CN102353349A - Machine vision based micro-sound film concentricity online testing system and testing method - Google Patents
Machine vision based micro-sound film concentricity online testing system and testing method Download PDFInfo
- Publication number
- CN102353349A CN102353349A CN2011102965532A CN201110296553A CN102353349A CN 102353349 A CN102353349 A CN 102353349A CN 2011102965532 A CN2011102965532 A CN 2011102965532A CN 201110296553 A CN201110296553 A CN 201110296553A CN 102353349 A CN102353349 A CN 102353349A
- Authority
- CN
- China
- Prior art keywords
- sound film
- subsystem
- circle
- motion control
- concentricity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a machine vision based micro-sound film concentricity online testing system and a testing method. The machine vision based micro-sound film concentricity online testing system comprises an optical imaging subsystem, a digital image processing subsystem, a motion control subsystem, a sound film eliminating subsystem, an image capture card and a motion control card, wherein signals of the optical imaging subsystem are sent to the image capture card through an interface, and the image capture card captures a frame of sound film gray scale image data and sends the data to the digital image processing subsystem to be processed and judged; a signal output end of the digital image processing subsystem is connected with a signal input end of the motion control card, and a signal port of the motion control card is respectively connected with the motion control subsystem and the sound film eliminating subsystem; and the motion control subsystem and the sound film eliminating subsystem are intensively controlled by the motion control card. The machine vision based micro-sound film concentricity online testing system realizes the precise positioning of sound films and the elimination of unqualified sound films by the motion control card controlling a stepper motor, a servo motor, a sensor, an eliminating device and the like, thereby realizing the high-precision online real-time testing of the sound films.
Description
Technical field
The present invention is a kind of miniature sound film concentricity on-line detecting system and detection method based on machine vision, belongs to based on the miniature sound film concentricity on-line detecting system of machine vision and the innovative technology of detection method.
Background technology
As global electro-acoustic element production and processing center and big export country, China has become can develop and grasp the whole production technologies of electro-acoustic element parts to finished product voluntarily, has formed electro-acoustic element manufacture system and perfect industrial chain.In recent years the ever-increasing while of electro-acoustic element demand, its performance is also continued to optimize, and novel electro-acoustic element (NXT, digital, silicon is integrated etc.) product emerges in an endless stream.Microminiaturization, slimming, high-fidelityization, chip type, low-power consumption, high power, multi-functional, modularization become the new development trend of electro-acoustic element, and security of products, greenization also are the key factors that influences its development prospect and market simultaneously.Particularly miniature loudspeaker heightens in the demand of consumer electronics product, communication, computing machine, automotive electronics etc.; Also have various small-sized stereo sets; Demand like product facilities such as walkman, smart mobile phone, panel computers constantly increases, extensive market, and demand is big.Therefore, the production and processing of its product and detection thereof just become the big factor of one in the market competition.
Loudspeaker is as the core component of electroacoustic whole set equipment, and performance index such as its frequency of operation, low-frequency resonance point, distortion are the keys of decision complete machine quality, and in a single day form, and can't adjust through other elements.But the production of loudspeaker and assembling are main with craft, semiautomation operation mainly still.The at present domestic sound film tonequality vision detection system that does not still have maturation, the method for still using the artificial vision to combine with the mechanical optics instrument does not have the equipment of online detection on the production line especially as yet.Each loudspeaker manufacturer adopts the image test appearance to extract the vibrating diaphragm of sound film and the inside and outside circle edge of voice coil loudspeaker voice coil basically, carries out the indirect measurement of concentricity.The detection method of this single test of under static state carrying out can't satisfy every requirement that the sound film detects one by one on the production line.So the existing detection method of loudspeaker manufacturer is a sampling Detection in batches, perhaps only mould is detected.This detection mode cost is high, efficient is low, labour intensity is big.The mode of hand labor has had a strong impact on the work efficiency that the sound film detects, and has not only wasted human resources, has increased the detection cost, and can not fundamentally guarantee the detection quality of sound film.
Machine vision is a multidisciplinary complex art that intersects, comprising digital image processing techniques, mechanical engineering technology, control technology, optical engineering, sensor technology, computer software technology etc.As one of basic technology of modern industry, detection technique is the key that guarantees product quality.In the line flow procedure, each product all will pass through various content different detection in modern times, has only qualified product just can render to market.
Summary of the invention
The objective of the invention is to consider the problems referred to above and provide a kind of automatic online that realizes sound film concentricity to detect, can significantly improve production efficiency and the miniature sound film concentricity on-line detecting system that improves the quality of products based on machine vision.Many advantages such as that the present invention has is untouchable, real-time, high-level efficiency.
Another object of the present invention is to provide a kind of detection method of convenient and practical miniature sound film concentricity on-line detecting system based on machine vision.
