JP4649828B2 - Image processing apparatus abnormality determination method - Google Patents

Image processing apparatus abnormality determination method Download PDF

Info

Publication number
JP4649828B2
JP4649828B2 JP2003357236A JP2003357236A JP4649828B2 JP 4649828 B2 JP4649828 B2 JP 4649828B2 JP 2003357236 A JP2003357236 A JP 2003357236A JP 2003357236 A JP2003357236 A JP 2003357236A JP 4649828 B2 JP4649828 B2 JP 4649828B2
Authority
JP
Japan
Prior art keywords
light source
abnormality
imaging
luminance
threshold
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
JP2003357236A
Other languages
Japanese (ja)
Other versions
JP2005121925A (en
Inventor
盛行 宮原
Original Assignee
Jfeスチール株式会社
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 Jfeスチール株式会社 filed Critical Jfeスチール株式会社
Priority to JP2003357236A priority Critical patent/JP4649828B2/en
Publication of JP2005121925A publication Critical patent/JP2005121925A/en
Application granted granted Critical
Publication of JP4649828B2 publication Critical patent/JP4649828B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Description

  The present invention is a proposal for a method for determining a light source used for illumination or an abnormality occurring in an imaging apparatus in an image processing apparatus using an imaging apparatus such as a CCD camera.

  An image processing apparatus using an imaging device such as a CCD camera can cope with high accuracy, high-speed processing, and high-mix low-volume processing of processing contents, and therefore functions as an inspection device and a monitoring device that replace "human eyes". In particular, the range of use is greatly expanded with the rapid progress of hardware and software in recent years and the reduction in the cost of devices. In particular, in an automated production line, it is used for confirmation of the presence / absence of a product, positioning confirmation, shape recognition, dimension measurement, defect inspection, remote monitoring of equipment operation status, and the like.

  As shown in FIG. 1, the image processing apparatus includes a light source 2 that illuminates an object to be imaged (work) 1 that is a measurement target, and an element that converts an optical signal reflected from the object to be imaged 1 into an electrical signal. Generally, it is composed of a CCD camera (imaging device) 3 and an image processing calculation unit 4. As a light source used for the illumination, a halogen lamp is often used in order to secure a necessary illuminance according to the shutter speed of the camera.

  As image data processing methods in the image processing apparatus, there are two methods of gray processing and binarization processing. The gray processing is a method in which image data obtained by a camera is used as processing data as it is, and for example, image data of a good product model is registered in advance, and this is image data of the object 1 to be measured. And the like can be identified, inspected for dirt, chipped, positioned, and the like. In addition, there is a feature that it is more resistant to illumination fluctuations than the binarization process and can perform a stable process. On the other hand, binarization processing is a method that binarizes image data obtained by the camera into “bright parts” and “dark parts” and processes them with the number of pixels and coordinates, and is suitable for shape discrimination, inclination, dimension inspection, etc. Since it is cheaper than gray processing, it is used in many fields.

  However, the binarization processing method described above is binarized by replacing “bright part (white)” with a certain brightness (luminance) or higher and “dark part (black)” below in the captured image data. Therefore, compared to the gray processing method, it is more affected by illumination fluctuations and appropriate image processing is often difficult. In addition, not only binarization processing and gray processing, but the lamp that is the light source has a lifetime, so it is regularly replaced, but if the light source still malfunctions during image data processing (Hereinafter referred to as “light source abnormality”) may determine that the object to be imaged is abnormal.

  There are two types of light source abnormality: “decrease in illuminance” and “light source stop”. The decrease in illuminance mainly means that the illuminance of light illuminating the object to be imaged decreases due to a decrease in the light emission function of the light source lamp over time. The light source stop is a state in which the light emitting function of the lamp itself is stopped and the function as a light source for illuminating the object to be imaged is completely stopped. In other words, when the light source is stopped, the illuminance illuminating the object to be imaged is the illuminance itself when there is no light source. It will be weak.

