CN112798599A - Full-automatic smart card thread take-up system based on machine vision - Google Patents

Full-automatic smart card thread take-up system based on machine vision Download PDF

Info

Publication number
CN112798599A
CN112798599A CN201911107796.XA CN201911107796A CN112798599A CN 112798599 A CN112798599 A CN 112798599A CN 201911107796 A CN201911107796 A CN 201911107796A CN 112798599 A CN112798599 A CN 112798599A
Authority
CN
China
Prior art keywords
card
picking
image
thread
smart card
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911107796.XA
Other languages
Chinese (zh)
Inventor
梁鹏
郝刚
吴玉婷
齐建阳
郑振兴
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.)
Guangdong Polytechnic Normal University
Original Assignee
Guangdong Polytechnic Normal University
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 Guangdong Polytechnic Normal University filed Critical Guangdong Polytechnic Normal University
Priority to CN201911107796.XA priority Critical patent/CN112798599A/en
Publication of CN112798599A publication Critical patent/CN112798599A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8854—Grading and classifying of flaws
    • G01N2021/8861—Determining coordinates of flaws
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10048—Infrared image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20021—Dividing image into blocks, subimages or windows

Abstract

The invention discloses a full-automatic intelligent card thread picking system based on machine vision, which comprises an image acquisition subsystem, an image processing subsystem and a motion control subsystem, wherein the image acquisition subsystem is used for acquiring an intelligent card surface image after groove milling operation and thread picking are finished and transmitting the intelligent card surface image to the image processing subsystem through an image acquisition card; the image processing subsystem is composed of an upper computer and is used for calculating and obtaining the moving coordinate of the picking needle in a three-dimensional space by analyzing the image transmitted by the image acquisition card; and after the motion control card receives the instruction of the upper computer, the motion control card controls a three-axis driving device of the thread take-up module to drive the correct moving position of the thread take-up module and carry out thread take-up operation. The invention introduces a machine vision technology, reduces manual intervention, accurately positions the moving displacement of the picking needle, and accurately calculates the space moving coordinate of the picking needle before and after the thread picking operation, thereby reducing the waste card rate on the high-speed production line of the intelligent card.

