KR101681149B1 - Apparatus and method for generating calibration element that is used to correct alignment of products - Google Patents

Apparatus and method for generating calibration element that is used to correct alignment of products Download PDF

Info

Publication number
KR101681149B1
KR101681149B1 KR1020150044336A KR20150044336A KR101681149B1 KR 101681149 B1 KR101681149 B1 KR 101681149B1 KR 1020150044336 A KR1020150044336 A KR 1020150044336A KR 20150044336 A KR20150044336 A KR 20150044336A KR 101681149 B1 KR101681149 B1 KR 101681149B1
Authority
KR
South Korea
Prior art keywords
image
product
angle
standard pattern
processing unit
Prior art date
Application number
KR1020150044336A
Other languages
Korean (ko)
Other versions
KR20160117690A (en
Inventor
김병만
정해
문창배
김현수
김태훈
이동원
김현용
Original Assignee
금오공과대학교 산학협력단
(주)노바소프트
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 금오공과대학교 산학협력단, (주)노바소프트 filed Critical 금오공과대학교 산학협력단
Priority to KR1020150044336A priority Critical patent/KR101681149B1/en
Publication of KR20160117690A publication Critical patent/KR20160117690A/en
Application granted granted Critical
Publication of KR101681149B1 publication Critical patent/KR101681149B1/en

Links

Images

Classifications

    • 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
    • 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
    • G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

The present invention can be used to correct the alignment of a product, which can increase the processing speed and reduce the error rate of the alignment by quickly and accurately generating the corrective elements necessary for alignment by selecting the position or standard position of the marker imprinted on the product And a method thereof. An apparatus for generating a correction factor used for correcting alignment of a product according to the present invention includes an image input unit configured to receive an image of a product through a camera and generate a digital image; (Histogram) of a standard pattern by inputting an image of a product whose position and angle are corrected from the image input unit, receiving an image of a product to be corrected for position and angle, receiving an image of a product to be corrected for position and angle, An image processing unit configured to calculate a correction element for correction (coordinates and angle of a standard pattern); And an image position selection unit configured to select a position of an image processed in the image processing unit.

Description

[0001] APPARATUS AND METHOD FOR GENERATING CALIBRATION ELEMENT THAT IS USED TO CORRECT ALIGNMENT OF PRODUCTS [0002]

The present invention relates to an apparatus and a method for generating a correction element (i.e., an angle and a coordinate of a standard pattern) used for alignment of a product used before and after a production process of a product, A correction factor generating device used for correcting an alignment of a product, which can improve the processing speed and reduce the error rate of the alignment by quickly and accurately generating the correction factor necessary for alignment by selecting the position of the marker or the standard position ≪ / RTI >

As the industry develops, the production system is also developing. The core technologies of the production system are machine vision technology, industrial robot control technology, industrial PC technology, PLC (programmable logic controller) technology and sensor technology . ≪ / RTI > Among them, machine vision technology is an important technology that can reduce production cost of production system or improve productivity. Machine vision technology can be categorized into two technologies before and after product production. The first is the technology that corrects the position of the product used in the production process, and the second is the technology that identifies the failure of the product. The common core technology of both technologies is the alignment correction technique, which utilizes markers on the product or corrects the angle and position of the product using a unique pattern (standard position) present in the product Technology. An important factor in alignment technology is accuracy and processing speed. Accuracy is to determine the exact angle and position of the input product, and in the case of processing speed it is time to determine the exact angle and position.

The conventional alignment calculation method includes, for example, a method of averaging the alignment mark measurement values of each layer, a method of converting the alignment mark measurement values of each layer into a certain ratio, And a method of selectively selecting only a specific axis value of the alignment mark.

However, in such a conventional alignment calculation method, in order to reduce the error rate, a large number of mark measurement values should be averaged to increase the accuracy. As the number of mark measurement values increases, the calculation speed of the alignment becomes slower and ultimately, Causing it to deteriorate.

SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a method and apparatus for correcting alignment of a product, And a method for generating the same.

According to an aspect of the present invention, there is provided an apparatus for generating a correction factor used for correcting alignment of a product according to an embodiment of the present invention includes an image input unit configured to receive an image of a product through a camera and generate a digital image; (Histogram) of a standard pattern by inputting an image of a product whose position and angle are corrected from the image input unit, receiving an image of a product to be corrected for position and angle, receiving an image of a product to be corrected for position and angle, An image processing unit configured to calculate a correction element for correction (coordinates and angle of a standard pattern); And an image position selection unit configured to select a position of an image processed in the image processing unit.

