WO2007125981A1

WO2007125981A1 - Boundary position decision device, boundary position decision method, program for functioning computer as the device, and recording medium

Info

Publication number: WO2007125981A1
Application number: PCT/JP2007/059025
Authority: WO
Inventors: Masakazu Yanase
Original assignee: Sharp Kabushiki Kaisha
Priority date: 2006-04-28
Filing date: 2007-04-26
Publication date: 2007-11-08
Also published as: JP4275149B2; JP2007298376A

Abstract

It is possible to accurately detect a position of an edge of a panel formed on a glass substrate. An edge position detection device executes: a step (S710) for performing initialization according to an instruction inputted to the device from outside; a step (S720) for extracting an image corresponding to the object region from an image expressing the entire glass substrate, a step (S730) for generating image data emphasizing an edge of the extracted image, a step (S740) for accumulating data expressing the image whose edge is emphasized according to the direction of the projection accumulation direction and generating one-dimensional projection accumulated data, a step (S750) for deciding a region as an object for which a statistical amount is to be calculated, a step (S760) for calculating the statistical amount according to the decided region and calculating a threshold value based on the statistical amount, and a step (S770) for using the threshold value to decide the position of the panel edge.

Description

Specification

Boundary position determination device, method for determining boundary position, program for causing computer to function as the device, and recording medium

Technical field

The present invention relates to a technique for determining the position of a boundary, and more specifically to a technique for determining the position of a boundary included in an image acquired by photographing a subject.

Background art

[0002] The inspection process in the manufacturing process plays an important role as a quality control method for manufacturing a high-quality thin panel. In recent years, a wide variety of defect inspection devices using image processing technology have been developed in order to stabilize costs and reduce costs by reducing the number of visual inspectors. In general, the larger the processing area, the more processing time is required for image processing. For this reason, the processing time is shortened by inspecting the image using only the necessary area.

On the other hand, as a method for producing a thin panel, it is common to produce a plurality of panels from a single glass substrate. In such a glass substrate defect inspection, an image acquired by imaging with a camera is used. In this defect inspection, as a proposal for shortening the image inspection processing time, there is a method in which only the inside of each panel is inspected and the other portions are not inspected.

In order to inspect only the inside of the panel, it is necessary to determine the boundary of the panel region in the image of the glass substrate, that is, the edge position of the panel.

[0005] As a method for determining the edge position, there is a method of using design data of the edge position. Specifically, the position of the edge in the image is calculated from the position of the edge with respect to the edge of the glass substrate and the positional relationship between the camera and the glass substrate.

[0006] However, in this method, an error of about 10 mm is generally generated due to a positioning error between the camera and the glass substrate. Therefore, it is necessary to determine the edge position by image processing.

As a method for determining an edge position by image processing, for example, Japanese Patent Laid-Open No. 5-266194 No. 1 (Patent Document 1) discloses a technique that can determine the end point of a straight line portion of a contour line without being affected by noise. According to this technique, first, an image is projected in gray in the direction of an edge, and one-dimensional projection accumulated data is obtained. Next, the magnitude of the one-dimensional projection accumulated data force gradient is obtained, and the position is detected as the position force edge position where the gradient magnitude reaches a peak.

[0008] Further, as a technique for detecting a connection portion of a plurality of parts displayed in an image, for example, Japanese Patent Laying-Open No. 2005-284725 (Patent Document 2) describes an object to be joined such as an extrusion-type material or a plate material to be joined together. It discloses a technology that can accurately detect the joint line even if the surface of the material is contaminated if it is contaminated.

[0009] Further, as a technique for detecting an edge, for example, Japanese Unexamined Patent Application Publication No. 2004-272313 (Patent Document 3) is a technique for detecting an edge with high accuracy by quantitatively analyzing an image having poor edge quality. Is disclosed.

[0010] Further, regarding the extraction of the edge of a subject, for example, Japanese Patent Laid-Open No. 2005-167802 (Patent Document 4) reads a document image by an area sensor and extracts the document edge from the image data by image processing. A technique for detecting the document size based on the contour and position of the document is disclosed.

Patent Document 1: JP-A-5-266194

Patent Document 2: Japanese Patent Laid-Open No. 2005-284725

Patent Document 3: Japanese Patent Application Laid-Open No. 2004-272313

Patent Document 4: Japanese Unexamined Patent Application Publication No. 2005-167802

Disclosure of the invention

Problems to be solved by the invention

Consider a case in which the panel edge of a panel on a glass substrate is determined using the first technique disclosed in Japanese Patent Laid-Open No. 5-266194. There is a wiring pattern area around the panel. The outside of the wiring pattern region is a glass substrate.

When a glass substrate having such a configuration is imaged by a camera, the panel edge, the edge of the wiring pattern, and the edge force of the glass substrate are output on the image data from the inside of the panel to the outside. [0013] According to the first technique, one-dimensional projection accumulation data is obtained by accumulating pixel values of an original image along a plurality of directions, and a peak value of projection gradient data is obtained for each. The peak value in the largest direction among the plurality of directions is set as the edge position.

[0014] According to this technique, there is a case where the position of the pattern edge is selected and the position of the panel edge is not selected, and there is a problem that the edge cannot be determined with high accuracy.

[0015] In addition, Japanese Patent Laid-Open No. 5-266194 discloses a second technique for obtaining a two-dimensional gradient distribution of an original image before obtaining one-dimensional projection accumulated data.

[0016] As a method of obtaining a two-dimensional gradient distribution, there is a method of using image data after performing Sobel filter processing. In this case as well, as with the method according to the first technique described above, the position of the pattern edge is selected and the position of the panel edge is selected even if the one-dimensional projection accumulated data force obtains the peak position of the gradient magnitude. May not be selected. As a result, the panel edge may not be determined with high accuracy.

The present invention has been made to solve the above-described problems, and an object of the present invention is to provide a position determination device that can accurately determine the position of the boundary. Another object is to provide a boundary position determination device that can improve the efficiency of image processing inspection of an inspection object.

[0018] Another object is to provide a method capable of accurately determining the position of the boundary. Another object is to provide a method for determining the boundary position, which can improve the efficiency of image processing inspection of the inspection object.

[0019] Another object is to provide a program for causing a computer to function as an apparatus that can accurately determine the position of a boundary. The sixth object is to provide a program for causing a computer to function as a boundary position determination device capable of improving the efficiency of image processing inspection of an inspection object.

Another object is to provide a recording medium storing a program for causing a computer to function as an apparatus that can accurately determine the position of a boundary. Still another object of the present invention is to provide a recording medium storing a program for causing a computer to function as a boundary position determination device capable of improving the efficiency of image processing inspection of an inspection object. is there.

