KR102003781B1 - Apparatus for detecting defects on the glass substrate using hyper-spectral imaging - Google Patents
Apparatus for detecting defects on the glass substrate using hyper-spectral imaging Download PDFInfo
- Publication number
- KR102003781B1 KR102003781B1 KR1020140122929A KR20140122929A KR102003781B1 KR 102003781 B1 KR102003781 B1 KR 102003781B1 KR 1020140122929 A KR1020140122929 A KR 1020140122929A KR 20140122929 A KR20140122929 A KR 20140122929A KR 102003781 B1 KR102003781 B1 KR 102003781B1
- Authority
- KR
- South Korea
- Prior art keywords
- image
- data
- defect
- defects
- glass
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
Abstract
The present invention discloses a glass defect detection apparatus using an ultra-spectral imaging technique. The glass defect detecting apparatus includes an ultrasound image generating unit for generating an ultrasound image of a glass to be inspected using an image photographing apparatus and a spectroscope; An ultrasound image analyzing unit for displaying each of the defects corresponding to the predetermined inspection item using the ultrasound image as image data, spectroscopic data, and spatial data values, and an ultrasound image analyzing unit for using both the displayed image data, And a defect detector for detecting defects among the defects.
Description
The present invention relates to a glass defect detection method, and more particularly, to a glass defect detection method using an ultra-spectroscopic image.
Conventionally, images are acquired by irradiating a plurality of lights at various angles in order to acquire multiple images from a single camera. In this situation, four or more images obtained from a single camera are combined, or two or more cameras disposed on the upper and lower sides are combined with 8 to 12 images to detect defective and good products. Even if there are multiple images due to a plurality of lighting conditions, it has been limited to express defective and good products with a gray value, and there have been limitations in detecting defects by type in glass and film inspection. In particular, there has been a problem in that it is impossible to classify attribute information such as printing or discoloration to maximize inspection yield.
In the present invention, it is desired to improve the accuracy of detecting various defects in the visual inspection of glass and film, and to provide classification according to types of defects.
As a preferred embodiment of the present invention, a glass defect detection method using an ultra-spectral imaging technique generates an ultrasound image for a glass, and the ultrasound image is composed of spectral images of different bands Selecting at least one spectral image in a band including a defect corresponding to a predetermined inspection item in the generated ultrasound image; Measuring a gray value for each defect in the spectroscopic image; Processing defect detection data for each defect in the spectroscopic image; And detecting defects by using the spectroscopic image, the measured shade value, and the processed defect detection data selected for each band for each defect corresponding to the inspection item.
Preferably, the defect detection data for the defect includes at least one of coordinates, center-of-gravity coordinates, area, circumference, and diagonal length of each of the defects.
Preferably, the defects are classified by type using band information of a spectroscopic image in which defects are detected.
According to another preferred embodiment of the present invention, there is provided a method of detecting a glass defect using an ultra-spectral imaging technique, comprising the steps of: generating an ultrasound image of a glass using an image photographing apparatus and a spectroscope; Acquiring image data, spectroscopic data, and spatial data measurement values for a defect corresponding to each of the predetermined inspection items using the generated ultrasonic image; Analyzing the image data, the spectral data and the spatial data reference value and the image data, the spectral data, and the spatial data measured values for the defect corresponding to each of the inspection items; And classifying defects corresponding to the inspection item as defective when the image data, the spectral data, and the spatial data measurement value exceed the preset image data, the spectral data, and the spatial data reference value as a result of the comparison .
According to another preferred embodiment of the present invention, a method of detecting a glass defect using an ultra-spectral imaging technique includes the steps of generating an ultra-spectroscopic image of an inspection object glass using an imaging device and a spectroscope; An ultrasound image analysis step of displaying each of the defects corresponding to the predetermined inspection item in the ultrasound image as image data, spectroscopic data, and spatial data values, and analyzing the ultrasound image data using spectroscopic data and spatial data values, And detecting whether each of the defects is defective.
In a preferred embodiment of the present invention, various defects can be accurately detected by visual inspection of glass and film. In particular, it has the effect of accurately detecting defects such as printing or discoloration, and accurately classifying floating foreign matter such as dust and dirt, thereby maximizing inspection yield.
FIG. 1 shows a glass defect inspection apparatus for generating an ultra-spectroscopic image according to a preferred embodiment of the present invention.