The correction factor generating device used for correcting the alignment of the product according to the embodiment may further include a display unit configured to display the correction factor calculated by the image processing unit.

The correction factor generation device used for correcting the alignment of the product according to the embodiment may further include a communication module configured to interface with the image processing part and the LAN or the USB port.

In the correction factor generation device used for correcting the alignment of the product according to the embodiment, the image processing unit may be configured to receive the image of the product whose position and angle are corrected through the image input unit, When the standard position or the position of the marker is selected, the coordinates and size of the selected position and the image arrangement are generated and the characteristic of the standard pattern is extracted while rotating the selected image a plurality of times in the setting angle range in the setting angle range, When an image of a product to be corrected for position and angle is input, a plurality of candidates are selected using a Naive Template Matching method, and the representative coordinates of each cluster are obtained by clustering the selected plurality of candidates , The feature (histogram) of the extracted standard pattern among the representative coordinates, A coordinate having a high degree of similarity to the coordinates of the selected standard pattern among the feature vectors of the extracted plurality of standard patterns may be selected and selected as an angle of the standard pattern have.

According to another aspect of the present invention, there is provided a correction element generation method for correcting an alignment of a product according to another embodiment of the present invention, A feature extraction step of extracting a feature (histogram) of a standard pattern; A correction element calculating step of calculating a correction element (coordinate and angle of a standard pattern) for alignment correction by using an image of a product to be corrected in position and angle from the image input unit by using the feature of the extracted standard pattern, ; And a display step of displaying the correction factor through a display unit.

In the correction element generating method used for correcting the alignment of the product according to the another embodiment, the feature pattern extracting step of the standard pattern includes a step of inputting an image of a product whose position and angle are corrected from the image inputting section, Selecting a standard position or a marker position in the image by the position selection unit, generating the coordinates and size of the selected position and the image arrangement, and the image processing unit selecting the selected image in the set angle range Determining whether the selected image position is within the set angle range; and determining whether the selected image position is within the set angle range; If the selected image position is within the set angle range, the controller proceeds to the rotating step. Otherwise, the controller proceeds to the correction element calculating step if the selected image position is not within the set angle range.

The correcting element calculating step may include a step of inputting an image of a product to be corrected in position and angle through the image input unit, Selecting a plurality of candidates using a processing unit nave template matching method, the image processing unit clustering the selected plurality of candidates to obtain representative coordinates of clusters, and the image processing unit extracts the representative coordinates Selecting a coordinate having a high degree of similarity with the feature of the standard pattern and selecting the coordinate having the high degree of similarity with the coordinates of the standard pattern, And selecting an angle of the standard pattern.

According to the correction-element generating apparatus and method used for correcting the alignment of the product according to the embodiments of the present invention, in calculating the correction factor for alignment correction, the candidate selected from the image to be corrected is clipped, Since the correction factor (coordinates and angle of the standard pattern) is selected after acquiring the representative coordinates, the correction factor required for alignment can be generated quickly and accurately, so that the error rate of the alignment can be increased while maintaining a low value have.

1 is a detailed circuit diagram showing a correction element generating apparatus used for correcting alignment of a product according to an embodiment of the present invention.
FIGS. 2A and 2B are flowcharts for explaining a correction element generating method used to correct alignment of a product according to an embodiment of the present invention.
FIG. 3 is a diagram showing a case where candidate candidates having high similarity are used at one point when all n candidates are used.
4 is a diagram showing a clustering process of candidates.
5 is a table showing the processing speed and the error rate when the correction elements are selected without clustering the candidates selected from the image to be corrected.
6 is a graph showing average processing time when clustering is applied to 20 candidates.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

1 is a detailed circuit diagram showing a correction element generating apparatus used for correcting alignment of a product according to an embodiment of the present invention.

1, the correction-element generating apparatus used for correcting alignment of a product according to an exemplary embodiment of the present invention includes an image input unit 100, an image processing unit 200, a video position selection unit 110, A display unit 310, and a communication module 320.

The image input unit 100 receives an image of a product through a camera (not shown), and generates a digital image.

