CN111183351A - Image sensor surface defect detection method and detection system - Google Patents
Image sensor surface defect detection method and detection system Download PDFInfo
- Publication number
- CN111183351A CN111183351A CN201880001803.5A CN201880001803A CN111183351A CN 111183351 A CN111183351 A CN 111183351A CN 201880001803 A CN201880001803 A CN 201880001803A CN 111183351 A CN111183351 A CN 111183351A
- Authority
- CN
- China
- Prior art keywords
- image sensor
- defect
- image
- defects
- camera
- 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.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 154
- 238000001514 detection method Methods 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 claims abstract description 34
- 230000001427 coherent effect Effects 0.000 claims abstract description 31
- 230000000007 visual effect Effects 0.000 claims abstract description 16
- 238000003384 imaging method Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000005286 illumination Methods 0.000 claims description 10
- 238000007689 inspection Methods 0.000 claims description 8
- 230000003287 optical effect Effects 0.000 description 11
- 238000003062 neural network model Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/47—Scattering, i.e. diffuse reflection
Abstract
The embodiment of the invention discloses a method and a system for detecting surface defects of an image sensor, which comprises the following steps: controlling a light source to generate coherent light to irradiate the surface of the image sensor; receiving the coherent light signal reflected or scattered by the image sensor through a signal receiving device and generating a speckle image; judging whether the surface of the image sensor has defects according to the speckle image; if the surface of the image sensor has no defect, finishing detection, and if the surface of the image sensor has the defect, performing image restoration on the speckle image to determine a position area of the defect; and detecting the position area of the defect by adopting a high-precision visual detection unit so as to confirm the size and the type of the defect. By adopting the detection method, the defect detection efficiency can be improved.
Description
The invention relates to the technical field of electronic element detection, in particular to a method and a system for detecting surface defects of an image sensor.
With the rapid development of integrated circuit manufacturing technology, the pixel size of an image sensor is continuously reduced, causing more and more tiny defects. Defects on the surface of the image sensor have been a major obstacle to yield. The requirements for the detection of surface defects of image sensors are generally: the method has the advantages of high efficiency, accuracy, effective defect capture and real-time online detection.
In the prior art, the relatively common surface defect detection methods are mainly divided into two main types, wherein the first type is manual detection; the second type is machine vision automated optical inspection.
For the manual detection method, the detection efficiency is not high, and the phenomena of missing detection and false detection often occur. For a machine vision automatic optical detection method, as the size of a pixel becomes smaller and smaller, the size of a defect is correspondingly reduced, in order to detect a smaller fatal defect, an automatic optical detection system must adopt an optical system with higher sensitivity and higher optical resolution, but high resolution and high-speed detection cannot be achieved at the same time, generally the resolution reaches several micrometers, the visual field range capable of being detected every time is very small, the detection of the whole area can be realized only by the assistance of a motion mechanism, and the detection efficiency hardly meets the requirement. Therefore, the high-speed and high-precision automatic optical defect detection technology becomes a key technology in the detection industry at present.
Therefore, in order to solve the technical problems that the machine vision automatic optical detection method in the prior art is low in detection efficiency and cannot give consideration to high precision and high speed, a method for detecting surface defects of an image sensor is particularly provided.
A method for detecting surface defects of an image sensor comprises the following steps:
controlling a light source to generate coherent light to irradiate the surface of the image sensor;
receiving the coherent light signal reflected or scattered by the image sensor through a signal receiving device and generating a speckle image;
judging whether the surface of the image sensor has defects according to the speckle image;
if the surface of the image sensor has no defect, finishing detection, and if the surface of the image sensor has the defect, performing image restoration on the speckle image to determine a position area of the defect; and
and detecting the position area of the defect by adopting a high-precision visual detection unit so as to confirm the size and the type of the defect.
In one embodiment, the signal receiving device is a photoelectric sensor, a camera, or a camera provided with an imaging lens.
In one embodiment, the camera is a CCD camera or a CMOS camera.
