CN111665261A - Chip crystal grain detection method based on machine vision - Google Patents
Chip crystal grain detection method based on machine vision Download PDFInfo
- Publication number
- CN111665261A CN111665261A CN202010501740.9A CN202010501740A CN111665261A CN 111665261 A CN111665261 A CN 111665261A CN 202010501740 A CN202010501740 A CN 202010501740A CN 111665261 A CN111665261 A CN 111665261A
- Authority
- CN
- China
- Prior art keywords
- crystal grain
- pixels
- picture
- vision
- crystal grains
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9501—Semiconductor wafers
-
- 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
-
- 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
- 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
- G01N2021/8411—Application to online plant, process monitoring
-
- 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
- G01N2021/8477—Investigating crystals, e.g. liquid crystals
-
- 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
- G01N2021/8883—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 involving the calculation of gauges, generating models
-
- 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
Abstract
The invention relates to chip crystal grain detection, in particular to a chip crystal grain detection method based on machine vision, which comprises the steps of enabling the front surfaces of all crystal grains embedded on a flexible film to be positioned on the same horizontal plane, carrying out image acquisition on the crystal grain surfaces, converting the acquired images into black and white images, calculating the coordinates of corner points of all the crystal grains, converting the corner points and the interior of each crystal grain into standard images with specified sizes, carrying out homogenization on the standard images, subtracting the standard sample images from the homogenized images, calculating the number of pixels with all absolute values exceeding a set threshold value, judging that the crystal grains are unqualified in appearance if the number of the pixels reaches an unqualified proportion, and judging that the crystal grains are qualified in appearance if the number of the pixels does not reach the unqua; the technical scheme provided by the invention can effectively overcome the defects of low efficiency and inaccuracy in appearance detection of the crystal grains inlaid on the flexible film in the prior art.
Description
Technical Field
The invention relates to chip crystal grain detection, in particular to a chip crystal grain detection method based on machine vision.
Background
In the production process of the LED chip, the die is subjected to appearance inspection, and about 70 ten thousand mini-LED dies can be contained on a 6-inch wafer. The detection generally comprises two procedures, wherein the first step is that crystal grains are on a wafer and are automatically detected by using the existing related detection equipment, a series of operations are carried out after the detection, the qualified crystal grains are taken down from the wafer and are embedded on a flexible plastic film to be ready for delivery.
However, in order to prevent the subsequent series of operations from polluting and damaging the chip again, the crystal grains embedded in the flexible film are subjected to appearance detection again, the crystal grains are rectangular blocks with small sizes, and tens of thousands or more crystal grains can be embedded in one flexible film.
However, because of the flexibility of the film, if the camera is used to directly photograph and detect, the heights of the surfaces of the crystal grains are different, so that some crystal grains on the photograph are separated from the focal plane, and the image is blurred, so that whether the crystal grains are qualified or not cannot be analyzed. Therefore, the appearance inspection of the second step still needs manual inspection under a microscope by naked eyes, which is not only inefficient, but also unstable in inspection result.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects in the prior art, the invention provides a chip crystal grain detection method based on machine vision, which can effectively overcome the defects of low efficiency and inaccuracy in appearance detection of crystal grains inlaid on a flexible film in the prior art.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
a chip crystal grain detection method based on machine vision comprises the following steps:
s1, enabling the front surfaces of all crystal grains embedded on the flexible film to be on the same horizontal plane, and carrying out image acquisition on the crystal grain surfaces;
s2, converting the collected picture into a black and white picture, and calculating the corner point coordinates of each crystal grain;
s3, converting the corner points and the interior of each crystal grain into standard pictures with specified sizes, and homogenizing the standard pictures;
s4, subtracting the normalized picture from the standard sample picture, and calculating the number of pixels of which all absolute values exceed a set threshold;
s5, if the number of the pixels in the S4 reaches the disqualification ratio, the appearance of the crystal grain is judged to be disqualified, otherwise, the appearance of the crystal grain is judged to be qualified.