Description

Full-automatic smart card thread take-up system based on machine vision
Technical Field
The invention relates to the field of smart card manufacturing, in particular to a full-automatic smart card thread take-up system based on machine vision.
Background
At present, the production flow of the IC card mainly comprises the following steps: the first procedure is to make the card body with built-in antenna by laminating; in the second procedure, a groove is milled at a designated position on the card, and the built-in antenna is exposed; the third procedure is to lift up the antenna exposed in the slot; straightening the picked antenna in the fourth procedure; and a fifth procedure of welding the antenna and the chip and packaging. In the prior art, the third process, thread picking, is mostly to place the IC card with the milled slot in a relatively fixed slot device on a conveyor belt, and then drive a manipulator to pick up the exposed antenna after the milled slot according to certain operation parameters.
In actual production, because the shapes and the positions of the metal wires embedded in each batch of smart cards are not uniform, the metal wires exposed after each groove milling cannot ensure the integrity of the appearance and the relative stability of the spatial position, and when the thread picking operation is performed on the picking needle, the currently adopted method is to manually set the three-dimensional space coordinates required by the mechanical motion of the picking needle for the batch of smart cards in advance and then perform blind picking. Problems with this approach are: 1) whether the metal wire of the intelligent card can be normally picked up is not confirmed before the picking, so that the intelligent card which can be directly discarded still carries out the picking operation, and wastes time and labor; 2) the thread picking is carried out without confirming the optimal thread picking position, so that the success rate of thread picking operation is low; 3) after the thread picking operation is completed by the picking needle, whether the smart card wire is normally picked out (note: there may be two cases here, in which the pick-up needle does not pick up the wire due to too short a vertical movement distance or the smart card is damaged by the pick-up needle due to too long a vertical movement distance). Both of these problems result in a straight-line increase in the rate of scrap cards on the production line.
The invention discloses an automatic IC card thread picking device and method based on machine vision [ CN201610545574.6] and designs an automatic thread picking device for an intelligent card, the device detects the IC card to be picked through the machine vision, screens and removes the waste card generated in the production process, positions and corrects the mechanical movement, and improves the production efficiency of the IC card. However, in actual production, the wire packaged in the smart card may be in an "M" shape or a "W" shape, and it is necessary to determine whether the wire is broken after the shape of the wire is confirmed, otherwise it is impossible to determine whether the thread picking position of the current card is the highest point or the lowest point, thereby causing the positioning failure of the thread picking point; in addition, if only a two-dimensional coordinate value of the horizontal plane movement is given, the vertical movement distance of the picking needle cannot be determined, so that the picking needle can be blindly picked only according to a numerical value set in advance. The problem with this invention still results in the failure of part of the thread-picking operation.
Therefore, the existing smart card thread-picking technology is further improved, and the rejection rate of the smart card caused by thread-picking failure is reduced.
Disclosure of Invention
In order to solve the technical problems, the invention provides a full-automatic intelligent card thread picking system based on machine vision, which introduces a machine vision technology to accurately position the three-dimensional space displacement of a picking needle, thereby reducing the waste card rate on the high-speed intelligent card production line.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows: the utility model provides a full-automatic smart card thread take-up system based on machine vision, includes image acquisition subsystem, image processing subsystem and motion control subsystem, wherein:
the image acquisition subsystem comprises a front-end image acquisition camera, a rear-end image acquisition camera and an image acquisition card, wherein the front-end image acquisition camera is used for acquiring a card surface image of the intelligent card after the groove milling operation is finished and transmitting the card surface image to the image processing subsystem through the image acquisition card; the rear-end image acquisition camera is used for acquiring the card surface image of the intelligent card after the wire picking is finished and transmitting the card surface image to the image processing subsystem through the image acquisition card;
the image processing subsystem is composed of an upper computer and is used for obtaining the moving coordinate of the picking needle in a three-dimensional space through calculation by analyzing the image transmitted by the image acquisition card and operating the motion control subsystem through a motion control card to carry out thread picking operation;
the motion control subsystem comprises a motion control card and a thread picking machine module, after the motion control card receives an instruction of an upper computer, the motion control card controls a three-axis driving device of the thread picking machine module to drive a moving part of the thread picking machine module to move a picking needle of the thread picking machine module to a moving coordinate of a three-dimensional space calculated by the upper computer, and thread picking operation is carried out.
Preferably, the image processing subsystem performs analysis processing on the received card face image of the smart card after the slot milling operation is completed: judging whether a metal wire packaged in the smart card body is W-shaped or M-shaped, and checking whether the metal wire is broken or not; and positioning the optimal thread picking position.
Preferably, the image processing subsystem performs a second analysis process on the received card face image of the smart card after the thread-picking operation is completed: judging whether the metal wire of the smart card is normally picked out or not; and judging whether the vertical movement displacement of the picking needle is proper or not.
Preferably, the thread take-up module is in including placing workstation, the support of treating the smart card of taking-up stand on the workstation with set up triaxial drive arrangement and moving part on the stand, be provided with the arm of taking-up on the triaxial drive part, install the take-up and take-up needle on the arm of taking-up, still be provided with infrared transmitter under treating the smart card of taking-up.
