CN113888497A - Machine vision-based semiconductor refrigeration device detection, reading and matching system and method thereof - Google Patents
Machine vision-based semiconductor refrigeration device detection, reading and matching system and method thereof Download PDFInfo
- Publication number
- CN113888497A CN113888497A CN202111145730.7A CN202111145730A CN113888497A CN 113888497 A CN113888497 A CN 113888497A CN 202111145730 A CN202111145730 A CN 202111145730A CN 113888497 A CN113888497 A CN 113888497A
- Authority
- CN
- China
- Prior art keywords
- machine vision
- image
- camera
- semiconductor
- reading
- 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
- 239000004065 semiconductor Substances 0.000 title claims abstract description 105
- 238000005057 refrigeration Methods 0.000 title claims abstract description 50
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000001816 cooling Methods 0.000 claims abstract description 14
- 238000012937 correction Methods 0.000 claims abstract description 9
- 230000000007 visual effect Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 9
- 230000007797 corrosion Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 5
- 238000005498 polishing Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 6
- 238000011161 development Methods 0.000 description 13
- 230000018109 developmental process Effects 0.000 description 13
- 230000008569 process Effects 0.000 description 8
- 238000003384 imaging method Methods 0.000 description 7
- 230000007547 defect Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 241001292396 Cirrhitidae Species 0.000 description 5
- 238000013461 design Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000005286 illumination Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 241001270131 Agaricus moelleri Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000000547 structure data Methods 0.000 description 2
- 229960001685 tacrine Drugs 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- YLJREFDVOIBQDA-UHFFFAOYSA-N tacrine Chemical compound C1=CC=C2C(N)=C(CCCC3)C3=NC2=C1 YLJREFDVOIBQDA-UHFFFAOYSA-N 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10544—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum
- G06K7/10712—Fixed beam scanning
- G06K7/10722—Photodetector array or CCD scanning
- G06K7/10732—Light sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/80—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30148—Semiconductor; IC; Wafer
Abstract
The invention discloses a semiconductor refrigeration device detecting, reading and matching system based on machine vision and a method thereof, wherein the method comprises the steps of placing a semiconductor refrigeration device on a checkerboard with a known specification and acquiring a surface image of the semiconductor refrigeration device through an industrial camera; carrying out distortion correction restoration on the image by using machine vision software according to the specification of the checkerboard to obtain a real image; identifying the semiconductor refrigeration device based on the real image; judging whether a semiconductor refrigerating device needing to be matched exists or not; if so, positioning and identifying the unmatched semiconductor refrigeration device and identifying the two-dimensional code of the currently positioned semiconductor refrigeration device to obtain a character string; judging whether the currently positioned semiconductor refrigerator is matched with the correspondingly read character string; if yes, the result is output to the table. The invention can effectively read the semiconductor cooling device detection and the character string on the semiconductor cooling device.
Description
Technical Field
The invention relates to the technical field of semiconductor refrigeration device detection, in particular to a semiconductor refrigeration device detection, reading and matching system and a method thereof based on machine vision.
Background
With the continuous development of science and technology, mechanization and automation are more and more the choices of various factories. Machine vision is an indispensable technology for automatic development, and semiconductor refrigeration device detection has entered into the aspects of our lives with the development of society, and can be used for defect detection of semiconductor refrigeration devices.
The manufacturing industry development at abroad is early, and compared with the domestic industry, the technology and space to be developed at home are more perfect. Some defects which are difficult to distinguish by traditional vision are relatively difficult to solve, machine vision is not fully intelligent in development, and the application of the defects is limited to the industrial field.
Disclosure of Invention
The invention aims to provide a semiconductor refrigeration device detection reading matching system based on machine vision and a method thereof.
The technical scheme adopted by the invention is as follows:
the semiconductor refrigeration device detection, reading and matching system based on machine vision comprises a light source, a camera, an industrial personal computer and an upper computer, wherein the light source is used for polishing a semiconductor refrigeration device, the camera is used for acquiring and obtaining a surface image of the semiconductor refrigeration device and outputting the image to the industrial personal computer, the industrial personal computer is used for transmitting the image to the upper computer, machine vision software is configured on the upper computer, the semiconductor refrigeration device detection identification and character string identification are carried out, and matching structure data are output.