Technical scheme of the present invention is: the miniature sound film concentricity on-line detecting system based on machine vision of the present invention; Include imaging optical subsystem; The Digital Image Processing subsystem; Motion control subsystem; The sound film is rejected subsystem; Image pick-up card; Motion control card; Wherein the signal of imaging optical subsystem is delivered to image pick-up card through interface; Image pick-up card collects frame sound film gray level image data and passes out to the Digital Image Processing subsystem and handle and judge; The signal output part of Digital Image Processing subsystem is connected with the signal input part of motion control card; The signal port of motion control card respectively with motion control subsystem; The sound film is rejected subsystem and is connected, and motion control subsystem and sound film are rejected subsystem by the motion control card centralized control.
Above-mentioned imaging optical subsystem includes high resolution CCD video camera, camera lens, led light source, and wherein led light source is radiated on the sound film, and camera lens is installed on the ccd video camera, and ccd video camera is installed on the position that can photograph sound film edge and vibrating diaphragm characteristic.
Above-mentioned ccd video camera adopts the high speed camera of the mega pixel level band IEEE1394b interface with middle high-resolution, and led light source adopts the blue led light source, and adopts white as a setting.
Above-mentioned motion control subsystem includes stepper motor, servomotor, sensor; Wherein the signal output part of sensor is connected with the signal input part of motion control card, and the signal output part of motion control card realizes that with the driven CCD video camera stepper motor that the front and back upper-lower position moves is connected and is connected with the servomotor that drives the transport tape rotation respectively.
It is jet device for eliminating that above-mentioned sound film is rejected subsystem; Include compressor, solenoid valve; The outlet of compressor through pipeline with can blow down that the nozzle of substandard product is connected on the streamline; Solenoid valve is installed on compressor and the pipeline that nozzle is connected, and the signal output part of motion control card is connected with the solenoid valve that can controlling plumbing fixtures ventilate.
The top hole pressure that above-mentioned sound film is rejected the compressor in the subsystem is 0.6MPa, and the opening time of solenoid valve is 200ms.
Also be equiped with air strainer on above-mentioned compressor and the pipeline that solenoid valve is connected.
The detection method of the miniature sound film concentricity on-line detecting system based on machine vision of the present invention comprises the steps:
1) configures the parameter of ccd video camera in the imaging optical subsystem, and ccd video camera is reset to point of fixity, just carry out image acquisition when sensor puts in place to the sound film;
2) the Digital Image Processing subsystem is handled the image of gathering, and extracts the inside and outside circle edge of sound film respectively and carries out the match of inside and outside circle, obtains inside and outside radius of a circle and central coordinate of circle, goes out sound film concentricity according to the calculation of parameter that obtains;
3) start and stop of motion control subsystem control transmission band;
4) the sound film rejecting subsystem concentricity that computing obtains according to the Digital Image Processing subsystem judges that starting nozzle is rejected substandard product.
The step of above-mentioned imaging optical subsystem image acquisition gathers as follows:
The 1st step: ccd video camera is demarcated, made the sound film vertical with the optical axis of ccd video camera;
The 2nd step: picture format, resolution, frame frequency parameter to ccd video camera are set, as etc., the initialization ccd video camera, and ccd video camera reset to point of fixity;
The 3rd step: gather the sound film image with ccd video camera.
The sound film inside and outside circle of above-mentioned Digital Image Processing subsystem extracts and the computing method of concentricity are the characteristics to sound film inside and outside circle, adopts substep to extract the inside and outside circle parameter, calculates the method for sound film concentricity parameter at last, and concrete steps are following:
1) extraction of cylindrical
The 1st step: sound film gray-scale map is carried out Threshold Segmentation, obtain binary image;
The 2nd step: sound film bianry image is carried out medium filtering, and the road wheel of going forward side by side is wide to be followed the tracks of, and obtains the excircle configuration of sound film;
The 3rd step: adopt the image after improved random Hough transformation is followed the tracks of profile to carry out the cylindrical detection, obtain the excircle configuration of sound film;
The 4th step: adopt the least square method algorithm that the outer circular edge data that the Hough change detection goes out are carried out match, thereby obtain the central coordinate of circle and the radius of accurate cylindrical;
2) extraction of circle in
The 1st step: circle regional area in confirming: the theoretical value of establishing sound film exradius and interior radius of circle is respectively R
0, r
0, the real radius of cylindrical is R
1, the center of circle is (A
1, B
1), the concentricity parameter is Δ r; At first according to R
0And r
0Obtain circle and exradius ratio t=r in the sound film
0/ R
0, then by the real radius R of cylindrical
1The estimation radius that estimates interior circle with t is r '=R
1* t, the scope of circle in coming thus to confirm must be with (A
1, B
1) be the center of circle, external diameter is r '+Δ r, internal diameter is on the annulus of r '-Δ r; Cutting is with (A
1, B
1) be the center, radius is the circle of r '+Δ r+ δ and with (A
1, B
1) be the center, radius is that zone between the circle of r '-Δ r-δ is as interior round regional area;
The 2nd step: adopt the Canny operator that the interior round regional area of confirming is carried out rim detection;
The 3rd step: under the condition of radius constraint, adopt improved random Hough transformation to carry out interior circle and detect circle contour in the sound film that obtains;
The 4th step: adopt the least square method algorithm that the internal circle edge data that the Hough change detection goes out are carried out match, thereby obtain the central coordinate of circle and the radius of accurate interior circle;
3) calculating of sound film concentricity
The computing formula of sound film concentricity is:
Wherein r is interior radius of circle, (x
1, y
1) be the cylindrical central coordinate of circle, (x
2, y
2) be in round heart coordinate.
