the work of concussion system.Currently,
Still there are hundreds of escapements to use on modern clock and watch.
For escapement gear shaft as the important part in timepiece escapement, accurate measurement is very crucial.Traditional size is surveyed
Amount means have slide calliper rule, gauge, universal tool-measuring microscope, contourgraph, X-ray etc., these detection means play in the industrial production
Huge effect, but with the development of modern industry and progress, especially in some high-precision industries, traditional detection means
The needs of production are no longer satisfied, although the detection means such as slide calliper rule, gauge are easy, quick, measurement data is less, and precision is not
It is high.Although the detection means such as universal tool-measuring microscope, contourgraph have higher precision, but require in specific equipment, specifically
It is detected under environment, not only large labor intensity, low efficiency, and detection process is separation, this and modern times with production process
The requirement of on-line checking required by industry, real-time control is not inconsistent.
In recent years, with the development of computer vision technique, people start in this kind of micro parts of measurement escapement gear shaft
Parameter measurement is carried out using the image of this kind of micro parts collected, this is a new technology.This new technology can pass through
Image is many in industrial detection link to solve the problems, such as, to replace backward artificial detection method, improves detection efficiency and work
Industry automatization level.Moreover, being detected using computer vision technique, not damage product to be checked, detection accuracy also high and more
Add intelligence.
Although having existed many measurement methods and system using Computer Vision Detection Technique in the prior art,
Time of measuring, measurement cost, in terms of there is still a need for constantly improve.Accordingly, it is desirable to provide preferably
Technical solution.
Summary of the invention
Least for above-mentioned technical problem is partially solved, the invention proposes following technical schemes.
The precision visual measuring system of the first micro parts according to the present invention, comprising: image acquiring device, for obtaining
The backlight image of micro parts to be measured is taken as input picture and exports the input picture comprising is successively arranged on guide rail
And the adjustable camera in position, telecentric lens, objective table and source of parallel light, source of parallel light therein be used for irradiate on objective table to
Micrometer small part, the backlight images of micro parts to be measured is obtained by telecentric lens as input picture for camera and to export this defeated
Enter image;Signature analysis and parameter measuring apparatus, connect with image acquiring device, for receiving input picture, to input figure
As carrying out signature analysis and extraction, acquisition and output measurement parameter.
Second of measuring system according to the present invention, signature analysis and parameter measuring apparatus therein include: pretreatment mould
Block, for carrying out holding edge filter to input picture and exporting pretreated image;Threshold value obtains module, pre- for calculating
The intensity profile histogram of treated image is simultaneously obtained threshold value based on intensity profile histogram and exports the threshold value;Binaryzation
Module, for converting bianry image for pretreated image according to threshold value and exporting the bianry image;Edge detection module,
For carrying out edge detection to bianry image using morphology operations and exporting edge detection results;Parameter measurement and calculating mould
Block obtains for measuring and calculating according to edge detection results and exports measurement parameter.
The first precision visual measurement method according to the present invention, the measurement for the first micro parts described above
System, comprising the following steps:
Step 1: image acquiring device obtains the backlight image of micro parts to be measured as input picture and exports the input
Image;
Step 2: signature analysis and parameter measuring apparatus receive input picture, signature analysis are carried out to input picture and is mentioned
Take, obtain and export measurement parameter.
Second of measurement method according to the present invention, for second of measuring system described above, step 2 packet
It includes:
Sub-step 1: preprocessing module carries out holding edge filter to input picture and exports pretreated image;
Sub-step 2: threshold value obtains module and calculates the intensity profile histogram of pretreated image and based on intensity profile
Histogram obtains threshold value and exports the threshold value;
Sub-step 3: binarization block converts bianry image for pretreated image according to threshold value and exports the two-value
Image;
Sub-step 4: edge detection module carries out edge detection to bianry image using morphology operations and exports edge inspection
Survey result;
Sub-step 5: parameter measurement and computing module are measured and are calculated according to edge detection results to obtain and export
Measurement parameter.
Second of measurement method according to the present invention, above-mentioned steps 2 further include:
Sub-step 4 ': after sub-step 4, information fitting is carried out to edge detection results, and after information is fitted
Edge detection results are as the edge detection results for being used for sub-step 5.
