KR101783324B1 - Method for calibrating align for machine vision - Google Patents

Abstract

According to one aspect of the present invention, there is provided a method for aligning a machine vision system, comprising: acquiring a first image through a camera that photographs a region of an alignment table for machine vision; registering a shape included in the first image as a pattern Moving the alignment table in the X-axis and Y-axis directions through a motion for moving the alignment table, and obtaining a second image through the camera, Calculating a first relational expression between the movement axis in the X and Y axis directions of the motion and the fixed axis of the camera based on the movement distance of the alignment table when detected, Obtaining a third image through the camera after rotating the alignment table, and when the registered pattern is detected from the third image, Is based can include the step of calculating a second relation between the rotation axis of the motion and the fixed axis of the camera.

Description

[0001] The present invention relates to a method for calibrating aligning machine vision for machine vision,

The present invention relates to machine vision. More particularly, it relates to a method for performing an alignment for machine vision.

Bondi, the term machine vision was used to mean the artificial visual function of a machine in contrast to human visual function. In the industrial field, the machine vision system is generally referred to as an image processing system that performs quality inspection or process monitoring based on images obtained through a camera.

BACKGROUND ART In recent years, with the improvement of semiconductor integration degree, electronic parts such as mobile communication terminals and memories tend to become smaller and smaller. In addition, human concentration on simple repetitive tasks, such as quality inspection or process monitoring, which depend on the human eye, is difficult to maintain for a long time. For this reason, machine vision is rapidly being introduced into various industries.

1, machine  For vision Align  FIG. 8 is an exemplary view showing a corrected image and an uncorrected image. FIG.

Prior to performing the machine vision as described above, a calibration operation for aligning between the camera and the table on which the object is located is essential. Referring to FIG. 1 (a), there is a distortion in an image obtained through a camera due to a camera position, a direction, a lens bending, or the like. Therefore, it is difficult to perform the machine vision on the basis of the image in which the distortion exists. FIG. 1 (b) is a result obtained by correcting an image in which distortion exists through a correction operation. Here, the calibration operation does not simply mean image correction but also includes setting an accurate relationship between the align table and the camera.

The task of establishing the relationship between the alignment table and the camera is to position the calibration jig on the alignment table and perform correction based on the image of the calibration jig. However, it is not easy for a person to position the calibration jig accurately so that it coincides with the axis of motion in which the aligned table is moved.

Further, it is difficult to precisely align the axis of the alignment and the axis of the camera, and it is also difficult to install the camera so as to be perpendicular to the alignment table. Furthermore, when a plurality of cameras are required to improve the accuracy of the machine vision, it is more difficult to install a plurality of cameras so that each camera is horizontal.

Korean Patent Laid-Open No. 10-2011-0029536 (Published March 23, 2011)

SUMMARY OF THE INVENTION The present invention provides a method of calibrating an alignment for a machine vision.

Another object of the present invention is to provide a computer program for executing a method of calibrating an alignment for machine vision.

The technical objects of the present invention are not limited to the above-mentioned technical problems, and other technical subjects not mentioned can be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided an alignment correction method comprising the steps of acquiring a first image through a camera that photographs a region of an alignment table for machine vision, A step of moving the alignment table in X and Y axis directions through a motion for moving the alignment table and acquiring a second image through the camera; Calculating a first relational expression between the movement axis in the X and Y axis directions of the motion and the fixed axis of the camera based on the movement distance of the alignment table when the registered pattern is detected from the two images, Obtaining a third image through the camera after rotating the alignment table through the motion, and detecting the registered pattern from the third image And calculating a second relation between the rotation axis of the motion and the fixed axis of the camera based on the rotation angle of the alignment table.

Wherein the step of calculating the first relational expression includes the steps of moving the alignment table by an integer multiple of the size of the registered pattern through the motion and obtaining a fourth image through the camera, Judging whether a closed area according to the movement path of the alignment table is divided into a plurality of blocks based on the size of the pattern when the registered pattern is detected, The first relation may be corrected based on the number of the divided blocks and the size of the pattern.

The step of determining whether to divide into the plurality of blocks includes obtaining an image for each of the plurality of blocks through the camera, and determining whether the registered pattern is detected from the image for each of the plurality of blocks can do.

The closed area may be an area where the blocks are arranged in a 5x5 form.