The image processing unit 200 receives an image of a product whose position and angle have been corrected from the image input unit 100, extracts a feature (a histogram) of the standard pattern, receives an image of a product to be corrected for position and angle, (Coordinates and angle of a standard pattern) for alignment correction using a feature of a pattern (histogram), and may be, for example, a microcomputer. The role of the image processing unit 200 will be described in more detail. The image of the product whose position and angle are corrected through the image input unit 100 is inputted and the standard position or the position of the marker is selected by the image position selection unit 110 The coordinates and the size of the selected position and the image arrangement are generated, and the feature of the standard pattern is extracted while the selected image is rotated a plurality of times in the setting unit in the set angle range, and the position and angle are corrected through the image input unit 100 When the image of the product is input, a plurality of candidates are selected using a Naive Template Matching method. The histogram of the selected candidate position is compared with the histogram of the extracted standard pattern to calculate the similarity of the candidates, clustering to obtain representative coordinates of each of the clusters, and acquiring representative coordinates of the extracted standard patterns (histogram And selecting a vector having a high degree of similarity with the coordinates of the selected standard pattern among the extracted feature vectors of the plurality of standard patterns to select an angle of the standard pattern .

The video position selection unit 110 selects a position of an image to be processed in the image processing unit 200 by a user's operation and may be an input device such as a mouse or a keyboard.

The display unit 310 displays the correction factors calculated by the image processing unit 200 and may be an output device such as a CRT, an LCD, an LED, and a PDP. Meanwhile, the display unit 310 may be configured to display all the processes performed by the image processing unit 200. FIG.

The communication module 320 functions to interface the image processing unit 200 with a LAN or a USB port.

Although the image input unit 100, the image position selection unit 110, the image processing unit 200, the display unit 310 and the communication module 320 are shown as separate components, ), A notebook computer, a smart phone, and the like.

A method of generating a correction element using a correction element generating apparatus used for correcting alignment of a product according to an embodiment of the present invention will be described with reference to the drawings.

2A and 2B are flowcharts for explaining a correction element generating method used for correcting alignment of a product according to an embodiment of the present invention, where S denotes a step.

The correction factor generation method used for correcting the alignment of the product according to the embodiment of the present invention is a correction factor generation method in which the image processing unit 200 receives the image of the product whose position and angle are corrected from the image input unit 100, A feature extraction step of extracting a feature of a standard pattern from the image input unit 100 and a feature extraction step of extracting an image of a product to be corrected from the image input unit 100, A correction factor calculating step of calculating a correction factor (coordinates and angle of a standard pattern) for displaying the correction factor, and a display step of displaying the correction factor through the display unit 310, and each step will be described in detail below.

[Feature extraction step of standard pattern]

The image processing unit 200 receives the image of the product whose position and angle are corrected from the image input unit 100 (S10).

Next, the user selects a standard position (e.g., a position of a unique pattern) or a marker position in the image using the image position selection unit 110 (S20).

The image processing unit 200 generates coordinates, size, and image arrangement of the position selected in step S20 (S30).

Subsequently, the image processing unit 200 rotates the image selected in step S20 in the setting angle range in step S40, extracts a feature (histogram) of the standard pattern (S50) It is determined whether or not it is within the set angle range (S60). For example, if the setting angle is -5 degrees to 5 degrees and the setting unit is 0.1, a total of 101 rotations are performed, and 101 standard pattern features are extracted.

If it is determined in step S60 that the image position is within the set angle range (YES), the process proceeds to step S40, whereas if the image position is outside the set angle range (NO), the process proceeds to the next step.

[Calculation element calculating step]

The image processing unit 200 receives an image of a product to be corrected in position and angle from the image input unit 100 in step S70 and selects a plurality of candidates using a Naive Template Matching method in step S80. The reason for choosing a plurality of candidates is that, when one candidate is used, it is impossible to detect an accurate product angle and position. FIG. 5 is a table showing the accuracy in the case of selecting a correction element without selecting the candidates selected from the image to be corrected. As the number of candidates increases, the error rate decreases but the image processing time increases. Therefore, the following clustering process is performed. In step S80, the image processing unit 200 selects a candidate position and compares the histogram of the candidate position with the histogram of the standard pattern extracted in step S50 to calculate the similarity of the candidates, Select a candidate.

Subsequently, the plurality of candidates selected in step S80 are clustered to obtain the representative coordinates of each cluster (S100).