Means for solving the problem

In order to solve the above-described problem, according to one aspect of the present invention, the boundary position determination device includes a storage unit that stores original image data representing an original image acquired by photographing a subject. The original image data is represented according to a two-dimensional coordinate axis. When the original image has a plurality of partial images, the apparatus includes first generation means for generating emphasized image data representing an image in which the boundary of each partial image is emphasized based on the original image data; Each luminance value of each partial area corresponding to each partial image after enhancement is integrated in the direction of the boundary, and the average value is calculated to express it according to the one-dimensional coordinate axis of the two-dimensional coordinate axes. A second generation unit that generates a plurality of one-dimensional data, a first determination unit that determines a range of data for determining a boundary position based on the design data of the subject, and a data Calculated based on a calculation means for calculating a threshold value for luminance values by calculating a statistic using a plurality of one-dimensional data included in the range, and a plurality of one-dimensional data included in the data range. Exceed threshold Second determination means for determining a coordinate value on a one-dimensional coordinate axis of the one-dimensional data corresponding to the luminance value as a boundary position;

[0022] Preferably, the first determination unit determines a data range based on a range determined by the original image data and a range specified by the design data.

[0023] Preferably, the first determining means calculates one-dimensional boundary data as calculation position data based on design data, and as actual position data based on original image data, Calculate one-dimensional boundary data, and determine the data range based on the difference between the calculated position data and the actual position data.

[0024] Preferably, the subject includes a first part to be inspected and a second part not to be inspected. The original image includes a first image corresponding to the first part and a second image corresponding to the second part. The first generation means generates data representing an image in which the boundary between the first image and the second image is enhanced as the enhanced image data.

[0025] Preferably, the subject is a glass substrate. The first part is the panel area processed into a glass substrate. The first generation means includes an image corresponding to the panel area and the panel area. Data representing an image in which a portion in contact with an image corresponding to a region other than is emphasized is generated.

[0026] Preferably, the calculating means calculates an average value and a standard deviation for a plurality of one-dimensional data, and calculates a threshold based on the average value and the standard deviation.

[0027] Preferably, the specifying unit specifies a plurality of one-dimensional data corresponding to a luminance value exceeding a threshold, and for each of the specified one-dimensional data, the upper limit value of the data range and the one-dimensional data are determined. The one-dimensional data that minimizes each calculated difference is determined as the one-dimensional data corresponding to the luminance value exceeding the threshold.

[0028] Preferably, the original image includes a rectangular region. The boundary is formed by the outline of the rectangular area. The first generation means generates data representing an image in which the boundary formed by the contour is emphasized as the emphasized image data.

[0029] Preferably, the second generation means calculates the average value by integrating the luminance values of the pixels corresponding to the rectangular area after the boundary is emphasized in one direction in the rectangular area. By

The plurality of one-dimensional data are generated, and the first determining means determines the data range so that the range of the data is included in the range defined by the one-dimensional data for the rectangular area.

[0030] Preferably, the statistic includes an average value and a standard deviation. The calculation means calculates the threshold value using each formula defined in advance according to each value of the plurality of standard deviations, and each formula varies depending on the value of each standard deviation.

[0031] According to another aspect of the invention, a method is provided for a computer to determine a position of a boundary included in an image. The computer includes a storage device that stores data and a processing device that executes a predetermined process using the data. In this method, the processing device includes a step of reading original image data representing an original image acquired by photographing a subject from the storage device. The original image data is represented according to a two-dimensional coordinate axis. In this method, when the original image has a plurality of partial images, the processing unit generates enhanced image data representing an image in which the boundary of each partial image is emphasized based on the original image data! Then, the processing device integrates each luminance value of each partial area corresponding to each partial image after the boundary is emphasized in the direction of the boundary, and calculates an average value, thereby obtaining a two-dimensional coordinate. A step of generating a plurality of one-dimensional data represented according to a one-dimensional coordinate axis of the standard axis, and a data processing target for the processing device to determine the boundary position based on the design data of the subject A step of determining a range, a step of calculating a threshold value for a luminance value by calculating a statistic using a plurality of one-dimensional data included in the data range, and a processing device A step of identifying one-dimensional data corresponding to a luminance value exceeding a threshold value based on a plurality of one-dimensional data included in the range, and the processing device coordinates the one-dimensional coordinate axis of the identified one-dimensional data. Determining the value as the position of the boundary.

According to another aspect of the present invention, there is provided a program for causing a computer to function as an apparatus for determining the position of a boundary included in an image. The computer includes a storage device that stores data and a processing device that executes a predetermined process using the data. This program causes the processing device to execute a step of reading original image data representing an original image acquired by photographing a subject from the storage device. The original image data is represented according to a two-dimensional coordinate axis. In the program, when the original image has a plurality of partial images, the program generates, based on the original image data, enhanced image data representing an image in which the boundary of each partial image is emphasized; Each luminance value of each partial area corresponding to each partial image after enhancement is integrated in the direction of the boundary, and the average value is calculated, so that it is expressed according to the one-dimensional coordinate axis out of the two-dimensional coordinate axes. A step of generating a plurality of one-dimensional data, a step of determining a range of target data for determining a boundary position based on the design data of the subject, and a plurality of one-dimensional data included in the range of the data Using the data to calculate the statistic, the step of calculating the threshold value for the luminance value and the luminance value exceeding the threshold value based on the multiple one-dimensional data included in the data range Identifying a corresponding one-dimensional data, a coordinate value on a one-dimensional coordinate axis of the one-dimensional data specified to execute a stearyl-up to determine the position of the boundary.

[0033] According to another aspect of the present invention, a computer-readable recording medium storing the above program is provided.

[0034] According to another aspect of the present invention, the boundary position determination device is obtained by photographing a subject. A storage unit for storing original image data representing the original image. The original image data is represented according to the two-dimensional coordinate axes. When the original image has a plurality of partial images, the apparatus includes a first generation unit that generates enhanced image data representing an image in which the boundary of each partial image is emphasized based on the original image data, and the boundary is It is expressed according to the one-dimensional coordinate axis of the two-dimensional coordinate axes by calculating the average value by integrating the luminance values of the partial areas corresponding to the emphasized partial images in the direction of the boundary. A second generation unit that generates a plurality of one-dimensional data; a first determination unit that determines a range of data for determining a boundary position based on the design data of the subject; and a data range Based on a plurality of one-dimensional data included in the data range, a calculation unit that calculates a threshold value for the luminance value by calculating a statistic using a plurality of one-dimensional data included in , Luminance value exceeding the calculated threshold Comprising a coordinate value on a one-dimensional coordinate axis of the corresponding one-dimensional data, and a second determination unit which determines a position of the boundary.

[0035] According to still another aspect of the present invention, a method for determining a position of a boundary included in an image is provided. The method includes a step of reading original image data representing an original image acquired by photographing a subject. The original image data is represented according to a two-dimensional coordinate axis. According to this method, when the original image has a plurality of partial images, the step of generating emphasized image data representing an image in which the boundary of each partial image is emphasized based on the original image data; Multiple brightness values of each partial area corresponding to each partial image after being emphasized are integrated in the direction of the boundary, and an average value is calculated, so that a plurality of two-dimensional coordinate axes can be represented according to the one-dimensional coordinate axis. Generating one-dimensional data, determining a range of data for determining the boundary position based on the design data of the subject, and a plurality of one-dimensional data included in the data range And calculating a statistic using the step of calculating a threshold value for the luminance value and a one-dimensional data corresponding to the luminance value exceeding the threshold value based on a plurality of one-dimensional data included in the data range. Comprising identifying a data, a coordinate value on a one-dimensional coordinate axis of the one-dimensional data specified, and determining a position of the boundary.