FIG. 2 illustrates an example of detecting a defect according to an inspection item of the glass to be inspected 140 and displaying spectroscopic data for each defect, according to a preferred embodiment of the present invention.
FIG. 3 shows an embodiment in which a spectroscopic image of a band in which a defect is detected in an ultra-spectroscopic image of a glass to be inspected 140 is detected according to an embodiment of the present invention.
FIG. 4 shows a preferred embodiment of the present invention in which a defect is detected in accordance with an inspection item of a glass to be inspected 140, and a wavelength value and a preset reference value measured for each detected defect are started.
FIG. 5 is a preferred embodiment of the present invention, in which the measured value of the defect density and the defect detection (Blob) data of the defect detected according to the inspection item of the
FIG. 6 shows an example of defect defect detection (Blob) data as a preferred embodiment of the present invention.
FIG. 7 illustrates an example of detecting glass defects using both image data, spectroscopic data, and spatial data as one preferred embodiment of the present invention.
FIG. 8 shows a glass defect detection flowchart using an ultra-spectral imaging technique as a preferred embodiment of the present invention.
BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention and methods of achieving them will be apparent with reference to the embodiments described in detail below with reference to the drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.
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 corresponding components throughout the drawings, and a duplicate description thereof will be omitted .
In the following embodiments, the terms first, second, and the like are used for the purpose of distinguishing one element from another element, not the limitative meaning.
In the following examples, the singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise.
In the following embodiments, terms such as inclusive or possessive are intended to mean that a feature, or element, described in the specification is present, and does not preclude the possibility that one or more other features or elements may be added.
In the drawings, components may be exaggerated or reduced in size for convenience of explanation. For example, the size and thickness of each component shown in the drawings are arbitrarily shown for convenience of explanation, and thus the present invention is not necessarily limited to those shown in the drawings.
FIG. 1 shows a glass defect inspection apparatus for generating an ultra-spectroscopic image according to a preferred embodiment of the present invention.
The glass
The glass
The spectroscope 130 disperses the light incident from the optical lens of the
Examples of the spectrometer 130 include a Fabry-Perrot Filter spectrometer including a Reflect Grating circuit, an AOBG (Acoustic Optical Bragg Grating) circuit, and a Volume Phase Holographic Grating And does not exclude additional spectroscopic components. Examples of the glass to be inspected 140 include Bare Glass, Print Glass, Touch Screen Pattern, smartphone cover glass, and film.
The ultrasound image combines the
The glass
In the ultrasound spectral
As an example of the image data, a gray scale value can be used. One or more spectral band images may be selected from the image data of the hyperspectral image generated by the glass
The spectral data uses the wavelength value of the hyperspectral image. In a preferred embodiment of the present invention, the glass
The spatial data can use the (x, y) position or the coordinate value of each pixel of the hyperspectral image. For example, coordinate values of 100 pixels, 100 pixels, or 10 mm, 10 mm, or the like can be used.
FIG. 2 illustrates an example of detecting a defect according to an inspection item of the glass to be inspected 140 and displaying spectroscopic data for each defect, according to a preferred embodiment of the present invention.
The spectral data includes the wavelength information of the image of each wavelength band continuously acquired in spectral resolution units in the spectral region. For example, when the spectral range is 400 nm to 1,000 nm and the spectral resolution is 2 nm, the spectral data can be obtained from the images acquired in the order of 400 nm, 402 nm, 404 nm, ..., 1000 nm.
When inspecting the defects of the glass sample, the inspection items include the print color 210, the print discoloration 212, the scratches 214 and 234, the foreign materials 216, 218, 220 and 222, the stamp 224, the chipping 226, , Speckle 228, Mura 230, dent 232, IR, or camera hole defects 236. As shown in FIG.
Referring to FIG. 2, the print color 210 is
The spectral data values of the foreign matter 216 were measured as λ4, 218 as λ5, salinity as (220) λ6, and conveyor belt as (222) λ7 depending on the type of foreign matter.
In addition, the striking 224 is λ8, the chipping 226 is λ9, the stain 228 is λ10, the Mura 230 is λ13, the dent 232 is λ12, and IR or camera hole defects (236), the spectral data value was measured at? 14.