The calculating of the second relational expression may include rotating the alignment table a plurality of times through the motion and obtaining a plurality of fifth images, and when the registered pattern is detected from the plurality of fifth images And correcting the second relational expression based on the rotation angle at which each image included in the fifth images is photographed.

The step of acquiring the fifth image may include calculating a maximum rotation range in which the alignment table can rotate from the third image, rotating the alignment table a plurality of times within the maximum rotation range, May be obtained.

The number of images included in the fifth image is eight, and the closed region along the rotation path of the alignment table may have an octagonal shape.

According to another aspect of the present invention, there is provided a computer-readable recording medium having a computer-readable recording medium storing a computer-readable program for causing a computer to execute: A step of registering a work shape including a pattern as a pattern, moving the alignment table in the X-axis and Y-axis directions through a motion for moving the alignment table, and acquiring a second image through the camera; Calculating a first relational expression between the movement axis in the X and Y axis directions of the motion and the fixed axis of the camera based on the movement distance of the alignment table when the registered pattern is detected from the second image , Rotating the alignment table through the motion and obtaining a third image through the camera, and obtaining the registered pattern from the third image A computer program recorded on the recording medium may be provided to perform a step of, if detected, calculating a second relation between the rotation axis of the motion and the fixed axis of the camera based on the rotation angle of the alignment table have.

According to the present invention as described above, it is possible to perform the alignment correction for machine vision without a separate calibration jig.

In addition, even if the axis for the alignment and the axis of the camera do not match, the alignment can be accurately corrected. Even if the alignment table and the camera are not perpendicular, the alignment can be corrected accurately. Furthermore, even if two or more cameras are not installed horizontally, the alignment can be accurately corrected.

FIG. 1 is an illustration showing an alignment-corrected image and an uncorrected image for machine vision.
2 is a block diagram of a machine vision system using one camera.
3 is a top view of an alignment table for machine vision using one camera.
4 is a block diagram of a machine vision system using a plurality of cameras.
5 is a top view of an alignment table for machine vision using a plurality of cameras.
FIG. 6 is a flow chart for explaining an alignment calibration method according to an embodiment of the present invention.
7 is an exemplary diagram for explaining an example of a registered pattern.
8 is an exemplary diagram for explaining a process of calculating a basic relation between a motion axis in the X and Y axis directions of motion and a fixed axis of the camera.
9 is an exemplary diagram for explaining a process for calculating a precision relation between a motion axis of the motion in the X and Y axis directions and a fixed axis of the camera.
10 is an exemplary diagram for explaining the process of calculating the maximum rotation range.
11 is a diagram for explaining a process for calculating a precision relation between a rotation axis of a motion and a fixed axis of a camera.
12 is a configuration diagram of a computing device for executing the alignment correction method according to an embodiment of the present invention.

It is noted that the technical terms used herein are used only to describe specific embodiments and are not intended to limit the invention. It is also to be understood that the technical terms used herein are to be interpreted in a sense generally understood by a person skilled in the art to which the present invention belongs, Should not be construed to mean, or be interpreted in an excessively reduced sense. Further, when a technical term used herein is an erroneous technical term that does not accurately express the spirit of the present invention, it should be understood that technical terms that can be understood by a person skilled in the art are replaced. In addition, the general terms used in the present invention should be interpreted according to a predefined or prior context, and should not be construed as being excessively reduced.

Also, the singular forms "as used herein include plural referents unless the context clearly dictates otherwise. In the present application, the term "comprising" or "having ", etc. should not be construed as necessarily including the various elements or steps described in the specification, and some of the elements or portions thereof Or may further include additional components or steps.

Furthermore, terms including ordinals such as first, second, etc. used in this specification can be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

When an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may be present in between. On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals refer to like or similar elements throughout the several views, and redundant description thereof will be omitted. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. It is to be noted that the accompanying drawings are only for the purpose of facilitating understanding of the present invention, and should not be construed as limiting the scope of the present invention with reference to the accompanying drawings. The spirit of the present invention should be construed as extending to all modifications, equivalents, and alternatives in addition to the appended drawings.

Hereinafter, the present invention will be described in more detail with reference to the accompanying drawings.

Fig. 2 is a view machine  Vision system. And Figure 3 is a top view of an alignment table for machine vision using one camera.