As a method of determining a light source abnormality as described above, conventionally, a sensor such as a photoelectric switch is installed in the irradiation range of the light source, and the illuminance is constantly measured to determine the abnormality. Further, in Patent Document 1, the brightness of a predetermined area in the monitoring area is changed, the image before and after the brightness change is processed, the density change area in the image is detected, and the function is automatically functioned from the result. There has also been proposed a method for determining the above.
JP-A-7-250317

  However, the above method of installing a sensor within the illumination range of the light source as a means for determining an abnormality of the light source requires a separate installation of the sensor and the signal processing unit, and requires maintenance. There is. In addition, the determination method disclosed in Patent Document 1 is employed because it is not possible to change the illumination light in the middle when it is required to always illuminate the measurement target and process the image data. It is not possible. Similarly, although the occurrence frequency is low, in addition to a light source abnormality, an abnormality of the imaging apparatus such as a decrease in sensitivity or a stop of the imaging apparatus such as a CCD camera may occur. Therefore, a technique for accurately determining these abnormalities is desired.

  An object of the present invention is advantageous in that a light source abnormality or an imaging apparatus abnormality in an image processing apparatus in which a light source is used for illuminating an object to be imaged is always required without requiring a special device from a remote location. This is to propose a method for determining the above.

  As a result of repeated investigations to solve the above-described problems of the prior art, the inventors constantly monitor image data (luminance data) detected by an imaging device such as a CCD camera and perform threshold processing on the image data. Thus, it has been found that a light source abnormality or an imaging apparatus abnormality can be accurately determined without stopping the line, and the present invention has been completed.

That is, the present invention is a method for determining an abnormality of an image processing apparatus that binarizes image data into a bright part and a dark part, and the image data is a luminance obtained by imaging an object to be illuminated by a light source The abnormality is any of the following (1), (3), and (4). In determining the abnormality, the luminance B at a specific position in the imaging range is set to the following thresholds H, M, and L ( However, it is classified by 0 (zero) <L <M <H), and when B> H, it is determined as normal,
Abnormal (1) when B ≦ H and B ≧ M,
Abnormal (3) when B <M and B ≧ L,
In the case of B <L, it is determined that the abnormality is (4).
Abnormality (1): Illuminance reduction of light source and / or sensitivity reduction abnormality of imaging device (3): Light source stop abnormality (4): Imaging device stop threshold H: Luminance B at the specific position when the image processing device is normal It is set to a lower luminance than the threshold threshold M: light source stop threshold threshold is set to a higher luminance than the luminance B of the specific position in the case L: rather lower than the luminance B of the specific position in the case of the light source stop , And the threshold value set to the brightness that can determine whether the imaging device is stopped

  According to the present invention, the light source abnormality of the image processing apparatus and the abnormality of the imaging apparatus can always be determined remotely, and the reliability of the image processing data can be greatly improved. In addition, since it is not necessary to use a special detection device, there is no increase in equipment costs and maintenance costs.

Hereinafter, the description of the present invention will be specifically described.
In the image processing apparatus adopting the binarization processing method, when both the light source and the imaging apparatus such as a CCD camera are operating normally, the image data detected by the imaging apparatus is as shown in FIG. In addition, threshold processing is performed in accordance with the luminance level, and a bright portion above the threshold is binarized to white, and a dark portion below the threshold is binarized to black. In the present invention, the luminance distribution before image processing obtained by the imaging device is referred to as “image data”, and the binarized image data is referred to as “binary data”. To do.

  On the other hand, when the imaging apparatus is normal and an abnormality in illuminance reduction occurs, the illuminance of light illuminating the object to be imaged decreases, so the image data and binarized data are as shown in FIG. . Conventionally, as a countermeasure against such a decrease in illuminance, a method of lowering a threshold level for distinguishing (binarizing) a bright part (white) and a dark part (black) has been generally used. However, the method of lowering the threshold gives rise to the possibility of erroneously processing a portion to be processed as a dark portion (black) as a bright portion (white) when the light source is normal. FIG. 3 schematically shows a case where the binarization processing is performed on the image data of the same object to be imaged as in FIG. 2 by lowering the threshold value P to the threshold value Q level. This part is processed as a dark part when the light source is normal, but is classified as a bright part when processed with the threshold value Q. The same thing happens when the sensitivity of the imaging device is reduced. Therefore, changing the threshold level for binarizing light and dark is not preferable because it causes erroneous processing.

  On the other hand, when the abnormality of the light source stop occurs, the light emitted from the object to be imaged is only the reflected light of natural light or light from other light sources, so the imaging device detects if the imaging device is normal. As the image data to be obtained, low luminance as shown in FIG. 4c is obtained, and when this is binarized, even if the threshold value is lowered, the whole is processed as a dark part (black). Will be. Similarly, when the imaging device stops functioning, the image data itself cannot be obtained in the first place (d in FIG. 4), so that the whole is below the threshold value and is processed as a dark part. Therefore, for these abnormalities, the type of abnormality cannot be determined with one threshold.