Preferably, the three-axis driving device comprises a vertical driving device, a longitudinal driving device and a transverse driving device, and the moving part comprises a vertical moving part, a longitudinal moving part and a transverse moving part;
the vertical moving part is connected with a vertical driving device, the longitudinal moving part is connected with a longitudinal driving device, and the transverse moving part is connected with a transverse driving device.
Preferably, the step of the image processing subsystem analyzing process one is as follows:
s1, image acquisition: when the intelligent card with the picked line enters the line picking position, infrared light emitted by an infrared emitter is shielded, an infrared receiving device in a front-end image acquisition camera does not receive an infrared signal, a motion control card is triggered to send a signal to an upper computer, and the upper computer sends an instruction for acquiring an image of the intelligent card to an image acquisition card;
the front-end image acquisition camera is driven by an image acquisition card to acquire images and transmit the acquired images to an upper computer;
s2: image preprocessing: the upper computer performs graying processing on the acquired color image, namely the gray value in the gray image is equal to the average value of RGB in the original color image, namely:
Gray＝(R+G+B)/3 (1)
s3: image binarization: carrying out binarization processing on the image after gray processing, namely setting the value of a pixel point larger than a certain threshold value as 1, and setting the values of the rest pixel points as 0:
Figure BDA0002268935740000031
in the formula, f (x, y) represents the gray value of a pixel point (x, y) before conversion, g (x, y) represents the value of the pixel point after conversion, and T is a binarization transformation threshold;
s4: edge extraction: extracting the edge of the image to extract the track of the metal wire in the card, adopting first order differential or second order differential operation to obtain the maximum value of the gradient or the zero crossing point of the second order differential, and finally selecting a certain threshold value to extract the edge of the image;
the Roberts operator is an operator that finds edges using a local difference operator, given by the following equation (3):
Figure BDA0002268935740000032
s5: after the accurate edge extraction of the card image is completed, the closed edge is used as a boundary block to obtain a corresponding block in the card slot area:
firstly, matching the shape of an M-shaped or W-shaped template prepared in advance, thereby determining the shape of a metal wire packaged in the current card; then, the block is averagely divided into a left half and a right half which are respectively called as a left block and a right block; then, the left block is subjected to left-to-right scanning, a point where effective content is detected firstly is recorded, and if the point is a certain distance away from the left boundary of the clamping groove, the fact that the metal wire is broken in the groove milling process is indicated; if the point is in direct contact with the card slot, the scanning is continued to the right boundary of the card slot, and if the situation that the effective content is discontinuous exists in the period, the metal wire is also broken.
Preferably, the step of locating the optimal thread-picking position by the image processing subsystem is as follows:
s6, after the accurate edge extraction of the card image is completed in the steps S1-S5, dividing the block by taking the closed edge as a boundary block to obtain blocks corresponding to the card slot area, dividing the block into a left half and a right half, respectively called as a left block and a right block, respectively scanning the left block and the right block line by line from top to bottom, and detecting the highest point of the effective content, namely the metal wire, namely the highest point of the required bent part.
8. The machine vision based fully automatic smart card thread take-up system as claimed in claim 7, wherein the thread take-up operation comprises the steps of:
d1, the motion control subsystem drives the transverse moving part of the picking needle to move the left and right picking needles to the accurate position of the transverse coordinate;
d2, the motion control subsystem drives the vertical moving part to vertically move the picking needle downwards until the picking needle head touches the smart card;
d3, the motion control subsystem drives the longitudinal moving part to move the picking needle longitudinally, and the needle head of the picking needle passes through the bottom of the metal wire;
and D4, the motion control subsystem drives the vertical moving part to vertically move the picking needle upwards so as to pick the metal wire out of the clamping groove.
Preferably, the image processing sub-analysis processing second judges whether the smart card wire is normally picked out; the method for judging whether the vertical movement displacement of the picking needle is proper is as follows:
f1, after finishing extracting the accurate edge of the card image, dividing the block by taking the closed edge as a boundary to obtain a corresponding block in the card slot area, averagely dividing the block into a left block and a right block which are respectively called as a left block and a right block, then respectively carrying out shape matching on the left block and the right block by using the left parabolic line segment and the right parabolic line segment obtained in S1-S5, and if only one edge is successfully matched, directly judging that the smart card is a waste card;
f2, if the two sides are successfully matched, further detecting a vertical line segment at the coordinate of the picking point, if the cross-section pixel value of the line segment is smaller than a specified threshold value, judging that no scratch is formed or the scratch is shallow, informing a motion control subsystem to increase a unit for the longitudinal displacement of the picking needle, judging the smart card as a waste card, and directly judging the rest conditions as the waste card;
f3, if the two sides are not matched successfully, further detecting a vertical line segment at the picking point coordinate, if the cross section pixel value of the line segment is larger than a specified threshold value, judging that the scratch is too deep, informing the motion control subsystem to reduce the longitudinal displacement of the picking needle by one unit, then judging the smart card as a waste card, and directly judging the other situations as a good card.
The invention has the beneficial technical effects that: the invention aims to establish a full-automatic intelligent card thread picking system based on machine vision, and accurately positions the moving coordinate of a picking needle through an image acquisition subsystem and an image processing subsystem. Through the image processing subsystem, before the thread picking operation, a two-dimensional coordinate value of the movement of the picking needle on the horizontal plane is judged, so that the precision of the thread picking position is ensured; after the thread picking operation, the distance value of the picking needle moving in the vertical direction is judged, so that the accuracy of the thread picking depth is ensured, and the waste card rate on the high-speed production line of the intelligent card is greatly reduced.