Preferably, the making of the front surfaces of all the crystal grains inlaid on the flexible film are on the same horizontal plane comprises the following steps:
the flexible film on the surface of the crystal grain is flattened and tightened by using the circular hoop, and then the transparent sheet is lightly pressed above the crystal grain.
Preferably, the calculation of the corner coordinates of each die uses a Shi-Tomasi corner detection algorithm or a Haris corner detection algorithm.
Preferably, the four corner points of each of the dies and the inside thereof are transformed into a standard picture of 100x100 pixels using a perspective transformation algorithm.
Preferably, the unqualified proportion is the proportion of the number of pixels with absolute values exceeding a set threshold value in the normalized picture to the total number of pixels.
Preferably, the mean value of the normalized picture is 0 and the variance is 1.
Preferably, the set threshold is set to 0.05, and the failure rate is set to 5%.
(III) advantageous effects
Compared with the prior art, the chip crystal grain detection method based on machine vision provided by the invention can enable the front sides of crystal grains on the flexible film to be on the same horizontal plane, is convenient for image acquisition, optimizes the detection algorithm, can perform appearance detection on the crystal grains embedded on the flexible film by means of a machine, effectively improves the detection efficiency, and can ensure the accuracy of the detection result.
Drawings
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 invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic view of a grain surface obtained by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all 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.
A chip die inspection method based on machine vision, as shown in fig. 1, includes the following steps:
s1, enabling the front surfaces of all crystal grains embedded on the flexible film to be on the same horizontal plane, and carrying out image acquisition on the crystal grain surfaces;
s2, converting the collected picture into a black and white picture, and calculating the corner point coordinates of each crystal grain;
s3, converting the corner points and the interior of each crystal grain into standard pictures with specified sizes, and homogenizing the standard pictures;
s4, subtracting the normalized picture from the standard sample picture, and calculating the number of pixels of which all absolute values exceed a set threshold;
s5, if the number of the pixels in the S4 reaches the disqualification ratio, the appearance of the crystal grain is judged to be disqualified, otherwise, the appearance of the crystal grain is judged to be qualified.
The crystal grain array is sleeved inside by the circular hoop, the flexible film is flattened outwards, the circular hoop is pressed to fix the flexible film, the transparent sheet is pressed above the crystal grains lightly, the front faces of all the crystal grains are in contact with the transparent sheet, and the front faces of all the crystal grains can be considered to be on the same horizontal plane.
The crystal grain surfaces are subjected to image acquisition, and the front surfaces of all the crystal grains are positioned on the same horizontal plane, so that a shot picture is clear, and the crystal grains which are not separated from a focal length and are blurred are avoided.
And converting the collected picture into a black and white picture, and calculating the corner coordinates of each crystal grain by using a Shi-Tomasi corner detection algorithm or a Haris corner detection algorithm.
And transforming four corner points and the interior of each crystal grain into a standard picture of 100x100 pixels by adopting a perspective transformation algorithm, and homogenizing the standard picture, wherein the mean value of the homogenized picture is 0, and the variance is 1.
And subtracting the normalized picture from the standard sample picture, and calculating the number of pixels with the absolute value exceeding 0.05.
If the proportion of the number of pixels with the absolute value exceeding 0.05 in the normalized picture to the total number of pixels reaches 5%, judging that the appearance of the crystal grain is unqualified, otherwise, judging that the appearance of the crystal grain is qualified.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (7)
1. A chip crystal grain detection method based on machine vision is characterized in that: the method comprises the following steps:
s1, enabling the front surfaces of all crystal grains embedded on the flexible film to be on the same horizontal plane, and carrying out image acquisition on the crystal grain surfaces;
s2, converting the collected picture into a black and white picture, and calculating the corner point coordinates of each crystal grain;
s3, converting the corner points and the interior of each crystal grain into standard pictures with specified sizes, and homogenizing the standard pictures;
s4, subtracting the normalized picture from the standard sample picture, and calculating the number of pixels of which all absolute values exceed a set threshold;
s5, if the number of the pixels in the S4 reaches the disqualification ratio, the appearance of the crystal grain is judged to be disqualified, otherwise, the appearance of the crystal grain is judged to be qualified.