Second of measurement method according to the present invention, further includes:
Sub-step 6: if it is determined that measurement parameter is unreasonable, then step 1 is repeated to sub-step 5;Otherwise, sub-step 7 is executed:
Complete the vision measurement of escapement gear shaft.
Second of measurement method according to the present invention, further includes:
Step 1 is repeated several times to carry out edge detection to sub-step 4 and export edge detection results.
The present invention compared with the existing technology the advantages of be: using contactless computer vision measurement technology, fastly
Speed accurately realizes the parameter measurement for being directed to the micro parts such as escapement gear shaft.More specifically, the advantage is that:
1) time of measuring is reduced, productivity is improved.
2) measurement cost is reduced.Using traditional measurement method large labor intensity, working efficiency is low, human error is larger,
Measurement accuracy is low, using computer vision and image processing techniques, realizes the image measurement of micro parts parameter, reduces survey
Measure cost.
3) measurement accuracy is improved, ensure that the stability in the smooth assembly and use process of part.
Detailed description of the invention
By reading the detailed description of following detailed description, various other advantages and benefits are common for this field
Technical staff will become clear.Attached drawing is only used for showing the purpose of specific embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is the schematic diagram of the clock and watch escapement gear shaft as example micro parts.
Fig. 2 is the schematic diagram of the image acquiring device in the precision visual measuring system of micro parts according to the present invention.
Fig. 3 is signature analysis and parameter measuring apparatus in the precision visual measuring system of micro parts according to the present invention
Block diagram.
Fig. 4 is the example flow diagram of the precision visual measurement method of micro parts according to the present invention.
Fig. 5 is thin for locking four of tooth shaft part to be measured in precision visual measurement method according to the present invention
The schematic diagram of long rectangular area.
Specific embodiment
The illustrative embodiments that the present invention will be described in more detail below with reference to accompanying drawings.Although showing this hair in attached drawing
Bright illustrative embodiments, it being understood, however, that may be realized in various forms the reality of the invention without that should be illustrated here
The mode of applying is limited.It is to be able to thoroughly understand the present invention on the contrary, providing these embodiments, and this can be sent out
Bright range is fully disclosed to those skilled in the art.
Fig. 1 is the schematic diagram of the clock and watch escapement gear shaft as example micro parts.Catching in mechanical clock as shown in Figure 1
Vertical tooth shaft, which is only that one kind of numerous micro parts is typical, to be represented, and is intended solely for illustrative purposes, hereinafter in conjunction with catching
Measuring system and method proposed by the invention is described in vertical tooth shaft.However, measuring system and side proposed by the invention
Method is not limited to clock and watch escapement gear shaft.
The precision visual measuring system of the first micro parts according to the present invention, including image interconnected obtain dress
(that is, tooth shaft part image obtains module) and signature analysis and parameter measuring apparatus are set (that is, tooth shaft part image signature analysis mentions
Modulus block (that is, characteristics analysis module) and tooth shaft parameter calculating module).Below in conjunction with attached drawing respectively to image acquiring device and
Signature analysis and parameter measuring apparatus are described in detail respectively.
Fig. 2 is the schematic diagram of the image acquiring device in the precision visual measuring system of micro parts according to the present invention.
Image acquiring device shown in Fig. 2 is used to obtain the backlight images of micro parts to be measured as input picture and defeated
Out comprising it is successively arranged on guide rail 6 and the adjustable camera 1 in position, telecentric lens 2, objective table 3 and source of parallel light 4,
In source of parallel light 4 be used to irradiate micro parts to be measured on objective table 3, camera 1 is obtained to be measured small by telecentric lens 2
The backlight image of part (being not shown in Fig. 2) is as input picture and exports the input picture.As shown in Fig. 2, camera 1 passes through
Camera installing plate is arranged on guide rail 6.
More specifically, 1) camera 1 in the image acquiring device in Fig. 1 by the way of installing in the horizontal direction;2) to
It surveys part to be placed on micro parts objective table 3 (0.3mm tempering film), the pick-and-place of tooth shaft part to be measured is carried out using tweezers, and
It can be finely adjusted;3) it is irradiated using back side source of parallel light 4, is highlighted the edge contour of part to be measured;4) guarantee telecentric lens
2, the center of part to be measured and source of parallel light 4 is in the same horizontal line.
Selectively, image acquiring device further includes light source switch 5 as shown in Figure 2, for controlling source of parallel light 4
Switch.
In conjunction with the image acquiring device according to the present invention that will be explained in greater detail below, which can be fast
Victory effectively completes measurement task.Above-mentioned measuring table (i.e., image acquiring device) has the advantages that
1) adjustable guide rail 6 and source of parallel light 4 etc., so that vision-based detection of the measuring table to the tooth shaft part of different size
There is better adaptability, which can also be used for the detection of his micro parts such as non-tooth axial workpiece, has and well may be used
Scalability.
2) telecentric lens 2 are used, from the source of parallel light 4 of back side illuminaton part to be measured, ensure that measurement accuracy, further
It, can highly efficient acquisition measurement result in conjunction with the means of image procossing.
Fig. 3 is that the signature analysis and parameter in the precision visual measuring system of second of micro parts according to the present invention are surveyed
Measure the block diagram of device.Signature analysis and parameter measuring apparatus in Fig. 3 is special for receiving input picture, carrying out to input picture
Sign analysis and extraction obtain and export measurement parameter.
As shown in figure 3, this feature analysis and parameter measuring apparatus include preprocessing module 31, threshold value acquisition module 32, two
Value module 33, edge detection module 34, parameter measurement and computing module 35.
Preprocessing module 31, for carrying out holding edge filter to input picture and exporting pretreated image.
For example, the method that the pretreatment for carrying out image in preprocessing module 31 uses smoothing processing, main purpose is to subtract
Few noise.Since the smoothing function of mean filter can make soft edge, and median filtering is while removing impulsive noise
Also the lines details of image can be removed, therefore, measurement method of the invention uses holding edge filter algorithm.Edge is kept
The basic process of filtering algorithm is as follows: taking to each pixel [i, j] of gray level image (that is, input picture) appropriately sized
One neighborhood (such as 3 × 3 neighborhoods), calculates separately upper left angular neighborhood, lower-left angular neighborhood, upper right angular neighborhood and the lower right corner of [i, j]
The intensity profile uniformity V of neighborhood, then takes the mean value in region corresponding to the smallest intensity profile uniformity as the pixel
New gray value.
Gray uniformization calculation formula are as follows:
V=∑ (f2[i,j]-(∑f[i,j])2/N)
Threshold value obtain module 32, for calculate pretreated image intensity profile histogram and based on intensity profile it is straight
Square figure obtains threshold value and exports the threshold value.
Binarization block 33, for converting bianry image for pretreated image according to threshold value and exporting the binary map
Picture.
In view of the convenience of image procossing, bianry image is converted gray images into.Selectively, specific algorithm is as follows:
T indicates threshold value in formula, and the basic thought of this threshold segmentation method is to find a threshold value, is made by this threshold
The erroneous segmentation probability that value divides target and background is minimum.
Edge detection module 34, for carrying out edge detection to bianry image using morphology operations and exporting edge detection
As a result (corresponding to " acquisition of tooth shaft image edge information " in Fig. 4).
Selectively, adoptable specific edge detection algorithm is as follows:
1) dilation operation, image and preservation after obtaining dilation operation are carried out to bianry image.
2) erosion operation, image and preservation after obtaining erosion operation are carried out to bianry image.
3) difference of respective pixel value in image obtained by dilation operation and erosion operation is calculated.If difference is 0, right
Should the mark value of pixel of result be denoted as 0;Otherwise 255 are denoted as, that is, the image border detected.
Parameter measurement and computing module 35 (that is, tooth shaft parameter calculating module), for being surveyed according to edge detection results
Amount and calculating are to obtain and export measurement parameter.
Fig. 4 is the example flow diagram of the precision visual measurement method of micro parts according to the present invention.Although Fig. 4 is contained
The illustrative operating procedure that the precision visual measurement method of micro parts according to the present invention can be used, but according to this hair
The precision visual measurement method of bright micro parts is without including all steps shown in Fig. 4.
For example, the first precision visual measurement method according to the present invention, for the first micro parts described above
Measuring system, comprising the following steps:
Step 1: image acquiring device obtains the backlight image of micro parts to be measured as input picture and exports the input
Image (corresponding to the step " acquisition of tooth shaft part image " in Fig. 4).
Step 2: signature analysis and parameter measuring apparatus receive input picture, carry out signature analysis and extraction to input picture
(corresponding to the step " image characteristic analysis and extraction " in Fig. 4) obtains and exports measurement parameter (corresponding to the step in Fig. 4
" tooth shaft size calculates and measurement ").
More specifically, for example, the acquisition of input picture can use following steps: 1) calibrated image acquiring device
Spatial pose is constant, and tooth shaft part is placed on micro parts objective table (0.3mm tempering film), opens back side source of parallel light 4;
2) it after placing tooth shaft part, keeps tooth shaft part position constant, adjusts source of parallel light 4, make the image outline of tooth shaft part
Clearly, convenient for acquisition;3) ten groups of image of tooth shaft part to be measured are shot, and select imaging clearly, have less external interference and
The image that part is located at picture centre as far as possible is analyzed as input picture.
In measurement method of the invention, due to only one object in input picture, image is relatively easy, and object with
Contrast is larger between background, all has more uniform intensity profile, therefore the method (example based on image grayscale characteristic can be used
Such as, using edge detection method) Lai Jinhang image segmentation is with the measured value that gets parms.It may also be said that the present invention is mentioned using edge
The thinking for taking algorithm is that target image is divided into target and background two parts using the algorithm of gray level image segmentation.
Therefore, the basic step for the measurement method that the present invention uses includes: straight first with the intensity profile of input picture
Square figure obtains the threshold value of the image grayscale, further according to threshold value by image binaryzation, forms sharpening image, then utilizes form student movement
The edge of detection image is calculated, finally obtains the curve of image border, and get parms survey according to detected boundary curve
Magnitude.
Selectively, second of measurement method according to the present invention, the view for second of micro parts described above
Feel that precision measurement system, the signature analysis and parameter measuring apparatus receive the input picture, carry out spy to the input picture
The step of sign analysis and extraction, acquisition and output measurement parameter includes that (sub-step 1 therein is right to sub-step 3 for following sub-step
Should be in the step " image characteristic analysis and extraction " in Fig. 4):
Sub-step 1: preprocessing module 31 carries out holding edge filter to input picture and exports pretreated image.
For example, the method that the pretreatment of image uses smoothing processing, main purpose is to reduce noise.Due to mean filter
Smoothing function can make soft edge, and median filtering can also remove the lines details of image while removing impulsive noise
Fall, therefore, measurement method of the invention uses holding edge filter algorithm.The basic process of holding edge filter algorithm is such as
Under: taking an appropriately sized neighborhood to each pixel [i, j] of gray level image (that is, input picture), (such as 3 × 3 is adjacent
Domain), the intensity profile for calculating separately the upper left angular neighborhood of [i, j], lower-left angular neighborhood, upper right angular neighborhood and bottom right angular neighborhood is uniform
V is spent, then takes the mean value in region corresponding to the smallest intensity profile uniformity as the new gray value of the pixel.
Gray uniformization calculation formula are as follows:
V=∑ (f2[i,j]-(∑f[i,j])2/N)
Sub-step 2: threshold value obtains module 32 and calculates the intensity profile histogram of pretreated image and based on gray scale point
Cloth histogram obtains threshold value and exports the threshold value.
Sub-step 3: binarization block 33 bianry image is converted for pretreated image according to threshold value and export this two
It is worth image.
In view of the convenience of image procossing, bianry image is converted gray images into.Selectively, specific algorithm is as follows:
T indicates threshold value in formula, and the basic thought of this threshold segmentation method is to find a threshold value, is made by this threshold
The erroneous segmentation probability that value divides target and background is minimum.
Sub-step 4: edge detection module 34 carries out edge detection to bianry image using morphology operations and exports edge
Testing result (corresponding to the step " acquisition of tooth shaft image edge information " in Fig. 4).
Selectively, step 1 can be repeated several times to sub-step 4 to carry out edge detection and export edge detection results
(corresponding to the left side circulation branch road in Fig. 4).
Selectively, adoptable specific edge detection algorithm is as follows:
1) dilation operation, image and preservation after obtaining dilation operation are carried out to bianry image.
2) erosion operation, image and preservation after obtaining erosion operation are carried out to bianry image.
3) difference of respective pixel value in image obtained by dilation operation and erosion operation is calculated.If difference is 0, right
The mark value of pixel is answered to be denoted as 0;Otherwise, the mark value of respective pixel is denoted as 255, that is, the image border detected.
Sub-step 5: parameter measurement and computing module 35 measure and calculate according to edge detection results obtain with it is defeated
Measurement parameter out (corresponding to the step " tooth shaft size calculates and measurement " in Fig. 4).
Selectively, the method that the present invention uses selection region operation, the tooth shaft that needs are measured are locked in known to one
Rectangular extent in and record the coordinate and parameter of rectangle, then generate four elongated rectangular areas as shown in Figure 5
1, it 2,3,4 goes to lock tooth shaft part to be measured, the length and diameter portion of measurement tooth shaft is finally gone using measurement operator,
Record the data measured.
Ideally, rectangular area mutually intersects to obtain a pair of profile parallel parallel to each other with tooth shaft part image profile
Line directly calculates the distance between this two profile parallel lines, and the length or diameter for needing the part measured can be obtained.Specifically
Ground, the calculating for the distance between a pair of contour line parallel to each other, can use following methods:
1) this linear equation to parallel contour line in image coordinate system is calculated separately
2) if this is parallel to each other (A to contour line1/B1=A2/B2), then it directlys adopt following formula and calculates this to parallel contours
The distance between line
Selectively, rectangular area 2 as shown in Figure 5 and rectangular area 3 measure same length, and two will calculated
A result is averaging, and keeps result more accurate.
However, in practical situations, due to the presence of edge detection error, in image coordinate precision, extract this
A pair of of contour line may not be parallel to each other.Therefore, the present invention uses least square regression fitting algorithm to mutually not flat first
Capable a pair of of escapement gear shaft parts profile line is fitted, and is then carried out again apart from calculating or measurement, to obtain such as part
The measurement parameters such as diameter, the length of different location.
Therefore, selectively, measurement method according to the present invention further include:
Sub-step 4 ': after sub-step 4, information fitting is carried out (corresponding to the step in Fig. 4 to edge detection results
" fitting of tooth shaft edge image information ").
For example, can fit the boundary curve that method sub-paragraphs 4 detect using as described below and intended
It closes:
1) it is done using fixed pixel as step value axial (for rectangular area 1 and rectangular area 4) or radial (for rectangular area
2 and rectangular area 3) virtual line is a plurality of, made straight line is by a pair of of Contour segmentation at a series of pairs of pixels.
2) midpoint coordinates for seeking the pixel connecting line segment of the single pair in each contour line is calculated separately.
3) for the coordinate at the midpoint of all single pair pixel connecting line segments of obtained each contour line, using most
Small two two contour lines for multiplying homing method to be fitted, after being fitted.
4) if two contour lines after fitting are parallel to each other (or the difference between its slope is less than threshold value), according to upper
The distance between parallel lines formula is stated to be calculated.
Moreover, in order to adapt to for using different resolution shot by camera the extracted edge line of image into
Row fitting determines that the straight line in sub-step 4 ' is quasi- according to resolution of video camera the invention also provides a kind of as represented by following formula
The method of straight line fitting step value and virtual line number used in closing:
S in above formula indicates that single step pixel value, N_L indicate that virtual line sum, L are wherein one of profile parallel line segment
Length, K be the pixel equivalent factor.
Selectively, measurement method according to the present invention further include:
Sub-step 6: if it is determined that measurement parameter is unreasonable, (corresponding to the step in Fig. 4, " whether analysis measurement result is closed
Reason "), then repeatedly step 1 (corresponding to the step " acquisition of tooth shaft part image " in Fig. 4) to sub-step 5 (corresponding in Fig. 4
Right side circulation branch road);Otherwise,
Execute sub-step 7: the vision measurement for completing escapement gear shaft (" completes the view of escapement gear shaft corresponding to the step in Fig. 4
Feel measurement ").
By above-mentioned measurement method, the non-contact vision measurement to escapement gear shaft can be completed, which successfully solves
The deficiency of traditional detection of having determined mode, and have the advantages that
Firstly, executing fast and efficiently vision measurement, time of measuring is significantly reduced, the production of tooth shaft part is improved
Efficiency.
Secondly, non-contact vision measurement system is stablized, service life is long;In the same time, a worker can complete
The measurement work of two or four workers, reduces human cost.Therefore, using non-contact vision measurement mode, significantly
Reduce measurement cost.
Finally, measurement accuracy has been increased to pixel precision by vision measurement mode, obtained high-acruracy survey result guarantees
Stabilization when component assembly and operation.
The above, illustrative specific embodiment only of the invention, but protection scope of the present invention is not limited to
This, anyone skilled in the art in the technical scope disclosed by the present invention, the variation that can readily occur in or replaces
It changes, should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection of the claim
Subject to range.
Claims (4)
1. a kind of precision visual measurement method of micro parts, which is characterized in that surveyed using a kind of precision visual of micro parts
Amount system realizes that the system includes:
Image acquiring device, for obtaining the backlight image of micro parts to be measured as input picture and exporting the input picture,
The image acquiring device includes successively being arranged on guide rail (6) and the adjustable camera in position (1), telecentric lens (2), objective table
(3) and source of parallel light (4), source of parallel light (4) therein are used for the micro parts to be measured irradiated on objective table (3), and camera (1) is logical
Telecentric lens (2) are crossed to obtain the backlight image of micro parts to be measured as the input picture and export the input picture;Its
In, the objective table (3) is 0.3mm tempering film;
Signature analysis and parameter measuring apparatus are connect with described image acquisition device, for receiving the input picture, to this
Input picture carries out signature analysis and extraction, acquisition and output measurement parameter, and the signature analysis and parameter measuring apparatus include:
Preprocessing module (31), for carrying out holding edge filter to the input picture and exporting pretreated image;
Threshold value obtains module (32), for calculating the intensity profile histogram of the pretreated image and based on the gray scale point
Cloth histogram obtains threshold value and exports the threshold value;
Binarization block (33) is somebody's turn to do for according to the threshold value converting the pretreated image to bianry image and exporting
Bianry image;
Edge detection module (34) is examined for carrying out edge detection to the bianry image using morphology operations and exporting edge
Survey result;
Parameter measurement and computing module (35), obtain and export for measuring and calculating according to the edge detection results
The measurement parameter;
Method includes the following steps:
Step 1: image acquiring device obtains the backlight image of micro parts to be measured as input picture and exports the input picture;
Step 2: preprocessing module carries out holding edge filter to the input picture and exports pretreated image;
Step 3: threshold value obtains module and calculates the intensity profile histogram of the pretreated image and based on the intensity profile
Histogram obtains threshold value and exports the threshold value;
Step 4: binarization block bianry image is converted for the pretreated image according to the threshold value and export this two
It is worth image;
Step 5: edge detection module carries out edge detection to the bianry image using morphology operations, and examines to the edge
It surveys result and carries out information fitting, then export edge detection results;
Step 6: parameter measurement and computing module are measured and are calculated according to the edge detection results to obtain and export institute
State measurement parameter, it is described that the edge detection results are carried out with information is quasi- to include:
Do that axially or radially virtual line is a plurality of, and made straight line is by a pair of of Contour segmentation at a series of using fixed pixel as step value
Pairs of pixel;
Calculate separately the midpoint coordinates for seeking the pixel connecting line segment of the single pair in each contour line;
For the coordinate at the midpoint of all single pair pixel connecting line segments of obtained each contour line, using least square
Homing method is fitted, two after being fitted contour line;
If two contour lines after fitting be parallel to each other or its slope between difference be less than threshold value, according to parallel lines it
Between range formula calculated.
2. measurement method according to claim 1, which is characterized in that determine the step value and the virtual line number
Method includes:
Wherein, S indicates step value, and N_L indicates that virtual line sum, L are wherein one length of profile parallel line segment, and K is picture
Plain equivalence factor.
3. measurement method according to claim 1 or 2, which is characterized in that the method also includes:
Sub-step 6: if it is determined that the measurement parameter is unreasonable, then step 1 is repeated to step 5;Otherwise,
It executes sub-step 7: completing the vision measurement of escapement gear shaft.
4. measurement method according to claim 3, which is characterized in that the method also includes:
Step 1 is repeated several times to carry out edge detection to step 4 and export edge detection results.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710153437.2A CN106841231B (en) | 2017-03-15 | 2017-03-15 | Visual precision measurement system and method for tiny parts |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710153437.2A CN106841231B (en) | 2017-03-15 | 2017-03-15 | Visual precision measurement system and method for tiny parts |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106841231A CN106841231A (en) | 2017-06-13 |
CN106841231B true CN106841231B (en) | 2019-08-16 |
Family
ID=59143760
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710153437.2A Expired - Fee Related CN106841231B (en) | 2017-03-15 | 2017-03-15 | Visual precision measurement system and method for tiny parts |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106841231B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108387516A (en) * | 2018-01-25 | 2018-08-10 | 陕西方元预应力机械有限公司 | Threading defects detection device and detection method based on CCD camera image processing technologies |
CN111652874B (en) * | 2020-06-04 | 2023-10-20 | 崧智智能科技(深圳)有限公司 | Method, device, terminal and computer readable storage medium for measuring go-no go gauge |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104567711A (en) * | 2015-01-23 | 2015-04-29 | 中国特种设备检测研究院 | Side expansion value measuring system and method based on projection and digital image processing |
CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
CN106248686A (en) * | 2016-07-01 | 2016-12-21 | 广东技术师范学院 | Glass surface defects based on machine vision detection device and method |
-
2017
- 2017-03-15 CN CN201710153437.2A patent/CN106841231B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104567711A (en) * | 2015-01-23 | 2015-04-29 | 中国特种设备检测研究院 | Side expansion value measuring system and method based on projection and digital image processing |
CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
CN106248686A (en) * | 2016-07-01 | 2016-12-21 | 广东技术师范学院 | Glass surface defects based on machine vision detection device and method |
Also Published As
Publication number | Publication date |
---|---|
CN106841231A (en) | 2017-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105069790B (en) | A kind of gear open defect fast image detection method | |
CN107239742B (en) | Method for calculating scale value of instrument pointer | |
CN106248686A (en) | Glass surface defects based on machine vision detection device and method | |
CN103759676A (en) | Non-contact type workpiece surface roughness detecting method | |
CN103792699A (en) | TFT-LCD Mura defect machine vision detecting method based on B spline surface fitting | |
CN111583114B (en) | Automatic measuring device and measuring method for pipeline threads | |
CN107230203A (en) | Casting defect recognition methods based on human eye vision attention mechanism | |
CN106290392A (en) | A kind of little micro-bearing surface pitting defects online test method and system thereof | |
CN106501272B (en) | Machine vision soldering tin positioning detection system | |
CN104777174B (en) | Axial workpiece abrupt change of cross-section portion faces fatigue crack detecting system and method | |
JP2021168143A (en) | System and method for efficiently scoring probe in image by vision system | |
CN111462156A (en) | Image processing method for acquiring corneal vertex | |
CN106841231B (en) | Visual precision measurement system and method for tiny parts | |
CN104749801B (en) | High Precision Automatic optical detecting method and system | |
CN113222955A (en) | Gear size parameter automatic measurement method based on machine vision | |
CN109241948A (en) | A kind of NC cutting tool visual identity method and device | |
CN108645490A (en) | Cold-water meter vision detection system based on image processing techniques and detection method | |
Deng et al. | Vison-based 3D shape measurement system for transparent microdefect characterization | |
Sulaiman et al. | DEFECT INSPECTION SYSTEM FOR SHAPE-BASED MATCHING USING TWO CAMERAS. | |
Sun et al. | Precision work-piece detection and measurement combining top-down and bottom-up saliency | |
JP2019215206A (en) | Surface inspection device and surface inspection method | |
CN109448012A (en) | A kind of method for detecting image edge and device | |
TW200842339A (en) | Mura detection method and system | |
CN107067432A (en) | The determination method of round edge circle in quartz pushrod detection | |
Lei | A machine vision system for inspecting bearing-diameter |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190816 Termination date: 20200315 |
|
CF01 | Termination of patent right due to non-payment of annual fee |