Drawings
FIG. 1 is a block diagram of the system of the present invention.
FIG. 2 is a schematic view of an "M" shaped wire on the smart card of the present invention.
FIG. 3 is a schematic view of a "W" shaped wire on the smart card of the present invention.
FIG. 4 is a schematic view of a "M" shaped wire break on the smart card of the present invention.
FIG. 5 is a schematic diagram of an optimal thread take-up position for an "M" shaped wire on a smart card of the present invention.
FIG. 6 is a schematic diagram of the success of the smart card wire take-up.
FIG. 7 is a schematic diagram of a failure of a smart card wire take-up.
FIG. 8 is a schematic view showing the picking needle of the present invention not reaching the clamping surface and the metal wire not being picked up.
FIG. 9 is a schematic diagram of the present invention with the picking needle too close to the clamping surface and the scratch too deep.
Fig. 10 is a schematic view of the internal structure of the wire picking machine module according to the present invention.
FIG. 11 is a schematic diagram of a thread-picking method according to the present invention.
Fig. 12 is a schematic view of the overall structure of the triaxial driving device and the moving member of the thread take-up module according to the present invention.
FIG. 13 is a diagram of the binarization effect of the wire image on the smart card collected by the present invention.
FIG. 14 is a graph of the effect of edge extraction of a wire image on a smart card collected in accordance with the present invention at different thresholds.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments, but the scope of the present invention is not limited to the following embodiments.
As shown in fig. 1-12, a fully automatic smart card thread-picking system based on machine vision includes an image acquisition subsystem, an image processing subsystem and a motion control subsystem, wherein:
the image acquisition subsystem comprises a front-end image acquisition camera, a rear-end image acquisition camera and an image acquisition card, wherein the front-end image acquisition camera is used for acquiring a card surface image of the intelligent card after the groove milling operation is finished and transmitting the card surface image to the image processing subsystem through the image acquisition card; the rear-end image acquisition camera is used for acquiring the card surface image of the intelligent card after the wire picking is finished and transmitting the card surface image to the image processing subsystem through the image acquisition card;
the image processing subsystem is composed of an upper computer and is used for obtaining the moving coordinate of the picking needle in a three-dimensional space through calculation by analyzing the image transmitted by the image acquisition card and operating the motion control subsystem through a motion control card to carry out thread picking operation;
the motion control subsystem comprises a motion control card and a thread picking machine module, after the motion control card receives an instruction of an upper computer, the motion control card controls a three-axis driving device of the thread picking machine module to drive a moving part of the thread picking machine module to move a picking needle of the thread picking machine module to a moving coordinate of a three-dimensional space calculated by the upper computer, and thread picking operation is carried out.
Specifically, the motion control card is a three-axis motion control card, the three-axis driving device comprises a vertical driving device, a longitudinal driving device and a transverse driving device, and the moving part comprises a vertical moving part, a longitudinal moving part and a transverse moving part; the vertical moving part is connected with a vertical driving device, the longitudinal moving part is connected with a longitudinal driving device, and the transverse moving part is connected with a transverse driving device.
After receiving the instruction of the upper computer, controlling the three-axis driving device to drive the moving part of the line taking-up machine module to move; the internal structure of the thread take-up module is shown in fig. 10, the thread take-up module comprises a workbench 20 for accommodating an intelligent card to be taken-up, a stand column 19 supported on the workbench, a three-axis driving device and a moving part arranged on the stand column, thread take-up mechanical arms 3 and 4 arranged on the three-axis driving part, two thread take-up needles 5 and 6 connected to the thread take-up mechanical arms, and an infrared emitter 15 arranged right below the card to be detected; wherein the three-axis driving device and the moving component comprise a vertical moving component and a vertical driving device 13 connected with the vertical moving component, longitudinal moving components and longitudinal driving devices 9 and 10 connected with the longitudinal moving component, and a transverse moving component and transverse driving devices 11 and 12 connected with the transverse moving component.
Preferably, the image processing subsystem performs analysis processing on the received card face image of the smart card after the slot milling operation is completed: judging whether a metal wire packaged in the smart card body is W-shaped or M-shaped, and checking whether the metal wire is broken or not; and positioning the optimal thread picking position.
Judging whether the metal wire packaged in the smart card body is W-shaped or M-shaped, and checking whether the metal wire is broken or not, wherein the steps are as follows:
s1, image acquisition: when the intelligent card with the picked line enters the line picking position, infrared light emitted by an infrared emitter is shielded, an infrared receiving device in a front-end image acquisition camera does not receive an infrared signal, a motion control card is triggered to send a signal to an upper computer, and the upper computer sends an instruction for acquiring an image of the intelligent card to an image acquisition card;
the front-end image acquisition camera is driven by an image acquisition card to acquire images and transmit the acquired images to an upper computer;
s2: image preprocessing: the upper computer performs graying processing on the collected color image, wherein graying is a process of making R, G, B component values of color pixels equal, namely, making a gray value in a gray image equal to an average value of RGB in an original color image, namely:
Gray＝(R+G+B)/3 (1)
s3: image binarization: carrying out binarization processing on the image after gray processing, namely setting the value of a pixel point larger than a certain threshold value as 1, and setting the values of the rest pixel points as 0:
Figure BDA0002268935740000071
in the formula, f (x, y) represents the gray value of a pixel point (x, y) before conversion, g (x, y) represents the value of the pixel point after conversion, and T is a binarization transformation threshold;