The invention's effect

[0036] According to the boundary position determining apparatus of the present invention, the boundary (for example, the edge portion of the panel) Can be accurately determined. According to the method of the present invention, the computer can accurately determine the position of the boundary. According to the program according to the present invention, the computer functions as an apparatus that can accurately determine the position of the boundary. When a recording medium according to the present invention is loaded on a computer and a program stored in the recording medium is executed, the computer that executes the program functions as an apparatus that can accurately determine the position of the boundary. can do. As a result, the efficiency of the image processing inspection of the inspection object can be improved.

Brief Description of Drawings

FIG. 1 is a diagram showing a configuration of an inspection system 10 according to an embodiment of the present invention.

FIG. 2 is a diagram showing an image 240 of a glass substrate 140.

FIG. 3 is a diagram showing an image of region 206.

FIG. 4 is a diagram showing an edge-enhanced image 400 generated by executing Sobel filter processing.

FIG. 5 is a block diagram showing the configuration of each function realized by edge position detection apparatus 100.

FIG. 6 is a diagram conceptually showing one mode of data storage in storage unit 540.

FIG. 7 is a flowchart showing a procedure of processing executed by processing unit 550 of edge position detection apparatus 100.

FIG. 8 is a diagram showing the appearance of a glass substrate 800.

FIG. 9 is a diagram showing an image 900 acquired when a glass substrate 800 is photographed with a camera.

FIG. 10 is a diagram for explaining an image 906;

FIG. 11 is a diagram showing an image obtained by performing Sobel filter processing on image 906.

FIG. 12 is a block diagram showing a hardware configuration of computer system 1200. Explanation of symbols

[0038] 10 inspection system, 140 glass substrate, 141, 142 non-nell, 206 area, 210, 220, 240, 300 image, 211, 212, 213, 214, 811, 812, 813, 814 nonel edge, 215, 815 Wiring pattern area, 216 Wiring pattern edge. BEST MODE FOR CARRYING OUT THE INVENTION

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, the same parts are denoted by the same reference numerals. Their names and functions are the same. Therefore, detailed description thereof will not be repeated.

With reference to FIG. 1, an inspection system 10 according to an embodiment of the present invention will be described.

FIG. 1 is a block diagram showing a hardware structure of an inspection system 10 having a function for determining the position of an edge. The inspection system 10 is electrically connected to the light 110, the edge position detection device 100 electrically connected to the light 110, the camera 120 electrically connected to the edge position detection device 100, and the edge position detection device 100. And a display 130 connected to the. The edge position detection device 100 detects the position of the boundary (edge) between the panel region formed on the glass substrate and the region other than the panel region. Specifically, as described later, the edge position detection device 100 detects the position of the boundary as a coordinate value on a coordinate axis defined in advance.

[0041] Into the inspection system 10, a glass substrate 140, which is an object to be inspected, is carried in and mounted at a predetermined position. Two thin panels 141 and 142 are formed on the glass substrate 140, respectively.

The light 110 irradiates light having a preset intensity on the glass substrate 140 mounted at the position based on a signal from the edge position detection device 100. The irradiated light is, for example, general white light.

The camera 110 receives and captures the reflected light from the glass substrate 140 and sends it to the edge position detection device 100 as image data. The camera 120 may be an area sensor camera or a line sensor camera. The imaging part of the camera 120 has a photoelectric conversion structure such as a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS).

[0044] The size of the image described in the present embodiment is, for example, horizontal 1000 pixels and vertical 1200 pixels. However, the size of the image is not limited to the above, and may be other sizes (for example, horizontal 500 pixels, vertical 600 pixels).

In addition, the luminance values of the pixels of the image described in the present embodiment are “0” to “255”. A range value. In the following explanation, when the luminance value is “0”, the corresponding pixel corresponds to black. When the luminance value is “255”, the corresponding pixel corresponds to white. Note that the luminance value of the image pixel used in the present embodiment is not limited to the value included in the range of “0” to “255” but may be a value included in other ranges.

With reference to FIG. 2, an image of glass substrate 140 taken by camera 120 will be described. FIG. 2 is a diagram showing an image 240 of the glass substrate 140. The image 240 includes a non-linear edge 211, 212, 213, 214 formed at the boundary between the panel 210 and the glass substrate, and a wiring pattern region 215 formed inside the glass substrate 140 so as to surround the non-linear 210. including.

For the nonel 220 as well, an image representing a wiring pattern region formed between the glass substrate 140 and the panel 220 and a panel edge surrounding the panel 220 in a rectangular shape is generated. Further, a wiring pattern edge (for example, a wiring pattern edge 216) is generated between the wiring pattern region 215 and the glass substrate 140. The area 206 is an image corresponding to the area to be inspected, in addition to the image 240.

[0048] The region 206 will be described with reference to FIG. FIG. 3 is a diagram representing an image 300 in the region 206.

Image 300 shows an image edge 201 corresponding to the edge of region 206, wiring pattern edge 216, nonel edge 211, and noise 230. The accumulation direction shown in Fig. 3 (A) represents the direction in which the luminance values included in each area are accumulated. This direction is predetermined for 140 glass substrates. For example, when the glass substrate 140 is rectangular, a direction parallel to any one side is defined as the accumulation direction.

FIG. 3 (B) is a diagram showing values calculated by integrating the luminance values corresponding to the image 300 in the accumulation direction. Specifically, for the region 310, the luminance value in each region is expressed as at least 160 or more when the X coordinate value is between 0 and a. For region 320, the luminance value is expressed as 180 when the X coordinate value is between a and b. Further, for the region 330, the luminance value is expressed as 0 in the range of the X coordinate value force ¾ or more. [0051] An image generated by the filtering process will be described with reference to FIG. FIG. 4 is a diagram showing an edge-enhanced image 400 generated by performing Sobel filter processing on an image corresponding to the region 206 in the image 240.

[0052] As shown in FIG. 4A, the edge-enhanced image 400 includes an image 410 corresponding to a part of the panel area, an image 420 corresponding to a part of the wiring pattern area, and a part of the glass substrate. And the corresponding image 430. The edge-enhanced image 400 includes an image 211 corresponding to the panel edge, an image 216 corresponding to the wiring pattern edge, and a noise 230. An accumulation direction 450 represents a direction in which luminance values of pixels corresponding to the respective images are integrated.

FIG. 4B is a diagram showing a result (integrated value) obtained by integrating the luminance values in accordance with the accumulation direction 450. For example, the integrated value for the image 410 corresponding to the normal area in the panel area is “0”. The integrated value of noise 230 is “20”. The integrated value for the image 211 corresponding to the panel edge is “40”. The integrated value for the image 420 corresponding to a part of the wiring pattern region is “0”. The integrated value for the image 216 corresponding to the wiring pattern edge is “127”. The integrated value for the image 430 corresponding to the glass substrate is “0”.

