KR101716111B1 - System and method for detecting foreign substance - Google Patents

System and method for detecting foreign substance Download PDF

Info

Publication number
KR101716111B1
KR101716111B1 KR1020150172637A KR20150172637A KR101716111B1 KR 101716111 B1 KR101716111 B1 KR 101716111B1 KR 1020150172637 A KR1020150172637 A KR 1020150172637A KR 20150172637 A KR20150172637 A KR 20150172637A KR 101716111 B1 KR101716111 B1 KR 101716111B1
Authority
KR
South Korea
Prior art keywords
image
resolution
foreign
pixel
foreign material
Prior art date
Application number
KR1020150172637A
Other languages
Korean (ko)
Inventor
최경주
전준기
전민성
송민수
Original Assignee
충북대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 충북대학교 산학협력단 filed Critical 충북대학교 산학협력단
Priority to KR1020150172637A priority Critical patent/KR101716111B1/en
Application granted granted Critical
Publication of KR101716111B1 publication Critical patent/KR101716111B1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
    • G01M11/02—Testing optical properties
    • G01M11/0242—Testing optical properties by measuring geometrical properties or aberrations
    • G01M11/0278—Detecting defects of the object to be tested, e.g. scratches or dust
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • G—PHYSICS
    • 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
    • G01N2021/9583—Lenses

Abstract

The present invention relates to a system and a method to detect foreign materials, comprising: a background removal unit to remove interference to an external background from a difference image between a reference image and an image to be detected; an ultrahigh resolution recovery unit repeating a process to recover the image from which the background is removed from a high resolution image to restore the recovered image into an ultrahigh resolution image; a foreign material objectification unit detecting an outline from the ultrahigh resolution image to objectify a focused foreign material; and a foreign material feature extraction unit to estimate characteristics of the foreign material including a size of the foreign material from a brightness value of each pixel through a correlation between the brightness and the area. According to the present invention, an image having an insufficient resolution and an ambiguous resolution to detect the foreign material through ultrahigh resolution image recovery is able to be converted into an image type easy to apply a foreign material detection algorithm; the size of the foreign material is able to precisely be measured through a correlation between the brightness and the area inside the pixel; and a type of dark spots, white spots, scratches, spots, etc., which are a defect factor of a lens, is able to also be correctly checked.

Description

TECHNICAL FIELD [0001] The present invention relates to a system and a method for detecting foreign matter,

The present invention relates to a foreign matter detection system and method, and more particularly, to a foreign matter detection system and method for measuring a foreign matter size below a resolution.

Today, the rapid development of the electronics industry and the information and telecommunications industry is leading to a rapid increase in the optical parts market. In order to minimize the errors of the products produced in the mass production system, the inspection of the foreign objects became an essential factor. Nevertheless, the defect inspection of the lens is mostly hand-tested by the skilled person. In addition, some of the used automatic lens inspection equipments are carried out only in a limited number of defective inspections, and the defective defects such as dirt are still being handled by skilled workers.

Korean Registered Patent No. 10-1469158 (Publication date Nov. 28, 2014)

SUMMARY OF THE INVENTION Accordingly, the present invention has been made keeping in mind the above problems occurring in the prior art, and it is an object of the present invention to provide a method and apparatus for measuring a size of a foreign substance less than a resolution through a correlation between super resolution image restoration, And a foreign matter detection system and method capable of inspecting a characteristic of a foreign matter.

According to another aspect of the present invention, there is provided a foreign matter detection system comprising: a background removal unit configured to remove an interference with an external background from a reference image as a reference and a difference image of an image to be detected; Resolution reconstruction unit for reconstructing a super-resolution image by repeating a process of reconstructing a high-resolution image with respect to an image from which the background is removed; A foreign object imitation unit for detecting a contour line from the super resolution image to objectize a foreign object to be imaged; And a foreign matter characteristic extracting unit for estimating a foreign matter characteristic including the size of the foreign object from a brightness value per pixel through a correlation between the intensity and the intensity.

According to another aspect of the present invention, there is provided a foreign matter detecting method comprising the steps of: (a) removing background interference from a reference image and a difference image of an image to be detected; (b) restoring the super-resolution reconstruction unit to a super-resolution image by repeating a process of restoring the super-resolution reconstructed image to a high-resolution image with respect to the image from which the background is removed; (c) detecting a contour line from the super-resolution image and objectizing the image-forming object in the foreign material objecting unit; And (d) the foreign matter characteristic extracting unit includes the size of the foreign object from the brightness value per pixel through the correlation between the lightness and the width.

