CN106290394B - System and method for detecting aluminum extrusion molding defects of CPU radiator - Google Patents
System and method for detecting aluminum extrusion molding defects of CPU radiator Download PDFInfo
- Publication number
- CN106290394B CN106290394B CN201610877132.1A CN201610877132A CN106290394B CN 106290394 B CN106290394 B CN 106290394B CN 201610877132 A CN201610877132 A CN 201610877132A CN 106290394 B CN106290394 B CN 106290394B
- Authority
- CN
- China
- Prior art keywords
- image
- extrusion molding
- aluminum extrusion
- computer
- correlation coefficient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
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
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
-
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G01N2021/8854—Grading and classifying of flaws
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a CPU radiator aluminum extrusion molding defect detection system, which comprises an image acquisition device, a computer image identification device and a computer detection display device; the invention also discloses a detection method applied to the CPU radiator aluminum extrusion molding defect detection system, which comprises the following steps: A. carrying out image acquisition on an aluminum extrusion molding product; B. sending the image data to a computer; C. carrying out filtering pretreatment on the image; D. carrying out gray level conversion processing on the image; E. classifying and identifying the image after the gray level processing; F. displaying the recognition result; I. and storing the identification result. The invention has the advantages of greatly improving the accuracy, reliability and efficiency of detection, improving the qualification rate of products and the like.
Description
Technical Field
The invention relates to a CPU radiator aluminum extrusion molding defect detection system and method, in particular to a CPU radiator aluminum extrusion molding defect detection system and method based on machine vision.
Background
In the running process of the computer, the CPU can generate a large amount of heat, and if the heat is not removed in time to reduce the working temperature of the CPU, the running performance of the computer can be adversely affected. With the increase of the speed of the CPU, the heat dissipation requirement of the heat radiator is continuously increased, and the heat radiator gradually develops towards the direction of dense teeth and high teeth. The CPU radiator generally adopts an aluminum extrusion template method to prepare an aluminum extrusion section, the traditional aluminum extrusion template method achieves the purpose of controlling the flow speed of aluminum flow by adjusting the height and the width of a working belt, the problem that the dense tooth plates cause insufficient supporting strength of steel materials exists, and the ratio of the height of the tooth plates to the distance between the tooth plates can only reach 15 times to the maximum. And then, a non-working-belt aluminum extrusion die appears, so that the density of the tooth plates is greatly improved, the ratio of the height of the tooth plates to the distance between the tooth plates is increased to more than 20 times, but the aluminum extrusion product is easy to distort and deform in the aluminum extrusion process, and surface defects such as adsorption particles, bubbles, metal burrs, unsmooth surface and the like appear, which all affect the heat dissipation performance of the radiator. The published data shows that most of the defect detection of the aluminum extrusion molding products adopts a manual detection method in the aluminum extrusion molding process at present, whether the products have defects is detected by means of human eye observation and experience, and the method has strong subjectivity, lacks accuracy and reliability, has low efficiency and cannot realize automatic detection. Therefore, it is necessary to adopt accurate technical means for detection.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides the detecting system for the defects of the aluminum extrusion molding of the CPU radiator, which has high defect detecting efficiency and precision and high detecting reliability.
The invention aims to overcome the defects of the prior art and provide a detection method applied to a CPU radiator aluminum extrusion molding defect detection system. The primary purpose of the invention is realized by the following technical scheme: a CPU radiator aluminum extrusion molding defect detection system comprises an image acquisition device, a computer image recognition device and a computer detection display device, wherein the image acquisition device is connected with the computer image recognition device, the computer image recognition device is connected with the computer detection display device, the image acquisition device comprises a CCD1 industrial camera, a CCD2 industrial camera, a first image acquisition card and a second image acquisition card, the computer image recognition device comprises an image processing module and a template matching module, the computer image recognition device is used for completing image preprocessing, gray level transformation and template matching identification, the computer detection display device comprises a detection display module and a storage module, the computer detection display device is used for displaying and storing a detection result, the output end of the CCD1 industrial camera is connected with the input end of the first image acquisition card, the output end of the CCD2 industrial camera is connected with the input end of the second image acquisition card, and the output ends of the first image acquisition card and the second image acquisition card are both connected with the RS232 serial port of a computer; the first image acquisition card is combined with a CCD1 industrial camera, the surface image data of the aluminum extrusion molding product is transmitted to a computer image recognition device through an RS232 serial port, the second image acquisition card is combined with a CCD2 industrial camera, the deformation image data of the aluminum extrusion molding product is transmitted to the computer image recognition device through the RS232 serial port, the computer image recognition device processes and recognizes the received image data and transmits the image recognition result to a computer detection display device, the detection display module displays the surface image recognition result and the deformation image recognition result, and the storage module stores the surface image recognition result and the deformation image recognition result.