2. The machine-vision-based chip die inspection method of claim 1, wherein: the method for making the front surfaces of all crystal grains embedded on the flexible film be on the same horizontal plane comprises the following steps:
the flexible film on the surface of the crystal grain is flattened and tightened by using the circular hoop, and then the transparent sheet is lightly pressed above the crystal grain.
3. The machine-vision-based chip die inspection method of claim 1, wherein: and the calculation of the corner coordinates of each crystal grain adopts a Shi-Tomasi corner detection algorithm or a Haris corner detection algorithm.
4. The machine-vision-based chip die inspection method of claim 1, wherein: and transforming four corner points and the interior of each crystal grain into a standard picture of 100x100 pixels by adopting a perspective transformation algorithm.
5. The machine-vision-based chip die inspection method of claim 1, wherein: the unqualified proportion is the proportion of the number of pixels of which the absolute value exceeds a set threshold value in the normalized picture to the total number of pixels.
6. The machine-vision-based chip die inspection method of claim 5, wherein: the mean value of the normalized picture is 0, and the variance is 1.
7. The machine-vision-based chip die inspection method of claim 5, wherein: the set threshold is set to 0.05 and the failure rate is set to 5%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010501740.9A CN111665261A (en) | 2020-06-04 | 2020-06-04 | Chip crystal grain detection method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010501740.9A CN111665261A (en) | 2020-06-04 | 2020-06-04 | Chip crystal grain detection method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111665261A true CN111665261A (en) | 2020-09-15 |
Family
ID=72386229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010501740.9A Pending CN111665261A (en) | 2020-06-04 | 2020-06-04 | Chip crystal grain detection method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111665261A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538586A (en) * | 2021-09-14 | 2021-10-22 | 武汉精创电子技术有限公司 | Grain row and column positioning method, device and system and computer readable storage medium |
| CN114130709A (en) * | 2021-10-14 | 2022-03-04 | 佛山市国星半导体技术有限公司 | LED crystal grain appearance detection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10246704A (en) * | 1997-03-04 | 1998-09-14 | Nippon Steel Corp | Method and apparatus for inspecting semiconductor wafer |
| US5949901A (en) * | 1996-03-21 | 1999-09-07 | Nichani; Sanjay | Semiconductor device image inspection utilizing image subtraction and threshold imaging |
| WO2001022070A1 (en) * | 1999-09-20 | 2001-03-29 | Matsushita Electric Industrial Co., Ltd. | Method and system of lcd inspection by pattern comparison |
| JP2007266448A (en) * | 2006-03-29 | 2007-10-11 | Fujitsu Ltd | Inspection method of ferroelectric film and manufacturing method of semiconductor device having inspection process |
| CN109978839A (en) * | 2019-03-08 | 2019-07-05 | 浙江大学 | The detection method of the low texture defect of wafer |
| CN110286126A (en) * | 2019-06-17 | 2019-09-27 | 浙江大学 | A kind of wafer surface defects subregion area detecting method of view-based access control model image |
-
2020
- 2020-06-04 CN CN202010501740.9A patent/CN111665261A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5949901A (en) * | 1996-03-21 | 1999-09-07 | Nichani; Sanjay | Semiconductor device image inspection utilizing image subtraction and threshold imaging |
| JPH10246704A (en) * | 1997-03-04 | 1998-09-14 | Nippon Steel Corp | Method and apparatus for inspecting semiconductor wafer |
| WO2001022070A1 (en) * | 1999-09-20 | 2001-03-29 | Matsushita Electric Industrial Co., Ltd. | Method and system of lcd inspection by pattern comparison |
| JP2007266448A (en) * | 2006-03-29 | 2007-10-11 | Fujitsu Ltd | Inspection method of ferroelectric film and manufacturing method of semiconductor device having inspection process |
| CN109978839A (en) * | 2019-03-08 | 2019-07-05 | 浙江大学 | The detection method of the low texture defect of wafer |
| CN110286126A (en) * | 2019-06-17 | 2019-09-27 | 浙江大学 | A kind of wafer surface defects subregion area detecting method of view-based access control model image |
Non-Patent Citations (4)
| Title |
|---|
| 宋方堃 等: "基于CCD 技术的生产线自动分选系统软件设计", 《机械制造与自动化》, vol. 43, no. 6, pages 133 - 135 * |
| 张传凯: "基于机器视觉的LED芯片定位与检测技术研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》, no. 2017, pages 138 - 4365 * |
| 张秀珍: "彩色印刷品缺陷检测方法研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》, no. 2016, pages 138 - 7038 * |
| 栾悉道 等: "《多媒体情报处理数据》", 31 May 2016, 国防工业出版社, pages: 45 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538586A (en) * | 2021-09-14 | 2021-10-22 | 武汉精创电子技术有限公司 | Grain row and column positioning method, device and system and computer readable storage medium |
| CN113538586B (en) * | 2021-09-14 | 2021-11-23 | 武汉精创电子技术有限公司 | Grain row and column positioning method, device and system and computer readable storage medium |
| CN114130709A (en) * | 2021-10-14 | 2022-03-04 | 佛山市国星半导体技术有限公司 | LED crystal grain appearance detection method |
| CN114130709B (en) * | 2021-10-14 | 2023-06-02 | 佛山市国星半导体技术有限公司 | LED crystal grain appearance detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107941808B (en) | 3D printing forming quality detection system and method based on machine vision | |
| CN111665261A (en) | Chip crystal grain detection method based on machine vision | |
| CN111242938B (en) | Automatic checking method for state of pressing plate | |
| US20090067701A1 (en) | System and method for detecting blemishes on surface of object | |
| CN110702035A (en) | Household appliance spraying quality detection system and method based on surface structured light | |
| CN113608378B (en) | Full-automatic defect detection method and system based on LCD (liquid crystal display) process | |
| CN109227352B (en) | Substrate defect repairing method and system | |
| CN110567968A (en) | part defect detection method and device | |
| CN108508022B (en) | Multi-camera splicing imaging detection method | |
| CN107993223A (en) | Scratch detection method, apparatus and electronic equipment | |
| CN108489989A (en) | The two-sided appearance detecting instrument of photovoltaic module based on the detection of polyphaser joining image-forming | |
| CN107248151B (en) | Intelligent liquid crystal display detection method and system based on machine vision | |
| CN117368214A (en) | Linear scanning PE coating detection method and visual detection device | |
| US8345965B2 (en) | Method and apparatus for positioning edges of photograph | |
| CN115731195A (en) | Defect detection method, device, equipment and system | |
| CN111242869B (en) | Method for background filtering of photo | |
| CN110930380B (en) | Defect observation machine and image analysis compensation method thereof | |
| CN108470326B (en) | Image completion method and device | |
| CN109447955B (en) | ROI segmentation method for lighting detection of mobile phone backlight module | |
| CN207946371U (en) | The two-sided appearance detecting instrument of photovoltaic module | |
| TWI780465B (en) | Defect-inspecting method of goggles and a system thereof | |
| KS et al. | Designing an affordable system for early defect detection using image processing | |
| CN114034706B (en) | Device and method for detecting surface defects of carbon fiber part | |
| CN213179855U (en) | Full-size detection device for battery | |
| CN110136148B (en) | Method and equipment for detecting and counting small pieces without silk-screen optical filter |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 230000 1st floor, no.6, Baihua industrial community, Wushan Town, Changfeng County, Hefei City, Anhui Province Applicant after: Anhui Anshi Intelligent Technology Co., Ltd Address before: 231100 No.5 ganghuai Road, Industrial Development Zone, Gangji Town, Changfeng County, Hefei City, Anhui Province Applicant before: Anhui Anshi Intelligent Technology Co., Ltd |