The step (b) includes: (b-1) loading an image photographed differently in focus; (b-2) generating an output image by zero-order interpolation using a nearest neighbor pixel as an output pixel using nearest neighbor interpolation; (b-3) enlarging the output image and performing blur processing; (b-4) extracting an outline from the blurred image; (b-5) performing a sharpening process on the extracted outline; (b-6) synthesizing images photographed differently from each other in focus; (b-7) reconstructing a gamma value? as a constant and reconstructing a high-resolution image of only the outline Edge; And (b-8) returning the set number of times to the step (b-2) to generate a super resolution image.

In step (d), the brightness value of each pixel is corrected, and the correction may be calculated by the following equation.

Corrected average brightness value = (average brightness value + number of outermost pixels / number of total foreign substances * (maximum value of intensities in foreign matter - minimum value in foreign matter)) -

As described above, according to the foreign matter detection system and method of the present invention, images having ambiguous resolution for insufficient resolution or foreign matter detection through super resolution image restoration can be easily applied to algorithms for detecting foreign matter (high resolution: To capture foreign objects smaller than one pixel existing within one pixel).

In addition, according to the present invention, it is possible to precisely measure the size of the foreign object through the correlation between the foreign object objecting, the intensities of the pixels and the width, and to accurately identify the kinds of black points, white points, scratches, .

1 is a configuration diagram of a foreign matter detection system according to an embodiment of the present invention.
2 is a flowchart of a foreign matter detection method according to an embodiment of the present invention.
3 is a flowchart illustrating a super-resolution image restoration process according to an embodiment of the present invention.
4 is a view illustrating an example of a foreign matter detection method according to an embodiment of the present invention.
Figure 5 shows the hard-threshold (A) and soft-threshold (B) for each pixel.
6 is a graph showing the weights (brightness values) of the hard-threshold value A and the soft-threshold value B, respectively.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a foreign matter detection system and method according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a configuration diagram of a foreign matter detection system according to an embodiment of the present invention.

Referring to FIG. 1, the foreign object detection system of the present invention includes a background removal unit 1 for removing interference from an external background from a reference image to be a reference and an image to be detected, Resolution reconstructing unit 2 for reconstructing a super-resolution image by repeating a process of reconstructing a high-resolution image of a super-resolution image, a foreign object im- movering unit 3 for objectifying a foreign object formed by detecting a contour line from a super-resolution image, And a foreign matter characteristic extracting unit 4 for estimating a foreign matter characteristic including the size of the foreign object from the brightness value per pixel through the correlation between the intensity and the intensity.

Hereinafter, the foreign matter detection method of the present invention using the system constructed as described above will be described.

2 is a flowchart of a foreign matter detection method according to an embodiment of the present invention.

Referring to FIG. 2, when an image to be detected is input (S), a difference image between a reference image to be a reference and an image to be detected is obtained (S2), and interference from an external background is removed from the difference image (S3 ). The background removal method is a method of obtaining the image of the external factors by selecting a pixel value of a plurality of groups in which there is no foreign substance and selecting the most appearing pixel value in a pixel at a specific position in the image group, To eliminate interference with the external environment (conditions outside the test sample, such as foreign objects on the illumination or image acquisition camera lens).

Subsequently, a process of restoring a high-resolution image with respect to a background-removed image is repeated to restore a super-resolution image (S4). And reconstructs a low-resolution image into a super-resolution image with an edge component of the image. A process of restoring a super-resolution image will be described in detail with reference to FIG.

Subsequently, contours are detected from the super-resolution image (S5), and the foreign object to be formed is detected (S6). When a pixel having intensity of a foreign substance is found through a pixel unit approach to an image reconstructed with a super resolution, 8 neighboring points of the pixel are continuously detected in a cyclic manner. When eight neighboring points are found and all pixels including a specific foreign substance are found, the image including the pixel is copied and stored as one foreign object. 4 shows an example of a foreign matter detection method, wherein "C" indicates a pixel in which a foreign substance exists, and "X" indicates a pixel in which no foreign matter exists. As described above, the foreign pixels connected to each other are recognized as one foreign object, and the foreign object information is stored. In this manner, masses, i.e., objects (contaminants) having contours in the image can be detected through objectification of the foreign object. On the other hand, by inputting the size condition of the foreign substance, a small object can be detected. Basically, detection is performed with one pixel as a basic unit. Therefore, we can not find foreign objects smaller than pixels.

Accordingly, the foreign matter characteristic including the foreign matter size smaller than the pixel is estimated from the brightness value of each pixel through the correlation between the intensity and the width (S7). That is, by obtaining a high-resolution image through the resolution restoration of a super-resolution image, it is possible to detect a foreign substance smaller than one pixel existing in the pixel of the original image, and to display the characteristic of the foreign substance in units of resolution or less. For this purpose, the average brightness value of the foreign object is calculated by using the correlation between the intensity of intensity and the width of the foreign substance, and then the average brightness value is calculated as the outermost pixel (the probability that the foreign substance in the pixel is partially contained since it is the outermost pixel) To correct the average brightness value. Subsequently, the corrected value is estimated as the brightness of the foreign substance, and the soft-threshold is advanced based on the estimated value. 5 and 6 show the hard-threshold value A and the soft-threshold value B for each pixel, and FIG. 6 shows the hard-threshold value A and the soft- FIG.

Here, the correction from the hard-threshold value (A) to the soft-threshold value (B) is calculated by the following equation.

Corrected average brightness value = (average brightness value + number of outermost pixels / number of total foreign substances * (maximum value of intensities in foreign matter - minimum value in foreign matter))

On the other hand, the center of gravity can be calculated by weighting each pixel with a proportional weight of brightness, or the length of a foreign object can be calculated by measuring the longest distance between pixels expressed by one foreign substance.

3 is a flowchart illustrating a super-resolution image restoration process according to an embodiment of the present invention.

Referring to FIG. 3, a background-removed image is loaded into a processing program. At this time, when capturing an image to be detected, a plurality of images whose focal positions are slightly different are inserted into the program (S41).

An output image is generated by zero-order interpolation using the nearest neighbor interpolation as the output pixel (S42).

Rough images up to S42 are in a state of blockiness and no improvement in image quality. The image processed up to S42 is enlarged and blurred to smoothly generate the image (S43).

An outline is extracted from the coarse image up to S43 (S44).

Sharpening processing is performed on the extracted outline, and the detected outline is processed more clearly (S45).

The processed images are combined into one (S46). The edge component of the image can be obtained more precisely through the difference from the low-resolution image by combining the images with different focuses.

The gamma value gamma is calculated as a constant, and the image is restored to a high-resolution image having only the outline Edge (S47).

In order to obtain the same image as the original, the process of S41 to S47 is repeated several times to generate a super resolution image (S48).

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the invention.

1: Background removal
2:
3:
4: Foreign matter characteristic extracting unit

Claims (4)

delete (a) removing background interference from an external background from a reference image to be detected and an image to be detected in the background removal;
(b) restoring the super-resolution reconstruction unit to a super-resolution image by repeating a process of restoring the super-resolution reconstructed image to a high-resolution image with respect to the image from which the background is removed;
(c) detecting a contour line from the super-resolution image and objectizing the image-forming object in the foreign material objecting unit; And
(d) estimating a foreign matter characteristic including the size of the foreign object from a brightness value per pixel through a correlation between the intensity and the width in the foreign substance characteristic extraction unit,
The step (b)
(b-1) loading an image photographed differently in focus;
(b-2) generating an output image by zero-order interpolation using a nearest neighbor pixel as an output pixel using nearest neighbor interpolation;
(b-3) enlarging the output image and performing blur processing;
(b-4) extracting an outline from the blurred image;
(b-5) performing a sharpening process on the extracted outline;
(b-6) synthesizing images photographed differently from each other in focus;
(b-7) reconstructing a gamma value? as a constant and reconstructing a high-resolution image of only the outline Edge; And
(b-8) returning the set number of times to the step (b-2) to generate a super resolution image.
delete 3. The method of claim 2,
In the step (d)
The brightness value of each pixel is corrected,
Wherein the correction is calculated by the following equation.
Corrected average brightness value = (average brightness value + number of outermost pixels / number of total foreign substances * (maximum value of intensities in foreign matter - minimum value in foreign matter)) -
KR1020150172637A 2015-12-04 2015-12-04 System and method for detecting foreign substance KR101716111B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150172637A KR101716111B1 (en) 2015-12-04 2015-12-04 System and method for detecting foreign substance

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150172637A KR101716111B1 (en) 2015-12-04 2015-12-04 System and method for detecting foreign substance

Publications (1)

Publication Number Publication Date
KR101716111B1 true KR101716111B1 (en) 2017-03-15

Family

ID=58403171

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150172637A KR101716111B1 (en) 2015-12-04 2015-12-04 System and method for detecting foreign substance

Country Status (1)