s4: edge extraction: extracting the edge of the image to extract the track of the metal wire in the card, adopting first order differential or second order differential operation to obtain the maximum value of the gradient or the zero crossing point of the second order differential, and finally selecting a proper threshold value to extract the edge of the image;
the Roberts operator is an operator that finds edges using a local difference operator, given by the following equation (3):
Figure BDA0002268935740000072
the image processed in step S3 is shown in fig. 13, and boundary extraction is performed on the binarized image by using Robert algorithm, where the extraction threshold starts from 0.00, the step size is 0.02, and operation is performed for 9 times continuously, and the effect is shown in fig. 14. It can be seen that, when the threshold value is 0.1, the effect of boundary extraction is the best, i.e. the best threshold value.
S5: after the accurate edge extraction of the card image is completed, the closed edge is used as a boundary block to obtain a corresponding block in the card slot area:
firstly, matching the shape of an M-shaped or W-shaped template prepared in advance, thereby determining the shape of a metal wire packaged in the current card; then, the block is averagely divided into a left half and a right half which are respectively called as a left block and a right block; then, the left block is subjected to left-to-right scanning, a point where effective content is detected firstly is recorded, and if the point is a certain distance away from the left boundary of the clamping groove, the fact that the metal wire is broken in the groove milling process is indicated; if the point is in direct contact with the card slot, the scanning is continued to the right boundary of the card slot, and if the situation that the effective content is discontinuous exists in the period, the metal wire is also broken.
The image processing subsystem positions the optimal thread picking position as follows:
s6, after the accurate edge extraction of the card image is completed in the steps S1-S5, dividing the block by taking the closed edge as a boundary block to obtain blocks corresponding to the card slot area, dividing the block into a left half and a right half, respectively called as a left block and a right block, respectively scanning the left block and the right block line by line from top to bottom, and detecting the highest point of the effective content, namely the metal wire, namely the highest point of the required bent part.
The specific operation of thread picking after finding the optimal thread picking position comprises the following steps:
d1, the motion control subsystem drives the transverse moving part of the picking needle to move the left and right picking needles to the accurate position of the transverse coordinate;
d2, the motion control subsystem drives the vertical moving part to vertically move the picking needle downwards until the picking needle head touches the smart card;
d3, the motion control subsystem drives the longitudinal moving part to move the picking needle longitudinally, and the needle head of the picking needle passes through the bottom of the metal wire;
and D4, the motion control subsystem drives the vertical moving part to vertically move the picking needle upwards so as to pick the metal wire out of the clamping groove.
The image processing subsystem carries out analysis processing on the received card surface image of the intelligent card after the thread picking operation is completed: judging whether the metal wire of the smart card is normally picked out or not; and judging whether the vertical movement displacement of the picking needle is proper or not.
Specifically, judging whether the metal wire of the smart card is normally picked out or not; the method for judging whether the vertical movement displacement of the picking needle is proper is as follows:
f1, after finishing extracting the accurate edge of the card image, dividing the block by taking the closed edge as a boundary to obtain a corresponding block in the card slot area, averagely dividing the block into a left block and a right block which are respectively called as a left block and a right block, then respectively carrying out shape matching on the left block and the right block by using the left parabolic line segment and the right parabolic line segment obtained in S1-S5, and if only one edge is successfully matched, directly judging that the smart card is a waste card;
f2, if the two sides are successfully matched, further detecting a vertical line segment at the coordinate of the picking point, if the cross-section pixel value of the line segment is smaller than a specified threshold value, judging that no scratch is formed or the scratch is shallow, informing a motion control subsystem to increase a unit for the longitudinal displacement of the picking needle, judging the smart card as a waste card, and directly judging the rest conditions as the waste card;
f3, if the two sides are not matched successfully, further detecting a vertical line segment at the picking point coordinate, if the cross section pixel value of the line segment is larger than a specified threshold value, judging that the scratch is too deep, informing the motion control subsystem to reduce the longitudinal displacement of the picking needle by one unit, then judging the smart card as a waste card, and directly judging the other situations as a good card.
The overall process of the system operation is as follows:
before the thread picking of the system starts, all parts are located at initial positions, when an intelligent card enters into the automatic thread picking equipment, the intelligent card 1 is horizontally placed on a conveying belt, the front end image acquisition camera, the rear end image acquisition camera, the thread picking mechanical arms 3 and 4, the thread picking and picking needles 5 and 6 are vertically located right above an IC card, and the needle heads 7 and 8 of the thread picking and picking needles are horizontally parallel to the card and are located right above a clamping groove. At the moment, the front-end image acquisition camera shoots a high-definition picture for the card and transmits the high-definition picture to the image processing subsystem. The upper computer firstly judges that the shape of a metal wire encapsulated in the smart card body is an M line or a W line, the shape is confirmed, the wire breakage condition in the smart card is detected, and if the wire breakage condition occurs, related parts of a production line are directly driven to move the card into a waste card area; if the metal wire is normal, the image processing subsystem continues to detect the card, searches the optimal selection position of the antenna and calculates a coordinate point of the corresponding position; then, the pick-up needle is driven to carry out the thread picking process.