The CCD1 industrial camera is used for detecting the surface defects of the aluminum extrusion molding products, and the CCD2 industrial camera is used for detecting the deformation of the aluminum extrusion molding products.
Still include aluminium extrusion die, aluminium extrusion die include aluminium crowded steel body, feed inlet, empty sword area and discharge gate are arranged in proper order and are link up the crowded steel body of aluminium, CCD1 industry camera install in the top of discharge gate, CCD2 industry camera is installed in the dead ahead of discharge gate.
The other purpose of the invention is realized by the following technical scheme: a detection method applied to the CPU radiator aluminum extrusion molding defect detection system comprises the following steps:
H. carrying out image acquisition on an aluminum extrusion molding product;
I. sending the image data to a computer;
J. carrying out filtering pretreatment on the image;
K. carrying out gray level conversion processing on the image;
l, classifying and identifying the image after gray processing;
m, displaying the identification result;
and N, storing the identification result.
In the step A, the first image acquisition card finishes the top view image acquisition of the aluminum extrusion molding product from the top through a CCD1 industrial camera, and the second image acquisition card finishes the front view image acquisition of the aluminum extrusion molding product from the front through a CCD2 industrial camera.
In step B, the image data is transmitted to the computer by adopting an RS232 serial port.
In step C, a gaussian filtering method is used to complete the filtering processing of the two images.
In step E, completing the classification and identification of the image by adopting a template matching algorithm, wherein the classification and identification steps are as follows:
d. selecting a standard aluminum extrusion molding product image without defects as a standard matching template image;
e. b, carrying out position matching on the acquired image to enable the image to be completely corresponding to the position of the standard matching template image in the step a;
f. b, matching the acquired image with the standard matching template image selected in the step a, calculating a correlation coefficient of the acquired image and the standard matching template image by adopting a correlation coefficient matching method, and comparing the calculated correlation coefficient with a correlation coefficient threshold value to determine whether the aluminum extrusion molding product is a defective product; the calculation formula is specifically as follows:
assuming that the collected image and the standard matching template image both have m × n pixels, the cross-correlation between the collected image and the standard matching template image is measured by using the following formula, and D represents the correlation:
wherein m represents the total pixel points in the abscissa direction of the collected image and the standard matching template image, n represents the total pixel points in the ordinate direction of the collected image and the standard matching template image, point i represents the abscissa, the range of i is 1 to m, j represents the ordinate, the range of j is 1 to n, T represents the standard matching template image, T (i, j) represents the gray value of the pixel point at (i, j) of the coordinate in the standard matching template image, S represents the collected image, and S (i, j) represents the gray value of the pixel point at (i, j) of the coordinate in the standard matching template image;
normalizing the correlation coefficient to obtain a template matching correlation coefficient, wherein R represents the correlation coefficient:
and calculating by adopting the formula to obtain a correlation coefficient of template matching, comparing the correlation coefficient R with a set correlation coefficient threshold, if the correlation coefficient R is greater than the correlation coefficient threshold, successfully matching, and indicating that the product is qualified, otherwise, determining that the matching is failed, and indicating that the product is unqualified.
The detection device of the present invention comprises: the computer image recognition device comprises a computer provided with image processing and analyzing software, and the computer detection display device displays and stores the detection result. The system adopts a machine vision detection technology to preprocess the acquired image of the aluminum extrusion molding product, adopts an image template matching technology to complete the detection of the aluminum extrusion molding product, greatly improves the accuracy, reliability and efficiency of the detection, and utilizes a detection result display system of the system, an operator can timely detect and process the aluminum extrusion mold according to the detection result, the quality of the follow-up aluminum extrusion molding product is ensured, and the qualification rate of the product is improved.