With reference to FIG. 5, an edge position detection apparatus 100 constituting the inspection system 10 will be described. FIG. 5 is a block diagram showing the configuration of each function realized by edge position detection apparatus 100. The edge position detection apparatus 100 includes a design data input unit 510, an image input unit 520, a temporary storage unit 530, a storage unit 540, and a processing unit 550. The processing unit 550 includes a writing unit 551, an initial setting unit 552, a coordinate acquisition unit 553, an extraction unit 554, an image generation unit 555, an integration unit 556, a data range determination unit 557, and a threshold calculation unit. 558, a position determination unit 559, and a display control unit 560.

Design data input unit 510 accepts data input representing the design specifications of panels 141 and 142 formed on glass substrate 140. This data includes, for example, size information of the glass substrate 140, size information of the panels 141 and 142, or data defining the positional relationship between the panels 141 and 142 and the glass substrate 140.

The image input unit 520 receives input of image data output from the camera 120. The temporary storage unit 530 is input by the design data input unit 510 or the image input unit 520. The received data or the data generated by the processing unit 550 is temporarily (volatilely) retained. Temporary storage unit 530 is realized as, for example, a RAM (Random Access Memory) or a frame notifier. Note that the temporary storage unit 530 is physically not limited to being implemented as a single memory, and may be configured by being divided into two or more memories.

Write unit 551 reads the data held in temporary storage unit 530 and writes the data in an area secured in storage unit 540. The storage unit 540 is a storage device that can hold data in a nonvolatile manner. The initial setting unit 552 performs an inspection process to be performed on the glass substrate 140 based on data stored in the storage unit 540 and an external instruction input to the edge position detection device 100. Are read from the storage unit 540 and stored in an area secured in the temporary storage unit 530.

Storage unit 540 stores image data generated by photographing glass substrate 140 (for example, data representing image 240 shown in FIG. 2). The storage unit 540 is realized as, for example, a flash memory or a hard disk device.

[0059] The coordinate acquisition unit 553 is based on the image data of the glass substrate 140 stored in the storage unit 540! /, To obtain the coordinates of the nore edge 211, 212, 213, 214. In addition, from the viewpoint of promoting the inspection of image processing, instead of obtaining the coordinates of each panel edge, the coordinates of any specific panel edge (for example, panel edge 211) may be obtained. Good.

The extraction unit 554 extracts the image of the region 206 (ie, the partial image divided by the boundary) from the image 240 based on the data stored in the storage unit 540. Specifically, first, the storage unit 540 stores coordinate values for specifying the area 206 set by the initial setting unit 552. The extraction unit 554 refers to each coordinate value, determines an area corresponding to the coordinate value from the image 240, and extracts data included in the determined area. Extraction unit 554 stores the extracted data in temporary storage unit 530 (extracted image data 531).

The image generation unit 555 executes a process for enhancing the contour of the image based on the image data stored in the temporary storage unit 530. Specifically, the image generation unit 555 uses the extracted image data 531 to generate a frame that is a general image conversion method in image processing. In addition to using the filter process, the filter process is executed based on the parameters previously input as initial setting values. The filter processing performed is, for example, a 3 × 3 Sobel filter, which is a common edge extraction filter. The image generation unit 555 stores the image data generated by executing the filter processing in the temporary storage unit 530 (image data 532 with edge enhancement).

[0062] Using the data stored in temporary storage unit 530, integrating unit 556 integrates the luminance values of the pixels constituting the image in one predetermined direction. Specifically, the integration unit 556 6 integrates the luminance value of each pixel having the same coordinate value with respect to the X coordinate specified in the image 240 in a predetermined integration direction (for example, the negative direction of the Y axis). . The integrating unit 556 further calculates an average value of the luminance values for the pixels having the same X coordinate value by dividing the integrated value by the number of integrated pixels. The accumulating unit 556 writes the primary projection data 533 thus calculated in the temporary storage unit 530.

The data range determination unit 557 determines the range of data that is a target for determining the position of the edge 211 using the primary projection data 533 stored in the temporary storage unit 530. When the data range determining unit 557 determines the data range, the data range determining unit 557 stores the data range as data 534 representing the data range in the area secured in the temporary storage unit 530.

[0064] The threshold value calculation unit 558 uses the primary projection data 533 to calculate a threshold value by executing a predetermined statistic calculation process for the range defined by the data 534 representing the data range. The threshold value according to the present embodiment is a luminance value used for determination to determine the position of the edge 211. When the threshold value calculation unit 558 determines the threshold value, the threshold value calculation unit 558 writes the threshold value in the temporary storage unit 530 (threshold value 535).

The position determination unit 559 determines the position (X coordinate value) of the panel edge 211 based on the primary projection data 533 and the threshold value 535. For example, the position determination unit 559 specifies the primary projection data 533 for the luminance value exceeding the threshold value 535, and determines the X coordinate value of the specified primary projection data 533 as the position of the panel edge 211. The position determination unit 559 writes the position data determined in this way into the temporary storage unit 530 (data 536 representing the position of the edge).

Display control unit 560 is based on a display instruction input via setting data input unit 510. Then, the data stored in the temporary storage unit 530 is read out, and the data is sent to the display unit (for example, the display 130) to display the captured image.

With reference to FIG. 6, the data structure of edge position detection apparatus 100 will be described. FIG. 6 is a diagram conceptually showing one mode of data storage in storage unit 540. Storage unit 540 includes memory area 602 to memory area 630 for storing data.

Image data acquired by photographing the glass substrate 140 on which the panels 141 and 142 are formed is recorded in the memory area 602. An offset value (Poff) input in advance for determining the data range is stored in the memory area 604. Coordinate values input in advance to define the region 206 as a target for detecting the position of the edge are input to the memory regions 606 and 608, respectively. For example, the coordinate value Pit at the upper left end of the area 206 is stored in the memory area 606 as (800, 1150). Similarly, the coordinate value Pbr (X, Y) representing the lower right corner of the area 206 is stored in the memory area 608 as (1000, 700).

[0069] The number of data Nd defined in advance as the number of data to be integrated for calculating the statistic is stored in the memory area 610. A constant “a” used in the formula for determining the threshold value is stored in the memory area 612. The projection accumulation direction Dp determined for accumulating the luminance value of each pixel in a predetermined direction is stored in the memory area 614 as, for example, “data indicating the negative direction of the Y coordinate axis”. Yes.

[0070] Parameter values used to execute the Sobel filter processing are stored in the memory area 616. Design data determined by panel design for forming the panels 141 and 142 on the glass substrate 140 is stored in the memory area 618. The design data includes, for example, the vertical and horizontal sizes (for example, length) of the glass substrate 140, the vertical and horizontal sizes of the panels 141 and 142 (for example, the number of pixels), the distance between the glass substrate 140 and the panels 141 and 142, Includes the spacing between panels 141 and 142.