The clustering process will be described in more detail. As shown in FIG. 4, if the x-axis distance and the y-axis distance of each candidate are calculated and included in the same cluster if the distance is smaller than the threshold value, If they are larger, they are assigned to different clusters. For example, assuming that there are k candidates in one cluster, there are k co-ordinates due to k candidates in one cluster. The degree of similarity is used to select representative coordinates from the k coordinates. If a cluster is composed of two coordinates, the coordinates of the first candidate are (10, 10) and the similarity of the second candidate is (11, 11) is 95% Since the similarity is better, the representative coordinate of the cluster is (10, 10).

Next, the image processing unit 200 selects a coordinate having a high degree of similarity to the feature (histogram) of the standard pattern extracted in the step S50 from among the representative coordinates acquired in the step S100, and selects the coordinate as the standard pattern S110).

Then, the image processing unit 200 selects a vector having a high degree of similarity to the coordinates of the standard pattern selected at the step S110 among the plurality of standard pattern feature vectors extracted at the step S50, (S120).

[Display step]

The image processing unit 200 outputs a display control signal for displaying the correction elements (coordinate and angle of the standard pattern) for the alignment correction selected in the above steps S110 and S120 to the display unit 310 to display the correction element (S130).

FIG. 5 is a table showing the accuracy when correcting elements are selected without clustering selected candidates in the image to be corrected. When the number of candidates is 20, the processing time is 7s 203ms and the average error rate is 0.00. Meanwhile, FIG. 6 is a graph showing the average processing time when clustering is applied to 20 candidates, and the average processing time is 0.75 to 4 s. Thus, it can be seen that the average error rate is significantly reduced while maintaining the pre-clustering value.

According to the correction element generation apparatus and method used for correcting the alignment of the product according to the embodiment of the present invention, in calculating the correction factor for alignment correction, the candidates selected from the images to be corrected are clipped, (Coordinates and angles of the standard pattern) after acquiring the coordinates, it is possible to quickly and accurately generate the correction elements required for alignment, thereby improving the processing speed while maintaining a low error rate of the alignment .

Although the best mode has been shown and described in the drawings and specification, certain terminology has been used for the purpose of describing the embodiments of the invention and is not intended to be limiting or to limit the scope of the invention described in the claims. It is not. Therefore, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the scope of the present invention. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

100: image input unit 110: image position selection unit
200: image processing unit 310:
320: Communication module

Claims (7)

An image input unit configured to receive an image of a product through a camera and generate a digital image;
The image of the product for which the position and the angle are corrected is extracted from the image input unit, the feature of the standard pattern is extracted, the image of the product to be corrected for the position and the angle is input, An image processing unit configured to calculate a correction factor; And
And a video position selection unit configured to select a position of an image to be processed in the image processing unit, the correction factor generation device being used for correcting the alignment of the product. The method according to claim 1,
And a display unit configured to display a correction factor calculated by the image processing unit, wherein the correction unit is used to correct the alignment of the product. The method according to claim 1,
Further comprising a communication module configured to interface the image processing unit with a LAN or a USB port, wherein the calibration module is used to correct alignment of the product. The method according to claim 1,
Wherein the image processing unit comprises:
When an image of a product whose position and angle are corrected through the image input unit is input and the standard position or the position of the marker is selected by the image position selection unit, coordinates and size of the selected position and an image arrangement are generated, Extracting a feature of a standard pattern while rotating a plurality of times in a set unit in an angle range, selecting a plurality of candidates using a nave template matching method when an image of a product to be corrected for position and angle is input through the image input unit, Selecting representative coordinates of representative clusters by selecting a coordinate having a high degree of similarity with the extracted characteristic of the standard pattern and selecting the coordinates as a standard pattern coordinate by clustering the selected plurality of candidates, A vector having a similarity to the coordinate of the selected standard pattern is selected A correction factor generator configured to select an angle of the standard pattern to correct an alignment of the product. A feature extracting step of extracting a feature of a standard pattern by receiving an image of a product whose position and angle are corrected from the image input unit;
A correction element calculating step of calculating a correction factor for alignment correction using a feature of the extracted standard pattern, the image processing part receiving an image of a product to be corrected in position and angle from the image input part; And
And a display step of displaying the correction factor through a display unit, wherein the correction factor is used to correct an alignment of a product. 6. The method of claim 5,
Wherein the step of extracting features of the standard pattern comprises:
A step of inputting an image of a product whose position and angle are corrected from the image input unit,
Selecting a standard position or a marker position in the image by a video position selection unit,
The image processing unit generates coordinate and size of the selected position and an image arrangement,
The image processing unit rotating the selected image in a setting unit in a set angle range, and
Wherein the image processing unit determines whether the selected image position is within the set angle range;
In the determining step, if the selected image position is within the set angle range, the process proceeds to the rotating step, while if the selected image position is not within the set angle range, the process proceeds to the correction factor calculating step. A method of creating a correction factor for use. 6. The method of claim 5,
Wherein the correcting element calculating step includes:
Inputting an image of a product to be corrected in position and angle through the image input unit,
Selecting a plurality of candidates using the image template matching method,
The image processing unit clustering the selected plurality of candidates to obtain representative coordinates of each cluster,
Wherein the image processing unit selects a coordinate having a high degree of similarity with a feature of the extracted standard pattern among the representative coordinates and selects the coordinate as a standard pattern,
Wherein the image processing unit selects a vector having a degree of similarity with the coordinates of the selected standard pattern among the extracted feature vectors of the plurality of standard patterns to select an angle of the standard pattern. A method of generating a correction factor to be used.
KR1020150044336A 2015-03-30 2015-03-30 Apparatus and method for generating calibration element that is used to correct alignment of products KR101681149B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150044336A KR101681149B1 (en) 2015-03-30 2015-03-30 Apparatus and method for generating calibration element that is used to correct alignment of products