Referring to FIGS. 2 and 3, a machine vision system according to an embodiment of the present invention can perform machine vision based on an image 11 obtained through one camera 10. In addition, the machine vision system may include an align table 20, motion 30, and computing device 100. Each of the components of the machine vision system represents functionally functioning functional elements, and one or more components can be integrated with each other in an actual physical environment.

Specifically, the camera 10 collects light emitted from a target of the machine vision through an image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor) Can be generated. The camera 10 according to the present invention may be any one of industrial cameras, but the present invention is not limited thereto, and any device capable of generating image information may be applicable.

The construction and principle of the camera 10 are well known to those skilled in the art, and a detailed description thereof will be omitted.

The alignment table 20 is a table for performing alignment for machine vision. In addition, the object to be machine vision may be located on the alignment table 20. The alignment table 20 according to the present invention may be any one of an XYT table and a UVW table, but is not limited thereto. On the other hand, the alignment table 20 may be described as a stage.

The alignment table 20 may include one or more guides 21 for aligning operations. The guide 21 may have a circular shape, but is not limited thereto, and may have various shapes such as a rectangle, a triangle, and the like that are easy to align. An example of the area 11 in which the alignment table 20 including the guide 21 is photographed through the camera 10 is as shown in Fig.

The motion 30 is a device for correcting the alignment table 20 for the alignment calibration. The motion 30 includes a motion 31 for correcting the alignment table 20 in the X axis direction, a motion 33 for correcting the alignment table 20 in the Y axis direction, And a motion 35 for correcting in the T axis direction. Here, the X-axis direction is the width direction of the aligned table. The T axis direction is the longitudinal direction of the alignment table. The direction of the T axis is the direction of rotation of the alignment table.

The computing device 100 is an apparatus in which a computer program for performing the align calibration method according to the present invention is executed. As such, the computing device 100 may be any one of a fixed computing device such as a desktop, a workstation, or a server, but is not limited thereto and may be a laptop, a portable computing device such as a smart phone, a phablet, a tablet, a personal digital assistant (PDA), an e-book reader, or the like.

Fig. 4 is a schematic diagram machine  Vision system. And FIG. 5 is a top view of an alignment table for machine vision using a plurality of cameras.

4 and 5, a machine vision system according to another embodiment of the present invention may perform machine vision based on a plurality of images 11a and 11b obtained through a plurality of cameras 10a and 10b have. Such a machine vision system may include an alignment table 20, a motion 30, and a computing device 100, similar to those described with reference to Figures 2 and 3. The description of each component is the same as that described with reference to Figs. 2 and 3. Fig.

As described above, the computing device 100 of the machine vision system using one or more cameras may be implemented with a computer program for performing the alignment correction method according to the present invention.

The alignment calibration method according to the present invention enables the alignment calibration for machine vision without a separate calibration jig. Even if the axis for alignment and the axis of the camera do not match, the alignment can be accurately calibrated. Even if the alignment table and the camera are not perpendicular, the alignment can be corrected accurately. In addition, even if two or more cameras are not installed horizontally, the alignment can be accurately corrected. Such an alignment calibration method capable of achieving such effects will be described below with reference to Figs. 6 and 11. Fig.

FIG. 6 is a cross- In the embodiment  Following Allein  To explain the calibration method It is a flowchart. .

Referring to FIG. 6, the computing device 100 acquires an image of one region of the alignment table 20 through the camera 10. Then, the computing device 100 registers a shape included in the acquired image as a pattern (S100). Here, the pattern means a spatial arrangement of one or more guides 21. The pattern may be composed of two or more guides 21, but is not limited thereto and may be composed of only one guide 21. An example of a registered pattern according to an embodiment of the present invention will be described later with reference to FIG.

The computing device 100 moves the alignment table 20 in the X-axis and Y-axis directions through the motion 30 (S200). The computing device 100 then calculates a basic relation between the movement axis of the motion 30 in the X and Y axis directions and the fixed axis of the camera 10 based on the movement distance of the alignment table 20 (S300).