In one embodiment, the step of determining whether the surface of the image sensor has a defect according to the speckle image includes: analyzing the speckle image by a neural network method to judge whether the surface of the image sensor has defects.
In one embodiment, the image restoration of the speckle image to determine the location area of the defect includes: and performing image restoration on the speckle images by a phase solving reconstruction method to determine the position area of the defect.
In one embodiment, the defect comprises at least one of a foreign object, a stain, a scratch, and a change in microstructure.
In one embodiment, the step of detecting the position of the defect of the image sensor by using a high-precision visual detection unit to confirm the size and type of the defect further comprises illuminating the image sensor by using a low-angle light source.
In one embodiment, the high-precision vision inspection unit includes: the system comprises a low-angle illumination light source for illumination, a high-resolution camera for defect detection, image processing software connected with the high-resolution camera and a high-resolution lens arranged on the high-resolution camera.
In addition, in order to solve the technical problems that the machine vision automatic optical detection method in the prior art is low in detection efficiency and cannot give consideration to high precision and high speed, a system for detecting surface defects of an image sensor is particularly provided.
A system for detecting surface defects of an image sensor, comprising:
a light source for generating coherent light to illuminate a surface of the image sensor;
the signal receiving device is used for receiving the coherent light signal reflected or scattered by the image sensor and generating a speckle image;
the detection judging unit is used for judging whether the surface of the image sensor has defects according to the speckle images and restoring the speckle images to determine the position areas of the defects; and
and the high-precision visual detection unit is used for detecting the position area of the defect so as to confirm the size and the type of the defect.
In one embodiment, the signal receiving device is a photoelectric sensor, a camera, or a camera provided with an imaging lens, and the camera is a CCD camera or a CMOS camera.
The embodiment of the invention has the following beneficial effects:
according to the detection method and the detection system for the surface defects of the image sensor, coherent light is adopted for illumination, whether the defects exist or not is judged through the acquired speckle images, if the image sensor has the defects, the speckle images are restored to find out the position areas where the defects exist, the high-precision visual detection unit is used for carrying out high-precision detection on the position areas where the defects exist only, the whole surface area of the image sensor is not required to be detected, and further, the detection efficiency of the system can be greatly improved while the high-precision detection is realized. And when the image sensor is judged to have no defects, the detection of the next product can be directly carried out, and the detection efficiency of the surface defects of the image sensor is greatly improved.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 is a flowchart of a method for detecting surface defects of an image sensor according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a principle of speckle image detection of different surface defects of an image sensor according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a system for detecting surface defects of an image sensor according to an embodiment of the present invention; and
fig. 4 is a schematic technical principle diagram of a method for detecting surface defects of an image sensor according to an embodiment of the present invention.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the technical problems that the machine vision automatic optical detection method in the prior art is low in detection efficiency and cannot give consideration to high precision and high speed, a method and a system for detecting surface defects of an image sensor are provided.
Referring to fig. 1 and 4, the present invention provides a method for detecting surface defects of an image sensor, which includes the following steps:
controlling a light source to generate coherent light to irradiate the surface of the image sensor;
receiving the coherent light signal reflected or scattered by the image sensor through a signal receiving device and generating a speckle image;
judging whether the surface of the image sensor has defects according to the speckle image;
if the surface of the image sensor has no defect, finishing the detection; if the surface of the image sensor has defects, performing image restoration on the speckle image to determine the position area of the defects; and
and detecting the position area of the defect by adopting a high-precision visual detection unit so as to confirm the size and the type of the defect.
It is understood that speckle is an interference phenomenon, and generally, the surface of an object is rough in the dimension of the wavelength of light, when light is irradiated on the rough surface, each point on the surface has scattered light, and the scattered light is coherent light, and only the amplitude of the scattered light is different from the phase, and the scattered light is randomly distributed; after the scattered light is superposed, granular structures with better contrast can be formed, and the granular structures are speckles. Different surface defects of the image sensor can cause the roughness or the concave-convex of the surface of the image sensor to change, and further, the speckle distribution of a coherent light speckle image on the optical sensor caused by the light irradiation is different from that of a defect-free image sensor, so that whether the surface of the image sensor has defects or not can be judged through the speckle image.