The X coordinate value (Xd) of the panel edge (for example, the panel edge 211) calculated based on the design data is stored in the memory area 620. Before the X coordinate value is calculated, for example, data representing “NULL” is stored. The same applies to other regions. The panel edge calculated using the image data obtained by shooting with force 120 For example, the X coordinate value (Xr) of the panel edge 211) is stored in the memory area 622. The X coordinate value (Xe) of the maximum value of the panel edge (for example, the panel edge 211) for which the computing power by the data range determination unit 557 is also calculated is stored in the memory area 624. Similarly, the minimum value (Xs) of the panel edge is stored in the memory area 626. Data stored in memory areas 624 and 626 corresponds to data 534 representing the data range shown in FIG. 5, for example. When the data range determination unit 557 is not executing the above-described processing, the memory areas 624 and 626 store information (NULL) indicating that no data exists in each area.

The threshold value Vth is stored in the memory area 628. A program used for realizing each of the above functions of the edge position detection apparatus 100 is stored in the memory area 630. When the program is executed by an arithmetic processing unit such as a processor, each function constituting the processing unit 550 shown in FIG. 5 is realized. The program is configured, for example, by combining modules that realize each function.

With reference to FIG. 7, a control structure of edge position detection apparatus 100 will be described. FIG. 7 is a flowchart showing a procedure of processing executed by processing unit 550. When the edge position detection device 100 is realized by a computer system, it functions as a processor power processing unit 550 included in the computer system.

In step S 710, processing unit 550 performs data reading and other initial settings based on an instruction input from the outside to edge position detection device 100. Specifically, the processing unit 550 reads out the data stored in the storage unit 540 as the initial setting unit 552 and writes it in the temporary storage unit 530. The data written by the initial setting is, for example, the actual panel edge calculated based on the X coordinate value Xs (211) of the panel edge 211 included in the image 240 and the data of the image 240, which is calculated based on the design data. Among the errors between the X coordinate value Xr (211) and the coordinate value Xs (211) of 211, the maximum error Xme (211), the coordinate value specifying the region 206, the offset Poff, the number of data Nd, the constant a, , Projection and accumulation direction Dp.

In step S 720, processing unit 550 extracts an image corresponding to region 206 from image 240 representing the entire glass substrate 140. Specifically, the processing unit 550 reads out the image data stored in the storage unit 540 as the extraction unit 554, and extracts the upper left coordinate value Pit and the lower right coordinate. The rectangular area to be extracted is identified with reference to the standard value Prb, and data included in the area is stored in another area secured in the temporary storage unit 530 (extracted image data 5 31 ). As an example, in the image 300 shown in FIG. 3A, the region 206 is a rectangular region, and the coordinate value Pit (X, Y) of the upper left end of the region 206 is (800, 1150), The coordinate value Prb (X, Y) at the lower right end of the region 206 is (1000, 700). Therefore, the luminance value of the pixel corresponding to the area included in the area specified by these coordinate values is stored in the temporary storage unit 530.

In step S730, processing unit 550 generates image data in which the edge of the extracted image is emphasized. Specifically, the processing unit 550 performs, as the image generation unit 555, the Sobel filter processing defined in advance with reference to the extracted image data 531, thereby enhancing the contour included in the region 206. Generated image data (image data 532). An image generated by the Sobel filter processing is, for example, an image 400 shown in FIG.

In step S740, the processing unit 550 integrates the data representing the edge-enhanced image according to the direction of the projection accumulation direction Dp to generate one-dimensional projection accumulation data. Specifically, the processing unit 550 reads out the edge-enhanced image data 532 from the temporary storage unit 530 as the integrating unit 556, and each pixel having the same X coordinate value along the negative direction of the Y coordinate axis. The luminance values of are integrated. Referring to the coordinate values (memory areas 606 and 608) shown in FIG. 6, the size of the image in the Y-axis direction is 450 pixels (= 1150−700). Therefore, 450 luminance values are accumulated. In the example of Fig. 4 (B), the above integration is performed along the accumulation direction 440.

In step S750, processing unit 550 determines a region for which a statistic is to be calculated. Specifically, processing unit 550 refers to primary projection data 533 as data range determination unit 557 and derives data 534 representing the data range. In the present embodiment, each luminance value is projected according to the Y-axis direction. Therefore, the range is specified by the X coordinate range (Xs to Xe).

[0079] The coordinate value Xr (211) corresponding to the actual panel edge 211 included in the image 240 is in the above region for calculating the statistic from the viewpoint of accurately determining the position of the edge. Must not be included. However, in reality, due to positioning errors between the camera 120 and the glass substrate 140, the X coordinate value Xs (211) of the panel edge 211 in the image 240 calculated based on the design data The X coordinate value Xr (211) of the actual panel edge 21 1 included in the image 240 may not match. In this case, the value of Xr (211) is unknown when step S750 is executed. Therefore, the upper limit X-coordinate value (Xe) that defines the range of data used to calculate the statistic, the X-coordinate value Xs (211), the maximum error Sme (211), and the offset Poff By subtracting, the actual panel edge 211 included in the image 240 can be set so as not to be included in the area for calculating the statistics. Similarly, the X coordinate value (Xs) of the lower limit value of the area is also calculated by subtracting the upper limit value Xe force from the data number Nd.

[0080] For example, the calculation using the values shown in Fig. 4 (B) is performed as follows.

Xe = Xs (211) -Xme (211) —Poff

= 950-20-10

= 920

Here, a force in which “10” is used as the offset value (Poff) may be used. The offset value is determined as follows, for example.

First, when Poff = 0, Xe = 950−20−0 = 930. This value coincides with the end of the area for calculating the statistic when the actual panel edge 211 has a maximum error shift. Therefore, the offset value may be at least “1” or more.

[0082] In the present embodiment, assuming that there is a gradient as a luminance value that is not noise near the actual panel edge, the average value and the variance of the luminance values that are more stable as non-defective products As shown, the offset value is set to “10”. In this embodiment, a pixel is used as the unit of the offset value.

[0083] Further, the X coordinate value Xs of the smaller area for calculating the statistic is obtained by subtracting the number of data Nd for calculating the upper limit value Xe force metric.

[0084] Xs = Xe-Nd + l

= 920-50 + 1

= 871 Here, the larger the number of data Nd is, the longer the processing time becomes. On the other hand, the smaller the value, the shorter the processing time. The force processing result is more susceptible to local noise, and the accuracy is reduced. Therefore, the number of data Nd is determined in consideration of the trade-off relationship between processing time and detection accuracy. This determination is made based on the results of the actual processing (processing time and detection accuracy).

As a result of the above calculation, the region for calculating the statistic in the present embodiment is determined as 871 to 920 for the X coordinate.

[0086] Taking the case of determining the other panel edges 212, 213, and 214 into consideration, the above contents will be generally described as follows. First, from the “coordinate value of the panel edge in the image calculated using the design data” toward the inside of the panel, the “coordinate value of the actual panel edge in the image and the design data force panel in the calculated image The number of pixels corresponding to the “maximum error with the edge coordinate value” is shifted. Next, the position where the number of pixels shifted by “offset, which is the displacement amount for determining the area for calculating the statistic”, is shifted by the boundary on the panel edge side of the “area for calculating the statistic”. is there. Furthermore, the position force is the other boundary obtained by shifting the number of data corresponding to the number of data (Nd) -1 for calculating the statistic from the “boundary on the panel edge side of the region for calculating the statistic”.

Referring again to FIG. 7, in step S760, processing unit 550 calculates a statistic based on the region determined in step S750, and further calculates a threshold Vth based on the statistic. The statistic includes, for example, the average value (Vave) and standard deviation (Vsig) of the one-dimensional projection accumulation data included in the region. Specifically, processing unit 550 derives threshold value 535 as threshold calculation unit 558 by referring to data 534 representing a data range.

[0088] For example, in the example shown in FIG. 4B, Nd (= 50) included in the upper limit X coordinate value Xe of the region from the lower X coordinate value Xs of the region for calculating the statistic. As for each value of the one-dimensional projection accumulated data, the value of 8 data is “20”, and the other values are “0”. In this case, the average value Vave is “3.2” and the standard deviation Vsig is about “7.4”. Therefore, the threshold Vth is calculated using Equation 1 as shown below.

[0089] Vth = Vave + a XVsig (Formula 1)

= 3. 2 + 3. 0 X 7.4 = 25.4

Here, the value of “3” in 3 σ used in the field of quality control is used as the value of the threshold determination constant a.

Referring to FIG. 7 again, in step S770, processing unit 550 determines the position of panel edge 211 using threshold value Vth. Specifically, processing unit 550 refers to threshold value 535 as position determination unit 559 to derive data 536 representing the position of the edge. For example, to calculate the statistics, from the upper limit value Xe (= 920) on the panel edge 211 side of the glue, in the direction of the panel edge 211 (that is, in the positive direction of the X axis), the threshold Vth (in FIG. 4 above) In the example, specify the coordinates that exceed 25.4) first. In this embodiment, as shown in FIG. 4B, the X coordinate value exceeding the threshold Vth (25.4) is “940”. This value consequently matches the X coordinate value Xs (211) of panel edge 211.

In step S760, in the present embodiment, a force using (Expression 1) may be used as an expression for calculating threshold value Vth. For example, as described below, the edge position can be determined with higher accuracy by changing the expression for calculating the threshold Vth according to the value of the standard deviation Vsig, that is, according to the degree of noise.

[0092] As a first case, when noise is hardly included in the image (when the relationship of "Vsig≤l. 0" is established), the equation (2) may be used.

[0093] Vth = Vave + a (Formula 2)

Where a = 9.0

Here, “9.0” is used as the value of the threshold determination constant a, which is larger than “6” in 6 σ used in the field of quality control. A value larger than this value may be used.

[0094] In the second case, if there is some noise in the image (for example, “1.0 <Vsig ≤ 5

(0)), equation (3) may be used.

[0095] Vth = Vave + a XVsig- · · (Formula 3)

Where a = 6.0

Here, “6” in 6 σ used in the field of quality control is used as the value for threshold determination constant a. [0096] As the third case, when there is a lot of noise (for example, when the relationship of "5.0 and Vsig" is established), equation (4) may be used.

[0097] Vth = Vave + a X Vsig-(Equation 4)

Where a = 3.0

By setting the formulas and constants in this way, when there is almost no noise (corresponding to the first case), it is possible to avoid that one local noise is erroneously detected as an edge position. it can. If the noise is large (corresponding to the third case), the difference between the edge strength of panel edge 211 and the edge strength of strong V-Zoise is reduced by reducing the constant a for determining the threshold Vth. In any case, erroneous detection of the position of the panel edge 211 can be avoided.

Here, another technique for determining the panel edge of the glass substrate 800 will be described with reference to FIGS. FIG. 8 is a diagram showing the appearance of the glass substrate 800. The glass substrate 800 includes two nonels 810 and 820.

A wiring pattern region 815 is formed around the panel 810. Between the panel 810 and the wiring node << turn area 815, there is a non-nore edge 811, 812, 813, 814 force ^. Further, the outside of the wiring pattern region 815 is a region where a panel is not formed on the glass substrate 800. For Nonel 820, areas similar to those described above for panel 810 are formed.

[0100] A region 806 is a target for explaining the technique. As is apparent from FIG. 8, the region 806 includes a part of the panel 810, a part of the wiring pattern region 815, and a part of the glass substrate 800.

FIG. 9 is a diagram showing an image 900 acquired when the glass substrate 800 is photographed with a camera. The imaging area 850 for the glass substrate 800 shown in FIG. 8 corresponds to the area 950 in the image 900. The image 900 includes images 910 and 920 of the non-nore 810, an image 911 of the non-no-re edge 811, and an image 916 of the wiring pattern edge that is a boundary between the wiring pattern region 815 and the glass substrate 800. An image 906 occupying a part of the image 900 is an image of an area 806 occupying a part of the glass substrate 800.

[0102] Next, a description will be given of the case where the arithmetic processing is executed in the accumulation direction shown in FIG. To do. FIG. 10 is a diagram for explaining the image 906 shown in FIG. As shown in FIG. 10A, the image 906 includes an image of the panel, a panel edge 1020, a wiring pattern edge 1030, and an end portion 1010 of the image in the direction of the panel force glass substrate.

[0103] For example, when the technique disclosed in Japanese Patent Laid-Open No. 5-266194 is used, one-dimensional projection accumulation data is obtained by accumulating the pixel values of the original image along a plurality of directions. The peak value of the projection gradient data is obtained for each. Of the plurality of directions, the peak value in the largest direction is set as the edge position.

Specifically, in FIG. 10A, the edge position is clearly the direction in which the peak value of the projection gradient data in the accumulation direction 1040 is the largest. In that case, the one-dimensional projection accumulation data when the pixel value is projected in the accumulation direction 1040 is shown in FIG. 10 (B). Here, the luminance value on the vertical axis of the one-dimensional projection accumulation data shown in FIG. 10 (B) represents the average value of the luminance values. As for the one-dimensional projection accumulated data force shown in Fig. 10 (B), when the peak position of the gradient magnitude is obtained, the position of the wiring pattern edge 1030 is selected, and the position of the panel edge 1 020 is not selected! /, .

[0105] FIG. 11 is a diagram for explaining yet another technique. Japanese Patent Application Laid-Open No. 5-266194 discloses a technique other than the above technique. The technique is to obtain the 2D gradient distribution of the original image before obtaining the 1D projection accumulation data.

Here, FIG. 11A shows an image obtained by performing Sobel filter processing as a method for obtaining a two-dimensional gradient distribution on the image 906 corresponding to the region 806. In this case as well, the edge position is projected in the accumulation direction 1140 shown in FIG. 11 (A), as in the case where the method that does not obtain the two-dimensional gradient distribution described with reference to FIG. 10 is applied. It is clear that the peak value of the gradient data is in the largest direction.