More specifically, after the pattern is registered, the computing device 100 moves the aligned table 20 through the motion 30 to the first position. Here, the first position is a position at which the registered pattern can be located in the center of the image photographed through the camera 10. [ The computing device 100 moves the alignment table 20 through the motion 30 to the second position. Here, the second position is a position at which the camera 10 can photograph one corner of the aligned table 20. The computing device 100 determines whether a registered pattern is detected from the image of the aligned table 20 moved to the second position. When the registered pattern is detected, the computing device 100 determines, based on the distance between the first position and the second position, the movement axis in the X-axis and Y-axis directions of the motion 30, Lt; / RTI > An example of a process of calculating a basic relation with a moving axis according to an embodiment of the present invention will be described with reference to FIG.

The computing device 100 moves the alignment table 20 by an integer multiple of the size of the pattern through the motion 30 (S400). Then, the computing device 100 calculates the precision relation by correcting the basic relation between the movement axis of the motion 30 and the fixed axis of the camera 10 based on the pattern size (S500).

More specifically, computing device 100 moves, via motion 30, the aligned table 20 by an integer multiple of the size of the pattern. For example, the computing device 100 may move a distance of two, three, four or five times the size of the pattern. The computing device 100 detects the registered pattern from the image of the moved position. The computing device 100 moves the aligned table 20 again over the motion 30 by an integer multiple of the size of the pattern. The computing device 100 detects the registered pattern from the image of the moved position again. The computing device 100 determines whether a closed area according to the movement path of the alignment table 20 is divided into a plurality of blocks based on the size of the pattern. For example, the closed region may be arranged such that blocks are arranged in the form of 2x2, 3x3, 4x4, 5x5, or nxn based on the size of the pattern in accordance with the moving distance of the alignment table 20 However, the present invention is not limited to this, and it may be an area arranged in the form of n x m. In addition, the computing device 100 may acquire an image for each of a plurality of blocks divided through the camera 10, and may determine a valid closed region only when a pattern is detected from an image of each of the obtained plurality of blocks . If the closed area is not divided into a plurality of blocks, the computing device 100 may move the aligned table 20 by an integer multiple of the size of the pattern.

When the closed area along the movement path of the alignment table 20 is divided into a plurality of blocks, the computing device 100 calculates X and Y of the motion 30 based on the number of divided blocks and the size of the pattern, The basic relation between the axis of movement in the axial direction and the fixed axis of the camera 10 is corrected to calculate the precision relation. An example of a process of calculating a precision relation with a moving axis according to an embodiment of the present invention will be described later with reference to FIG.

The computing device 100 rotates the alignment table 20 through the motion 30 (S600). The computing device 100 determines whether a pattern is detected from the image for the rotated alignment table 20. [ When a pattern is detected from an image for the rotated alignment table 20, the computing device 100 determines the alignment table 20 based on the angle of rotation of the alignment table 20 and the shape of the detected pattern. Is calculated (S700). An example of a process of calculating the maximum rotation range according to an embodiment of the present invention will be described below with reference to FIG.

The computing device 100 rotates the alignment table 20 a plurality of times through the motion 30 within the calculated maximum rotation range (S800). Then, the computing device 100 calculates a precision relation between the rotation axis of the motion 30 and the fixed axis of the camera 10 based on the rotation angle of the alignment table 20 (S900).

More specifically, the computing device 100 rotates the alignment table 20 a plurality of times through the motion 30. Here, the number of rotations of the alignment table 20 is related to the accuracy of the precision relation with the rotation axis. That is, the greater the number of rotations of the alignment table 20, the more accurate the precision relation with the rotation axis can be. However, the larger the number of rotations of the alignment table 20, the longer the time required for the alignment calibration. Therefore, the alignment calibration method according to an embodiment of the present invention proposes eight rotations in a relation between the precision time of the precision relation with the rotation axis and the required time. In this case, the closed area along the rotation path of the alignment table 20 may have an octagonal shape having vertexes located at the same distance about the rotation axis of the motion 30.

The computing device 100 determines whether a registered pattern is detected from images of the rotated alignment table 20 every time the alignment table 20 is rotated. When a registered pattern is detected from each image for the rotated alignment table 20, the computing device 100 determines whether each image for the rotated alignment table 20 is based on the captured rotation angle, And a precision relation between the rotation axis of the motion 30 and the fixed axis of the camera 10 is calculated.

Hereinafter, with reference to FIG. 7 to FIG. 11, a description will be made of a process of performing the alignment calibration method according to an embodiment of the present invention.