The present invention is owing to adopt ccd video camera, camera lens, led light source etc. to construct a machine vision imaging optical subsystem that can effectively reflect sound film inside and outside circle edge; And can accurately ask for miniature sound film concentricity through the Digital Image Processing subsystem; Realize the accurate location of sound film and the rejecting of defective sound film through motion control card control step motor, servomotor, sensor, device for eliminating etc.; Integrate the control function of vision subsystem image acquisition and Mechanical & Electrical Transmission subsystem at last; The high accuracy in line that whole sound film concentricity detection system is realized the sound film detects; Automatically judge according to concentricity whether miniature sound film is qualified, start and reject subsystem rejecting substandard product.The present invention utilizes machine vision techniques such as optical technology, high-resolution camera technique and image processing techniques to realize that the automatic online of sound film concentricity detects; Have many advantages such as untouchable, real-time, high-level efficiency; The present invention has replaced the conventional artificial method with improve production efficiency and product quality in this way; The flase drop and the omission of solved that manual method efficient is low, speed is slow and uncertain factor such as examined personnel's subjectivity restriction is brought realize that also better 100% On-line Product detects.The present invention is that a kind of design is ingenious, function admirable, convenient and practical miniature sound film concentricity on-line detecting system and detection method based on machine vision.
Description of drawings
Fig. 1 is a theory diagram of the present invention;
Fig. 2 is the theory diagram of machine vision imaging optical subsystem of the present invention;
Fig. 3 is the processing flow chart of Digital Image Processing subsystem of the present invention;
Fig. 4 is the theory diagram of motion control subsystem of the present invention;
Fig. 5 rejects the schematic diagram of subsystem for sound film of the present invention.
Embodiment
Embodiment:
Theory diagram of the present invention as shown in Figure 1; Miniature sound film concentricity on-line detecting system based on machine vision of the present invention; Include imaging optical subsystem 1; Digital Image Processing subsystem 2; Motion control subsystem 3; The sound film is rejected subsystem 4; Image pick-up card 5; Motion control card 6; Wherein the signal of imaging optical subsystem 1 is delivered to image pick-up card 5 through interface; Image pick-up card 5 collects frame sound film gray level image data and passes out to Digital Image Processing subsystem 2 and handle and judge; The signal output part of Digital Image Processing subsystem 2 is connected with the signal input part of motion control card 6; The signal port of motion control card 6 respectively with motion control subsystem 3; The sound film is rejected subsystem 4 and is connected, and motion control subsystem 3 and sound film are rejected subsystem 4 by motion control card 6 centralized control.
Above-mentioned imaging optical subsystem 1 includes high resolution CCD video camera 11, camera lens 12, led light source 13; Wherein led light source 13 is radiated on the sound film; Camera lens 12 is installed on the ccd video camera 11, and ccd video camera 11 is installed on the position that can photograph the sound film edge that places transport tape and vibrating diaphragm characteristic.
The high speed camera that above-mentioned ccd video camera 11 adopts the mega pixel level band IEEE1394b interface with middle high-resolution, led light source 13 adopts the blue led light source, and adopts white as a setting.The fundamental purpose of above-mentioned imaging optical subsystem 11 is to gather high-quality clearly sound film picture, to make things convenient for the Flame Image Process of back.
Above-mentioned Digital Image Processing subsystem 2 has adopted a cover accurately to ask for the inside and outside circle center of circle of sound film and the Digital Image Processing algorithm of radius parameter fast, and accurately calculates the concentricity parameter of sound film.The software flow pattern of this Digital Image Processing algorithm as shown in Figure 3.
Above-mentioned motion control subsystem 3 includes stepper motor 31, servomotor 32, sensor 33; Wherein the signal output part of sensor 33 is connected with the signal input part of motion control card 6, and the signal output part of motion control card 6 realizes that with driven CCD video camera 11 stepper motor 31 that the front and back upper-lower position moves is connected and is connected with the servomotor 32 that drives the transport tape rotation respectively.Above-mentioned motion control subsystem 3 is carried out speed regulation and start stop operation through 6 pairs of stepper motors of motion control card 31 and servomotor 32; Servomotor 32 drives transport tape and rotates; When motion control card 6 detects sensor 33 and transmits the sound film and put signal in place; Servomotor 32 stops to drive the rotation of transport tape, to realize the accurate control of sound film location; Motion control card 6 control step motors 31 are realized moving of camera front and back upper-lower position, guarantee the alignment of camera, light source and miniature sound film.
