CN102565083A - Offline inspection system and method for printed electronic product - Google Patents

Abstract

The invention discloses an offline inspection system for a printed electronic product. The offline inspection system comprises an image acquisition system, an image processing system and an alarm prompt system. The invention additionally discloses an offline inspection method for the printed electronic product. The offline inspection method comprises the following steps of: 1) using the image acquisition system to acquire the image of the finished printed electronic product; 2) using the image processing system to find out the difference between the real-time acquired image and the image of a sample; 3) pointing out defects and using the alarm prompt system to give out an alarm in time; and 4) using the image processing system to conduct statistical analysis to the defects. By using the system and the method to inspect the printed electronic product off line, the inspection efficiency is high, the inspection accuracy is high, the product quality can be effectively improved and the reject rate is reduced at the same time.

Description

A kind of printing electronic product off-line checking system and method

Technical field

The present invention relates to print product detection technique field, be meant a kind of printing electronic product off-line checking system and method especially.

Background technology

No matter international or domestic, the printing electronic product is owing to use printing technology (is main with serigraphy and ink jet printing), and wherein ink jet printing is the inevitable choice of printing that becomes more meticulous.Therefore, the printing defects problem that in the paper products printing process, exists exists at the printing process of printing electronic product equally inevitably:

● register trouble: the base unit of chip is a transistor; Transistor has sandwich constructions such as insulated substrate layer, N-type semiconductor, P-type semiconductor, electrode, passivating film; The material of every layer of structure is different, needs the multiplex priting operation, adopts different ink materials just can be completed for printing respectively.For guaranteeing the consistance and the stability of transistor electrical parameter, require the position of per pass printing process chromatography very accurate.Because the tension force of organic film influences with variation of ambient temperature, cause the problem of printing register trouble easily, thereby cause the transistor electricity performance parameter to destroy and scrap, like untimely online detection, in the batch printing of volume to volume, will cause huge waste.

● circuit adhesion: when the close between circuit and the circuit,, cause signal shorts, destroy circuit function because the expansion of electrically conductive ink ink droplet and the variation of permeance property might a bit be sticked together adjacent two lines at certain.

● circuit breaks off: when circuit very narrow, in the spray printing process because the contingency of shower nozzle is stopped up or shake, and dust granule, winged insect etc. drop on will the circuit of spray printing on, cause the spray printing circuit to break off, signal can't pass through, thereby destroys circuit function.

● the circuit thickness is inhomogeneous: in the spray printing process, stop up owing to the contingency of shower nozzle or the mechanical shaking of printing platform causes, influence the electrical parameter of circuit.

● the circuit edge is rough, because the mechanical shaking of printing platform, or the variation of the expansion of ink droplet and permeance property, makes the circuit marginal existence burr of spray printing, influences the electrical parameter of circuit.

The quality on-line detection system of paper printed matter just rises at present, is used to print the detection of electronic product printing quality but can not directly take back.At first, both accuracy of detection require different, and the former accuracy of detection is low relatively, and the requirement of the latter's accuracy of detection is higher, and are also higher to algorithm and equipment requirements; Secondly, the latter's circuit surface has the metallic luster reflection, and imaging is had bigger interference, requires higher to image processing algorithm.

Summary of the invention

In view of this, the objective of the invention is to propose a kind of printing electronic product off-line checking system and method, it can carry out offline inspection to the finished product of printing electronic product, guarantees product percent of pass, and the auxiliary properties of product of optimizing.

Based on above-mentioned purpose a kind of printing electronic product off-line checking system provided by the invention, comprising:

Image capturing system; Comprising lighting source, camera, scrambler, image pick-up card; Said lighting source shines printing electronic product surface; Said camera is vertically taken printing electronic product surface, utilizes the scrambler control that is connected with the printing equipment controller to print the synchronized movement of the shooting action of electronic product and camera, and collects the printing electronic product information through the image pick-up card that is connected on the camera;

Image processing system, comprising computing machine, be used to search for printing defects the printing defects detection system based on Fast template matching algorithm, be used for the printing defects sorter of printing equipment fault diagnosis;

The alarm system is comprising alarm controller and alarm.

Optional, said printing electronic product to be detected is provided with triggered mark, and said image capturing system is provided with the triggering sensor, when said triggering sensor sensing arrives triggered mark, triggers said camera and carries out IMAQ.

Preferable, also be provided with on the image capturing system and be used for the synchronous photoelectric encoder of IMAQ.

Preferable, said Fast template matching algorithm is the modified genetic algorithm, utilizes low precision search to get rid of impossible position earlier, uses the searched with high precision defective again.

Optional, said printing defects sorter is divided into wire, point-like, band shape, planar with printing defects, and the defective classification is carried out statistical study.

The present invention also provides a kind of printing electronic product off-line checking method, comprises the following steps:

Real-time continuous is gathered the printing electronic product image that printing equipment is produced, and its size of adopting graph region is consistent with the examination criteria template size;

Adopt the Flame Image Process Fast template matching algorithm, real-time images acquired and examination criteria template are mated and contrast, find with the inconsistent place of examination criteria template and be defective locations;

Utilize the printing defects detection system that defective locations is analyzed, iris out the size and the shape of defective, and in former figure frame, indicate the position and the shape of defective, on graphoscope, show, provide alerting signal simultaneously to alarm controller, alarm equipment alarm;

Printing defects is divided into wire, point-like, band shape, planar, adds up respectively and deposit, be used for the later stage inquiry and show the picture frame that all kinds of defectives are corresponding, realize playback again and analysis.

Optional, described camera is industrial camera or smart camera.

Optional, described camera is face battle array industrial camera or linear array industrial camera.

Accordingly, described lighting source is chosen as area array light source or strip light source.

Preferable, the IMAQ mode of described camera acquisition testing standard form is the one-step control mode.

Optional, described examination criteria template is to obtain through the image information of gathering printing electronic product sample, or directly calls existing template from computing machine.

Preferable, said camera keeps vertical with printing electronic product surface, and the scrambler control that is connected with the printing equipment controller of utilization and keep camera picked-up action and print synchronous that electronic product moves.

Saidly can find out from top; A kind of printing electronic product off-line checking system provided by the invention and method; Printing electronic product through the online detection of this system and method; Its detection efficiency and accuracy of detection all are superior to common print product detection mode greatly, and can effectively improve the quality of products and reduce the number of rejects and seconds rate simultaneously.

Description of drawings

Fig. 1 is the printing electronic product off-line checking system synoptic diagram of the embodiment of the invention;

Fig. 2 is a template matching algorithm in the embodiment of the invention, and when being K=2, template size is 4 * 4 o'clock, the pixel synoptic diagram of selecting when carrying out rough matching;

Fig. 3 is that template matching algorithm improves later algorithm flow chart synoptic diagram in the embodiment of the invention.

Embodiment

For making the object of the invention, technical scheme and advantage clearer, below in conjunction with specific embodiment, and with reference to accompanying drawing, to further explain of the present invention.

With reference to figure 1; Be the printing electronic product off-line checking system synoptic diagram of the embodiment of the invention, comprising lighting source 1, checkout equipment roll shaft 2, camera 3, scrambler 4, image pick-up card 5, computing machine 6, alarm controller 7, alarm 8, printing electronic product 9, triggered mark 10.

Wherein, image capturing system has comprised lighting source 1, camera 3, scrambler 4, image pick-up card 5 and has been arranged on the triggered mark 10 on the printing electronic product 9; Image processing system has comprised computing machine 6, and 6 in computing machine has comprised printing defects detection system and printing defects sorter; The alarm system has comprised alarm controller 7 and alarm 8.

Described image capturing system is erected at the checkout equipment top; The surface of lighting source 1 oblique illumination printing at a certain angle electronic product 9; The surface of printing electronic product 9 is provided with triggered mark 10; The rotation of checkout equipment roll shaft 2 drives printing electronic product 9 and travels forward; Checkout equipment top is provided with the triggering sensor accordingly with triggered mark 10 positions, and said triggered mark 10 is set to, when the reference position of the part of printing electronic product 9 required detections move to camera 3 under the time; Trigger said triggering sensor and send the signal that begins to gather to said camera 3; Camera 3 begins to absorb the image information on printing electronic product 2 surfaces, said camera 3 be arranged on the said printing electronic product 2 that need carry out IMAQ the surface directly over, said camera 3 is vertically taken printing electronic product 2 surfaces; Utilize the scrambler 4 that is connected with the printing equipment controller to control the synchronized movement of the shooting action of printing electronic products 2 and camera 3, and collect the image information of printing electronic product 2 through the image pick-up card 5 that is connected on the camera 3.

Computing machine 6 in the said image processing system is after the image information that receives the image capturing system collection; Image information is carried out defective through the printing defects detection system that adopts a kind of Fast template matching algorithm based on improved genetic algorithm and is searched in computing machine 6; It utilizes low precision search to get rid of impossible position earlier; With the searched with high precision matched position and find defective, this algorithm principle is following again:

Only need find approximate location get final product in genetic algorithm part, and if malposition also can pass through climbing method and return the continued searching, matching process and adopt rough matching process accurately during coupling.In the matching process of each coordinate points, need not compare, but selected part point gets final product corresponding point in points all in the template and the original image.Choose the pixel that is spaced apart K on the template on the level and vertical direction and mate, the calculated amount of genetic algorithm part is original 1/K like this ², the situation when Fig. 1 is K=2.Genetic algorithm fitness function after the improvement is following:

Wherein:

At genetic algorithm Partial K=min{P, Q}/10, and, promptly partly still adopt original accurate matching process at climbing method in climbing method Partial K=1, can guarantee the accuracy of algorithm like this.

With reference to figure 2, be K=2, template size is 4 * 4 o'clock, the pixel of selecting when carrying out rough matching; Grey color dot is to choose the point that matees among Fig. 2.

In order to prevent that the point that carried out the climbing method search from getting into the climbing method search procedure once more; Increased the point that a searching route table is kept at process in the climbing method process in the algorithm; When the optimum position is the point in the routing table, just no longer get into the climbing method search procedure.

Improve later algorithm flow chart with reference to figure 3.

Can find out, this algorithm utilized genetic algorithm fast search speed reduce match time, utilize the climbing method local search ability strong simultaneously, the advantage that can rapidly converge to the exact position guarantees matching precision.Secondly, this algorithm also incorporated first thick after carefully, accurate searching idea progressively, when beginning to search for, utilize low precision search, get rid of impossible position fast; Adopt the searched with high precision matching process in possible position, find the exact position.And compare with traditional matching algorithm, the speed of this algorithm is faster, locatees more accurate.

After image processing system finds defective, this information is delivered to the alarm system, alarm controller 7 receives alerting signal, and it is delivered to alarm 8, and alarm 8 is reported to the police, and defective has appearred in prompting staff print product.

In addition, image processing system carries out fault diagnosis through the printing defects sorter in the computing machine 6 to printing equipment, and its principle is following:

Extract the profile of defective, it is carried out ellipse fitting, measure the parameter information of defective at last: defect area, barycentric coordinates, major and minor axis length.

The area that the simplest provincial characteristics is the zone:

$a=\left|R\right|=\underset{(r,c)\∈R}{\mathrm{\Σ}}1=\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{ce}}_i-{\mathrm{cs}}_i+1---\left(1\right)$

Can know that by following formula the area a in zone is exactly counting in the zone | R|.If the zone representes with a width of cloth bianry image, so with the area of first the equality zoning of suing for peace in the following formula; If the zone representes with run-length encoding, so with the area of second in the following formula equality zoning of suing for peace.

Area is a special case that is called as in the generalized character of square in zone.P >=0, q >=0 o'clock, (p, q) the rank square is defined as:

$m_{p,q}=\underset{(r,c)\∈R}{\mathrm{\Σ}}{r}^p{c}^q---\left(2\right)$

Note m _0,0It is exactly the area in zone.Similar with reference area, calculate square because only can derive based on the simple equation of stroke, so just can calculate square expeditiously when using the stroke representation.

Square in the equality (2) depends on the size in zone.Usually our expectation has some characteristics not change with dimension of object, and for obtaining such characteristic, when p+q >=1, square has just obtained normalized square divided by the area in zone:

$n_{p,q}=\frac{1}{a}\underset{(r,c)\∈R}{\mathrm{\Σ}}{r}^p{c}^p---\left(3\right)$

The most interesting characteristic that obtains from normalized square derivation is the center of gravity in zone, i.e. (n _1,0, n _0,1).It can be used to describe the position in zone.

Normalized square is by the determining positions in the image.Usually, characteristic is not changed is of great use with the change in location in zone in the image.This can realize with respect to the square of regional barycenter through calculating.These central moments are obtained by computes when (p+q >=2):

${\mathrm{\μ}}_{p,q}=\frac{1}{a}\underset{(r,c)\∈R}{\mathrm{\Σ}}{(r-n_{\mathrm{1,0}})}^p{(c-n_{\mathrm{0,1}})}^q---\left(4\right)$

Notice that these central moments also are after normalization is handled.Second-order moment around mean (p+q=2) especially merits attention, they can be used for defined range direction with the zone scope.This is to realize from first moment and second moment that an ellipse obtains the zone through hypothesis.Then, derive five oval geometric parameters from these five squares.Oval center is consistent with the center of gravity in zone.Long axis of ellipse r ₁With minor axis r ₂, and can obtain by computes with respect to the angle of transverse axis:

$r_1=\sqrt{2({\mathrm{\μ}}_{\mathrm{2,0}}+{\mathrm{\μ}}_{\mathrm{0,2}}+\sqrt{{({\mathrm{\μ}}_{2,0}-{\mathrm{\μ}}_{\mathrm{0,2}})}^2+4{\mathrm{\μ}}_{\mathrm{1,1}}^2})}$

${\mathrm{<figure-callout\; id="2"\; label="r"\; filenames="HDA0000130373480000011.png,HDA0000130373480000012.png"\; state="\{\{state\}\}">r</figure-callout>}}_2=\sqrt{2({\mathrm{\&mu;}}_{\mathrm{2,0}}+{\mathrm{\&mu;}}_{\mathrm{0,2}}-\sqrt{{({\mathrm{\&mu;}}_{\mathrm{2,0}}-{\mathrm{\&mu;}}_{\mathrm{0,2}})}^2+4{\mathrm{\&mu;}}_{\mathrm{1,1}}^2})}---\left(5\right)$

$\mathrm{\&theta;}=-\frac{1}{2}\mathrm{<figure-callout\; id="2"\; label="arctan"\; filenames="HDA0000130373480000011.png,HDA0000130373480000012.png"\; state="\{\{state\}\}">arctan</figure-callout>}\frac{2{\mathrm{\&mu;}}_{\mathrm{1,1}}}{{\mathrm{\&mu;}}_{\mathrm{0,2}}-{\mathrm{\&mu;}}_{\mathrm{2,0}}}$

Through the parameter of ellipse, we can derive another very useful characteristic: anisotropy r ₁/ r ₂This characteristic quantity is to keep invariable when area zoom, and it can describe the elongated degree in a zone.

Classifier design:

If the printing image defect area is Area, the ratio R=r of minor axis and major axis ₂/ r ₁, then classifier design is following:

If (Area＜=4) then defective is a point-like;

If (Area＞4) and (R＜0.3) then defective is a wire;

If (Area＞4) and (0.3=＜R＜0.6) then defective is banded;

If (Area＞4) and (0.6=＜R＜=1) then defective is planar;

Above classifier design; Extract the AP characteristic of existing printing defects, made up the sorting criterion function of printing defects, formed the printing defects sorter; Can printing defects be divided into wire, point-like, band shape, planar class; And carry out statistical study, and be used for the fault diagnosis of printing equipment, be convenient to the follow-up printing equipment defective that is directed against and debug.

The printing electronic product off-line checking method that utilizes described printing electronic product off-line checking system to carry out is following:

The first step is provided with triggered mark 10 with the corresponding position of triggering sensor on printing electronic product 9 and its sample;

Second step; Open lighting source 1, light shines the sample of printing electronic product 9 at a certain angle, when triggering sensor sensing to triggered mark 10; Trigger camera 3 and vertically the sample surface of printing electronic product 2 is captured pickup image information; And a two field picture of preserving the sample that prints electronic product 9 as the examination criteria template, and defines the regional magnitude range of template to computing machine 6;

The 3rd step; Keep camera 3 and printing electronic product 9 Surface Vertical; And 4 controls of the scrambler that is connected with the printing equipment controller of utilization and keep camera 3 picked-up actions and 9 motions of printing electronic product synchronously; Utilize camera 3 and image pick-up card 5 real-time continuous to gather the image information of the printing electronic product 9 of printing equipment production, its size of adopting graph region is consistent with the examination criteria template size;

In the 4th step, computing machine 6 adopts the Flame Image Process Fast template matching algorithm through the printing defects detection system, and real-time images acquired and examination criteria template are mated and contrast, finds with the inconsistent place of examination criteria template and is defective locations;

The 5th step, utilize the printing defects detection system that defective locations is analyzed, iris out the size and the shape of defective; And in former figure frame, indicate the position and the shape of defective; On graphoscope, show, provide alerting signal simultaneously to alarm controller 7, alarm 8 is reported to the police;

The 6th step was divided into wire, point-like, band shape, planar with printing defects, added up respectively and deposited, and was used for the later stage inquiry and showed the picture frame that all kinds of defectives are corresponding, realized playback again and analysis.

Can find out; Through the printing electronic product of this system and method offline inspection, because of it has adopted the Fast template matching algorithm of modified genetic algorithm printing defects is searched, improved the efficient that defective is searched greatly; And precision is high; Thereby cooperate the detection efficiency of this System and method for of print product offline inspection of this algorithm high, accuracy of detection is high, and can effectively improve the quality of products and reduce the number of rejects and seconds rate simultaneously; Simultaneously, adopt the printing defects sorter that printing equipment is carried out fault diagnosis, can defective be carried out statistic of classification and analysis,, and printing equipment is carried out corresponding debugging play good booster action, saved time and efforts for the follow-up printing defects of searching.

It is to be noted; Said camera 3 is optional with industrial camera, smart camera or other cameras that can utilize machine vision to take; Preferably face battle array industrial camera or linear array industrial camera; 1 corresponding of lighting source can be selected area array light source or strip light source for use, and the IMAQ mode of camera acquisition testing standard form then is preferably the one-step control mode.

In addition, under the situation of conditions permit, described examination criteria template also can directly be called the existing Template Information that has stored in the computing machine 6, needn't all carry out IMAQ to the sample that prints electronic product at every turn; Triggered mark 10 can be provided with the setting that triggers sensor as required; And the effect that triggered mark 10 is set is to reject the part that does not need images acquired information; Between the part that needs images acquired at interval hour; Also can take the mode of continuous acquisition image, then need not to be provided with separately again triggered mark 10.

The those of ordinary skill in affiliated field is to be understood that: the above is merely specific embodiment of the present invention; Be not limited to the present invention; All within spirit of the present invention and principle, any modification of being made, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.

Claims (17)

1. a printing electronic product off-line checking system is characterized in that, comprising:

Image capturing system; Comprising lighting source, camera, scrambler, image pick-up card; Said lighting source shines printing electronic product surface; Said camera is vertically taken printing electronic product surface, utilizes the scrambler control that is connected with the printing equipment controller to print the synchronized movement of the shooting action of electronic product and camera, and collects the printing electronic product information through the image pick-up card that is connected on the camera;

Image processing system, comprising computing machine, be used to search for printing defects the printing defects detection system based on Fast template matching algorithm, be used for the printing defects sorter of printing equipment fault diagnosis;

The alarm system is comprising alarm controller and alarm.

2. printing electronic product off-line checking system according to claim 1; It is characterized in that; Said printing electronic product to be detected is provided with triggered mark; Said image capturing system is provided with the triggering sensor, when said triggering sensor sensing arrives triggered mark, triggers said camera and carries out IMAQ.

3. printing electronic product off-line checking system according to claim 1 is characterized in that, also is provided with on the image capturing system to be used for the synchronous photoelectric encoder of IMAQ.

4. printing electronic product off-line checking system according to claim 1; It is characterized in that; Said Fast template matching algorithm is the modified genetic algorithm, and utilizing earlier low precision search to get rid of can not the position, again with the searched with high precision matched position and find defective.

5. printing electronic product off-line checking system according to claim 1 is characterized in that said printing defects sorter is divided into wire, point-like, band shape, planar with printing defects, and the defective classification is carried out statistical study.

6. printing electronic product off-line checking system according to claim 1 is characterized in that described camera is industrial camera or smart camera.

7. a printing electronic product off-line checking method is characterized in that, comprises the following steps:

Real-time continuous is gathered the printing electronic product image that printing equipment is produced, and its size of adopting graph region is consistent with the examination criteria template size;

Adopt the Flame Image Process Fast template matching algorithm, real-time images acquired and examination criteria template are mated and contrast, find with the inconsistent place of examination criteria template and be defective locations;

Utilize the printing defects detection system that defective locations is analyzed, iris out the size and the shape of defective, and in former figure frame, indicate the position and the shape of defective, on graphoscope, show, provide alerting signal simultaneously to alarm controller, alarm equipment alarm;

Printing defects is divided into wire, point-like, band shape, planar, adds up respectively and deposit, be used for the later stage inquiry and show the picture frame that all kinds of defectives are corresponding, realize playback again and analysis.

8. printing electronic product off-line checking method according to claim 7; It is characterized in that; Said printing electronic product to be detected is provided with triggered mark; Said image capturing system is provided with the triggering sensor, when said triggering sensor sensing arrives triggered mark, triggers said camera and carries out IMAQ.

9. printing electronic product off-line checking method according to claim 7 is characterized in that, also is provided with on the image capturing system to be used for the synchronous photoelectric encoder of IMAQ.

10. printing electronic product off-line checking method according to claim 7; It is characterized in that; Said Fast template matching algorithm is the modified genetic algorithm, and utilizing earlier low precision search to get rid of can not the position, again with the searched with high precision matched position and find defective.

11. printing electronic product off-line checking method according to claim 7 is characterized in that said printing defects sorter is divided into wire, point-like, band shape, planar with printing defects, and the defective classification is carried out statistical study.

12. printing electronic product off-line checking method according to claim 7 is characterized in that described camera is industrial camera or smart camera.

13. printing electronic product off-line checking method according to claim 12 is characterized in that, described camera is face battle array industrial camera or linear array industrial camera.

14. printing electronic product off-line checking method according to claim 13 is characterized in that, described lighting source is area array light source or strip light source.

15. printing electronic product off-line checking method according to claim 7 is characterized in that, described examination criteria template is to obtain through the image information of gathering printing electronic product sample, or directly calls existing template from computing machine.

16. printing electronic product off-line checking method according to claim 15 is characterized in that the IMAQ mode of described camera acquisition testing standard form is the one-step control mode.

17. according to any described printing electronic product off-line checking method of claim 7 to 16; It is characterized in that; Said camera keeps vertical with printing electronic product surface, and the scrambler control that is connected with the printing equipment controller of utilization and keep camera picked-up action and print synchronous that electronic product moves.

Images