7 is an exemplary diagram for explaining an example of a registered pattern.

Referring to Fig. 7, the computing device 100 acquires an image 11 for one area of the aligned table 20 photographed through the camera 10. [ The computing device 100 detects the guide 21 contained in the acquired image 11. The computing device 100 may register the spatial arrangement of the detected guide 21 as a pattern 23 when the spatial arrangement of the detected guide 21 is included in the preset detection pattern list.

Figure 8 Motion  Axis direction and the fixed axis of the camera in the X-axis and Y-axis directions.

Referring to FIG. 8, the computing device 100 moves the aligned table 20 to the first position via the motion 30. The computing device 100 detects the registered pattern 23 from the first image 11 of the first position photographed through the camera 10. [ The computing device 10 moves the alignment table 20 to the second position via the motion 20. The computing device 10 detects the registered pattern 23 from the second image 13 at the second position photographed through the camera 10. [ Then, the computing device 100 calculates a basic relation between the movement axis in the X-axis and Y-axis directions of the motion 30 and the fixed axis of the camera 10 based on the distance between the first position and the second position can do.

9 is a cross- Motion  Axis direction and a fixed axis of the camera in the X-axis direction and the Y-axis direction.

Referring to FIG. 9, the computing device 100 moves the aligned table 20 through the motion 30 by an integer multiple of the size of the pattern. The computing device 100 moves the aligned table 20 back through the motion 30 by an integer multiple of the size of the pattern. The computing device 100 determines whether the closed area 40 along the path of travel of the alignment table 20 is divided into a plurality of blocks 41 based on the size of the pattern. The computing device 100 may move the aligned table 20 again by an integer multiple of the size of the pattern if the closed area 40 is not divided into a plurality of blocks 41. [ 9 shows a closed area 40 where the blocks are arranged in a 2x3 form.

The computing device 100 may move the motion 30 in the X and Y axis directions based on the number of blocks 41 and the size of the pattern when the closed area 40 is divided into a plurality of blocks 41. [ It is possible to calculate the precision relation by correcting the basic relational expression between the axis and the fixed axis of the camera 10. [

10 is an exemplary diagram for explaining the process of calculating the maximum rotation range.

Referring to FIG. 10, the computing device 100 rotates the alignment table 20 via the motion 30. The computing device 100 determines whether a registered pattern 23 is detected from the image 11 for the rotated alignment table 20. [ When the registered pattern 23 is detected from the image 11 for the rotated alignment table 20, the computing device 100 calculates the angle of rotation of the aligned table 20 and the detected pattern 23 , The maximum rotation range of the alignment table 20 can be calculated.

11 Motion  FIG. 4 is a diagram illustrating a process for calculating a precision relation between a rotation axis and a fixed axis of a camera; FIG.

Referring to FIG. 11, the computing device 100 rotates the alignment table 20 a plurality of times through the motion 30. The computing device 100 determines whether the registered pattern 23 is detected from the images 11 for the rotated alignment table 10 every time the alignment table 20 is rotated. When the registered pattern 23 is detected from each image 11 for the rotated alignment table 10, the computing device 100 determines the respective image 11 for the rotated alignment table 20, Based on the photographed rotation angle, a precision relation between the rotation axis of the motion 30 and the fixed axis of the camera 10 can be calculated.

Figure 12 is a graph In the embodiment  Following Allein  Fig. 2 is a configuration diagram of a computing device for executing a calibration method.

12, a computing device 100 includes a processor 110, a memory 120, a transceiver 130, an input / output device 140, and a data bus 150 And storage 160. In this embodiment,

The processor 110 may implement the operations and functions associated with the alignment calibration method based on instructions in accordance with the machine vision software 170a residing in the memory 120. [ Memory 120 may be loaded with machine vision software 170a. The transceiver 130 is capable of transmitting and receiving data to and from the camera 10 and the motion 30. The input / output device 140 receives data necessary for performing the alignment calibration method, and can output the machine vision performance result. The data bus 150 is connected to the processor 110, the memory 120, the transceiver 130, the input / output device 140, and the storage 160 to transfer data between the respective components.

The storage 160 may store an application programming interface (API), a library file, a resource file, and the like necessary for executing the machine vision software 170a. In addition, the storage may store machine vision software 170b.