In the invention, a CCD camera, an image acquisition card and a computer are sequentially connected to form a control system, the CCD industrial camera comprises a CCD1 industrial camera and a CCD2 industrial camera, the CCD1 industrial camera is arranged above a discharge port of an aluminum extrusion die and is used for detecting the surface defects of an aluminum extrusion forming product, and the CCD2 industrial camera is arranged in front of the discharge port of the aluminum extrusion die and is used for detecting whether the aluminum extrusion forming product is distorted or not. The image acquisition card comprises a first image acquisition card and a second image acquisition card, and is respectively matched with a CCD1 industrial camera and a CCD2 industrial camera to realize image acquisition, the acquired images comprise an image 1 and an image 2, the image 1 is an upward view image of the aluminum extrusion molding product, and the image 2 is an orthographic view image of the aluminum extrusion molding product. The image acquisition card transmits image data to a computer image identification device through an RS232 serial port, the computer image identification device performs filtering pretreatment and gray level conversion treatment on the received image, and adopts a template matching algorithm, firstly, a standard aluminum extrusion molding product image without defects is selected as a standard matching template image, then, the position of the acquired image is matched to be completely corresponding to the position of the standard matching template image, and after the position matching is completed, a correlation coefficient method is adopted to calculate the correlation coefficient between the acquired image and the standard matching template image, and the specific calculation formula is as follows:
assuming that the collected image and the standard matching template image both have m × n pixels, the standard matching template image is represented by T, T (i, j) represents the gray value of a pixel point at (i, j) in the standard matching template image, the collected image is represented by S, and S (i, j) represents the gray value of a pixel point at (i, j) in the standard matching template image, the cross-correlation between the collected image and the standard matching template image is measured by the following formula:
normalizing the correlation coefficient to obtain a template matching correlation coefficient:
The invention has the beneficial effects that: the machine vision can be used for detecting the aluminum extrusion molding product, a template matching algorithm is adopted to judge whether the product has defects or not, and the detection result is displayed and stored on a computer detection display device, so that the efficiency, the accuracy and the reliability of product quality detection are improved, and the quality of a CPU radiator is ensured.
Drawings
FIG. 1 is a system block diagram of the present invention.
Fig. 2 is a schematic diagram of the system of the present invention.
FIG. 3 is a flow chart of the template matching algorithm of the present invention; wherein, 1 represents an aluminum extruded steel body; 2 denotes an empty cutter band; 3 denotes a feed inlet; 4 denotes a discharge port; 5 denotes a CCD2 industrial camera; 6 denotes a CCD1 industrial camera; 7 denotes a second image acquisition card; 8 denotes a first image acquisition card; and 9 denotes a computer.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Examples
As shown in fig. 1, the CPU heat sink aluminum extrusion molding defect detection system includes an image acquisition device, a computer image recognition device, and a computer detection display device, wherein the image acquisition device includes a CCD1 industrial camera and a CCD2 industrial camera, the CCD1 industrial camera is installed above a discharge port of an aluminum extrusion model to acquire an upper view image of an aluminum extrusion product, the CCD2 industrial camera is installed in front of the discharge port of the aluminum extrusion model to acquire an orthographic view image of the aluminum extrusion product, the acquired image of the aluminum extrusion molding product is transmitted to the computer image recognition device, the computer image recognition device includes a computer equipped with image processing and analyzing software, the received image is subjected to filtering preprocessing and graying processing, and the image is recognized by a template matching algorithm, and the computer detection display device displays and stores an image detection result.
As shown in figure 2, an aluminum flow enters an empty cutter belt (2) from a feeding hole (3), a cooled aluminum extruded product is discharged from a discharging hole (4), a CCD1 industrial camera (6) is installed above the discharging hole (4), a CCD2 industrial camera (5) is installed in front of the discharging hole, a first image acquisition card (8) acquires an upper view image of the aluminum extruded product by using the CCD1 industrial camera (6), a second image acquisition card (7) acquires an orthographic view image of the aluminum extruded product by using the CCD2 industrial camera (5), the two acquired images are sent to a computer (9), a computer image recognition device carries out pretreatment and gray level conversion treatment, a template matching algorithm is adopted to recognize the images, and finally, an image detection result is sent to a computer detection display device to be displayed and stored.