Country Link
KR (1) KR101716111B1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102218734B1 (en) 2020-05-20 2021-02-24 켐아이넷(주) Artificial intelligence-based interpolation method of high-resolution data
US10939036B2 (en) 2017-05-23 2021-03-02 Samsung Display Co., Ltd. Spot detecting apparatus and method of detecting spot using the same
CN113390902A (en) * 2020-02-26 2021-09-14 丰田自动车株式会社 Method and apparatus for inspecting membrane electrode assembly
US11538149B2 (en) 2019-07-31 2022-12-27 Samsung Display Co., Ltd. Spot detection device, spot detection method, and display device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050004589A (en) * 2003-07-03 2005-01-12 주식회사 한택 Apparatus and method for inspecting display panel using pixel interpolation
JP2009162563A (en) * 2007-12-28 2009-07-23 Canon It Solutions Inc Device appearance inspection apparatus and method, program
JP2010085238A (en) * 2008-09-30 2010-04-15 Toppan Printing Co Ltd Method of identifying defect
KR20130075957A (en) * 2011-12-28 2013-07-08 한국기초과학지원연구원 Apparatus and method of reconstructing super-resoultion image
KR101469158B1 (en) 2013-07-29 2014-12-04 (주)에이피텍 Detecting device of camera lense module and detecting method thereof

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050004589A (en) * 2003-07-03 2005-01-12 주식회사 한택 Apparatus and method for inspecting display panel using pixel interpolation
JP2009162563A (en) * 2007-12-28 2009-07-23 Canon It Solutions Inc Device appearance inspection apparatus and method, program
JP2010085238A (en) * 2008-09-30 2010-04-15 Toppan Printing Co Ltd Method of identifying defect
KR20130075957A (en) * 2011-12-28 2013-07-08 한국기초과학지원연구원 Apparatus and method of reconstructing super-resoultion image
KR101469158B1 (en) 2013-07-29 2014-12-04 (주)에이피텍 Detecting device of camera lense module and detecting method thereof

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10939036B2 (en) 2017-05-23 2021-03-02 Samsung Display Co., Ltd. Spot detecting apparatus and method of detecting spot using the same
US11330169B2 (en) 2017-05-23 2022-05-10 Samsung Display Co., Ltd. Spot detecting apparatus and method of detecting spot using the same
US11538149B2 (en) 2019-07-31 2022-12-27 Samsung Display Co., Ltd. Spot detection device, spot detection method, and display device
CN113390902A (en) * 2020-02-26 2021-09-14 丰田自动车株式会社 Method and apparatus for inspecting membrane electrode assembly
KR102218734B1 (en) 2020-05-20 2021-02-24 켐아이넷(주) Artificial intelligence-based interpolation method of high-resolution data

Similar Documents

Publication Publication Date Title
US7783103B2 (en) Defect detecting device, image sensor device, image sensor module, image processing device, digital image quality tester, and defect detecting method
US8879869B2 (en) Image defect map creation using batches of digital images
US7683946B2 (en) Detection and removal of blemishes in digital images utilizing original images of defocused scenes
US7315658B2 (en) Digital camera
KR101716111B1 (en) System and method for detecting foreign substance
US7310450B2 (en) Method of detecting and correcting dust in digital images based on aura and shadow region analysis
CN101464418A (en) Flaw detection method and apparatus
CN114998314B (en) PCB defect detection method based on computer vision
JP2005172559A (en) Method and device for detecting line defect on panel
KR20190023374A (en) Method for testing display pannel
KR101792564B1 (en) Image processing System and Image processing Method
JP4244046B2 (en) Image processing method and image processing apparatus
JP2009139133A (en) Flaw detection method and flaw detector
JP2004212311A (en) Method and apparatus for detecting unevenness defect
KR100754969B1 (en) Image inspecting apparatus, image inspecting method, and computer-readable storage medium
CN115272173A (en) Tin ball defect detection method and device, computer equipment and storage medium
KR101993654B1 (en) Inspecting apparatus mura of display panel and method thereof
KR20230036650A (en) Defect detection method and system based on image patch
JP4863050B2 (en) Color unevenness defect inspection method and apparatus
Mishra et al. Surface defects detection for ceramic tiles using image processing and morphological techniques
JP2007081513A (en) Blot defect detecting method for solid-state imaging element
JP2022018507A (en) Image processing apparatus for subject determination, and image processing method
JP3870208B2 (en) Image processing method and inspection apparatus
JP4272438B2 (en) Shading correction method in surface defect inspection apparatus
JP2004286708A (en) Defect detection apparatus, method, and program

Legal Events

Date Code Title Description
E701 Decision to grant or registration of patent right
GRNT Written decision to grant