Then, the machine vision software 170a, 107b acquires a first image through a camera 10 that photographs a region of the alignment table 20 for machine vision, And the alignment table 20 is moved in the X-axis and Y-axis directions through the motion 30 for moving the alignment table 20, and then the second image is acquired through the camera 10 Axis direction of the motion 30 and the fixed axis of the camera 10 on the basis of the movement distance of the alignment table 20 when a registered pattern is detected from the second image, Obtaining a first image through the camera 10 after rotating the alignment table through the motion 30, and calculating a first correlation of the first image using the camera 10 when the registered pattern is detected from the third image , The rotation axis of the motion (30) and the rotation axis of the alignment table (20) In order to execute the step of calculating a second relation between the fixed axis of the camera 10, a computer program recorded on a recording medium.

Here, the step of calculating the first relational expression may include acquiring the fourth image through the camera 10 after moving the alignment table 20 by an integer multiple of the size of the registered pattern through the motion 30, Judging whether a closed area according to the movement path of the alignment table 20 is divided into a plurality of blocks based on the size of the pattern when a registered pattern is detected from the fourth image, And if the closed area is divided into a plurality of blocks, correcting the first relation based on the number of divided blocks and the size of the pattern.

The calculating of the second relational expression may include rotating the alignment table a plurality of times through motion, obtaining a plurality of fifth images, and, when a registered pattern is detected from the plurality of fifth images, And correcting the second relational expression based on the rotation angle of each image included in the five images.

The processor 110 may include an application-specific integrated circuit (ASIC), other chipset, logic circuitry, and / or a data processing device. The memory 120 may include a read-only memory (ROM), a random access memory (RAM), a flash memory, a memory card, a storage medium, and / or other storage devices. The transceiver 130 may include a baseband circuit for processing wired and wireless signals. The input / output device 140 may be an input device such as a keyboard, a mouse, and / or a joystick, a liquid crystal display (LCD), a light emitting diode (LED) An image output device such as an organic light emitting diode (OLED) and / or an active matrix organic light emitting diode (AMOLED), a printer, a plotter, and the like. When the embodiments included in the present specification are implemented in software, the above-described method may be implemented by a module (a process, a function, and the like) that performs the functions described above. The modules may be stored in the memory 120 and executed by the processor 110. The memory 120 may be internal or external to the processor 110 and may be coupled to the processor 110 in a variety of well known ways.

Each component shown in FIG. 12 may be implemented by various means, for example, hardware, firmware, software, or a combination thereof. In the case of hardware implementation, an embodiment of the present invention may include one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs) field programmable gate arrays, processors, controllers, microcontrollers, microprocessors, and the like.

In addition, in the case of an implementation by firmware or software, an embodiment of the present invention may be embodied in the form of a module, a procedure, a function, and the like for performing the functions or operations described above, Lt; / RTI > Here, the recording medium may include program commands, data files, data structures, and the like, alone or in combination. Program instructions to be recorded on a recording medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. For example, the recording medium may be an optical recording medium such as a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, a compact disk read only memory (CD-ROM), a digital video disk (DVD) Optical media such as a floppy disk and a hardware device specifically configured to store and execute program instructions such as ROM, RAM, flash memory and the like. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like. Such hardware devices may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, It will be apparent to those skilled in the art. Furthermore, although specific terms are used in this specification and the drawings, they are used in a generic sense only to facilitate the description of the invention and to facilitate understanding of the invention, and are not intended to limit the scope of the invention. Accordingly, the foregoing detailed description is to be considered in all respects illustrative and not restrictive. The scope of the present invention should be determined by rational interpretation of the appended claims, and all changes within the scope of equivalents of the present invention are included in the scope of the present invention.

In addition, a device or terminal according to the present invention may be driven by instructions that cause one or more processors to perform the functions and processes described above. Such instructions may include, for example, interpreted instructions such as script commands, such as JavaScript or ECMAScript commands, or other instructions stored in executable code or computer readable media. Further, the apparatus according to the present invention may be implemented in a distributed manner across a network, such as a server farm, or may be implemented in a single computer device.