As shown in fig. 3, the template matching algorithm specifically comprises the following steps: firstly, sending acquired image data to a computer image recognition device, then carrying out Gaussian filtering pretreatment on the image, carrying out gray level conversion treatment on the image, then selecting a standard matching template image, carrying out position matching on the image of an acquisition zone and the standard matching template image, then calculating a correlation coefficient R of the acquired image and the matching template image by adopting a correlation coefficient method, and calculating a correlation coefficient threshold R according to the correlation coefficient R and the correlation coefficient threshold R Setting up The size comparison of the template judges whether the template matching is successful, and therefore whether the aluminum extrusion product is qualified is detected.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such modifications are intended to be included in the scope of the present invention.
Claims (8)
1. The utility model provides a CPU radiator aluminium extrusion molding defect detecting system which characterized in that: the computer image recognition device comprises a CCD1 industrial camera, a CCD2 industrial camera, a first image acquisition card and a second image acquisition card, the computer image recognition device comprises an image processing module and a template matching module, the computer image recognition device is used for completing image preprocessing, gray level conversion and template matching recognition, the computer detection display device comprises a detection display module and a storage module, the computer detection display device is used for displaying and storing a detection result, the output end of the CCD1 industrial camera is connected with the input end of the first image acquisition card, the output end of the CCD2 industrial camera is connected with the input end of the second image acquisition card, and the output ends of the first image acquisition card and the second image acquisition card are connected with the RS232 input end of the computer; the first image acquisition card is combined with a CCD1 industrial camera, and transmits the acquired surface image data of the aluminum extrusion molding product to a computer image recognition device through an RS232 serial port, the second image acquisition card is combined with a CCD2 industrial camera, and transmits the acquired deformation image data of the aluminum extrusion molding product to the computer image recognition device through the RS232 serial port, the computer image recognition device processes and recognizes the received image data, and transmits an image recognition result to a computer detection display device, the detection display module displays the surface image recognition result and the deformation image recognition result, and the storage module stores the surface image recognition result and the deformation image recognition result.
2. The CPU radiator aluminum extrusion molding defect detection system according to claim 1, wherein: the CCD1 industrial camera is used for detecting the surface defects of the aluminum extrusion molding products, and the CCD2 industrial camera is used for detecting the deformation of the aluminum extrusion molding products.
3. The CPU radiator aluminum extrusion molding defect detection system according to claim 1, wherein: still include aluminium extrusion die, aluminium extrusion die include aluminium crowded steel body, feed inlet, empty sword area and discharge gate are arranged in proper order and are link up the crowded steel body of aluminium, CCD1 industry camera install in the top of discharge gate, CCD2 industry camera is installed in the dead ahead of discharge gate.
4. The detection method applied to the CPU radiator aluminum extrusion molding defect detection system of claim 1 is characterized by comprising the following steps:
A. carrying out image acquisition on an aluminum extrusion molding product;
B. sending the image data to a computer;
C. carrying out filtering pretreatment on the image;
D. carrying out gray level conversion processing on the image;
E. classifying and identifying the image after the gray level processing;
F. displaying the recognition result;
G. and storing the identification result.
5. The detection method according to claim 4, characterized in that: in the step A, the first image acquisition card finishes the top view image acquisition of the aluminum extrusion molding product from the top through a CCD1 industrial camera, and the second image acquisition card finishes the front view image acquisition of the aluminum extrusion molding product from the front through a CCD2 industrial camera.
6. The detection method according to claim 4, characterized in that: in step B, the image data is transmitted to the computer by adopting an RS232 serial port.
7. The detection method according to claim 4, characterized in that: in step C, a gaussian filtering method is used to complete the filtering processing of the two images.
8. The detection method according to claim 4, characterized in that: in step E, completing the classification and identification of the image by adopting a template matching algorithm, wherein the classification and identification steps are as follows:
a. selecting a standard aluminum extrusion molding product image without defects as a standard matching template image;
b. b, carrying out position matching on the acquired image to enable the image to be completely corresponding to the position of the standard matching template image in the step a;
c. matching the acquired image with the standard matching template image selected in the step a, calculating the correlation coefficient of the acquired image and the standard matching template image by adopting a correlation coefficient matching method, and comparing the calculated correlation coefficient with a correlation coefficient threshold value to determine whether the aluminum extrusion molding product is a defective product; the calculation formula is specifically as follows:
assuming that the collected image and the standard matching template image both have m × n pixels, the cross-correlation between the collected image and the standard matching template image is measured by using the following formula, and D represents the correlation:
wherein m represents the total pixel points in the abscissa direction of the collected image and the standard matching template image, n represents the total pixel points in the ordinate direction of the collected image and the standard matching template image, point i represents the abscissa, the range of i is 1 to m, j represents the ordinate, the range of j is 1 to n, T represents the standard matching template image, T (i, j) represents the gray value of the pixel point at (i, j) of the coordinate in the standard matching template image, S represents the collected image, and S (i, j) represents the gray value of the pixel point at (i, j) of the coordinate in the standard matching template image;
normalizing the correlation coefficient to obtain a template matching correlation coefficient, wherein R represents the correlation coefficient:
and calculating by adopting the formula to obtain a correlation coefficient of template matching, comparing the correlation coefficient R with a set correlation coefficient threshold, if the correlation coefficient R is greater than the correlation coefficient threshold, successfully matching, and indicating that the product is qualified, otherwise, determining that the matching is failed, and indicating that the product is unqualified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610877132.1A CN106290394B (en) | 2016-09-30 | 2016-09-30 | System and method for detecting aluminum extrusion molding defects of CPU radiator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610877132.1A CN106290394B (en) | 2016-09-30 | 2016-09-30 | System and method for detecting aluminum extrusion molding defects of CPU radiator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106290394A CN106290394A (en) | 2017-01-04 |
| CN106290394B true CN106290394B (en) | 2023-04-07 |
Family
ID=57716764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610877132.1A Active CN106290394B (en) | 2016-09-30 | 2016-09-30 | System and method for detecting aluminum extrusion molding defects of CPU radiator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106290394B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146704A (en) * | 2017-07-10 | 2017-09-08 | 河南远中电力设备有限公司 | A kind of transformer processing unit (plant) and production technology |
| CN110046630A (en) * | 2018-01-16 | 2019-07-23 | 上海电缆研究所有限公司 | Defect mode identification method/the systems/devices and readable storage medium storing program for executing of object |
| CN108508021B (en) * | 2018-03-28 | 2021-07-30 | 健特(浙江)交通器材股份有限公司 | Flaw detection device for monitoring quality of die |
| CN108956095A (en) * | 2018-05-17 | 2018-12-07 | 北京风云天地信息科技有限公司 | A kind of optical lens pollution level measurement method and device |
| CN112082946A (en) * | 2019-06-13 | 2020-12-15 | 撼讯科技股份有限公司 | Automatic detection system and method thereof |
| CN112465809B (en) * | 2020-12-15 | 2023-05-05 | 北京市计算中心有限公司 | Mold defect detection method based on image recognition, computer readable storage medium and device |
| CN114378546B (en) * | 2022-01-05 | 2023-03-24 | 江苏蔚联精密科技有限公司 | Novel aluminum extruded cavity special-shaped radiating fin manufacturing process |
| CN116500086B (en) * | 2023-06-28 | 2023-09-05 | 深圳市鑫典金光电科技有限公司 | Deep learning-based copper complex aluminum heat dissipation bottom plate production evaluation method and system |
| CN116843680B (en) * | 2023-08-29 | 2023-12-15 | 深圳市华盛源机电有限公司 | IGBT power module radiator surface defect identification method |