FIG. 3 shows an embodiment for classifying the defects detected by the glass defect inspection apparatus (FIGS. 1 and 100) according to the type, according to a preferred embodiment of the present invention.
The glass defect inspection apparatus (FIGS. 1 and 100) can recategorize the ultrasound image generated for the inspection target glass 310 according to the types of defects detected. The glass defect inspection apparatuses (FIGS. 1 and 100) can classify images by material in an ultra-spectroscopic image composed of images taken by more than one hundred consecutive bands or channels (310, 312, 314, 316 , 318, 320, 330, and 340).
For example, in the case of having a wavelength of? 1 310, a defect of bare glass, a case of having a wavelength of? 2 312 and a case of having a wavelength of? 3 to? 4 (314 and 316) When the
FIG. 4 illustrates an embodiment of measuring spectroscopic data of defects detected in an ultra-spectroscopic image of a glass to be inspected according to an embodiment of the present invention.
The
As a result of measuring the ultrasound
In one preferred embodiment of the present invention, it is confirmed whether the
For example, referring to FIG. 4, in the case of the
5 is a preferred embodiment of the present invention. As one preferred embodiment of the present invention, the measurement of the inspection target glass (510, 512, 514, 516, 518, 520, 522, 524, 526) Measurement values 530 and 550 of image data and spatial data, and predetermined spatial
FIG. 6 shows defect detection (Blob) data of the
In a preferred embodiment of the present invention, the ultraspectral image is subjected to image processing, and defect detection (blob) data for defects in the image-processed ultrasound image can be extracted and used. In this case, image processing for detecting defects is performed. Among them, a smoothing filter (averaging, Gaussian, etc.) for removing noise is typically used, an edge filter (Sobel filter, Canny filter) for detecting contour, a morphological morphology processing technique (Number of defects, location, center, area, contour information), image binarization (single binarization technique, dynamic binarization technique) But not limited to, techniques for recognizing defects of an object in an image.
In one preferred embodiment of the present invention, after acquiring the ultrasound
Next, the gray value of the detected defect is measured (530) as in the embodiment shown in FIG. In this process, noise cancellation is performed using a smoothing filter of an image, an outline of a test object is detected using an outline detection filter, a morphological surface of the image is expressed by a morphological morphology processing technique, and various mathematical operations are performed It is also said. In addition, the GV binary value 540 can be obtained through the binarization filter according to the purpose before or after performing the various image processing. Thereafter, the above-mentioned image processing method may be variously modified according to the purpose of detecting defects, but not limited thereto, and may include all techniques for recognizing defects of an object in an image.
In a preferred embodiment of the present invention, the
FIG. 7 shows an embodiment for detecting defects using both spectral data, image data, and spatial data, according to a preferred embodiment of the present invention.
In a preferred embodiment of the present invention, a spectroscopic image including a defect to be detected is selected from an ultrasound image to be inspected using spectral data (see FIG. 3). Thereafter, the gray value of the defect is measured using the image data of the defect in the selected spectroscopic image (see FIG. 5). Thereafter, the defect detection data is extracted using a defect blob function of the defect in the binary image obtained by binarizing the measured gray value (see FIG. 5).
(FIG. 5, 550) of defects provided by the defect detection data (FIG. 5, 552), and finally determines whether or not each defect is defective.
Referring to FIG. 7, the following description will be given.
A spectroscopic image including a defect corresponding to the inspection item is selected from the ultraspectral image of the glass to be inspected. A defect corresponding to a predetermined inspection item is detected in each of the
Examples of the preset inspection items include an IR (710), a color (712), a color change (714), a scratch (716), a
The band 730 in which the
The areas where the
The spectral data and the image data acquired by the above method are then subjected to image processing (742, 744, and 746). Examples of the image processing include at least one of image processing using a filter, mathematical operation, logical operation processing, and binarization processing.
Thereafter, the defect detection data of the defect is calculated using the value of the
Through the above process, the difference from the predetermined standard is compared or calculated and classified into good, bad, and rework (S780).
FIG. 8 shows a glass defect detection flowchart using an ultra-spectral imaging technique as a preferred embodiment of the present invention.
The glass defect inspection apparatus (FIGS. 1 and 100) of the present invention generates an ultrasound image of a glass to be inspected using an ultrasound image camera (FIGS. 1 and 102) (S800).