Accordingly, the inventors of the abnormality of the imaging device such as a reduction or cessation of sensitivity of the light source abnormality and an image pickup apparatus such as illumination intensity and light stop, separately from the threshold value for the original binarization processing, a level different Do that three We have developed a method for determining with high accuracy by setting a threshold. That is, the present invention focuses on a specific position of the imaging range, the third threshold value different Do that level for evaluating the luminance B of the particular location is provided, the abnormality by comparing the brightness B of the specific position This is a method of determining.

Specifically, when three different threshold levels H, M and L (where 0 <L <M <H) are set,
Abnormality (1): Illuminance reduction of light source and / or sensitivity reduction abnormality of imaging device (3): Light source stop abnormality (4): When luminance B at a specific position exceeds threshold value H when imaging device is stopped It is determined that both the light source and the imaging device are normal, and when the threshold value is equal to or lower than the threshold value H and equal to or higher than the threshold value M, it is determined to be abnormal (1) If it is L or more, it is determined as abnormal (3) (light source stop), and if it is less than the threshold L, it is determined as abnormal (4) (imaging device stopped) (see FIG. 6).

  Here, the above-mentioned specific position may be a part of a manufacturing facility within the imaging range of an imaging apparatus such as a CCD camera or a standard object to be provided. If the measurement target is constant in a specific shape, a part or the whole of the object to be imaged can be selected as the specific position. 5 and 6 described above are examples in which a specific position is set at the apex of the image data, that is, the highest luminance part. However, if the change in luminance due to the change in illuminance is large, an abnormality can be accurately determined. There is no particular limitation.

The threshold levels H, M, and L for classifying the luminance B at a specific position are set as follows.
First, the threshold value H set to a high level is set to be less than the normal brightness B at the specific position selected as described above in order to accurately determine the illuminance reduction of the light source or the sensitivity reduction of the imaging device. It should be less than and near the normal brightness.

  In addition, since the purpose of the medium level threshold value M is to determine whether the light source is stopped and / or the sensitivity of the imaging apparatus is lowered, the level is determined in advance by measuring the luminance B at a specific position in a state where the light source is stopped. , Set just above the brightness. Further, the low-level threshold L is set to a level that is 0 (zero) or higher and lower than the luminance B at a specific position in the light source stop state because the purpose is to determine whether the light source is stopped or the camera is stopped. .

In the above description, the example in which the number of threshold values to be set is three has been described. However, the present invention is not limited to these examples, and the number of threshold values can be increased according to the purpose of the determination. Further, the number of specific positions to be selected is not limited to one, and accuracy can be improved by selecting two or more specific positions. Furthermore, the setting of the above / less than or less than / less than the threshold for threshold processing is not limited to the example of the present invention, and can be arbitrarily set.

  INDUSTRIAL APPLICABILITY The present invention is effective for determining abnormality of image processing apparatuses used for positioning, inspection, monitoring apparatuses, etc. in various production facilities and production lines, especially image processing apparatuses that binarize image data. . In particular, it is effective for automatically and remotely determining abnormality in image processing apparatuses installed in a large number of automated long lines such as steel product manufacturing lines.

It is a figure which shows an example of a structure of an image processing apparatus. It is a figure which shows typically the change of binarization data when an imaging device is normal and a light source changes from normal to illuminance fall abnormality. It is a figure which shows typically the change of binarization data when changing the threshold level of binarization. It is a figure which shows typically image data and binarization data in the case of a light source stop or an imaging device stop. It is a figure which shows typically the method of determining abnormality from the brightness | luminance change of a specific position using three threshold values from which a level differs.

Explanation of symbols

1. Measurement target (object to be imaged, workpiece)
2. Light source CCD camera (imaging device)
4). Calculation unit

Claims (1)

  1. An abnormality determination method for an image processing apparatus that binarizes image data into a bright part and a dark part, wherein the image data is a luminance distribution obtained by imaging an object to be illuminated by a light source, and the abnormality Is one of the following (1), (3), and (4). In determining the abnormality, the luminance B at a specific position within the imaging range is set to the following thresholds H, M, and L (however, 0 (zero)) <L <M <H), and if B> H, it is judged normal,
    Abnormal (1) when B ≦ H and B ≧ M,
    Abnormal (3) when B <M and B ≧ L,
    An abnormality determination method for an image processing apparatus, characterized in that an abnormality (4) is determined when B <L.
    Abnormality (1): Illuminance reduction of light source and / or sensitivity reduction abnormality of imaging device (3): Light source stop abnormality (4): Imaging device stop threshold H: Luminance B at the specific position when the image processing device is normal It is set to a lower luminance than the threshold threshold M: light source stop threshold threshold is set to a higher luminance than the luminance B of the specific position in the case L: rather lower than the luminance B of the specific position in the case of the light source stop , And the threshold value set to the brightness that can determine whether the imaging device is stopped
JP2003357236A 2003-10-17 2003-10-17 Image processing apparatus abnormality determination method Active JP4649828B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2003357236A JP4649828B2 (en) 2003-10-17 2003-10-17 Image processing apparatus abnormality determination method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2003357236A JP4649828B2 (en) 2003-10-17 2003-10-17 Image processing apparatus abnormality determination method

Publications (2)

Publication Number Publication Date
JP2005121925A JP2005121925A (en) 2005-05-12
JP4649828B2 true JP4649828B2 (en) 2011-03-16

Family

ID=34614181

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2003357236A Active JP4649828B2 (en) 2003-10-17 2003-10-17 Image processing apparatus abnormality determination method

Country Status (1)

Country Link
JP (1) JP4649828B2 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4742223B2 (en) 2008-05-12 2011-08-10 株式会社日本Aeパワーシステムズ Electron beam irradiation device with monitoring device
JP5380026B2 (en) * 2008-09-24 2014-01-08 シスメックス株式会社 Sample imaging device
JP5426181B2 (en) * 2009-01-21 2014-02-26 シスメックス株式会社 Specimen processing system, cell image classification apparatus, and specimen processing method
JP5786631B2 (en) * 2010-10-25 2015-09-30 Jfeスチール株式会社 Surface defect inspection equipment
JP6451263B2 (en) * 2014-11-28 2019-01-16 富士通株式会社 Image processing apparatus, image processing system, image processing method, and image processing program

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5875008A (en) * 1981-10-30 1983-05-06 Kawasaki Steel Corp Shape measuring method
JPS60113575A (en) * 1983-11-24 1985-06-20 Fujitsu Ltd Optical quantity control method of optical reader
JPS63175739A (en) * 1987-01-16 1988-07-20 Toshiba Corp Automatic inspection device for lightening state of light emitting element
JPS63256842A (en) * 1987-04-15 1988-10-24 Nec Corp Pattern recognizing device
JPH01209869A (en) * 1988-02-18 1989-08-23 Toshiba Corp Original reading controller
JPH01246967A (en) * 1988-03-29 1989-10-02 Mitsubishi Electric Corp Picture processor
JPH03214695A (en) * 1990-01-18 1991-09-19 Matsushita Electric Ind Co Ltd Image recognizer of electronic parts mounting equipment
JPH0462423A (en) * 1990-06-29 1992-02-27 Sumitomo Precision Prod Co Ltd Optical sensor
JPH04122841A (en) * 1990-09-14 1992-04-23 Matsushita Electric Ind Co Ltd Observing apparatus of electronic component mounted board
JPH07140092A (en) * 1993-11-16 1995-06-02 Fuji Electric Co Ltd Picture inspection system
JPH0843048A (en) * 1994-07-26 1996-02-16 Kanebo Foods Ltd Method and apparatus for compensating inspection accuracy of inspecting system for appearance of article
JPH0850099A (en) * 1994-08-08 1996-02-20 Nok Corp Inspection device
JPH08261721A (en) * 1995-03-22 1996-10-11 Teijin Ltd Deterioration detecting method for image processing illuminating means
JPH09189522A (en) * 1996-01-09 1997-07-22 Nikon Corp Optical dimension-measuring device
JPH11284982A (en) * 1998-03-31 1999-10-15 Babcock Hitachi Kk Monitoring device and method
JPH11355814A (en) * 1998-06-03 1999-12-24 Toshiba Corp Camera characteristics quantitating device