Specifically, in the method for detecting the surface defect of the image sensor provided by the invention, coherent light is adopted to illuminate the image sensor to be detected, the coherent light is irradiated on all microstructures including defects (such as redundancy, internal structure defects or mechanical damage) on the surface of the image sensor to be detected and then reflected or scattered, the signal receiving device can receive coherent light signals reflected or scattered back by the image sensor and can generate a speckle image, and further, information of all defects on the surface of the image sensor is contained in the obtained speckle image of the image sensor, so that the existence of the defects in the speckle image can be detected.
Fig. 2 is a schematic diagram illustrating a principle of speckle image detection of different surface defects of an image sensor according to an embodiment of the present invention, and referring to fig. 2, after an image sensor 2 is irradiated with coherent light, light reflected or scattered by the image sensor 2 interferes with a signal receiving device 3 (e.g., a photosensor), the interference is strengthened to form a bright spot 11 on the photosensor 3, and the interference is weakened to form a dark spot on the photosensor 3, so that the photosensor can obtain a granular speckle image and transmit the granular speckle image to a processing device such as a computer. The image sensors 2 having different defects (e.g., the surface of the image sensor 201 has a structure loss defect, the surface of the image sensor 202 has a structure deformation defect, the surface of the image sensor 203 has a foreign substance, the surface of the image sensor 204 has a damage defect, etc.) have different surface structures, and the speckle distributions on the speckle images (e.g., the speckle images 301, 302, 303, 304) formed on the photosensors are different, so that whether the image sensor 2 has a defect can be determined from the speckle image obtained by the image sensor 2.
It is to be understood that various conventional signal receiving devices may be used to receive the coherent light signal reflected or scattered back from the image sensor and generate the speckle image, and the invention is not limited thereto, as long as the device can receive the coherent light signal reflected or scattered back from the image sensor and generate the speckle image. For example, in some embodiments of the present invention, the signal receiving device may be a photosensor, a camera, or a camera provided with an imaging lens (i.e., an imaging lens is provided on the camera). The speckle image of the image sensor is obtained through the photoelectric sensor or the camera, the distance between the photoelectric sensor or the camera and the image sensor can be selected at will according to the actual situation, and the angle between the photoelectric sensor or the camera and the image sensor can be adjusted at will according to the actual situation.
Also, the present invention is not limited to the kind of camera, which may be any of various cameras commonly used in the art, for example, in some embodiments of the present invention, a CCD camera or a CMOS camera is used to receive the coherent light signal reflected or scattered by the image sensor and generate the speckle image. The specific structure and operation principle of the CCD camera and the CMOS camera are well known to those skilled in the art, and the detailed description of the present invention is omitted.
It can be understood that when a structure combining a camera and an imaging lens is adopted to receive coherent light signals reflected or scattered by an image sensor, since the object distance is limited by the working distance of the imaging lens, the coherent light signals can only be placed within the working distance range of the imaging lens to receive signals reflected or scattered by the image sensor to acquire images of object speckles.
Further, in some embodiments of the present invention, referring to fig. 4, the speckle image is analyzed by a neural network method to determine whether there is a defect on the surface of the image sensor.
For example, an artificial neural network method may be used to train and learn large sample data of interference speckle images formed by the image sensor, for example, several hundred or more speckle images are collected in advance according to different defect samples, and a deep learning neural network is used to perform classification training on the speckle images capable of indirectly reflecting the surface microstructure of the image sensor, so as to obtain a correct neural network model, thereby detecting and judging whether the surface defects of the image sensor exist. It can be understood that the speckle image is input in the process of judging whether the defect exists, and the comparison and judgment of the input current speckle image is performed through the neural network model, so that whether the surface of the image sensor corresponding to the speckle image has the defect can be determined. It is understood that the principles of deep training and learning of artificial neural networks are well known to those skilled in the art, and the present invention is not described in detail herein.