Further, the machine vision software is Halcon machine vision software, OpenCV machine vision software, VisionPro machine vision software or MIL machine vision software.
Further, the working distance of the camera is 180mm +/-5 mm; the visual field range of the camera is 230mm multiplied by 175 mm; the camera is 1000w pixels; the picture resolution is 4096 × 3000, and the bit depth is 8 bit; the single pixel precision is 0.056mm/pixel; the source angle is 50 degrees.
Further, the camera adopts a C-type or CS-type interface lens with 12 mm.
Further, the machine vision software employs VisionPro machine vision software.
The machine vision based semiconductor refrigeration device detecting, reading and matching method includes the following steps:
step 1, placing a semiconductor refrigeration device on a checkerboard with a known specification and acquiring a surface image of the semiconductor refrigeration device by an industrial camera;
step 2, carrying out distortion correction and restoration on the image by using machine vision software according to the specification of the checkerboard to obtain a real image;
and 3, identifying the semiconductor refrigerating device based on the real image, and specifically comprising the following steps:
step 3-1, carrying out gray level adjustment processing on the real image;
step 3-2, carrying out gray scale corrosion on the image subjected to gray scale adjustment to enlarge the area proportion of black in the image so as to enable the black to be easily distinguished;
3-3, identifying the detected position of the semiconductor refrigerating device according to the set black area;
step 4, judging whether a semiconductor refrigerating device needing to be matched exists; if yes, positioning and identifying the semiconductor cooling device which is not matched yet and executing the step 5; otherwise, finishing matching;
step 5, identifying the two-dimensional code of the currently positioned semiconductor refrigeration device to obtain a character string;
step 6, judging whether the semiconductor refrigerator positioned currently is matched with the character string read correspondingly; if yes, outputting to a table and executing the step 3; otherwise, the matching is ended.
Further, in the step 1, strip light sources are respectively arranged on two opposite sides above the semiconductor refrigeration device to polish the semiconductor refrigeration device, the distance between the two strip light sources is 380mm, and the included angle between the strip light sources and the horizontal plane is 50 degrees.
Further, in the step 1, the distance between the lens of the industrial camera and the upper surface of the semiconductor refrigerating device is ensured to be 180mm +/-5 mm; the visual field range of the camera is 230mm multiplied by 175 mm; the camera is 1000w pixels; the picture resolution is 4096 × 3000, and the bit depth is 8 bit; the single pixel precision is 0.056mm/pixel; the source angle is 50 degrees.
Furthermore, in the step 1, the checkerboard is placed at the image capturing position of the camera for image capturing, and the area of the captured image covers the whole visual field as much as possible.
Further, the machine vision software in the step 2 adopts VisionPro machine vision software.
Further, a positioning coordinate system is added in the space tree of the real image through a CogFixtureTool1 tool in the step 3, the coordinate system is beneficial to the tool to follow the picture, and the tool can be used for adjusting more intuitively and conveniently with the support of the coordinate system.
Further, in step 5, a CogIDTool decoding tool which is VisionPro is used for reading a plurality of one-dimensional codes in the same image so as to detect the semiconductor refrigeration device.
Furthermore, the CogIDTool tool provides two decoding algorithms, namely IDQuick, which is suitable for quickly reading codes with better quality and higher contrast; IDMax is suitable for reading some codes with poor image quality. The CogIDTool tool uses the IDMax algorithm by default.
Further, step 5 sets various forms of character strings and sets them as fixed character strings using the CogOCRMaxTool2 tool in order to match similar higher character strings.
By adopting the technical scheme, the semiconductor refrigeration device detection matching and detecting system developed by VisionPro software based on machine vision can realize the basic requirements and functions of the design and can effectively read the detection and character strings of the semiconductor refrigeration device on the semiconductor refrigeration device.
Drawings
The invention is described in further detail below with reference to the accompanying drawings and the detailed description;
FIG. 1 is a schematic diagram of a machine vision system;
FIG. 2 is a schematic diagram of the actual installation and use of the machine vision system;
FIG. 3 is a schematic top view of a machine vision system in actual installation and use;
fig. 4 is a schematic flow chart of the semiconductor cooling device detection, reading and matching method based on machine vision according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
The detection identification of the semiconductor refrigeration device is an indispensable part in the production process, the flaw detection is convenient, the data recording of the semiconductor refrigeration device is convenient, meanwhile, along with the international pressure and development opportunities, the development of intelligent manufacturing is a common target of the industrial era, the machine vision is an essential tool in the automatic upgrading process, the error can be effectively reduced, the precision of each numerical value of the semiconductor refrigeration device is improved, and therefore the international competitiveness of the semiconductor refrigeration device in China is greatly improved.
Machine vision detects and has multiple advantages than naked eye detection: (1) machine vision possesses long-term stability, and compared with artificial vision fatigue, machine vision is not tired. (2) Machine vision can be used for detection of higher precision, and a camera with higher precision can have pictures with higher resolution ratio for processing, so that compared with manual detection, the method has higher precision, and a plurality of tiny defects can be detected. (3) Not only detection, but also machine vision can be positioned and interacted with a robot hand to realize automatic development.
Labor power can be better liberated, talents are put on more posts to promote the upgrading of industrial structures, the reduction of labor cost of factories is beneficial to improving the international competitiveness of semiconductor refrigerating devices in China, the semiconductor refrigerating devices have more competitiveness in quantity and quality, profits are obtained and put into the upgrading of manufacturing, and China is led to move to the strong manufacturing lines and ranks more quickly.
The invention discloses a semiconductor refrigerating device detection, reading and matching system based on machine vision, which comprises a light source, a camera, an industrial personal computer and an upper computer, wherein the light source is used for polishing a semiconductor refrigerating device, the camera is used for acquiring and acquiring a surface image of the semiconductor refrigerating device and outputting the image to the industrial personal computer, the industrial personal computer is used for transmitting the image to the upper computer, machine vision software is configured on the upper computer, the semiconductor refrigerating device detection identification and character string identification are carried out, and matching structure data are output.
Specifically, the light of the light source can be red light or blue light, but the blue light is more advantageous for detecting the defect. The red light wavelength is 650nm, and the blue light wavelength is 405 nm. Smaller wavelengths (higher frequencies) allow more efficient testing of nano-scale defects. Blue light is known for its detection of flaws using a blue laser with a shorter wavelength. The blue light greatly improves the accuracy of detection, and the blue light provides an opportunity for detecting the development of semiconductor refrigeration devices.
Further, the machine vision software is Halcon machine vision software, OpenCV machine vision software, VisionPro machine vision software or MIL machine vision software.
Further, the working distance of the camera is 180mm +/-5 mm; the visual field range of the camera is 230mm multiplied by 175 mm; the camera is 1000w pixels; the picture resolution is 4096 × 3000, and the bit depth is 8 bit; the single pixel precision is 0.056mm/pixel; the source angle is 50 degrees.
Further, the camera adopts a C-type or CS-type interface lens with 12 mm.
Further, the machine vision software employs VisionPro machine vision software.
The machine vision based semiconductor refrigeration device detecting, reading and matching method includes the following steps:
step 1, placing a semiconductor refrigeration device on a checkerboard with a known specification and acquiring a surface image of the semiconductor refrigeration device by an industrial camera;
step 2, carrying out distortion correction and restoration on the image by using machine vision software according to the specification of the checkerboard to obtain a real image;
and 3, identifying the semiconductor refrigerating device based on the real image, and specifically comprising the following steps:
step 3-1, carrying out gray level adjustment processing on the real image;
step 3-2, carrying out gray scale corrosion on the image subjected to gray scale adjustment to enlarge the area proportion of black in the image so as to enable the black to be easily distinguished;
3-3, identifying the detected position of the semiconductor refrigerating device according to the set black area;
step 4, judging whether a semiconductor refrigerating device needing to be matched exists; if yes, positioning and identifying the semiconductor cooling device which is not matched yet and executing the step 5; otherwise, finishing matching;
step 5, identifying the two-dimensional code of the currently positioned semiconductor refrigeration device to obtain a character string;
step 6, judging whether the semiconductor refrigerator positioned currently is matched with the character string read correspondingly; if yes, outputting to a table and executing the step 3; otherwise, the matching is ended.
Further, in the step 1, strip light sources are respectively arranged on two opposite sides above the semiconductor refrigeration device to polish the semiconductor refrigeration device, the distance between the two strip light sources is 380mm, and the included angle between the strip light sources and the horizontal plane is 50 degrees.
Further, in the step 1, the distance between the lens of the industrial camera and the upper surface of the semiconductor refrigerating device is ensured to be 180mm +/-5 mm; the visual field range of the camera is 230mm multiplied by 175 mm; the camera is 1000w pixels (pixels); the picture resolution is 4096 × 3000, and the bit depth is 8 bit; the single pixel precision is 0.056mm/pixel; the source angle is 50 degrees.
Furthermore, in the step 1, the checkerboard is placed at the image capturing position of the camera for image capturing, and the area of the captured image covers the whole visual field as much as possible.
Further, the machine vision software in the step 2 adopts VisionPro machine vision software.
Further, a positioning coordinate system is added in the space tree of the real image through a CogFixtureTool1 tool in the step 3, the coordinate system is beneficial to the tool to follow the picture, and the tool can be used for adjusting more intuitively and conveniently with the support of the coordinate system.
Further, in step 5, a CogIDTool decoding tool which is VisionPro is used for reading a plurality of one-dimensional codes in the same image so as to detect the semiconductor refrigeration device.
Furthermore, the CogIDTool tool provides two decoding algorithms, namely IDQuick, which is suitable for quickly reading codes with better quality and higher contrast; IDMax is suitable for reading some codes with poor image quality. The CogIDTool tool uses the IDMax algorithm by default.
Further, step 5 sets various forms of character strings and sets them as fixed character strings using the CogOCRMaxTool2 tool in order to match similar higher character strings.
The following is a detailed description of the specific working principle of the present invention:
as shown in fig. 1, a basic vision system includes a camera, a light source, a lens, an industrial personal computer and other hardware, and necessary vision software is added, a semiconductor refrigeration device is converted into a digital signal through the camera, the digital signal is processed by the software, a result is sent to an upper computer, and the upper computer of a machine station receives a signal and judges the quality of the semiconductor refrigeration device according to a protocol. This is the basic flow of a vision workstation. With the development of science and technology, a plurality of embedded cameras are also provided, the intelligent cameras can complete some basic processes and directly process, a plurality of steps are omitted, but the processing capacity is lower than that of the traditional method, and the method is suitable for small machines or simple processing.
Industrial cameras are one of the basic components of a vision system, which is used to convert optical signals into electrical signals. Some parameters are of major interest when selecting a camera: (1) resolution ratio: the number of pixel points of the image collected by the camera; (2) pixel depth: the number of pixel data bits, typically 8bit, 10bit, 12bit, etc.; (3) exposure and shutter speed: the larger the exposure is, the brighter the picture is, but the image taking time of the camera is increased; (4) frame rate: the speed at which the camera transmits the image; (5) phase source size (6) spectral response characteristics: different characteristics exhibited by light of different wavelengths
Halcon Machine Vision software, Halcon is a complete set of standard Machine Vision algorithm package (commercial use) developed by MVtec corporation in Germany, is recognized as Machine Vision software with the best efficiency in the industry of Europe and Japan, and Halcon supports Windows, Linux and Mac OS X operating environments; the programming interface supports C, C + +, CCP.net, Delphi, C #, VB.net and other programming languages.
OpenCV machine vision software, OpenCV is a cross-platform computer vision library (open source use); the programming interface supports C, C + +, Python, C #, Java and other programming languages.
VisionPro machine vision software, VisionPro is machine vision software (commercially available) developed by Cognex corporation, USA; the programming interface supports C + +, C #, VB.net and other programming languages [9 ].
MIL machine vision software, MIL is a machine vision software (commercial use) developed by Matrox corporation, canada; the programming interface supports programming languages such as C + +, C #, VB.net and the like.
The invention adopts VisionPro machine vision software to be combined with C #, and the development mode is as follows: the first development mode has low programming requirements, is fast, can use Quickbuild to modify vision, work, input and output, but is flexible and low. The second type of application, which is easy to customize, requires some programming but also has framework limitations. The third degree of freedom allows full control of the operator interface. The fourth uses API direct customization with complete freedom. The reasonable selection in the actual process can save the development cost and ensure the work to be smoother.
Hardware of the whole system: the method comprises the following steps of positioning and detecting a target semiconductor refrigerating device, detecting the semiconductor refrigerating device, detecting a character string and matching, and has the following functions and requirements: (1) the whole height does not exceed 1 meter due to the limited working space; (2) the field of view is about 20mm by 20 mm; (3) the single pixel precision does not exceed 1 mm/pixel; (4) the accuracy is higher than 95%.
As shown in fig. 2 or 3, the final hardware solution based on the above requirements is as follows: as shown in table 1, according to the actual situation: the working distance of the camera is 180mm +/-5 mm; the visual field range of the camera is 230mm multiplied by 175 mm; the camera is 1000w pixels; the picture resolution is 4096 × 3000, and the bit depth is 8 bit; the single pixel precision is about 0.056mm/pixel; the source angle is about 50 degrees.
TABLE 1 Vision parameters
| Hardware | Parameter(s) |
| Visual field | 230mm×175mm |
| Camera with a camera module | 1000w pixels、4096×3000 pixel2 |
| Lens barrel | 12mm |
| Light source | Stripe light x2 |
| Working distance of camera | 180mm |
| Working distance of light source | 125mm |
| Single pixel accuracy | 0.056mm/pixel |
Selecting the type of the camera, wherein a hardware system selects an area array industrial camera, and the main parameters are as follows:
(1) the pixel depth of the area array industrial camera is used for defining gray scales of light and shade with different gray scales, the darkest numerical value of the 8-bit camera is 0, and the brightest numerical value is 255. Values between 0 and 255 represent indices of different luminance values. In addition, 10 bits and 12 bits are 1024 gray levels and 4096 gray levels respectively. 8 bits, 10 bits or 12 bits can be selected according to requirements, and the higher value can enhance the measurement precision and also can influence the processing time of the system. This time, an 8bit camera [10] was used.
(2) A camera shutter:
the mechanical shutter controls imaging by means of a machine, and light enters the camera for imaging by opening and closing the shutter.
An electronic shutter: a circuit is used to manipulate the exposure of the CCD/CMOS control shutter. The CCD/CMOS is utilized to work only by electrifying, and when no current passes through the CCD, no image is formed no matter the CCD is opened, which is equivalent to no image. When the CCD/CMOS is powered on by using an electronic time circuit, the shutter is opened and closed. Compared with a mechanical shutter, the electronic shutter is faster in imaging and shorter in snapshot time, and the mechanical shutter has the advantage of being capable of working without being electrified. The design adopts an electronic shutter (11).
(3) Chip sizes are shown in table 2:
TABLE 2 chip size
Selecting a lens: the size of the lens interface is internationally unified, and the types of the lens interface are generally three, namely an F-type interface, a C-type interface and a CS-type interface. An F-type interface is typically used for lenses with focal lengths greater than 25 mm; lenses with focal length less than 25mm typically use either a C-type or CS-type interface, and the lenses of both interfaces are not large in size and are more suitable.
And various lenses are selected for comparison, and the difference of the visual field ranges of different lenses is obvious. The 12mm lens field of view is approximately 230mm by 175mm depending on the choice of field of view, while the 25mm lens field of view is less than 200mm and differs significantly. And the lens of 24mm is not convenient for the overall design of the system to have a lens of 12mm in terms of working distance and depth of field, and the lens of 12mm is finally selected according to data obtained by a plurality of different actual lens experiments.
Light source selection and lighting mode: the light source may be classified into a back illumination, a front illumination, a structured light, a strobe illumination, and the like according to its irradiation manner. The back lighting is that the light source is behind the measured object, its advantage is to enable the image acquisition to have higher contrast; the forward illumination is that the light source is at the same side as the camera, and the light source is convenient to install; the structured light illumination is to project a grating or a line light source on a measured object to modulate three-dimensional information of the measured object; the stroboscopic light irradiates a high-frequency light pulse on an object, and can effectively shoot the object moving at high speed.
Designing image processing software: as shown in fig. 4, the image is taken, the acquired image is corrected, and the semiconductor cooling device is positioned, and each positioned semiconductor cooling device performs the identification of the detection of the semiconductor cooling device and the identification of the character string, and the data of the two devices are matched and output to the table.
GigE configuration in VisionPro: GigE Vision is a camera interface standard developed based on the gigabit ethernet communication protocol. In industrial machine Vision semiconductor cooling device applications, GigE Vision allows users to perform fast image transmission over long distances using inexpensive standard cables.
The camera and the computer use the network port to connect and start the Cognex GigE Vision Configurator setting network port in the menu bar, and the IP address of the computer and the IP address of the camera need to be in the same network segment. The Host IP is consistent with the first three bits of the IP address, the last bit is optional, the Host subnet needs to be consistent with the subnet and then click the Update, and when one industrial personal computer is connected with the multiple cameras, the third bits of all the network ports need to be different.
Detailed design: specifically, the following functions are included.
(1) The CogCalibCheckeroardTool 1 tool: the present invention uses the calibcockboard tool, distortion correction. Because the chip processes of the lens and the camera imaging are different, the lens and the camera imaging are limited by the manufacturing process and the precision and can generate distortion in the imaging process, and the adopted camera and the lens can generate distortion due to the height limitation of the invention. When distortion occurs, distortion correction is usually performed by using a CalibCheckerbard tool, the principle is that a checkerboard is placed at the image capturing position of a camera for image capturing, the area of the captured image covers the whole visual field as much as possible, because the specification of the checkerboard is certain (for example, the specification used for the distortion correction is 3x3), a corresponding relation between the image and the reality can be formed according to the proportion through the distortion correction, and then the captured semiconductor refrigeration device can be restored to be a more real image through the distortion correction.
(2) The CogPixelMapTool 1: the CogPixelMapTool tool is used to change the gray scale value of the picture phase, facilitating processing. The effect can be achieved by increasing the exposure, but increasing the exposure time can slow the image capturing speed, in the present invention, the speed of the semiconductor cooling device is required, and if the exposure time is increased blindly or the light source intensity is adjusted, the image capturing time is too long, which may cause the semiconductor cooling device to miss and leak. Therefore, a gray scale adjustment tool is added, and the picture may be distorted by using gray scale adjustment, but the influence can be ignored in the process of the invention, but the image taking environment requiring high precision needs to pay attention.
(3) The cogiponemagetool 1: the CogIPOneImageTool tool is used for carrying out algorithm processing on a single picture and comprises the following components: addition and subtraction constants, convolution 3x3, convolution n x m, equalization, expansion, flip/rotate, gaussian sampler, gray scale shape adjustment, high pass filter, 3x3 median, missing pixels, pixel mapping, quantization, sample convolution, subsampler, etc.
The invention uses corrosion in gray scale form adjustment, the corrosion can enlarge the black area in imaging according to a certain range proportion, and the black position can be better distinguished when the next tool is used for running, so that the program is more stable.
(4) CogBlobTool1 tool: the CogBlobTool1 tool is one of the commonly used tools. The method can detect and position the shape in a certain gray scale range in the image, can be used for obtaining the information such as the shape, the number, the central position and the like, can select the required area range according to the set gray scale value threshold, eliminates unnecessary miscellaneous items by setting numerical values, selects the area in a certain range, can effectively find the required target value, and is a very convenient tool. The size of the black area is set according to the following graph, and the detection position of the semiconductor refrigerating device can be accurately identified and transmitted to the identification tool by searching the detection area of the semiconductor refrigerating device in a reasonable area.
(5) The CogFixtureTool1 tool: the CogFixtureTool tool can add a positioning coordinate system into the space tree, can also provide an output image after positioning for other tools to call, and the coordinate system is favorable for the tools to follow the picture, so that the tool can be more intuitively and conveniently used for adjustment by the aid of the support of the coordinate system in the running process.
(6) CogIDTool1 tool: the CogIDTool tool is an important decoding tool of VisionPro, can read a plurality of one-dimensional codes in the same image, and is used for detecting a semiconductor refrigerating device. The CogIDTool tool provides two decoding algorithms
The IDQuick is suitable for fast reading codes with better quality and higher contrast.
IDMax is suitable for reading some codes with poor image quality.
The CogIDTool tool uses the IDMax algorithm by default.
(7) The CogOCRMaxTool2 tool: the CogOCRMaxTool tool supports a set of parameters that dictate how characters and backgrounds and characters are separated, which need to be set taking into account factors such as distance between characters, character type, image quality, etc., and generally, default segmentation parameters do not adequately segment characters.
The training system has some default character string information to distinguish most character strings, but because the gray value of the image and the form of the character strings are different, character strings which can not be distinguished usually exist, the strong function of the OCR tool is embodied at the moment, the character strings in various forms can be set into fixed character strings, and the character strings are matched with similar higher character strings according to the algorithm.
By adopting the technical scheme, the semiconductor refrigeration device detection matching and detecting system developed by VisionPro software based on machine vision can realize the basic requirements and functions of the design and can effectively read the detection and character strings of the semiconductor refrigeration device on the semiconductor refrigeration device.
It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. The embodiments and features of the embodiments in the present application may be combined with each other without conflict. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the detailed description of the embodiments of the present application is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. 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 application.
Claims (10)
1. The machine vision-based semiconductor refrigeration device detection, reading and matching method is characterized by comprising the following steps of: which comprises the following steps:
step 1, placing a semiconductor refrigeration device on a checkerboard with a known specification and acquiring a surface image of the semiconductor refrigeration device by an industrial camera;
step 2, carrying out distortion correction and restoration on the image by using machine vision software according to the specification of the checkerboard to obtain a real image;
and 3, identifying the semiconductor refrigerating device based on the real image, and specifically comprising the following steps:
step 3-1, carrying out gray level adjustment processing on the real image;
step 3-2, carrying out gray scale corrosion on the image subjected to gray scale adjustment to enlarge the area proportion of black in the image so as to enable the black to be easily distinguished;
3-3, identifying the detected position of the semiconductor refrigerating device according to the set black area;
step 4, judging whether a semiconductor refrigerating device needing to be matched exists; if yes, positioning and identifying the semiconductor cooling device which is not matched yet and executing the step 5; otherwise, finishing matching;
step 5, identifying the two-dimensional code of the currently positioned semiconductor refrigeration device to obtain a character string;
step 6, judging whether the semiconductor refrigerator positioned currently is matched with the character string read correspondingly; if yes, outputting to a table and executing the step 3; otherwise, the matching is ended.
2. The machine vision based semiconductor cooler inspection reading matching method according to claim 1, wherein: in the step 1, strip light sources are respectively arranged on two opposite sides above the semiconductor refrigerating device to polish the semiconductor refrigerating device, the distance between the two strip light sources is 380mm, and the included angle between the strip light sources and the horizontal plane is 50 degrees; the distance between the lens of the industrial camera and the upper surface of the semiconductor refrigerating device is ensured to be 180mm +/-5 mm; the visual field range of the camera is 230mm multiplied by 175 mm; the camera is 1000w pixels; the picture resolution is 4096 × 3000, and the bit depth is 8 bit; the single pixel precision is 0.056mm/pixel, and the light source angle is 50 degrees.
3. The machine vision based semiconductor cooler inspection reading matching method according to claim 1, wherein: in the step 1, the checkerboard is placed at the image capturing position of a camera for image capturing, and the area of the captured image covers the whole visual field as much as possible.
4. The machine vision based semiconductor cooler inspection reading matching method according to claim 1, wherein: and the machine vision software in the step 2 adopts VisionPro machine vision software.
5. The machine vision based semiconductor cooler inspection reading matching method according to claim 1, wherein: in step 3, a positioning coordinate system is added to the spatial tree of the real image by the CogFixtureTool1 tool.
6. The machine vision based semiconductor cooler inspection reading matching method according to claim 1, wherein: in step 5, a CogIDTool decoding tool which is VisionPro is adopted to read a plurality of one-dimensional codes in the same image so as to detect the semiconductor refrigeration device.
7. The machine vision based semiconductor cooler inspection reading matching method according to claim 1, wherein: step 5 sets various forms of strings and sets them as fixed strings using the CogOCRMaxTool2 tool in order to match similar higher strings.
8. The machine vision-based semiconductor cooling device detection, reading and matching system adopts the machine vision-based semiconductor cooling device detection, reading and matching method of claim 1, and is characterized in that: the system comprises a light source, a camera, an industrial personal computer and an upper computer, wherein the light source is used for polishing the semiconductor refrigerating device, the camera is used for acquiring and acquiring a surface image of the semiconductor refrigerating device and outputting the image to the industrial personal computer, the industrial personal computer is used for transmitting the image to the upper computer, machine vision software is configured on the upper computer, recognition of detection of the semiconductor refrigerating device and recognition of character strings are carried out, and data of a matching structure are output.
9. The machine-vision-based semiconductor cooler inspection-reading-matching system of claim 8, wherein: the working distance of the camera is 180mm +/-5 mm; the visual field range of the camera is 230mm multiplied by 175 mm; the camera is 1000w pixels; the picture resolution is 4096 × 3000, and the bit depth is 8 bit; the single pixel precision is 0.056mm/pixel, and the light source angle is 50 degrees; the camera adopts a C-type or CS-type interface lens with 12 mm.
10. The machine-vision-based semiconductor cooler inspection-reading-matching system of claim 8, wherein: the machine vision software adopts VisionPro machine vision software.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111145730.7A CN113888497A (en) | 2021-09-28 | 2021-09-28 | Machine vision-based semiconductor refrigeration device detection, reading and matching system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111145730.7A CN113888497A (en) | 2021-09-28 | 2021-09-28 | Machine vision-based semiconductor refrigeration device detection, reading and matching system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113888497A true CN113888497A (en) | 2022-01-04 |
Family
ID=79007560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111145730.7A Pending CN113888497A (en) | 2021-09-28 | 2021-09-28 | Machine vision-based semiconductor refrigeration device detection, reading and matching system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113888497A (en) |
-
2021
- 2021-09-28 CN CN202111145730.7A patent/CN113888497A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6946188B2 (en) | Methods and equipment for multi-technology depth map acquisition and fusion | |
| US10373305B2 (en) | Positioning method for searching a previously registered standard pattern out of an inspection target image | |
| CN107945152A (en) | The defects of industrial camera detecting and controlling system and method | |
| US11295434B2 (en) | Image inspection system and image inspection method | |
| CN109856164B (en) | Optimization device for acquiring large-range images by machine vision and detection method thereof | |
| CN111624203B (en) | Relay contact point alignment non-contact measurement method based on machine vision | |
| CN114445330A (en) | Method and system for detecting appearance defects of components | |
| JP6405124B2 (en) | Inspection device, inspection method, and program | |
| CN105509657B (en) | A kind of high-precision measuring method of IC card chip scratch area and gray scale parameter | |
| CN114280075A (en) | Online visual inspection system and method for surface defects of pipe parts | |
| CN110570412B (en) | Part error vision judgment system | |
| CN109870463B (en) | Electronic chip fault detection device | |
| CN107833223B (en) | Fruit hyperspectral image segmentation method based on spectral information | |
| JP6585793B2 (en) | Inspection device, inspection method, and program | |
| CN107145741A (en) | Ear based on graphical analysis examines collecting method and device | |
| CN113888497A (en) | Machine vision-based semiconductor refrigeration device detection, reading and matching system and method thereof | |
| US11012612B2 (en) | Image inspection system and image inspection method | |
| CN116908185A (en) | Method and device for detecting appearance defects of article, electronic equipment and storage medium | |
| CN116781881A (en) | Real-time three-dimensional vision imaging system based on microscope | |
| CN105548210A (en) | Detection method for American-standard power source extension wire based on machine vision | |
| CN115801942A (en) | Automatic detection system of cell-phone | |
| Shreya et al. | Design of machine vision system for high speed manufacturing environments | |
| CN114022820A (en) | Intelligent beacon light quality detection method based on machine vision | |
| CN111189836A (en) | Labview-based product defect detection method | |
| CN109931881A (en) | Image processing system, computer readable recording medium and image processing method |
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 |