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5875008A (en) * 1981-10-30 1983-05-06 Kawasaki Steel Corp Shape measuring method
JPS60113575A (en) * 1983-11-24 1985-06-20 Fujitsu Ltd Optical quantity control method of optical reader
JPS63175739A (en) * 1987-01-16 1988-07-20 Toshiba Corp Automatic inspection device for lightening state of light emitting element
JPS63256842A (en) * 1987-04-15 1988-10-24 Nec Corp Pattern recognizing device
JPH01209869A (en) * 1988-02-18 1989-08-23 Toshiba Corp Original reading controller
JPH01246967A (en) * 1988-03-29 1989-10-02 Mitsubishi Electric Corp Picture processor
JPH03214695A (en) * 1990-01-18 1991-09-19 Matsushita Electric Ind Co Ltd Image recognizer of electronic parts mounting equipment
JPH0462423A (en) * 1990-06-29 1992-02-27 Sumitomo Precision Prod Co Ltd Optical sensor
JPH04122841A (en) * 1990-09-14 1992-04-23 Matsushita Electric Ind Co Ltd Observing apparatus of electronic component mounted board
JPH07140092A (en) * 1993-11-16 1995-06-02 Fuji Electric Co Ltd Picture inspection system
JPH0843048A (en) * 1994-07-26 1996-02-16 Kanebo Foods Ltd Method and apparatus for compensating inspection accuracy of inspecting system for appearance of article
JPH0850099A (en) * 1994-08-08 1996-02-20 Nok Corp Inspection device
JPH08261721A (en) * 1995-03-22 1996-10-11 Teijin Ltd Deterioration detecting method for image processing illuminating means
JPH09189522A (en) * 1996-01-09 1997-07-22 Nikon Corp Optical dimension-measuring device
JPH11284982A (en) * 1998-03-31 1999-10-15 Babcock Hitachi Kk Monitoring device and method
JPH11355814A (en) * 1998-06-03 1999-12-24 Toshiba Corp Camera characteristics quantitating device

Also Published As

Publication number Publication date
JP2005121925A (en) 2005-05-12

Similar Documents

Publication Publication Date Title
KR101214806B1 (en) Apparatus and method for defect inspection of wafer
KR0166593B1 (en) Method and apparatus for inspecting transparent object for defect
JP3927353B2 (en) Image alignment method, comparison inspection method, and comparison inspection apparatus in comparison inspection
JP4450776B2 (en) Defect inspection method and appearance inspection apparatus
KR950000331B1 (en) Method and apparatus for inspecting surface pattern of object
JP4536849B2 (en) Method and apparatus for detecting residual yarn in spinning cup winding tube
TW583389B (en) A surface conduction examination method and a substrate examination device
EP1472890B1 (en) Method for verifying the functional reliability of an image sensor and device comprising an image sensor
JP3051279B2 (en) Bump appearance inspection method and bump appearance inspection device
US7260244B2 (en) Print inspection method and print inspection apparatus
EP0595261A1 (en) Method of inspecting solid body for foreign matter
US5293538A (en) Method and apparatus for the inspection of defects
US20030223061A1 (en) Tribological debris analysis system
US7328871B2 (en) Railroad car coupler gap analyzer
KR20040014371A (en) Coin discriminating method and apparatus
US20110311126A1 (en) Defect inspecting apparatus and defect inspecting method
KR20050120420A (en) In-line typed apparatus for auto wafer-defect classification and control method thereof
JP2009128345A (en) Object recognition method and visual inspection apparatus of substrate using the method
JP2011117788A (en) Concrete surface inspection device
JP4454428B2 (en) Component edge detection method, component edge detection program, and inspection apparatus
EP1742016A1 (en) Apparatus and method for inspecting screw portions
JPWO2006054545A1 (en) Automatic discrimination device and automatic discrimination method
JP4776308B2 (en) Image defect inspection apparatus, image defect inspection system, defect classification apparatus, and image defect inspection method
KR940002503B1 (en) Soldering appearance inspection apparatus
EP1677098A1 (en) Surface defect inspecting method and device

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20060914

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20100105

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20100511

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20100804

A911 Transfer of reconsideration by examiner before appeal (zenchi)

Free format text: JAPANESE INTERMEDIATE CODE: A911

Effective date: 20100910

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20101116

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20101129

R150 Certificate of patent or registration of utility model

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20131224

Year of fee payment: 3