Furthermore, after the interference speckle image formed by the image sensor is subjected to large sample data training and learning by a neural network method, different neural network models can be obtained, so that the detection precision and efficiency are further improved. For example, several hundred or more speckle images of a pattern sensor with a defect of "foreign matter" are collected, and the speckle images are trained through a deep learning neural network, so that a neural network model with the defect of "foreign matter" can be obtained; the method is characterized in that speckle images of hundreds of or more image sensors with 'scratch' defects are collected, the speckle images are trained through a deep learning neural network, a neural network model with 'scratch' defects can be obtained, the neural network models with various defects can be obtained by analogy, and then the types of the defects can be preliminarily judged while whether the surface of the image sensor has the defects or not, so that the detection efficiency is improved. Meanwhile, the subsequent high-precision detection result is compared with the preliminarily judged defect type, so that the neural network model can be further optimized, the comparison accuracy of the neural network model is improved, and the detection result can be more accurate.
It can be understood that when it is determined that there is no defect on the surface of the image sensor, the detection of the current image sensor can be finished, and on the production line, the detection of the next image sensor can be directly performed. Under the condition, the workpiece does not need to be subjected to comprehensive high-precision defect detection, and the defect detection efficiency can be greatly improved.
In the detection method provided by the invention, when the surface of the image sensor is judged to have the defect, the speckle image is subjected to image restoration to determine the position area of the defect. It is understood that the speckle image can be restored by various conventional methods, and the invention is not limited thereto. In some embodiments of the invention, the speckle image is image-restored by phase solution reconstruction to determine the location area of the defect. It is understood that the method for reconstructing the restored image by phase solving is well known to those skilled in the art, and the detailed description of the method is omitted here. That is, in this embodiment, the speckle image with the surface structure information of the image sensor is directly subjected to phase inversion to obtain a restored image of the image, so that the position area of the defect can be located, and the later high-precision visual detection is facilitated.
Furthermore, when the position area where the defect is located, the defect can be detected with high precision aiming at the position area, and the detection precision can be further ensured, namely: a high-precision visual detection unit is adopted to detect the position area of the defect of the image sensor so as to confirm the size and the type of the defect. Therefore, the detection method provided by the invention only needs to detect the defect with high precision in the position area where the defect is located, does not need to detect the surface of the whole image sensor with high precision, and can improve the efficiency of defect detection while obtaining high precision.
It is to be understood that various conventional high-precision visual inspection units may be employed, and the present invention is not particularly limited thereto. For example, in some embodiments of the present invention, a high-precision vision inspection unit comprises: the defect detection system comprises an illumination light source for illumination, a high-resolution camera for defect detection, image processing software connected with the high-resolution camera and a high-resolution lens arranged on the high-resolution camera. Further, in an embodiment of the present invention, when performing high-precision defect detection, a low-angle light source may be used to illuminate the image sensor, so as to improve the detection precision.
It is understood that the detection method of the high-precision visual detection unit and the method for determining the size and type of the defect are well known to those skilled in the art, and the detailed description of the invention is omitted. It is understood that the detection method provided by the invention can detect various defects on the surface of the image sensor, such as foreign matters, dirt, scratches and microstructure changes.
In addition, in order to solve the technical problems that the machine vision automatic optical detection method in the prior art is low in detection efficiency and cannot give consideration to high precision and high speed, a system for detecting surface defects of an image sensor is particularly provided.
Referring to fig. 3, the present invention provides a system for detecting surface defects of an image sensor, comprising: the device comprises a light source 1, a signal receiving device 3, a detection judging unit 4 and a high-precision visual detection unit 5. The light source 1 is used for generating coherent light to irradiate the surface of the image sensor 2, the signal receiving device 3 is used for receiving coherent light signals reflected or scattered by the image sensor 2 and generating a speckle image 21, the detection judging unit 4 is used for judging whether the surface of the image sensor 2 has defects according to the speckle image 21 and carrying out image restoration on the speckle image 21 to determine the position areas of the defects, the high-precision visual detection unit 5 is used for detecting the position areas of the defects to confirm the size and the type of the defects, and the high-precision visual detection unit 5 can obtain a fine defect image 22.
It is understood that the signal receiving device 3 can be any signal receiving device commonly used in the art, and the invention is not limited in this regard as long as it can receive the coherent light signal reflected or scattered back by the image sensor 2 and generate the speckle image 21. For example, in some embodiments of the present invention, the signal receiving device 3 may be a photosensor, a camera, or a camera provided with an imaging lens.
When the speckle image 21 of the image sensor 2 is obtained by the photoelectric sensor or the camera, the distance between the photoelectric sensor or the camera and the image sensor 2 can be selected at will according to the actual situation, and the angle between the photoelectric sensor or the camera and the image sensor 2 can also be adjusted at will according to the actual situation.
Also, the present invention is not limited to the kind of camera, which may be any kind of camera commonly used in the art, for example, in some embodiments of the present invention, a CCD camera or a CMOS camera is used to receive the coherent light signal reflected or scattered by the image sensor 2 and generate the speckle image 21.
It can be understood that when a combined structure of a camera and an imaging lens is adopted to receive the coherent light signal reflected or scattered by the image sensor 2, since the object distance is limited by the working distance of the imaging lens, the coherent light signal can only be placed within the working distance range of the imaging lens to receive the signal reflected or scattered by the image sensor 2 to acquire the speckle image 21 of the object.
It will also be appreciated that the detection judgment unit 4 may be any of various conventional detection judgment units, such as a computer. For example, in an embodiment of the present invention, the computer obtains an accurate neural network model through a neural network learning method, and then compares and judges the input current speckle image through the neural network model, so as to determine whether the surface of the image sensor 2 corresponding to the speckle image has a defect.
Similarly, the high-precision vision inspection unit 5 may be any of various conventional high-precision vision inspection units, and the present invention is not limited thereto. For example, in some embodiments of the present invention, the high-precision vision inspection unit 5 includes: an illumination source for illumination, a high resolution camera for defect detection, image processing software (e.g., stored in a computer) connected to the high resolution camera, and a high resolution lens disposed on the high resolution camera.
Furthermore, after the detection and judgment unit 4 judges that the surface of the image sensor 2 corresponding to the speckle image has defects, and performs image restoration on the speckle image to determine the position area of the defects, the image of the position area of the defects of the image sensor 2 is acquired through the high-resolution lens and the high-resolution camera, and the specific type of the defects on the image sensor 2 can be accurately analyzed through image processing software. Further, in an embodiment of the present invention, when performing high-precision defect detection, the low-angle light source 51 may be used to illuminate the image sensor, so as to improve the detection precision. After the high-precision vision detection unit 5 performs fine detection on the defect position, the size and type of the defect can be calculated, and it can be understood that various methods commonly used in the field can be adopted as the method for calculating the size and type of the defect by the high-precision vision detection unit 5, and the invention is not particularly limited thereto.
The embodiment of the invention has the following beneficial effects:
according to the detection method and the detection system for the surface defects of the image sensor, coherent light is adopted for illumination, whether the defects exist or not is judged through the acquired speckle images, if the image sensor has the defects, the speckle images are restored to find out the position area where the defects exist, if the defects exist, the high-precision visual detection unit is used for carrying out high-precision detection on the position area where the defects exist, for example, when the position area where the defects exist is determined to be a certain area of the upper left corner of the image sensor, the specific size and type of the defects can be determined only by carrying out high-precision detection on the area, the whole surface area of the image sensor does not need to be detected, and further, the detection efficiency of the system can be greatly improved while the high-precision detection is realized.
And when the image sensor is judged to have no defects, the detection of the next product can be directly carried out, and the detection efficiency of the surface defects of the image sensor is greatly improved.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (10)
- A method for detecting surface defects of an image sensor is characterized by comprising the following steps:controlling a light source to generate coherent light to irradiate the surface of the image sensor;receiving the coherent light signal reflected or scattered by the image sensor through a signal receiving device and generating a speckle image;judging whether the surface of the image sensor has defects according to the speckle image;if the surface of the image sensor has no defect, finishing the detection; if the surface of the image sensor has defects, performing image restoration on the speckle image to determine the position area of the defects; andand detecting the position area of the defect by adopting a high-precision visual detection unit so as to confirm the size and the type of the defect.
- The method of claim 1, wherein the signal receiver is a photosensor, a camera, or a camera with an imaging lens.
- The method of claim 2, wherein the camera is a CCD camera or a CMOS camera.
- The method for detecting the surface defect of the image sensor according to claim 1, wherein the step of judging whether the surface of the image sensor has the defect according to the speckle image comprises the following steps: analyzing the speckle image by a neural network method to judge whether the surface of the image sensor has defects.
- The method of claim 1, wherein the image reconstruction of the speckle image to determine the location area of the defect comprises: and performing image restoration on the speckle images by a phase solving reconstruction method to determine the position area of the defect.
- The method of claim 1, wherein the defect comprises at least one of a foreign object, a stain, a scratch, and a change in microstructure.
- The method of claim 1, wherein the step of detecting the location of the defect of the image sensor with a high-precision vision inspection unit to determine the size and type of the defect further comprises illuminating the image sensor with a low-angle light source.
- The method of claim 1, wherein the high-precision vision inspection unit comprises: the system comprises a low-angle illumination light source for illumination, a high-resolution camera for defect detection, image processing software connected with the high-resolution camera and a high-resolution lens arranged on the high-resolution camera.
- A system for detecting surface defects of an image sensor, comprising:a light source for generating coherent light to illuminate a surface of the image sensor;the signal receiving device is used for receiving the coherent light signal reflected or scattered by the image sensor and generating a speckle image;the detection judging unit is used for judging whether the surface of the image sensor has defects according to the speckle images and restoring the speckle images to determine the position areas of the defects after judging that the surface of the image sensor has the defects; andand the high-precision visual detection unit is used for detecting the position area of the defect so as to confirm the size and the type of the defect.
- The detection system according to claim 9, wherein the signal receiving device is a photosensor, a camera, or a camera provided with an imaging lens, and the camera is a CCD camera or a CMOS camera.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2018/105111 WO2020051780A1 (en) | 2018-09-11 | 2018-09-11 | Image sensor surface defect detection method and detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111183351A true CN111183351A (en) | 2020-05-19 |
Family
ID=69777329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201880001803.5A Pending CN111183351A (en) | 2018-09-11 | 2018-09-11 | Image sensor surface defect detection method and detection system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111183351A (en) |
| WO (1) | WO2020051780A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359247A (en) * | 2023-03-03 | 2023-06-30 | 中国科学院上海高等研究院 | Mask defect detection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5127726A (en) * | 1989-05-19 | 1992-07-07 | Eastman Kodak Company | Method and apparatus for low angle, high resolution surface inspection |
| CN103245671A (en) * | 2013-05-09 | 2013-08-14 | 深圳先进技术研究院 | Surface defect detection device and method for stamping piece |
| CN203191327U (en) * | 2013-04-19 | 2013-09-11 | 杭州电子科技大学 | Printed circuit board (PCB) defect automatic detection device based on machine vision |