Further, a computer program (also known as a program, software, software application, script or code) that is loaded on the apparatus according to the present invention and which implements the method according to the present invention includes a compiled or interpreted language, a priori or procedural language , And may be deployed in any form including standalone programs or modules, components, subroutines, or other units suitable for use in a computer environment. A computer program does not necessarily correspond to a file in the file system. The program may be stored in a single file provided to the requested program, or in multiple interactive files (e.g., a file storing one or more modules, subprograms, or portions of code) (E.g., one or more scripts stored in a markup language document). A computer program may be deployed to run on multiple computers or on one computer, located on a single site or distributed across multiple sites and interconnected by a communications network.

Moreover, in describing the embodiments according to the present invention, operations are depicted in the drawings in a particular order, but it is to be understood that they should perform such operations in that particular order or sequential order shown in order to obtain the desired result, Should not be understood as being performed. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the described program components and systems will generally be integrated together into a single software product or packaged into multiple software products It should be understood.

Claims (10)

Obtaining a first image through a camera that photographs one area of the alignment table for machine vision;
Registering a shape included in the first image as a pattern;
Moving the alignment table in the X-axis and Y-axis directions through a motion for moving the alignment table, and acquiring a second image through the camera;
Calculating a first relational expression between the motion axis in the X and Y axis directions of the motion and the fixed axis of the camera based on the movement distance of the alignment table when the registered pattern is detected from the second image step;
Rotating the alignment table through the motion and acquiring a third image through the camera; And
Calculating a second relational expression between the rotation axis of the motion and the fixed axis of the camera based on the rotation angle of the alignment table when the registered pattern is detected from the third image,
The step of calculating the first relationship may comprise:
Acquiring a fourth image through the camera after moving the alignment table by an integer multiple of the size of the registered pattern through the motion;
Determining whether a closed area according to the movement path of the alignment table is divided into a plurality of blocks based on the size of the pattern when the registered pattern is detected from the fourth image; And
And correcting the first relationship based on the number of divided blocks and the size of the pattern when the closed area is divided into a plurality of blocks. delete The method of claim 1, wherein determining whether to divide into the plurality of blocks comprises:
Acquiring an image for each of the plurality of blocks through the camera; And
Determining whether the registered pattern is detected from an image for each of the plurality of blocks. The method according to claim 1,
Characterized in that the closed area is an area in which the blocks are arranged in a 5x5 form. 2. The method of claim 1, wherein the calculating the second relationship further comprises:
Rotating the alignment table a plurality of times through the motion and obtaining a plurality of fifth images; And
And correcting the second relational expression based on a rotation angle at which each image included in the fifth images is captured when the registered pattern is detected from the plurality of fifth images. Calibration method. 6. The method of claim 5, wherein obtaining a fifth image comprises:
Calculating a maximum rotation range at which the alignment table can rotate from the third image; And
And rotating the alignment table a plurality of times within the maximum rotation range to obtain the fifth images. 6. The method of claim 5,
The number of images included in the fifth image is eight,
Wherein the closed region along the rotation path of the alignment table has an octagonal shape. Coupled to the computing device,
Obtaining a first image through a camera that photographs one area of the alignment table for machine vision;
Registering a shape included in the first image as a pattern;
Moving the alignment table in the X-axis and Y-axis directions through a motion for moving the alignment table, and acquiring a second image through the camera;
Calculating a first relational expression between the motion axis in the X and Y axis directions of the motion and the fixed axis of the camera based on the movement distance of the alignment table when the registered pattern is detected from the second image step;
Rotating the alignment table through the motion and acquiring a third image through the camera; And
And calculating a second relational expression between the rotation axis of the motion and the fixed axis of the camera based on the rotation angle of the alignment table when the registered pattern is detected from the third image,
The step of calculating the first relationship may comprise:
Acquiring a fourth image through the camera after moving the alignment table by an integer multiple of the size of the registered pattern through the motion;
Determining whether a closed area according to the movement path of the alignment table is divided into a plurality of blocks based on the size of the pattern when the registered pattern is detected from the fourth image; And
And a step of correcting the first relation based on the number of divided blocks and the size of the pattern when the closed area is divided into a plurality of blocks. delete 9. The method of claim 8, wherein calculating the second relationship further comprises:
Rotating the alignment table a plurality of times through the motion and obtaining a plurality of fifth images; And
And correcting the second relational expression based on a rotation angle at which each image included in the fifth images is captured when the registered pattern is detected from the plurality of fifth images. ≪ / RTI >

Images