FIG. 11B shows one-dimensional projection accumulation data when the two-dimensional gradient distribution shown in FIG. 11A is projected in the accumulation direction 1140. The luminance value on the vertical axis of the one-dimensional projection accumulation data shown in Fig. 11 (B) represents the average value of the luminance values. Even if the peak position of the gradient magnitude is obtained from the one-dimensional projection accumulated data shown in Fig. 11 (B), the position of the pattern edge 1130 is selected and the position of the panel edge 1120 is not selected! / ,.

As described above, according to the conventional technique, the panel which is the boundary between the panel and the wiring pattern region is used. Edge, for example, panel edge 1020 in Figure 10, panel edge in Figure 11 1

120 may not be determined with high accuracy.

[0109] According to the inspection system 10 according to the embodiment of the present invention described with reference to Figs. 1 to 7, the position of the edge is highly accurate based on the following technical features. It can also be determined in a short time.

[0110] First, as described in step S750, an area for calculating a statistic is set inside a panel which is a rectangular area, and a threshold is set using the statistic of a part of the area inside the panel.

Vth is determined. In this way, the periphery of the panel area (ie, the wiring pattern area

) Is not a target for calculating statistics, so the boundary between the inside of the panel and the outside of the panel, which is the wiring pattern area, is determined with high accuracy.

[0111] Further, as described in step S770, since the position closest to the area for calculating the statistic is determined as the edge position among the positions exceeding the threshold Vth, the wiring pattern and the inside of the panel are determined. The boundary with the region is determined with high accuracy.

[0112] Further, as described in step S710, the coordinates Xs (211) of the panel edge 211 in the image calculated from the design data are used to determine the target area. Thus, the region 206 including the panel edge 211 can be cut out (extracted) from the image 240 with an appropriate size without waste, and the time required to determine the edge position can be shortened.

[0113] Further, as described in step S710, the coordinates Xr in the image of the panel edge 211 are displayed.

(211) and the maximum error Xme (211) between the coordinates Xs (211) of the panel edge 211 in the image calculated from the design data are used. As described in step S750, the coordinate value Xs (21 1) force is also at least Xme (211) pixels away from the coordinate value, and the statistic is calculated as the limit of the area for calculating the above statistic. Region force for calculation The coordinates Xr (211) in the image of the panel edge 211 are removed. Thereby, the statistic of the noise component not including the panel edge 211 is calculated. As a result, the threshold value Vth can be determined appropriately, and the edge position can be determined with high accuracy.

[0114] As described in detail above, the edge position detection apparatus 100 according to the embodiment of the present invention is realized as a hardware configuration by combining circuit elements that execute each process. Can be configured. For example, a program that executes each process The program is also realized in a manner in which software and hardware cooperate by causing a CPU (Central Processing Unit) or other processor to execute the program.

[0115] Therefore, a computer system 1200 that implements the edge position detection apparatus 100 will be described with reference to FIG. FIG. 12 is a block diagram showing a hardware configuration of computer system 1200.

[0116] The computer system 1200 is defined in advance by the CPU 1210, the mouse 1220 and the keyboard 1230 that accept input of instructions by the user of the computer system 1200, and the data or program to be input as the main components of the hardware. RAM 1240 for storing data temporarily generated when processing is executed, hard disk 1250 capable of storing a large amount of data, compact disk-read only memory (CD-ROM) drive device 1260, Includes monitor 1280 and communication IF (Interface) 1290. Each component described above is connected by a data bus. The CD-ROM drive unit 1260 is loaded with CD-ROM1262 force S.

The processing in the computer system 1200 functioning as the edge position detection device 100 is realized by the hardware and software executed by the CPU 1210. Such software may be pre-stored in RAM 1240 or hard disk 1250, or may be stored in a CD-ROM 1262 or other recording medium and distributed as a product, CD-ROM drive 1260 or other reader May be read from the recording medium and stored in the hard disk 1250. The software is read from RAM 1240 or hard disk 1250 and executed by CPU 1210. The hardware itself of the computer system 1200 shown in FIG. 12 is general. Therefore, it can be said that the essential part of the present invention is software stored in the RAM 1240, the hard disk 1250, the CD-ROM 1262, and other recording media. Since the operation of each hardware of computer system 1200 is well known, detailed description will not be repeated.

Note that the scope to which the technical idea included in the present embodiment described in detail above is applied is not limited to the detection of the boundary (edge) as described above. For example, even when the position of the outer frame of the rectangular area in the image representing the rectangular area including the boundary is detected as the boundary, The same applies.

[0119] Further, in order to simplify the description of the present embodiment, the present embodiment has been described in the case where an image acquired by photographing a subject is rectangular. However, the present invention can be similarly applied to a case where the image is not a rectangle, for example, a polygon. For example, only one side constituting the polygon is set as a position detection target, the above-described processing is executed, and the processing is repeated for each side. By doing so, even in the case of a polygonal image having a shape other than a rectangle, the position of the boundary between the region having the shape and another region can be determined.

[0120] The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

Industrial applicability

The present invention is used for, for example, an image inspection apparatus, an image conversion apparatus, an image recognition apparatus, a pattern matching apparatus, a positioning apparatus using an image, an autonomous robot with an image recognition function, an industrial robot with an image recognition function, and the like. Is done.

Claims

The scope of the claims

[1] Storage means for storing original image data representing an original image acquired by photographing a subject

(530), wherein the original image data is represented according to a two-dimensional coordinate axis, and when the original image has a plurality of partial images, each of the portions is based on the original image data. First generating means (555) for generating emphasized image data representing an image in which an image boundary is emphasized;

The luminance values of the partial areas corresponding to the partial images after the boundary is emphasized are integrated in the direction of the boundary, and an average value is calculated, thereby obtaining a one-dimensional one of the two-dimensional coordinate axes. Second generation means (556) for generating a plurality of one-dimensional data represented according to the coordinate axes of

First determining means (557) for determining a range of data for determining the position of the boundary based on the design data of the subject;

A calculation means (558) for calculating a threshold value for a luminance value by calculating a statistic using the plurality of one-dimensional data included in the data range;

Based on the plurality of one-dimensional data included in the data range, the coordinate values on the one-dimensional coordinate axis of the one-dimensional data corresponding to the luminance value exceeding the calculated threshold value are A boundary position determining device, comprising: a second determining means (559) for determining the boundary position.

[2] The range according to claim 1, wherein the first determination means determines the range of the data based on a range determined by the original image data and a range specified by the design data. Descriptive boundary location device.

[3] The first determining means is:

Based on the design data, one-dimensional data of the boundary is calculated as position data for calculation,

Based on the original image data, the one-dimensional data of the boundary is calculated as actual position data,

3. The boundary position determining apparatus according to claim 2, wherein a range of the data is determined based on a difference between the calculated position data and the actual position data. [4] The subject includes a first part to be inspected and a second part not to be inspected.