Thereafter, a spectral image (see FIG. 3) in a band including a defect corresponding to a predetermined inspection item in the generated ultrasound image is selected (S810). In this case, one or more spectroscopic images can be selected.
The gray value of the defect is measured in the selected spectral image (S820). Thereafter, the selected spectroscopic image is binarized by performing a mathematical, logical operation, or an image prescription method, and defect detection data for a defect in the binarized ultrasound image is calculated (S830).
After judging whether or not a predetermined standard is satisfied by using all of the wavelength data (spectral band), gray value data and defect detection data of the defect in the selected spectroscopic image, it is judged that the good, rework, defect Is classified as defective (S840).
The method of the present invention can also be embodied as computer readable code on a computer readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored.
Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like. The computer-readable recording medium may also be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner.
The present invention has been described above with reference to preferred embodiments thereof. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the foregoing description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.
Claims (15)
An ultrasound image generating unit for generating an ultrasound image of a glass to be inspected using a radiographing apparatus and a spectroscope;
An ultrasound image analyzing unit for displaying each of defects corresponding to a predetermined inspection item using the ultrasound image as image data, spectroscopic data and spatial data values;
And a defect detector for detecting defects among the defects using both the displayed image data, the spectral data, and the spatial data values,
Wherein the spectroscopic data is used to recategorize defects detected in the generated hyperspectral image by type, and in this case, the spectroscopic data includes a wavelength.
The total number of defects, the coordinates of each defect, the coordinates of the center of gravity, the area, the circumference, and the diagonal length.
At least one of a coordinate, a gravity center coordinate, an area, a circumference, and a diagonal length of each of the defects is used as the spatial data by using the wavelength value of each of the defects as the spectroscopic data, Or more.
Wherein the image includes at least one of print color, print discoloration, scratch, foreign body, impression, chipping, stain, dent, Mura, IR or camera hole defect.
And determining that the defect is a defect if at least one of the displayed image data, the spectral data, and the spatial data value is out of a predetermined value.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020140122929A KR102003781B1 (en) | 2014-09-16 | 2014-09-16 | Apparatus for detecting defects on the glass substrate using hyper-spectral imaging |
PCT/KR2015/003634 WO2016043397A1 (en) | 2014-09-16 | 2015-04-10 | Glass defect detection method and apparatus using hyperspectral imaging technique |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020140122929A KR102003781B1 (en) | 2014-09-16 | 2014-09-16 | Apparatus for detecting defects on the glass substrate using hyper-spectral imaging |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20160032593A KR20160032593A (en) | 2016-03-24 |
KR102003781B1 true KR102003781B1 (en) | 2019-07-25 |
Family
ID=55533418
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020140122929A KR102003781B1 (en) | 2014-09-16 | 2014-09-16 | Apparatus for detecting defects on the glass substrate using hyper-spectral imaging |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR102003781B1 (en) |
WO (1) | WO2016043397A1 (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR3053126B1 (en) * | 2016-06-27 | 2019-07-26 | Saint-Gobain Glass France | METHOD AND DEVICE FOR LOCATING THE ORIGIN OF A DEFECT AFFECTING A STACK OF THIN LAYERS DEPOSITED ON A SUBSTRATE |
KR101958539B1 (en) * | 2017-01-17 | 2019-03-14 | 서울시립대학교 산학협력단 | Apparatus and method for discriminating a concrete status using a hyperspectral image |
JP7208233B2 (en) | 2017-11-15 | 2023-01-18 | コーニング インコーポレイテッド | Method and apparatus for detecting surface defects in glass sheets |
JP2019152518A (en) | 2018-03-02 | 2019-09-12 | セイコーエプソン株式会社 | Inspection device, inspection system, and method for inspection |
CN109001213B (en) * | 2018-07-19 | 2021-08-10 | 华南理工大学 | Reel-to-reel ultrathin flexible IC substrate appearance detection method |