On workbench; The installation site relative fixed of the detecting sensor that puts in place 33; Because system camera adopts the software trigger mode to take pictures; Sensor 33 detects sound film and camera has individual short time delay between taking pictures; The length of delay time is relevant with the position between the camera with sensor 33, and this just requires camera to move flexibly front and back.In addition, because each serial sound film is in different size, so the distance between sound film and the camera lens also can change to some extent, this just requires camera can move up and down the object distance of taking to change.In order to realize that camera is accurately located, system adopts two stepper motors of motion control card 6 controls to realize moving of camera front and back upper-lower position.
It is jet device for eliminating that above-mentioned sound film is rejected subsystem 4; Include compressor 41, solenoid valve 43; The outlet of compressor 41 through pipeline with can blow down that the nozzle of substandard product is connected on the streamline; Solenoid valve 43 is installed on compressor 41 and the pipeline that nozzle is connected, and the signal output part of motion control card 6 is connected with the solenoid valve 43 that can controlling plumbing fixtures ventilate.Also be equiped with air strainer 42 on above-mentioned compressor 41 and the pipeline that solenoid valve 43 is connected.Air compressor 41, solenoid valve 43, air strainer 42 and some other auxiliary element constitute the atmospheric control of sound film, and control the start and stop of whole atmospheric control through the general delivery outlet of motion control card 6.In addition, atmospheric control also includes air lift pump, gas tank, source of the gas regulating device and stop valve etc., and the job step of atmospheric control is following: air lift pump produces gases at high pressure and is stored in the gas tank, and stop valve is responsible for controlling the switch of whole gas circuit.Open stop valve, Pneumatic pipe cleaner is crossed the source of the gas regulating device air pressure is reduced to about 6 atmospheric pressure, passes through air strainer 42 then; The contaminant filters such as dust moisture of gas are fallen; And fogging oil is injected airflow, solenoid valve 43 is lubricated effect, to improve the life-span of solenoid valve 43.Solenoid valve 43 1 ends connect sound suppressor, to eliminate treble noise.The general delivery outlet that solenoid valve 43 passes through is controlled, when motion control card 6 sends when rejecting sound film signal, solenoid valve 43 electric, with valve open, thus make pressurized air in the nozzle fast ejection go, reach the effect of rejecting defective sound film.Because the sound film is extremely thin and in light weight, so do not need the pressurized air of too big pressure and long jet time, just can reject the sound film.
The top hole pressure that above-mentioned sound film is rejected the compressor 41 in the subsystem 4 is 0.6MPa, and the opening time of solenoid valve 43 is 200ms.
The detection method of the miniature sound film concentricity on-line detecting system based on machine vision of the present invention, it comprises the steps:
1) machine vision imaging optical subsystem 1 is according to configuring the parameter of machine phase and camera being reset to point of fixity, when sensor is then carried out image acquisition to the sound film;
2) 2 pairs of Digital Image Processing subsystems are adopted image and are handled, and extract the inside and outside circle edge of sound film respectively and carry out the match of inside and outside circle, obtain inside and outside radius of a circle and central coordinate of circle, go out sound film concentricity according to the calculation of parameter that obtains;
3) start and stop of motion control subsystem 3 control transmission bands;
4) sound film rejecting subsystem 4 concentricity that 2 computings obtain according to the Digital Image Processing subsystem is judged, starts device for eliminating and rejects substandard product.
The step of above-mentioned machine vision imaging optical subsystem 1 image acquisition gathers as follows:
The 1st step: camera is demarcated, made the sound film vertical with the camera optical axis;
The 2nd step: the parameter of camera such as picture format, resolution, frame frequency etc. are set, the initialization camera, and camera reset to point of fixity;
The 3rd step: programming realizes the collection of sound film image under Visual C++6.0 platform;
The sound film inside and outside circle of above-mentioned Digital Image Processing subsystem 2 extracts and the computing method of concentricity are the characteristics to sound film inside and outside circle, adopts substep to extract the inside and outside circle parameter, calculates the method for sound film concentricity parameter at last, and concrete steps are following:
1, the extraction of cylindrical
The 1st step: sound film gray-scale map is advanced Threshold Segmentation, obtain binary image;
The 2nd step: sound film bianry image is carried out medium filtering, and the road wheel of going forward side by side is wide to be followed the tracks of, and obtains the excircle configuration of sound film;
The 3rd step: adopt the image after improved random Hough transformation is followed the tracks of profile to carry out the cylindrical detection, obtain the excircle configuration of sound film;
The 4th step: adopt the least square method algorithm that the outer circular edge data that the Hough change detection goes out are carried out match, thereby obtain the central coordinate of circle and the radius of accurate cylindrical.
2, the extraction of interior circle
The 1st step: circle regional area in confirming.If the theoretical value of sound film exradius and interior radius of circle is respectively R
0, r
0, the real radius of cylindrical is R
1, the center of circle is (A
1, B
1), the concentricity parameter is Δ r.At first according to R
0And r
0Obtain circle and exradius ratio t=r in the sound film
0/ R
0, then by the real radius R of cylindrical
1The estimation radius that estimates interior circle with t is r '=R
1* t, the scope of circle in coming thus to confirm must be with (A
1, B
1) be the center of circle, external diameter is r '+Δ r, internal diameter is on the annulus of r '-Δ r.Cutting is with (A
1, B
1) be the center, radius is the circle of r '+Δ r+ δ and with (A
1, B
1) be the center, radius is that zone between the circle of r '-Δ r-δ is as interior round regional area.
The 2nd step: adopt the Canny operator that the interior round regional area of confirming is carried out rim detection.
The 3rd step: under the condition of radius constraint, adopt improved random Hough transformation to carry out interior circle and detect circle contour in the sound film that obtains;
The 4th step: adopt the least square method algorithm that the internal circle edge data that the Hough change detection goes out are carried out match, thereby obtain the central coordinate of circle and the radius of accurate interior circle.
3, the calculating of sound film concentricity
The computing formula of sound film concentricity is:
Wherein r is interior radius of circle, (x
1, y
1) be the cylindrical central coordinate of circle, (x
2, y
2) be in round heart coordinate.
It is following that the present invention is used for specifically detecting embodiment:
The model that enterprise provides is that the sound film of R1020H is divided into qualified and defective two kinds; Format diameter is 26.9mm; Randomly drawing 10 for every kind tests; Its result is shown in table 1, table 2; Wherein X, Y, R are respectively horizontal ordinate, ordinate and the exradius in the cylindrical center of circle, x, y, r be respectively in horizontal ordinate, ordinate and the interior radius of circle of the round heart.
1, detection speed
Detection speed is 1/second, in carrying out the sampling Detection process, is that qualified and underproof sound film detects to manual detection, can find out that from the table 1 and the data of table 2 all be less than 1 second detection time.
2, accuracy of detection
Accuracy of detection is 0.01mm, and the resolution of image detection precision and camera is relevant with the image processing algorithm of employing.System adopts high-resolution CCD camera, and in image processing process, the match of adopting least square method sub-pix algorithm to justify, its precision can reach 0.1-0.2 pixel, thereby measuring accuracy is improved greatly, the measuring accuracy of accessible 0.01mm.
The qualified sound film of table 1 detects tables of data
Table1?Measure?Data?Table?of?Qualified?Voice?Diaphragm
The defective sound film of table 2 detects tables of data
Table2?Measure?Data?Table?of?Unqualified?Voice?Diaphragm
Claims (10)
1. miniature sound film concentricity on-line detecting system based on machine vision; Include imaging optical subsystem (1); Digital Image Processing subsystem (2); Motion control subsystem (3); The sound film is rejected subsystem (4); Image pick-up card (5); Motion control card (6); Wherein the signal of imaging optical subsystem (1) is delivered to image pick-up card (5) through interface; Image pick-up card (5) collects frame sound film gray level image data and passes out to Digital Image Processing subsystem (2) and handle and judge; The signal output part of Digital Image Processing subsystem (2) is connected with the signal input part of motion control card (6); The signal port of motion control card (6) respectively with motion control subsystem (3); The sound film is rejected subsystem (4) and is connected, and motion control subsystem (3) and sound film are rejected subsystem (4) by motion control card (6) centralized control.
2. the miniature sound film concentricity on-line detecting system based on machine vision according to claim 1; It is characterized in that above-mentioned imaging optical subsystem (1) includes high resolution CCD video camera (11), camera lens (12), led light source (13); Wherein led light source (13) is radiated on the sound film; Camera lens (12) is installed on the ccd video camera (11), and ccd video camera (11) is installed on the position that can photograph the sound film edge that places transport tape and vibrating diaphragm characteristic.
3. the miniature sound film concentricity on-line detecting system based on machine vision according to claim 1; It is characterized in that above-mentioned ccd video camera (11) adopts the high speed camera of the mega pixel level band IEEE1394b interface with middle high-resolution; Led light source (13) adopts the blue led light source, and adopts white as a setting.
4. the miniature sound film concentricity on-line detecting system based on machine vision according to claim 1; It is characterized in that above-mentioned motion control subsystem (3) includes stepper motor (31), servomotor (32), sensor (33); Wherein the signal output part of sensor (33) is connected with the signal input part of motion control card (6), and the signal output part of motion control card (6) realizes that with driven CCD video camera (11) stepper motor (31) that the front and back upper-lower position moves is connected and is connected with the servomotor (32) that drives the transport tape rotation respectively.
5. according to each described miniature sound film concentricity on-line detecting system of claim 1 to 4 based on machine vision; It is characterized in that it is jet device for eliminating that above-mentioned sound film is rejected subsystem (4); Include compressor (41), solenoid valve (43); The outlet of compressor (41) through pipeline with can blow down that the nozzle of substandard product is connected on the streamline; Solenoid valve (43) is installed on compressor (41) and the pipeline that nozzle is connected, and the signal output part of motion control card (6) is connected with the solenoid valve (43) that can controlling plumbing fixtures ventilate.
6. the miniature sound film concentricity on-line detecting system based on machine vision according to claim 5 is characterized in that it is 0.6MPa that above-mentioned sound film is rejected the top hole pressure of the compressor (41) in the subsystem (4), and the opening time of solenoid valve (43) is 200ms.
7. the miniature sound film concentricity on-line detecting system based on machine vision according to claim 5 is characterized in that also being equiped with air strainer (42) on above-mentioned compressor (41) and the pipeline that solenoid valve (43) is connected.
8. the detection method of the miniature sound film concentricity on-line detecting system based on machine vision according to claim 1 is characterized in that comprising the steps:
1) configures the parameter of ccd video camera (11) in the imaging optical subsystem (1), and ccd video camera (11) is reset to point of fixity, put in place and just carry out image acquisition when sensor (33) detects the sound film;
2) Digital Image Processing subsystem (2) is handled the image of gathering, and extracts the inside and outside circle edge of sound film respectively and carries out the match of inside and outside circle, obtains inside and outside radius of a circle and central coordinate of circle, goes out sound film concentricity according to the calculation of parameter that obtains;
3) start and stop of motion control subsystem (3) control transmission band;
4) sound film rejecting subsystem (4) concentricity that computing obtains according to Digital Image Processing subsystem (2) judges that starting nozzle is rejected substandard product.
9. the detection method of the miniature sound film concentricity on-line detecting system based on machine vision according to claim 8 is characterized in that the step of above-mentioned imaging optical subsystem (1) image acquisition gathers as follows:
The 1st step: ccd video camera (11) is demarcated, made the sound film vertical with the optical axis of ccd video camera (11);
The 2nd step: picture format, resolution, frame frequency parameter to ccd video camera (11) are set, as etc., initialization ccd video camera (11), and ccd video camera (11) reset to point of fixity;
The 3rd step: gather the sound film image with ccd video camera (11).
10. the detection method of the miniature sound film concentricity on-line detecting system based on machine vision according to claim 8; It is characterized in that the sound film inside and outside circle extraction of above-mentioned Digital Image Processing subsystem (2) and the computing method of concentricity are the characteristics to sound film inside and outside circle; Adopt substep to extract the inside and outside circle parameter; Calculate the method for sound film concentricity parameter at last, concrete steps are following:
1) extraction of cylindrical
The 1st step: sound film gray-scale map is carried out Threshold Segmentation, obtain binary image;
The 2nd step: sound film bianry image is carried out medium filtering, and the road wheel of going forward side by side is wide to be followed the tracks of, and obtains the excircle configuration of sound film;
The 3rd step: adopt the image after improved random Hough transformation is followed the tracks of profile to carry out the cylindrical detection, obtain the excircle configuration of sound film;
The 4th step: adopt the least square method algorithm that the outer circular edge data that the Hough change detection goes out are carried out match, thereby obtain the central coordinate of circle and the radius of accurate cylindrical;
2) extraction of circle in
The 1st step: circle regional area in confirming: the theoretical value of establishing sound film exradius and interior radius of circle is respectively R
0, r
0, the real radius of cylindrical is R
1, the center of circle is (A
1, B
1), the concentricity parameter is Δ r; At first according to R
0And r
0Obtain circle and exradius ratio t=r in the sound film
0/ R
0, then by the real radius R of cylindrical
1The estimation radius that estimates interior circle with t is r '=R
1* t, the scope of circle in coming thus to confirm must be with (A
1, B
1) be the center of circle, external diameter is r '+Δ r, internal diameter is on the annulus of r '-Δ r; Cutting is with (A
1, B
1) be the center, radius is the circle of r '+Δ r+ δ and with (A
1, B
1) be the center, radius is that zone between the circle of r '-Δ r-δ is as interior round regional area;
The 2nd step: adopt the Canny operator that the interior round regional area of confirming is carried out rim detection;
The 3rd step: under the condition of radius constraint, adopt improved random Hough transformation to carry out interior circle and detect circle contour in the sound film that obtains;
The 4th step: adopt the least square method algorithm that the internal circle edge data that the Hough change detection goes out are carried out match, thereby obtain the central coordinate of circle and the radius of accurate interior circle;
3) calculating of sound film concentricity
The computing formula of sound film concentricity is:
(wherein r is interior radius of circle, (x
1, y
1) be the cylindrical central coordinate of circle, (x
2, y
2) be in round heart coordinate).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110296553.2A CN102353349B (en) | 2011-09-30 | 2011-09-30 | Machine vision based micro-sound film concentricity online testing system and testing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110296553.2A CN102353349B (en) | 2011-09-30 | 2011-09-30 | Machine vision based micro-sound film concentricity online testing system and testing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102353349A true CN102353349A (en) | 2012-02-15 |
| CN102353349B CN102353349B (en) | 2014-01-15 |
Family
ID=45576970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110296553.2A Expired - Fee Related CN102353349B (en) | 2011-09-30 | 2011-09-30 | Machine vision based micro-sound film concentricity online testing system and testing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102353349B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102611981A (en) * | 2012-03-19 | 2012-07-25 | 东莞市科伟自动化设备有限公司 | Sound film detection method and detection system for implementing detection method |
| CN106442536A (en) * | 2016-07-01 | 2017-02-22 | 广东技术师范学院 | Machine-vision-based IC card automatic thread take-up device and method |
| CN107101598A (en) * | 2017-03-10 | 2017-08-29 | 华南理工大学 | A kind of piezoelectric ceramics silver strip concentricity quality automatic detection method and device |
| CN108636830A (en) * | 2018-05-10 | 2018-10-12 | 苏州大学 | The method, apparatus and equipment of defective capsule detection sorting based on machine vision |
| CN108838099A (en) * | 2018-03-28 | 2018-11-20 | 广州大学 | Safety pin badge Defect Detection system and method based on machine vision |
| CN108848439A (en) * | 2018-07-18 | 2018-11-20 | 慧眼自动化科技（广州）有限公司 | Sound film detecting device |
| CN110470247A (en) * | 2019-07-30 | 2019-11-19 | 湖北三江航天万山特种车辆有限公司 | The detection device and detection method of disc concentricity inside and outside a kind of part |
| CN112284258A (en) * | 2020-12-24 | 2021-01-29 | 中国电力科学研究院有限公司 | System for measuring cable structure size parameters based on machine vision algorithm |
| CN113390368A (en) * | 2021-07-08 | 2021-09-14 | 南京航空航天大学 | Monocular vision-based helicopter transmission system concentricity measuring method |
| CN116222438A (en) * | 2023-03-16 | 2023-06-06 | 宁波川原精工机械有限公司 | System for detecting state of inner ring and outer ring of bearing ring |
| CN116625239A (en) * | 2023-07-19 | 2023-08-22 | 深圳灿维科技有限公司 | Step hole detection method, device and system based on image processing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4984885A (en) * | 1989-12-15 | 1991-01-15 | General Electric Company | Method and apparatus for high power optical fiber injection and alignment |
| US5488479A (en) * | 1992-12-17 | 1996-01-30 | The United States Of America As Represented By The Secretary Of Agriculture | Machine vision system for inspection of agricultural commodities |
| CN101504280A (en) * | 2009-03-02 | 2009-08-12 | 华中科技大学 | Imaging system for component axial centering detection apparatus |
| CN101556145A (en) * | 2009-04-29 | 2009-10-14 | 徐州工程学院 | Device and method for monitoring slow-speed and over-load rotor eccentricity image |
| CN101699217A (en) * | 2009-11-03 | 2010-04-28 | 武汉大学 | Method used for detecting concentric circle of industrial part |
| CN202284949U (en) * | 2011-09-30 | 2012-06-27 | 广东工业大学 | On-line detection system of minitype sound film concentricity based on machine vision |
-
2011
- 2011-09-30 CN CN201110296553.2A patent/CN102353349B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4984885A (en) * | 1989-12-15 | 1991-01-15 | General Electric Company | Method and apparatus for high power optical fiber injection and alignment |
| US5488479A (en) * | 1992-12-17 | 1996-01-30 | The United States Of America As Represented By The Secretary Of Agriculture | Machine vision system for inspection of agricultural commodities |
| CN101504280A (en) * | 2009-03-02 | 2009-08-12 | 华中科技大学 | Imaging system for component axial centering detection apparatus |
| CN101556145A (en) * | 2009-04-29 | 2009-10-14 | 徐州工程学院 | Device and method for monitoring slow-speed and over-load rotor eccentricity image |
| CN101699217A (en) * | 2009-11-03 | 2010-04-28 | 武汉大学 | Method used for detecting concentric circle of industrial part |
| CN202284949U (en) * | 2011-09-30 | 2012-06-27 | 广东工业大学 | On-line detection system of minitype sound film concentricity based on machine vision |
Non-Patent Citations (3)
| Title |
|---|
| 《湖北工业大学硕士学位论文》 20090617 代娜 《基于机器视觉的小型规则零件二维尺寸测量研究》 第6-7页 8 , * |
| 代娜: "《基于机器视觉的小型规则零件二维尺寸测量研究》", 《湖北工业大学硕士学位论文》 * |
| 柏长冰: "《光电工程》", 《HOUGH变换快速检测圆形PCB MARK》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102611981A (en) * | 2012-03-19 | 2012-07-25 | 东莞市科伟自动化设备有限公司 | Sound film detection method and detection system for implementing detection method |
| CN106442536A (en) * | 2016-07-01 | 2017-02-22 | 广东技术师范学院 | Machine-vision-based IC card automatic thread take-up device and method |
| CN107101598A (en) * | 2017-03-10 | 2017-08-29 | 华南理工大学 | A kind of piezoelectric ceramics silver strip concentricity quality automatic detection method and device |
| CN107101598B (en) * | 2017-03-10 | 2023-11-03 | 华南理工大学 | Automatic detection method and device for concentricity quality of piezoelectric ceramic silver sheet |
| CN108838099A (en) * | 2018-03-28 | 2018-11-20 | 广州大学 | Safety pin badge Defect Detection system and method based on machine vision |
| CN108636830A (en) * | 2018-05-10 | 2018-10-12 | 苏州大学 | The method, apparatus and equipment of defective capsule detection sorting based on machine vision |
| CN108848439B (en) * | 2018-07-18 | 2023-10-13 | 慧眼自动化科技（广州）有限公司 | Sound film detection device |
| CN108848439A (en) * | 2018-07-18 | 2018-11-20 | 慧眼自动化科技（广州）有限公司 | Sound film detecting device |
| CN110470247A (en) * | 2019-07-30 | 2019-11-19 | 湖北三江航天万山特种车辆有限公司 | The detection device and detection method of disc concentricity inside and outside a kind of part |
| CN112284258B (en) * | 2020-12-24 | 2021-04-02 | 中国电力科学研究院有限公司 | System for measuring cable structure size parameters based on machine vision algorithm |
| CN112284258A (en) * | 2020-12-24 | 2021-01-29 | 中国电力科学研究院有限公司 | System for measuring cable structure size parameters based on machine vision algorithm |
| CN113390368A (en) * | 2021-07-08 | 2021-09-14 | 南京航空航天大学 | Monocular vision-based helicopter transmission system concentricity measuring method |
| CN116222438A (en) * | 2023-03-16 | 2023-06-06 | 宁波川原精工机械有限公司 | System for detecting state of inner ring and outer ring of bearing ring |
| CN116625239A (en) * | 2023-07-19 | 2023-08-22 | 深圳灿维科技有限公司 | Step hole detection method, device and system based on image processing |
| CN116625239B (en) * | 2023-07-19 | 2023-09-15 | 深圳灿维科技有限公司 | Step hole detection method, device and system based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102353349B (en) | 2014-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102353349B (en) | Machine vision based micro-sound film concentricity online testing system and testing method | |
| CN102253048B (en) | Machine vision detection method and system for detection of various products | |
| CN202284949U (en) | On-line detection system of minitype sound film concentricity based on machine vision | |
| CN102218406B (en) | Intelligent detection device of defects of mobile phone outer shell based on machine vision | |
| CN100501312C (en) | Gem tri-dimensional cut detection device based on machine vision | |
| CN107052086A (en) | Stamping parts surface defect detection apparatus and detection method based on 3D vision | |
| CN108311409A (en) | A kind of printed circuit board (PCB) detecting system based on artificial intelligence image recognition | |
| CN207503914U (en) | A kind of wafer defect of view-based access control model identification detects, selects integrated apparatus automatically | |
| CN105783723A (en) | Machine vision-based precise die surface processing precision detection device and method | |
| CN102139260A (en) | Method and device for automatically detecting coating of glue sprayer | |
| CN101424514A (en) | Band tape graduation on-line automatic detection system and method based on image processing | |
| CN106027729A (en) | Android mobile phone function automatic test system and method | |
| CN206981462U (en) | Stamping parts surface defect detection apparatus based on 3D vision | |
| CN103557807A (en) | Method and device for detecting quality of cigarette filter stick end face shape | |
| CN108037132A (en) | A kind of visual sensor system and method for the detection of dry cell pulp layer paper winding defect | |
| CN204090324U (en) | High accuracy LED paster apparatus | |
| CN104677782A (en) | Machine vision online detection system and method for electric connector shell | |
| CN107991795A (en) | A kind of liquid crystal module automatic optical detecting system | |
| CN107238955A (en) | Liquid crystal module screen detecting system | |
| CN109909175A (en) | A kind of volume key appearance AOI detection device and its detection method | |
| CN107957245A (en) | Engine link dimension measuring device and its measuring method based on machine vision | |
| CN104976959B (en) | A kind of spring sizes on-line measurement system and its method based on machine vision | |
| CN109622404A (en) | A kind of micro workpiece Automated Sorting System and method based on machine vision | |
| CN204128554U (en) | The rapid automatized detection system of timepiece industry precision parts quality | |
| CN208438057U (en) | A kind of tool wear visual examination device for numerical control workshop |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140115 Termination date: 20170930 |