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150044336A KR101681149B1 (en) 2015-03-30 2015-03-30 Apparatus and method for generating calibration element that is used to correct alignment of products

Publications (2)

Publication Number Publication Date
KR20160117690A KR20160117690A (en) 2016-10-11
KR101681149B1 true KR101681149B1 (en) 2016-12-15

Family

ID=57161946

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150044336A KR101681149B1 (en) 2015-03-30 2015-03-30 Apparatus and method for generating calibration element that is used to correct alignment of products

Country Status (1)

Country Link
KR (1) KR101681149B1 (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100679054B1 (en) 2006-02-15 2007-02-06 삼성전자주식회사 Apparatus and method for displaying three-dimensional image

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101253283B1 (en) * 2011-08-16 2013-04-10 한국과학기술연구원 Method and system for reconstructing zoom-in image having high resolution

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100679054B1 (en) 2006-02-15 2007-02-06 삼성전자주식회사 Apparatus and method for displaying three-dimensional image

Also Published As

Publication number Publication date
KR20160117690A (en) 2016-10-11

Similar Documents

Publication Publication Date Title
CN106097361B (en) Defect area detection method and device
CN111028213A (en) Image defect detection method and device, electronic equipment and storage medium
JP2017091079A5 (en)
US8780223B2 (en) Automatic determination of compliance of a part with a reference drawing
US10430650B2 (en) Image processing system
CN108573471B (en) Image processing apparatus, image processing method, and recording medium
CN105424190A (en) Grayscale detection method of product appearance
CN106815444B (en) Method for automatically measuring distance between PCB (printed circuit board) drawing components
TW201516969A (en) Visual object tracking method
JP5914732B2 (en) Image verification method, image verification apparatus, and program
CN105823504A (en) Zero-point-crossing processing method of encoder
JP5469532B2 (en) Image processing apparatus, image processing method, and computer program
Zhang et al. A new algorithm for accurate and automatic chessboard corner detection
CN108627103A (en) A kind of 2D laser measurement methods of parts height dimension
CN111199533B (en) Image processing apparatus and method
KR101681149B1 (en) Apparatus and method for generating calibration element that is used to correct alignment of products
CN111507949A (en) Chip identification method based on vision
KR102099112B1 (en) Method of teaching for electronic parts information
US20150227811A1 (en) Image processing device, image processing method, and image processing program
CN111380474A (en) Aperture detection method based on binocular vision
KR101559941B1 (en) A system for detecting fault of print pattern
US10599710B2 (en) System and method for generating digital information and altering digital models of components with same
US20150317779A1 (en) Image processing system, image processing method, and computer program product
CN116894939B (en) Regional positioning method and device for special-shaped screen, electronic equipment and storage medium
KR20170094709A (en) Apparatus and method for detecting feature of circle object

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
FPAY Annual fee payment

Payment date: 20190905

Year of fee payment: 4