The original image includes a first image corresponding to the first part and a second image corresponding to the second part,

The first generation unit according to claim 1, wherein the first generation means generates data representing an image in which a boundary between the first image and the second image is enhanced as the enhanced image data. Boundary positioning device.

[5] The subject is a glass substrate,

The first part is a panel region processed into the glass substrate;

5. The range according to claim 4, wherein the first generation means generates data representing an image in which a portion where an image corresponding to the panel area and an image corresponding to an area other than the panel area are in contact with each other is emphasized. The boundary position determining device described in 1.

[6] The range according to claim 1, wherein the calculation means calculates an average value and a standard deviation for the plurality of one-dimensional data, and calculates the threshold based on the average value and the standard deviation. Descriptive boundary location device.

[7] The specifying means includes:

A plurality of the one-dimensional data corresponding to the luminance values exceeding the threshold are specified, and for each of the specified one-dimensional data, a difference between the upper limit value of the data range and the one-dimensional data is calculated. And

2. The boundary position determining apparatus according to claim 1, wherein the one-dimensional data in which each calculated difference is minimum is determined as the one-dimensional data corresponding to a luminance value exceeding the threshold value.

[8] The original image includes a rectangular region,

The boundary is formed by an outline of the rectangular region;

2. The boundary position determining device according to claim 1, wherein the first generation means generates data representing an image in which the boundary formed by the contour is emphasized as the emphasized image data.

[9] The second generation means may correspond to each of the rectangular areas after the boundary is emphasized. The luminance values of the pixels are integrated in one direction in the rectangular area to calculate an average value, thereby generating the plurality of one-dimensional data.

9. The request range according to claim 8, wherein the first determination means determines the range of the data so that the range of the data is included in a range defined by the one-dimensional data for the rectangular region. Boundary positioning device.

[10] The statistic includes an average value and a standard deviation,

2. The range according to claim 1, wherein the calculation means calculates the threshold value using each formula defined in advance according to each value of a plurality of standard deviations, and each formula varies depending on each standard deviation value. The boundary position determining device described in 1.

[11] A method in which a computer determines a position of a boundary included in an image, wherein the converter includes a storage device that stores data, and a processing device that executes a predetermined process using the data. The method comprises:

The processing device comprises a step of reading original image data representing an original image acquired by photographing a subject from the storage device, the original image data being represented according to a two-dimensional coordinate axis;

When the original image has a plurality of partial images, the processing device generates enhanced image data representing an image in which the boundary of each partial image is emphasized based on the original image data; ,

The processing device integrates the luminance values of the partial areas corresponding to the partial images after the boundary is emphasized in the direction of the boundary, and calculates an average value, thereby calculating the two-dimensional coordinate axis. Generating a plurality of one-dimensional data represented according to a one-dimensional coordinate axis of

The processor determines a range of data to be determined for determining the position of the boundary based on the design data of the subject; and

The processing device calculates a statistic using the plurality of one-dimensional data included in the data range, thereby calculating a threshold value based on a luminance value; and the processing device includes the data Identifying the one-dimensional data corresponding to the luminance value exceeding the threshold based on the plurality of one-dimensional data included in the range of: A method for determining a boundary position, comprising: determining, as the boundary position, a coordinate value on the one-dimensional coordinate axis of the identified one-dimensional data.

[12] A program for causing a computer to function as a device for determining a position of a boundary included in an image, wherein the computer executes a storage device that stores data and a predetermined process using the data A processing device, and the program is stored in the processing device.

A step of reading original image data representing an original image acquired by photographing a subject from the storage device is executed, and the original image data is represented according to a two-dimensional coordinate axis;

When the original image has a plurality of partial images, a step of generating enhanced image data representing an image in which boundaries of the partial images are enhanced based on the original image data; and

The luminance values of the partial areas corresponding to the partial images after the boundary is emphasized are integrated in the direction of the boundary, and an average value is calculated, thereby obtaining a one-dimensional one of the two-dimensional coordinate axes. Generating a plurality of one-dimensional data represented in accordance with the coordinate axes of: determining a range of data to be determined for determining the position of the boundary based on the design data of the subject !,

Calculating a threshold value for a luminance value by calculating a statistic using the plurality of one-dimensional data included in the data range; and

Identifying the one-dimensional data corresponding to a luminance value exceeding the threshold based on the plurality of one-dimensional data included in the data range; and

And determining a coordinate value on the one-dimensional coordinate axis of the identified one-dimensional data as the position of the boundary.

[13] A computer-readable recording medium storing the program according to claim 12.

[14] a storage unit (530) for storing original image data representing an original image acquired by photographing a subject, wherein the original image data is represented according to a two-dimensional coordinate axis; When the original image has a plurality of partial images, a first generation unit (555 that generates enhanced image data representing an image in which the boundary of each partial image is enhanced based on the original image data. )When,

The luminance values of the partial areas corresponding to the partial images after the boundary is emphasized are integrated in the direction of the boundary, and an average value is calculated, thereby obtaining a one-dimensional one of the two-dimensional coordinate axes. A second generation unit (556) for generating a plurality of one-dimensional data represented according to the coordinate axes of

A first determination unit (557) for determining a range of data to be determined for determining the position of the boundary based on the design data of the subject;

A calculation unit (558) for calculating a threshold value for a luminance value by calculating a statistic using the plurality of one-dimensional data included in the data range;

Based on the plurality of one-dimensional data included in the data range, the coordinate values on the one-dimensional coordinate axis of the one-dimensional data corresponding to the luminance value exceeding the calculated threshold value are A boundary position determination device comprising: a second determination unit (559) that determines the boundary position.

[15] The first determination unit determines the range of the data based on a range determined by the original image data and a range specified by the design data. The boundary position determining device according to item.

[16] The first determination unit includes:

16. The boundary position determining apparatus according to claim 15, wherein a range of the data is determined based on a difference between the calculated position data and the actual position data.

[17] The subject includes a first part to be inspected and a second part not to be inspected,

The original image corresponds to the first image corresponding to the first part and the second part. And a second image to

15. The method according to claim 14, wherein the first generation unit generates data representing an image in which a boundary between the first image and the second image is emphasized as the emphasized image data. Boundary positioning device.

[18] The subject is a glass substrate,

The first part is a panel region processed into the glass substrate;

The range according to claim 17, wherein the first generation unit generates data representing an image in which a portion where an image corresponding to the panel area and an image corresponding to an area other than the panel area are in contact with each other is emphasized. Descriptive boundary location device.

[19] The range according to claim 14, wherein the calculation unit calculates an average value and a standard deviation for the plurality of one-dimensional data, and calculates the threshold based on the average value and the standard deviation. Descriptive boundary location device.

[20] A method of determining a position of a boundary included in an image,

A step of reading original image data representing an original image acquired by photographing a subject, wherein the original image data is represented according to a two-dimensional coordinate axis;

The coordinate value on the one-dimensional coordinate axis of the identified one-dimensional data is expressed as the position of the boundary. Determining the position of the boundary.