CN111445452B (en) * | 2020-03-23 | 2022-03-01 | Oppo(重庆)智能科技有限公司 | Defect detection method and device of electronic product and computer readable storage medium |
CN111693546A (en) * | 2020-06-16 | 2020-09-22 | 湖南大学 | Defect detection system, method and image acquisition system |
CN112465741B (en) * | 2020-10-10 | 2024-03-26 | 湖南大捷智能装备有限公司 | Defect detection method and device for suspension spring and valve spring and storage medium |
WO2022085822A1 (en) * | 2020-10-22 | 2022-04-28 | (주)레이텍 | Hyperspectral inspection device capable of detecting soft foreign substance |
CN114466183A (en) * | 2022-02-21 | 2022-05-10 | 江东电子材料有限公司 | Copper foil flaw detection method and device based on characteristic spectrum and electronic equipment |
CN115880301B (en) * | 2023-03-06 | 2023-06-06 | 长沙韶光芯材科技有限公司 | Recognition system for bubble defects of glass substrate |
CN116297497B (en) * | 2023-05-23 | 2023-08-15 | 武汉大学 | Mobile phone panel quality detection method based on hyperspectral remote sensing |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030218743A1 (en) | 2002-05-13 | 2003-11-27 | Klaus Gerstner | Method and apparatus for detecting defects in a continuously moving strip of transparent material |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101367078B1 (en) * | 2006-12-26 | 2014-02-25 | 엘지디스플레이 주식회사 | Mura test method for liquid crystal display |
US9128036B2 (en) * | 2011-03-21 | 2015-09-08 | Federal-Mogul Corporation | Multi-spectral imaging system and method of surface inspection therewith |
KR101278249B1 (en) * | 2011-06-01 | 2013-06-24 | 주식회사 나노텍 | Apparatus for Detecting a Defect in Edge of Glass Plate and the Method Thereof |
JP2013061185A (en) | 2011-09-12 | 2013-04-04 | Toshiba Corp | Pattern inspection device and pattern inspection method |
KR101400757B1 (en) * | 2012-07-19 | 2014-05-27 | (주) 인텍플러스 | Display panel inspection apparatus |
-
2014
- 2014-09-16 KR KR1020140122929A patent/KR102003781B1/en active IP Right Grant
-
2015
- 2015-04-10 WO PCT/KR2015/003634 patent/WO2016043397A1/en active Application Filing
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030218743A1 (en) | 2002-05-13 | 2003-11-27 | Klaus Gerstner | Method and apparatus for detecting defects in a continuously moving strip of transparent material |
Also Published As
Publication number | Publication date |
---|---|
WO2016043397A1 (en) | 2016-03-24 |
KR20160032593A (en) | 2016-03-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102003781B1 (en) | Apparatus for detecting defects on the glass substrate using hyper-spectral imaging | |
JP6945245B2 (en) | Visual inspection equipment | |
JP7391173B2 (en) | Food inspection aid system, food inspection aid device, and computer program | |
US9927369B2 (en) | Automated defect detection and mapping for optical filters | |
JP6052590B2 (en) | Surface inspection apparatus and surface inspection method for automobile body | |
CN108090890B (en) | Inspection device and inspection method | |
Boukouvalas et al. | ASSIST: automatic system for surface inspection and sorting of tiles | |
JP7139243B2 (en) | Image analysis system and method | |
WO2015136620A1 (en) | Tablet inspection device, tablet inspection method, and tablet inspection program | |
JP6295798B2 (en) | Inspection method | |
JP2021128097A (en) | Defect detector, defect detection method, and defect correction device | |
CN111879789A (en) | Metal surface defect detection method and system | |
JPH0534281A (en) | Evaluating apparatus for appearance of melon | |
JP2016090476A (en) | Foreign matter detection method | |
JP7039700B2 (en) | Inspection device with light watermark | |
JP2007271507A (en) | Defect detecting method, defect detector and defect detecting program | |
WO2023098187A1 (en) | Processing method, processing apparatus, and processing system | |
JP4820971B2 (en) | Surface inspection method | |
JP2020529618A5 (en) | ||
JP2009222683A (en) | Method and apparatus for surface inspection | |
JP2002243647A (en) | Method of detecting and analyzing surface facture of sample | |
CN109087290B (en) | Optical element surface defect detection method based on spectral estimation and electronic beam splitting technology | |
JP2010038723A (en) | Flaw inspecting method | |
JP5787668B2 (en) | Defect detection device | |
Carstensen et al. | Creating surface chemistry maps using multispectral vision technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
N231 | Notification of change of applicant | ||
E701 | Decision to grant or registration of patent right |