| CN105092607A (en) * | 2015-08-27 | 2015-11-25 | 浙江大学 | Method for evaluating surface defects of spherical optical components |
| CN105973912A (en) * | 2016-06-12 | 2016-09-28 | 合肥汉重智能装备有限公司 | Leather surface defect detecting system and method based on machine vision |
| CN108332689A (en) * | 2018-02-08 | 2018-07-27 | 南京航空航天大学 | A kind of optical measuring system and method for detection surface roughness and surface damage |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103857982A (en) * | 2011-08-15 | 2014-06-11 | 纽约市哥伦比亚大学理事会 | Systems and methods for performing machine vision using diffuse structured light |
| CN103528518A (en) * | 2013-10-18 | 2014-01-22 | 中国科学院西安光学精密机械研究所 | Flash frequency laser speckle three-dimensional target obtaining system and method |
| JP6568672B2 (en) * | 2015-11-13 | 2019-08-28 | コグネックス・コーポレイション | System and method for detecting defects on specular surfaces in a vision system |
| CN105627942A (en) * | 2015-12-25 | 2016-06-01 | 华南理工大学 | Imaging apparatus and method for detecting object surface micro deformation through machine vision |
| CN106226270B (en) * | 2016-07-01 | 2019-07-19 | 深圳睿晟自动化技术有限公司 | The method of the dirty defect of detection image sensor surface |
-
2018
- 2018-09-11 CN CN201880001803.5A patent/CN111183351A/en active Pending
- 2018-09-11 WO PCT/CN2018/105111 patent/WO2020051780A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5127726A (en) * | 1989-05-19 | 1992-07-07 | Eastman Kodak Company | Method and apparatus for low angle, high resolution surface inspection |
| CN203191327U (en) * | 2013-04-19 | 2013-09-11 | 杭州电子科技大学 | Printed circuit board (PCB) defect automatic detection device based on machine vision |
| CN103245671A (en) * | 2013-05-09 | 2013-08-14 | 深圳先进技术研究院 | Surface defect detection device and method for stamping piece |
| CN105092607A (en) * | 2015-08-27 | 2015-11-25 | 浙江大学 | Method for evaluating surface defects of spherical optical components |
| CN105973912A (en) * | 2016-06-12 | 2016-09-28 | 合肥汉重智能装备有限公司 | Leather surface defect detecting system and method based on machine vision |
| CN108332689A (en) * | 2018-02-08 | 2018-07-27 | 南京航空航天大学 | A kind of optical measuring system and method for detection surface roughness and surface damage |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359247A (en) * | 2023-03-03 | 2023-06-30 | 中国科学院上海高等研究院 | Mask defect detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020051780A1 (en) | 2020-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JPH04166751A (en) | Method and apparatus for inspecting defect in bottle and the like | |
| WO2017202114A1 (en) | Method and apparatus for determining illumination intensity for inspection, and optical inspection method and apparatus | |
| JP2006284471A (en) | Pattern inspection method, pattern inspection device and pattern inspecting program | |
| JP2007292699A (en) | Surface inspection method of member | |
| JP2006010392A (en) | Through hole measuring system, method, and through hole measuring program | |
| CN114280075A (en) | Online visual inspection system and method for surface defects of pipe parts | |
| CN104316530A (en) | Part detection method and application | |
| JP4910128B2 (en) | Defect inspection method for object surface | |
| JPWO2019216303A1 (en) | Inspection equipment, inspection methods, learning methods, and programs | |
| CN111183351A (en) | Image sensor surface defect detection method and detection system | |
| CN110402386A (en) | Cylinder surface examining device and cylinder surface inspecting method | |
| JPH0921628A (en) | Method for detecting projecting/recessed defect of surface of cylindrical object | |
| JP4523310B2 (en) | Foreign matter identification method and foreign matter identification device | |
| US20230138331A1 (en) | Motion in images used in a visual inspection process | |
| KR20070101669A (en) | Apparatus and mathod for vision inspecting of mounting plate assembly | |
| CN111638226B (en) | Detection method, image processor and detection system | |
| JP4967132B2 (en) | Defect inspection method for object surface | |
| JP2010038723A (en) | Flaw inspecting method | |
| Bonnot et al. | Machine vision system for surface inspection on brushed industrial parts | |
| Lin et al. | Computer-aided transmitted deformation inspection system for see-through glass products | |
| KR102618194B1 (en) | Semiconductor package board processing hole 3d automatic process inspection method and system | |
| CN116523882B (en) | Vision-based optical target area accuracy detection method and system | |
| JPH11194098A (en) | Defect inspection apparatus | |
| JP3144632B2 (en) | Defect detection method | |
| Perng et al. | A novel vision system for CRT panel auto-inspection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |