CN102303019B - Method for automatically detecting scales of injector needle cylinders by using machine vision system - Google Patents

Method for automatically detecting scales of injector needle cylinders by using machine vision system Download PDF

Info

Publication number
CN102303019B
CN102303019B CN 201110109643 CN201110109643A CN102303019B CN 102303019 B CN102303019 B CN 102303019B CN 201110109643 CN201110109643 CN 201110109643 CN 201110109643 A CN201110109643 A CN 201110109643A CN 102303019 B CN102303019 B CN 102303019B
Authority
CN
China
Prior art keywords
image
scale
scales
needle cylinders
injector needle
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
Application number
CN 201110109643
Other languages
Chinese (zh)
Other versions
CN102303019A (en
Inventor
董仲伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuxi Zhongwang Siwei Technology Co Ltd
Original Assignee
Wuxi Zhongwang Siwei Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuxi Zhongwang Siwei Technology Co Ltd filed Critical Wuxi Zhongwang Siwei Technology Co Ltd
Priority to CN 201110109643 priority Critical patent/CN102303019B/en
Publication of CN102303019A publication Critical patent/CN102303019A/en
Application granted granted Critical
Publication of CN102303019B publication Critical patent/CN102303019B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention provides a method for automatically detecting scales of injector needle cylinders by using a machine vision system. The method comprises the following steps of: shooting scale pictures of a standard product to serve as scale standard pictures in advance, and storing in a computer; setting difference proportions of the scale standard pictures to be detection parameters; setting detection accuracy and qualified ranges of difference detection parameters according to requirements of users; starting a camera by using external trigger and control signals to shoot the scale pictures of the injector needle cylinders operated on line in real time, and transmitting the shot pictures to the computer for detection; processing the pictures by using the computer by a picture algorithm; extracting the scale pictures of the injector needle cylinders, and computing scale differences; and judging whether a product is a qualified product or a waste product through the computed scale differences, and eliminating the waste product from a specified material outlet through the external trigger and control signals. By the method, the scales of the injector needle cylinders can be detected at high accuracy and high speed, and the yield of the product can be effectively ensured.

Description

NI Vision Builder for Automated Inspection is to the automatic testing method of scales of injector needle cylinders
Technical field
The present invention relates to the technical field of utilizing NI Vision Builder for Automated Inspection to detect online, relate in particular in the scales of injector needle cylinders printing on-the-spotly, utilize NI Vision Builder for Automated Inspection whether scales of injector needle cylinders is printed the complete method that automatically detects.
Background technology
Whether the scales of injector needle cylinders printing in continuous productive process is on-the-spot, need to meet the requirements to the printing quality of injector syringe high scale and detect online.In the prior art, online detection dependence to scales of injector needle cylinders manually detects, establishing approximately on injector syringe production machine side, 80 people carry out detection and the processing of scales of injector needle cylinders, according to testing result product is divided into certified products (such as scale disappearance ratio<10%, or scale excessively thick/meticulous ratio<10%, and do not have other scale defectives) and defective work (such as scale disappearance ratio 〉=10%, or or scale excessively thick/meticulous ratio 〉=10%, or above other scale defectives beyond two kinds are arranged).Defective work is directly as goods rejection.
The shortcoming that manual detection exists mainly contains: the on-the-spot ventilation of workshop is poor, and workman's testing environment is abominable, and labour intensity is large; The normal eye namely can dim eyesight, the discomfort such as eye is swollen about uninterrupted observation moving object 30min, and for a long time non-stop run of testing staff can't guarantee the product export qualification rate; It is to be with very high-precision detection, human eye accurately to judge that scales of injector needle cylinders detects, and error is large, and the chance of makeing mistakes is a lot, can't guarantee to detect quality; The speed that the professional detects scales of injector needle cylinders is up to 0.5/s, and throughput rate is had very big restriction.
The content of invention
Online detection dependence to scales of injector needle cylinders manually detects for prior art, the workman easily produces visual fatigue, labour intensity is large, can't guarantee product percent of pass and detect quality, the problems such as monitoring velocity is low the invention provides a kind of NI Vision Builder for Automated Inspection to the automatic testing method of scales of injector needle cylinders, and it reduces workman's detection labour intensity greatly, accuracy of detection is high, speed is fast, the qualification rate of the product that can effectively guarantee to dispatch from the factory.
Technical scheme of the present invention is as follows:
A kind of NI Vision Builder for Automated Inspection may further comprise the steps the automatic testing method of scales of injector needle cylinders:
(1) end face with injector syringe is fixed on the frock bar anchor clamps, makes frock bar anchor clamps on-line operation, the shooting camera is fixed on frock bar anchor clamps one side of on-line operation; According to the size of injector syringe to be detected and injector syringe towards, select the focal length of camera lens, adjust shooting angle, shooting distance, aperture size, the time for exposure of taking camera, in order to obtain clearly photographic images;
(2) start described industrial camera, the pre-syringe dial chart picture of taking a standardized product, and with the image transmitting taken to computer, computer is processed by image algorithm, extract the image of scales of injector needle cylinders, this scales of injector needle cylinders image of obtaining as the scale merit image, is stored in the computer;
(3) will be made as the detection parameter with the difference ratio of scale merit image, and accuracy of detection and the acceptability limit of described detection parameter will be set according to customer requirements;
(4) computer is obtained camera and production process synchronous triggering and control signal, starts the image that described camera is taken the on-line operation scales of injector needle cylinders in real time by external trigger and control signal, and with the image transmitting taken to computer for detecting;
(5) computer is processed by image algorithm, extracts the image of scales of injector needle cylinders;
(6) computer calculates the difference ratio of described scales of injector needle cylinders image and scale merit image; This difference ratio is the ratio that accounts for this correspondence image piece area in the scale merit image in each image block in the described scales of injector needle cylinders image and the scale merit image with the area discrepancy of its correspondence image piece, get the maximum in the aforementioned proportion, the difference ratio that this ratio maximum namely is scales of injector needle cylinders;
(7) judge that by the difference ratio that calculates this product belongs to certified products or waste product, by external trigger and control signal waste product is rejected from the discharging opening of appointment.
Its further technical scheme is: to described (7) step, specifically carry out in the steps below judgement and the go-on-go of scale:
(8) whether judge scale difference ratio at acceptability limit<10%, as then turned to for (9) step at acceptability limit, if item turned to for (10) step more than or equal to acceptability limit 〉=10%;
(9) sort as certified products;
(10) directly as goods rejection.
And its further technical scheme is: to described (7) step, when detecting product and be waste product, computer will carry out picture cues by man-machine interface, and start warning device.
Useful technique effect of the present invention is:
The present invention adopts NI Vision Builder for Automated Inspection that scales of injector needle cylinders is carried out automatic on-line and detects, and replaces manual detection, and the user can carry out the adjusting of accuracy of detection automatically.Have the record, classification, statistics, storage, the query function that product are detected certified products, this two series products of waste product.And in image, point out the defective work situation by friendly man-machine interface, and give sound, light alarm, greatly reduce workman's detection labour intensity.
Manual detection speed is generally 0.5/s, and the NI Vision Builder for Automated Inspection detection speed can reach 3 ~ 4/s, and the product detection speed of NI Vision Builder for Automated Inspection is artificial 6 ~ 8 times, has greatly improved production efficiency.
Manual detection can't uninterruptedly be carried out product quality in 24 hours and detect owing to environment and physiological reason, adopted NI Vision Builder for Automated Inspection to detect and then made it become possibility.The production time of equipment can prolong to greatest extent, has improved the utilization rate of equipment.
The artificial detection because poor, the vision fatiguability that ventilates is difficult to the Continuous Tracking product quality.Detect accuracy and guarantee by artificial being difficult to, improper defect rate generally about 8 ~ 10%, has caused the significant wastage of the resources of production and production cost; The accuracy of detection of NI Vision Builder for Automated Inspection is higher, thereby greatly improves product percent of pass and detect quality.
Description of drawings
Fig. 1 is normal syringe graduation image.
Fig. 2 is the syringe graduation image that has the scale disappearance.
Fig. 3 is the syringe graduation image that exists scale excessively thick.
Fig. 4 is process sequence diagram of the present invention.
The specific embodiment
Below in conjunction with accompanying drawing the specific embodiment of the present invention is described further.
Fig. 1, Fig. 2, Fig. 3 take from the injector syringe side and real image after treatment.
In Fig. 1, Fig. 2, photographic images shown in Figure 3, blank parts is the transparent space after the injector syringe image is processed through denoising software all around, shown in lines be profile, scale and digital picture after injector syringe is processed.
Embodiment 1, to there being the detection of scale disappearance product:
Scales of injector needle cylinders image as shown in Figure 2, wherein there is the scale disappearance in capable 20, the scale capable 15 of scale.
Basler ACA640-100GM type industrial camera is fixed on the side of injector syringe, camera is about 100mm apart from the distance of injector syringe side, uses to execute and bears zoom lens, and focal length transfers to 8mm, and aperture is transferred to maximum, and the time for exposure is adjusted to 0.41ms.Set the normal scale disappearance of certified products ratio and be 10% to the maximum.Adopt special-purpose White LED bowl light source, shine (positive light) from the same side of the relative injector syringe of camera, and block the impact that the metal framework shields extraneous veiling glare with semiclosed, in order to obtain visual pattern more stablely, embody the obvious characteristic of scales of injector needle cylinders.The LED bowl light source of this project uses the machine vision special light source (also can use the LED bowl light source of other companies) of CCS company, in order to can photograph clearly image more stablely, and is shown in the screen of computer.Adopt the frock bar anchor clamps on the production line that the end face of injector syringe is fixed, the end face unification that makes each injector syringe towards (owing to also being so fixing end face during at the printing scale, therefore unified end face towards, namely unified scale towards).Carry out the conveying of injector syringe by belt transmission system, guarantee that injector syringe by certain direction and speed, stably enters checkout gear.
Start described industrial camera, the pre-syringe dial chart picture of taking a standardized product, and with the image transmitting taken to computer, computer is processed by image algorithm, extract the image of scales of injector needle cylinders, this scales of injector needle cylinders image of obtaining as scale merit image (such as Fig. 1), is stored in the computer.
Computer is according to the different control systems of institute of different production firm production equipment, obtain the synchronous triggering of camera and production process and control signal, start described industrial camera and take the image of the scales of injector needle cylinders disappearance of on-line operation, and with the scales of injector needle cylinders disappearance image that obtains, be stored in the computer.
Computer carries out image to captured image by edge extracting, smoothing denoising, binary conversion treatment, Fourier Tranform scheduling algorithm to be processed, and makes image more clear, more meets the truth of scales of injector needle cylinders disappearance.The algorithm that adopts in the above-mentioned image processing process is conventional algorithm of the prior art.
Computer calculates the disappearance ratio of scales of injector needle cylinders.This disappearance ratio be in each image block in the described scale disappearance image and the scale merit image with the area discrepancy of its correspondence image piece, the ratio that accounts for the area of this correspondence image piece in the scale merit image is (capable for scale, refer in every delegation scale and the scale merit image area discrepancy with its corresponding row scale, account for the ratio of the area of this corresponding row scale in the scale merit image; For the scale numeral, refer in each scale numeral and the scale merit image area discrepancy of corresponding scale numeral with it, account in the scale merit image ratio of area that should correspondence scale numeral), get the maximum in the aforementioned proportion, this maximum namely is the disappearance ratio of scales of injector needle cylinders.
As the disappearance ratio that detects scale capable 20 is 50%, the disappearance ratio of scale capable 15 is the situation among 9%(Fig. 2); Then to get maximum be 50% to the disappearance ratio of this product, and then this product is defective work.Such as detected disappearance ratio for all less than 10%, then this product is certified products.Computer is pointed out the defective work situation by friendly man-machine interface in image, and gives sound, light alarm, and certified products are recorded, classify, add up warehouse-in.
Embodiment 2, to exist scale excessively thick/detection of meticulous product:
Scales of injector needle cylinders image as shown in Figure 3, wherein capable 1, the scale capable 2 of capable 0, the scale of scale exists scale excessively thick.
Basler ACA640-100GM type industrial camera is fixed on the side of injector syringe, camera is about 100mm apart from the distance of injector syringe side, uses to execute and bears zoom lens, and focal length transfers to 8mm, and aperture is transferred to maximum, and the time for exposure is adjusted to 0.41ms.Set the normal scale of certified products excessively thick/meticulous ratio is 10% to the maximum.Adopt special-purpose White LED bowl light source, shine (positive light) from the same side of the relative injector syringe of camera, and block the impact that the metal framework shields extraneous veiling glare with semiclosed, in order to obtain visual pattern more stablely, embody the obvious characteristic of scales of injector needle cylinders.The LED bowl light source of this project uses the machine vision special light source (also can use the LED bowl light source of other companies) of CCS company, in order to can photograph clearly image more stablely, and is shown in the screen of computer.Adopt the frock bar anchor clamps on the production line that the end face of injector syringe is fixed, the end face unification that makes each injector syringe towards (owing to also being so fixing end face during at the printing scale, therefore unified end face towards, namely unified scale towards).Carry out the conveying of injector syringe by belt transmission system, guarantee that injector syringe by certain direction and speed, stably enters checkout gear.
Start described industrial camera, the pre-syringe dial chart picture of taking a standardized product, and with the image transmitting taken to computer, computer is processed by image algorithm, extract the image of scales of injector needle cylinders, this scales of injector needle cylinders image of obtaining as scale merit image (such as Fig. 1), is stored in the computer.
Computer is according to the different control systems of institute of different production firm production equipment, obtain the synchronous triggering of camera and production process and control signal, start described industrial camera and take the excessively thick image of scales of injector needle cylinders of on-line operation, and the scales of injector needle cylinders that obtains crossed thick image, be stored in the computer.
Computer carries out image to captured image by edge extracting, smoothing denoising, binary conversion treatment, Fourier Tranform scheduling algorithm to be processed, and makes image more clear, more meets the excessively thick truth of scales of injector needle cylinders.The algorithm that adopts in the above-mentioned image processing process is conventional algorithm of the prior art.
Computer calculates the thick ratio of the mistake of scales of injector needle cylinders.This cross thick ratio be in each image block in the described scale disappearance image and the scale merit image with the area discrepancy of its correspondence image piece, the ratio that accounts for the area of this correspondence image piece in the scale merit image is (capable for scale, refer in every delegation scale and the scale merit image area discrepancy with its corresponding row scale, account for the ratio of the area of this corresponding row scale in the scale merit image; For the scale numeral, refer in each scale numeral and the scale merit image area discrepancy of corresponding scale numeral with it, account in the scale merit image ratio of area that should correspondence scale numeral), get the maximum in the aforementioned proportion, this maximum namely is the thick ratio of the mistake of scales of injector needle cylinders;
As the thick ratio of mistake that detects scale capable 0 is 20%, and the thick ratio of mistake of scale capable 1 and scale capable 2 is the situation among 8%(Fig. 2); Then to get maximum be 20% to the thick ratio of the mistake of this product, and then this product is defective work.Such as the thick ratio of detected mistake for all less than 10%, then this product is certified products.Computer is pointed out the defective work situation by friendly man-machine interface in image, and gives sound, light alarm, and certified products are recorded, classify, add up warehouse-in.
For the meticulous image of scale, its detection method and in like manner above-mentioned.
In above-mentioned two embodiment, also have other unknown scale flaw images to occur if process discovery through image algorithm, think that then this injector syringe is defective work, rejects this injector syringe as waste product.
The control system (hardware and software) of the image capture device that uses among above all embodiment (camera, radiation source, power supply, image pick-up card etc.) and storage device (hard disk, CD, floppy disk etc.), image processing equipment (hardware of image processor and software), image display (hardware and software), warning device and each part mentioned above all adopts prior art to design and produce or directly adopts relevant commercially available prod.
Above-described processing step of the present invention is shown in Fig. 4.
It should be noted that at last above-described only is preferred embodiment of the present invention, the invention is not restricted to above embodiment.Be appreciated that other improvement and variation that those skilled in the art directly derive or associate under the prerequisite that does not break away from spirit of the present invention and design, all should think to be included within protection scope of the present invention.

Claims (3)

1. a NI Vision Builder for Automated Inspection is characterized in that may further comprise the steps to the automatic testing method of scales of injector needle cylinders:
(1) end face with injector syringe is fixed on the frock bar anchor clamps, makes frock bar anchor clamps on-line operation, the shooting camera is fixed on frock bar anchor clamps one side of on-line operation; According to the size of injector syringe to be detected and injector syringe towards, select the focal length of camera lens, adjust shooting angle, shooting distance, aperture size, the time for exposure of taking camera, in order to obtain clearly photographic images;
(2) start described camera, the pre-syringe dial chart picture of taking a standardized product, and with the image transmitting taken to computer, computer is processed by image algorithm, extract the image of scales of injector needle cylinders, this scales of injector needle cylinders image of obtaining as the scale merit image, is stored in the computer;
(3) will be made as the detection parameter with the difference ratio of scale merit image, and accuracy of detection and the acceptability limit of described detection parameter will be set according to customer requirements;
(4) computer is obtained camera and production process synchronous triggering and control signal, starts the image that described camera is taken the on-line operation scales of injector needle cylinders in real time by external trigger and control signal, and with the image transmitting taken to computer for detecting;
(5) computer is processed by image algorithm, extracts the image of scales of injector needle cylinders;
(6) computer calculates the difference ratio of described scales of injector needle cylinders image and scale merit image; This difference ratio is the ratio that accounts for this correspondence image piece area in the scale merit image in each image block in the described scales of injector needle cylinders image and the scale merit image with the area discrepancy of its correspondence image piece, get the maximum in the aforementioned proportion, the difference ratio that this ratio maximum namely is scales of injector needle cylinders;
(7) judge that by the difference ratio that calculates this product belongs to certified products or waste product, by external trigger and control signal waste product is rejected from the discharging opening of appointment.
2. described NI Vision Builder for Automated Inspection is characterized in that described (7) step is specifically carried out judgement and the go-on-go of scale in the steps below to the automatic testing method of scales of injector needle cylinders according to claim 1:
(8) whether judge scale difference ratio at acceptability limit<10%, as then turn at acceptability limit (9) step, if 〉=10% turn to (10) step;
(9) sort as certified products;
(10) directly as goods rejection.
3. described NI Vision Builder for Automated Inspection is characterized in that when detecting product and be waste product, computer will carry out picture cues by man-machine interface to described (7) step, and starts warning device the automatic testing method of scales of injector needle cylinders according to claim 1.
CN 201110109643 2011-04-29 2011-04-29 Method for automatically detecting scales of injector needle cylinders by using machine vision system Expired - Fee Related CN102303019B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201110109643 CN102303019B (en) 2011-04-29 2011-04-29 Method for automatically detecting scales of injector needle cylinders by using machine vision system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201110109643 CN102303019B (en) 2011-04-29 2011-04-29 Method for automatically detecting scales of injector needle cylinders by using machine vision system

Publications (2)

Publication Number Publication Date
CN102303019A CN102303019A (en) 2012-01-04
CN102303019B true CN102303019B (en) 2013-01-02

Family

ID=45376987

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201110109643 Expired - Fee Related CN102303019B (en) 2011-04-29 2011-04-29 Method for automatically detecting scales of injector needle cylinders by using machine vision system

Country Status (1)

Country Link
CN (1) CN102303019B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110763687A (en) * 2019-10-30 2020-02-07 江苏理工学院 Medical treatment cylinder syringe defect detecting device
CN111569191A (en) * 2020-05-27 2020-08-25 广州市赛康尼机械设备有限公司 Detection method, clearance inspection equipment and screw rod system
CN111947576A (en) * 2020-08-19 2020-11-17 广州市赛康尼机械设备有限公司 Method, device and system for detecting position of screw rod of labeling machine and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2280155Y (en) * 1996-10-08 1998-04-29 辽河石油勘探局测井公司 Graduation checking tool of sound wave well surveying instrument
KR20050013345A (en) * 2003-07-28 2005-02-04 백우인 Device for printing of injector
CN101424514A (en) * 2008-12-04 2009-05-06 上海大学 Band tape graduation on-line automatic detection system and method based on image processing
CN101644585A (en) * 2008-08-06 2010-02-10 北京谊安医疗系统股份有限公司 Detection device used for syringe putter of syringe pump

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2765559C (en) * 2009-06-18 2017-09-05 Peer Medical Ltd. Multi-camera endoscope

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2280155Y (en) * 1996-10-08 1998-04-29 辽河石油勘探局测井公司 Graduation checking tool of sound wave well surveying instrument
KR20050013345A (en) * 2003-07-28 2005-02-04 백우인 Device for printing of injector
CN101644585A (en) * 2008-08-06 2010-02-10 北京谊安医疗系统股份有限公司 Detection device used for syringe putter of syringe pump
CN101424514A (en) * 2008-12-04 2009-05-06 上海大学 Band tape graduation on-line automatic detection system and method based on image processing

Also Published As

Publication number Publication date
CN102303019A (en) 2012-01-04

Similar Documents

Publication Publication Date Title
CN102303017B (en) Method for automatically detecting bending of injector steel needles by using machine vision system
CN101696945B (en) On-line detection method of machine vision system to photovoltaic glass flaws
CN101509766B (en) On-line detecting method for spring end plane angle by machine vision system
CN102494773A (en) Automatic detection method of machine vision system on snap-fastener chromatic aberration
CN102303018B (en) Method for automatically detecting burrs of injector steel needles by using machine vision system
CN203750868U (en) Computer vision-based burr detection device
CN101696943B (en) On-line detection method of machine vision system to medical surgical knife flaws
CN101696877A (en) On-line detection method of machine vision system to spring verticality
CN101726265A (en) Online detection method of parallelism of spring by machine vision system
CN102218406A (en) Intelligent detection device of defects of mobile phone outer shell based on machine vision
CN104614379A (en) Plate surface defect detection system and method
CN106706656A (en) Machine vision-based zipper detection device and method
CN104132945A (en) On-line surface quality visual inspection device for bar based on optical fiber conduction
CN102305597A (en) Method for automatically detecting abnormal shape of injector part by using mechanical vision system
CN102303019B (en) Method for automatically detecting scales of injector needle cylinders by using machine vision system
CN102305592A (en) Method for automatically detecting back-stitching of steel needle of injector by using mechanical vision system
CN102305603B (en) Method for automatically detecting inclination of steel needle of injector by machine vision system
CN202351182U (en) Online high-speed detection system for defects on surface of tinplate
CN102305797A (en) Method for automatically detecting foreign matter of medical product package by using machine vision system
CN115423785A (en) Defect detection system, method and device, electronic equipment and storage medium
CN102305950A (en) Method for automatically detecting missed accessory during automatic assembly of injector by using machine visual system
CN102507602A (en) Method for automatically detecting rupture of infusion bottle mouth by using machine vision system
CN108195847A (en) A kind of relief pattern Online Video detection device and its detection method
CN102495077A (en) Automatic detecting method of machine vision system for detecting flaws of infusion bottle
CN202074946U (en) Cigarette case appearance detecting device

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

Granted publication date: 20130102