The thread picking process is divided into five actions at a time, wherein the action is as follows: under the drive of the transverse driving devices 11 and 12, moving the picking needle mechanical arms 3 and 4 according to the calculated transverse axis coordinates to enable the transverse positions of the picking needles 5 and 6 to be at the optimal antenna hooking positions; and the second action: under the drive of a vertical driving device 13, according to the fixed vertical distance between the card body and the picking needle, the picking needle mechanical arms 3 and 4 are moved to drive the picking needles 5 and 6 to move downwards perpendicular to the card surface until the picking needle heads 7 and 8 are close to touch the card body; and action three: under the drive of the longitudinal driving devices 9 and 10, according to the calculated longitudinal displacement (if the card is the first card of the batch, the experience value set by an operator in advance is directly used), the mechanical arms 3 and 4 are moved longitudinally to drive the picking heads 7 and 8 to move longitudinally to penetrate through the bottom of the antenna; and fourthly, action: the picking needles 5 and 6 are driven to move upwards perpendicular to the card surface under the drive of the vertical driving device 13, and the antenna is picked up; and fifthly: under the drive of the transverse driving devices 11 and 12, the mechanical arms 3 and 4 are transversely moved to drive the picking needles 5 and 6 and the antenna to move towards the two sides of the clamping groove, and the thread picking operation is completed.
And then, the intelligent card after the thread picking is moved to a specified position right below the rear-end image acquisition camera by the conveyor belt, and the rear-end image acquisition camera shoots a high-definition picture for the card and transmits the high-definition picture to the image processing subsystem. The upper computer firstly detects whether the left and right metal wires are normally picked out, if both sides are not picked out and no obvious scratch is seen at the picking coordinate point, the longitudinal displacement of the picking needle is less, the metal wires are not picked, the motion control subsystem needs to be informed to increase one unit of the longitudinal displacement of the picking needle, and related parts of the assembly line are driven to move the card into a waste card area; if both sides are picked out and the scratch at the thread picking coordinate point is too obvious, the longitudinal displacement of the picking needle is large, the scratch possibly affects the back of the intelligent card body, a motion control subsystem needs to be informed to reduce the longitudinal displacement of the picking needle by one unit, and related parts of a production line are driven to move the card into a waste card area; if both sides of the metal wires are picked out and the scratch at the thread picking coordinate point belongs to a normal range, the longitudinal displacement of the picking needle belongs to an affair range, and the subsequent operation of the current card and the thread picking operation of the next card can be continuously executed; if other conditions exist, the related parts of the assembly line are directly driven to move the card into the card waste area.
Referring to fig. 12, the movement of the moving member driven by the take-up three-axis driving device is described as follows:
the thread take-up module comprises two Z-axis lead screws 10-5 which are symmetrically arranged and are respectively fixed by two Z-axis bearing blocks 10-1, the two Z-axis lead screws 10-5 are connected through a Z-axis synchronous belt 10-6 to ensure that the two Z-axis lead screws 10-5 synchronously move, a Z-axis stepping motor 10-2 is fixed beside the Z-axis bearing block 10-1 on one side, and a Z-axis synchronous belt wheel 10-3 at the output end of the Z-axis stepping motor 10-2 is connected with one Z-axis lead screw 10-5 through a Z-axis transmission belt 10-4. After a Z-axis displacement instruction is received, the Z-axis stepping motor 10-2 drives a Z-axis transmission belt 10-4 to rotate by rotating a Z-axis synchronous belt wheel 10-3, and further rotates a Z-axis screw 10-5, and because a Z-axis synchronous belt 10-6 is connected between the two Z-axis screws 10-5, the two Z-axis stepping motors can synchronously rotate, so that the longitudinal displacement of the XY-axis horizontal support 11-8 is ensured not to incline, and the Z-axis displacement of the thread taking mechanical arm 3 is further ensured.
Similarly, two Y-axis synchronous rotating shafts 11-4 are symmetrically arranged, an intermediate synchronous belt wheel 11-1 with 4 end points is connected through two parallel Y-axis synchronous belts 11-2, so that the two Y-axis synchronous rotating shafts 11-4 can move synchronously, a Y-axis stepping motor 11-9 is fixedly arranged on one side of an XY-axis horizontal support 11-8, the output end of the Y-axis stepping motor 11-9 is connected with one Y-axis synchronous rotating shaft 11-4 through a transmission belt, and the two Y-axis synchronous belts 11-2 and two Y-axis guide rails 11-3 are respectively connected with two ends of an X-axis guide rail seat 11-5. After a Y-axis displacement instruction is received, a Y-axis stepping motor 11-9 drives a Y-axis synchronous rotating pump 11-4 to rotate through a transmission belt, two parallel Y-axis synchronous belts 11-2 are connected between the two Y-axis synchronous rotating shafts 11-4, when one Y-axis synchronous rotating pump 11-4 rotates, two parallel Y-axis synchronous belts 11-2 are driven to synchronously rotate through a middle synchronous belt pulley 11-1 with 4 end points, the Y-axis synchronous belts 11-2 are connected with an X-axis guide rail seat 11-5, the X-axis guide rail seat 11-5 is enabled to uniformly move along a Y-axis guide rail 11-3, and Y-axis displacement of a thread picking mechanical arm 3 is further guaranteed;
similarly, an X-axis stepping motor 11-10 is fixedly installed on one side of an X-axis guide rail seat 11-5, the output end of the X-axis stepping motor 11-10 is connected with one end of an X-axis synchronous belt 11-7, the X-axis synchronous belt 11-7 is connected with a fixed seat at the top end of the take-up mechanical arm 3, and two X-axis guide rails 11-6 are respectively connected with two ends of the fixed seat at the top end of the take-up mechanical arm 3. After an X-axis displacement instruction is received, the X-axis stepping motor 11-10 drives the X-axis synchronous belt 11-7 to move, and the fixed seat at the top end of the take-up mechanical arm 3 uniformly moves along the X-axis guide rail 11-6 along with the X-axis synchronous belt 11-7, so that the X-axis displacement of the take-up mechanical arm 3 is guaranteed.
The invention has the advantages that the machine vision technology is introduced, the manual intervention is reduced, the moving displacement of the picking needle is accurately positioned, and the space moving coordinate of the picking needle is accurately calculated before and after the thread picking operation by utilizing the machine vision technology, so that the waste card rate on the high-speed production line of the intelligent card is reduced.
Variations and modifications to the above-described embodiments may occur to those skilled in the art, which fall within the scope and spirit of the above description. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and some modifications and variations of the present invention should fall within the scope of the claims of the present invention. Furthermore, although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

Claims (9)

1. The utility model provides a full-automatic smart card thread take-up system based on machine vision, which comprises an image acquisition subsystem, an image processing subsystem and a motion control subsystem, wherein:
the image acquisition subsystem comprises a front-end image acquisition camera, a rear-end image acquisition camera and an image acquisition card, wherein the front-end image acquisition camera is used for acquiring a card surface image of the intelligent card after the groove milling operation is finished and transmitting the card surface image to the image processing subsystem through the image acquisition card; the rear-end image acquisition camera is used for acquiring the card surface image of the intelligent card after the wire picking is finished and transmitting the card surface image to the image processing subsystem through the image acquisition card;
the image processing subsystem is composed of an upper computer and is used for obtaining the moving coordinate of the picking needle in a three-dimensional space through calculation by analyzing the image transmitted by the image acquisition card and operating the motion control subsystem through a motion control card to carry out thread picking operation;
the motion control subsystem comprises a motion control card and a thread picking machine module, after the motion control card receives an instruction of an upper computer, the motion control card controls a three-axis driving device of the thread picking machine module to drive a moving part of the thread picking machine module to move a picking needle of the thread picking machine module to a moving coordinate of a three-dimensional space calculated by the upper computer, and thread picking operation is carried out.
2. The fully automatic smart card thread-taking-up system based on machine vision as claimed in claim 1, wherein said image processing subsystem performs analysis processing on the received smart card face image after completing the slot-milling operation by: judging whether a metal wire packaged in the smart card body is W-shaped or M-shaped, and checking whether the metal wire is broken or not; and positioning the optimal thread picking position.
3. The fully automatic smart card thread-picking system based on machine vision as claimed in claim 1, wherein the image processing subsystem performs analysis processing on the received smart card face image after thread-picking operation is completed: judging whether the metal wire of the smart card is normally picked out or not; and judging whether the vertical movement displacement of the picking needle is proper or not.
4. The full-automatic smart card thread take-up system based on machine vision as claimed in claim 2 or 3, wherein the thread take-up module comprises a workbench for placing the smart card to be taken-up, a stand column supported on the workbench, a three-axis driving device and a moving component, the three-axis driving device and the moving component are arranged on the stand column, the three-axis driving component is provided with a thread take-up mechanical arm, a thread take-up needle is arranged on the thread take-up mechanical arm, and an infrared emitter is further arranged right below the smart card to be taken-up.
5. The machine vision-based fully automatic smart card thread take-up system as claimed in claim 4, wherein said three-axis driving means comprises a vertical driving means, a longitudinal driving means and a lateral driving means, and said moving means comprises a vertical moving means, a longitudinal moving means and a lateral moving means;
the vertical moving part is connected with a vertical driving device, the longitudinal moving part is connected with a longitudinal driving device, and the transverse moving part is connected with a transverse driving device.
6. The fully automatic smart card thread-picking system based on machine vision as claimed in claim 4, wherein the step of the image processing subsystem analyzing and processing one is as follows:
s1, image acquisition: when the intelligent card with the picked line enters the line picking position, infrared light emitted by an infrared emitter is shielded, an infrared receiving device in a front-end image acquisition camera does not receive an infrared signal, a motion control card is triggered to send a signal to an upper computer, and the upper computer sends an instruction for acquiring an image of the intelligent card to an image acquisition card;
the front-end image acquisition camera is driven by an image acquisition card to acquire images and transmit the acquired images to an upper computer;
s2: image preprocessing: the upper computer performs graying processing on the acquired color image, namely the gray value in the gray image is equal to the average value of RGB in the original color image, namely:
Gray＝(R+G+B)/3 (1)
s3: image binarization: carrying out binarization processing on the image after gray processing, namely setting the value of a pixel point larger than a certain threshold value as 1, and setting the values of the rest pixel points as 0:
Figure FDA0002268935730000021
in the formula, f (x, y) represents the gray value of a pixel point (x, y) before conversion, g (x, y) represents the value of the pixel point after conversion, and T is a binarization transformation threshold;
s4: edge extraction: extracting the edge of the image to extract the track of the metal wire in the card, adopting first order differential or second order differential operation to obtain the maximum value of the gradient or the zero crossing point of the second order differential, and finally selecting a certain threshold value to extract the edge of the image;
the Roberts operator is an operator that finds edges using a local difference operator, given by the following equation (3):
Figure FDA0002268935730000022
s5: after the accurate edge extraction of the card image is completed, the closed edge is used as a boundary block to obtain a corresponding block in the card slot area:
firstly, matching the shape of an M-shaped or W-shaped template prepared in advance, thereby determining the shape of a metal wire packaged in the current card; then, the block is averagely divided into a left half and a right half which are respectively called as a left block and a right block; then, the left block is subjected to left-to-right scanning, a point where effective content is detected firstly is recorded, and if the point is a certain distance away from the left boundary of the clamping groove, the fact that the metal wire is broken in the groove milling process is indicated; if the point is in direct contact with the card slot, the scanning is continued to the right boundary of the card slot, and if the situation that the effective content is discontinuous exists in the period, the metal wire is also broken.
7. The fully automatic smart card thread-picking system based on machine vision as claimed in claim 6, wherein the image processing subsystem locates the optimal thread-picking position by the following steps:
s6, after the accurate edge extraction of the card image is completed in the steps S1-S5, dividing the block by taking the closed edge as a boundary block to obtain blocks corresponding to the card slot area, dividing the block into a left half and a right half, respectively called as a left block and a right block, respectively scanning the left block and the right block line by line from top to bottom, and detecting the highest point of the effective content, namely the metal wire, namely the highest point of the required bent part.
8. The machine vision based fully automatic smart card thread take-up system as claimed in claim 7, wherein the thread take-up operation comprises the steps of:
d1, the motion control subsystem drives the transverse moving part of the picking needle to move the left and right picking needles to the accurate position of the transverse coordinate;
d2, the motion control subsystem drives the vertical moving part to vertically move the picking needle downwards until the picking needle head touches the smart card;
d3, the motion control subsystem drives the longitudinal moving part to move the picking needle longitudinally, and the needle head of the picking needle passes through the bottom of the metal wire;
and D4, the motion control subsystem drives the vertical moving part to vertically move the picking needle upwards so as to pick the metal wire out of the clamping groove.
9. The full-automatic smart card thread-picking system based on machine vision as claimed in claim 8, wherein said image processing sub-analysis process determines whether the smart card wire is picked normally; the method for judging whether the vertical movement displacement of the picking needle is proper is as follows:
f1, after finishing extracting the accurate edge of the card image, dividing the block by taking the closed edge as a boundary to obtain a corresponding block in the card slot area, averagely dividing the block into a left block and a right block which are respectively called as a left block and a right block, then respectively carrying out shape matching on the left block and the right block by using the left parabolic line segment and the right parabolic line segment obtained in S1-S5, and if only one edge is successfully matched, directly judging that the smart card is a waste card;
f2, if the two sides are successfully matched, further detecting a vertical line segment at the coordinate of the picking point, if the cross-section pixel value of the line segment is smaller than a specified threshold value, judging that no scratch is formed or the scratch is shallow, informing a motion control subsystem to increase a unit for the longitudinal displacement of the picking needle, judging the smart card as a waste card, and directly judging the rest conditions as the waste card;
f3, if the two sides are not matched successfully, further detecting a vertical line segment at the picking point coordinate, if the cross section pixel value of the line segment is larger than a specified threshold value, judging that the scratch is too deep, informing the motion control subsystem to reduce the longitudinal displacement of the picking needle by one unit, then judging the smart card as a waste card, and directly judging the other situations as a good card.
CN201911107796.XA 2019-11-13 2019-11-13 Full-automatic smart card thread take-up system based on machine vision Pending CN112798599A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911107796.XA CN112798599A (en) 2019-11-13 2019-11-13 Full-automatic smart card thread take-up system based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911107796.XA CN112798599A (en) 2019-11-13 2019-11-13 Full-automatic smart card thread take-up system based on machine vision

Publications (1)

Publication Number Publication Date
CN112798599A true CN112798599A (en) 2021-05-14

Family

ID=75803325

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911107796.XA Pending CN112798599A (en) 2019-11-13 2019-11-13 Full-automatic smart card thread take-up system based on machine vision

Country Status (1)

Country Link
CN (1) CN112798599A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105224979A (en) * 2015-08-06 2016-01-06 广东曙光自动化设备股份有限公司 A kind of Automatic Production System of double-interface card and production method
CN106203598A (en) * 2016-07-14 2016-12-07 广东技术师范学院 IC-card automatical line apparatus based on machine vision
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

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105224979A (en) * 2015-08-06 2016-01-06 广东曙光自动化设备股份有限公司 A kind of Automatic Production System of double-interface card and production 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
CN106203598A (en) * 2016-07-14 2016-12-07 广东技术师范学院 IC-card automatical line apparatus based on machine vision

Similar Documents

Publication Publication Date Title
CN108918543B (en) Dynamic detection device and method for mirror surface scratch
CN201844981U (en) Machine vision based automatic defect detecting device for printed circuit boards
CN110866903B (en) Ping-pong ball identification method based on Hough circle transformation technology
CN103357672B (en) A kind of strip steel boundary online test method
CN101639452A (en) 3D detection method for rail surface defects
CN104914109B (en) A kind of cell phone back chitin amount detection systems and detection method
CN107747912B (en) Workpiece edge track scanning device and scanning method
CN105654001A (en) Test method for two-dimensional code scanning equipment performance based on different field depths
CN113689509A (en) Binocular vision-based disordered grabbing method and system and storage medium
CN110607405A (en) Leather inner contour recognition cutting device and method based on machine vision industrial application
CN114004814A (en) Coal gangue identification method and system based on deep learning and gray scale third moment analysis
CN216348416U (en) Rivet quality inspection equipment and image and contour acquisition equipment thereof
CN112798599A (en) Full-automatic smart card thread take-up system based on machine vision
CN105258647A (en) Visual detection method of automobile lock catch rivet point
CN107516329B (en) Positioning method for oil holes of speed reducer
CN208042989U (en) A kind of large-scale sheet metal works almost T-stable automatic detection device
JP6823156B2 (en) Backup pin recognition method and component mounting device
CN205786374U (en) Special-shaped stamping parts profile defects vision detection system based on coupling
CN107966118A (en) A kind of plane of motion detection device and its detection method
CN113723266B (en) Brushless motor punching sheet screening system and method
CN208673130U (en) A kind of glass processing device of view-based access control model guidance
CN110793454A (en) Device and method for detecting plug jack depth by laser
CN114392940B (en) Pin detection method and device for special-shaped component
CN113705487B (en) Precision workpiece identification and technological parameter association system and identification method
CN115980061A (en) Circuit board pin height detection device and method based on point cloud data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20210514

WD01 Invention patent application deemed withdrawn after publication