| CN116930196B (en) * | 2023-09-18 | 2023-12-22 | 山东卓越精工集团有限公司 | Machine vision-based aluminum profile production defect analysis processing method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101107512A (en) * | 2005-01-28 | 2008-01-16 | Ykk株式会社 | Article visual inspection device |
| CN102183524A (en) * | 2011-01-10 | 2011-09-14 | 哈尔滨工业大学 | Double-CCD (Charge Coupled Device) detecting method and system for apparent defect assessment of civil engineering structure |
| CN103593670A (en) * | 2013-10-14 | 2014-02-19 | 浙江工业大学 | Copper sheet and strip surface defect detection method based on-line sequential extreme learning machine |
| WO2014139273A1 (en) * | 2013-03-14 | 2014-09-18 | 苏州华源包装股份有限公司 | Weld seam defect detection method |
| CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
| WO2015055060A1 (en) * | 2013-10-16 | 2015-04-23 | 湖南镭目科技有限公司 | Online detecting method for continuous casting slab surface quality |
| CN104992449A (en) * | 2015-08-06 | 2015-10-21 | 西安冉科信息技术有限公司 | Information identification and surface defect on-line detection method based on machine visual sense |
-
2016
- 2016-09-30 CN CN201610877132.1A patent/CN106290394B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101107512A (en) * | 2005-01-28 | 2008-01-16 | Ykk株式会社 | Article visual inspection device |
| CN102183524A (en) * | 2011-01-10 | 2011-09-14 | 哈尔滨工业大学 | Double-CCD (Charge Coupled Device) detecting method and system for apparent defect assessment of civil engineering structure |
| WO2014139273A1 (en) * | 2013-03-14 | 2014-09-18 | 苏州华源包装股份有限公司 | Weld seam defect detection method |
| CN103593670A (en) * | 2013-10-14 | 2014-02-19 | 浙江工业大学 | Copper sheet and strip surface defect detection method based on-line sequential extreme learning machine |
| WO2015055060A1 (en) * | 2013-10-16 | 2015-04-23 | 湖南镭目科技有限公司 | Online detecting method for continuous casting slab surface quality |
| CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
| CN104992449A (en) * | 2015-08-06 | 2015-10-21 | 西安冉科信息技术有限公司 | Information identification and surface defect on-line detection method based on machine visual sense |
Non-Patent Citations (1)
| Title |
|---|
| 磁瓦表面缺陷自动检测系统的研究;严俊龙等;《计算机工程与应用》;20091221(第36期);第232-235页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106290394A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106290394B (en) | System and method for detecting aluminum extrusion molding defects of CPU radiator | |
| CN107145905B (en) | Image recognition detection method for looseness of elevator fastening nut | |
| CN103499585B (en) | Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision | |
| CN104101600B (en) | Cross Section of CC Billet testing of small cracks method | |
| CN107392232B (en) | Flotation working condition classification method and system | |
| CN104504388B (en) | A kind of pavement crack identification and feature extraction algorithm and system | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| US9064157B2 (en) | Pedestrian detection systems and methods | |
| CN110490842B (en) | Strip steel surface defect detection method based on deep learning | |
| CN106018422B (en) | Based on matched special-shaped stamping parts profile defects vision detection system and method | |
| CN104537651B (en) | Proportion detecting method and system for cracks in road surface image | |
| CN109978940B (en) | Visual measurement method for SAB safety airbag size | |
| WO2023168972A1 (en) | Linear array camera-based copper surface defect detection method and apparatus | |
| CN109506628A (en) | Object distance measuring method under a kind of truck environment based on deep learning | |
| CN104613869B (en) | Method and system for detecting elliptical hole group based on maximum inscribed circle | |
| CN114972356B (en) | Plastic product surface defect detection and identification method and system | |
| CN113375566B (en) | Accurate measurement method and system for object size | |
| CN106875441A (en) | A kind of online PE bottles of recognition positioning method based on machine vision | |
| CN106780437B (en) | A kind of quick QFN chip plastic packaging image obtains and amplification method | |
| CN105334228A (en) | Bottled liquid impurity and liquid level detection method based on image processing | |
| CN114445707A (en) | Intelligent visual fine detection method for defects of bottled water labels | |
| CN112067618A (en) | Product quality defect acquisition and analysis system based on imaging | |
| CN113177605A (en) | Scrap steel carriage grade judgment method based on video monitoring | |
| CN111968082A (en) | Product packaging defect detection and identification method based on machine vision | |
| CN103699876A (en) | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |