CN109975309B - Template matching detection method for six-bridge defects of aluminum cover based on machine vision - Google Patents

Template matching detection method for six-bridge defects of aluminum cover based on machine vision Download PDF

Info

Publication number
CN109975309B
CN109975309B CN201910210273.1A CN201910210273A CN109975309B CN 109975309 B CN109975309 B CN 109975309B CN 201910210273 A CN201910210273 A CN 201910210273A CN 109975309 B CN109975309 B CN 109975309B
Authority
CN
China
Prior art keywords
bridge
aluminum cover
detection
annular
cover
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910210273.1A
Other languages
Chinese (zh)
Other versions
CN109975309A (en
Inventor
周文举
王子琦
栾松宇
费敏锐
孔佳杰
李汶瑾
王海宽
周天放
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Chuangdian Intelligent Technology Co.,Ltd.
Original Assignee
Shandong Chuangdian Intelligent Technology Co ltd
Ludong University
University of Shanghai for Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong Chuangdian Intelligent Technology Co ltd, Ludong University, University of Shanghai for Science and Technology filed Critical Shandong Chuangdian Intelligent Technology Co ltd
Priority to CN201910210273.1A priority Critical patent/CN109975309B/en
Publication of CN109975309A publication Critical patent/CN109975309A/en
Application granted granted Critical
Publication of CN109975309B publication Critical patent/CN109975309B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G01N21/8851—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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Image Analysis (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention belongs to the technical field of machine vision identification, and discloses a template matching detection method for six-bridge defects of an aluminum cover based on machine vision, which comprises the following steps: A. collecting a qualified aluminum cover image; B. measuring the inner radius and the outer radius of the six-bridge annular area of the cover surface of the aluminum cover in the qualified aluminum cover image; C. establishing an annular detection template which is radially divided into a plurality of sector ring blocks with equal size; D. collecting an image of an aluminum cover to be detected; E. establishing a six-bridge detection array according to the annular detection template and the brightness value of the cover surface of the aluminum cover in the image to be detected; F. and judging whether the defects of the six bridges on the cover surface of the aluminum cover exist or not according to the six-bridge detection array. Therefore, the method can quickly position the area where the six bridges of the aluminum cover are located, can accurately detect the defects of the six bridges of the aluminum cover, and improves the speed and the precision of the detection of the aluminum cover.

Description

Template matching detection method for six-bridge defects of aluminum cover based on machine vision
The technical field is as follows:
the invention belongs to the field of image processing of aluminum cover visual inspection, and particularly relates to a template matching detection method for six-bridge defects of an aluminum cover based on machine vision.
Background art:
with the improvement of the living standard in recent years, people pay more attention to health problems, medical health and public health are continuously improved, and the packaging safety problem of medical medicines is not small. The aluminum cover is used as a key component of the aluminum-plastic combined cover for medical packaging, the quality of the aluminum cover is related to the safety of the medicine in storage and transportation, and particularly the integrity of the six bridges of the aluminum cover directly influences the tightness of the medicine, so that the aluminum cover with defects of the six bridges needs to be detected and removed before the aluminum-plastic combined cover is assembled. Six-bridge detection of the appearance of the aluminum cover generally comprises two methods, namely a manual naked eye detection method and a machine vision detection method. Traditional six bridge detection of aluminium lid relies on artifical bore hole to discern the detection, and not only detection speed is low, and different testing personnel also have individual difference to the judgement standard of six bridge of aluminium lid moreover, and testing personnel are engaged in the detection operation for a long time and are tired easily, and the condition such as wrong detection, omission can appear in the inevitable, is difficult to satisfy the requirement to detection quality in the actual production. Simultaneously, aluminium lid production is accomplished on the assembly line, and production efficiency is high, can produce a large amount of aluminium lids in the short time, need arrange a large amount of workman and carry out quality testing, can cause serious wasting of resources, has increased the manufacturing cost of aluminium lid.
According to the method, an industrial camera is used for obtaining the image of the aluminum cover, the six-bridge image of the aluminum cover is detected by adopting a template matching method, and the quick detection of the six-bridge defect of the aluminum cover is realized.
Disclosure of Invention
The invention provides a template matching detection method for six-bridge defects of an aluminum cover based on machine vision, which can not only quickly position the area where the six-bridge of the aluminum cover is positioned, but also accurately detect the six-bridge defects of the aluminum cover, and improve the detection speed and the detection precision of the aluminum cover.
In order to achieve the purpose, the invention has the following conception: and (3) establishing an annular detection template covering a six-bridge area of the cover surface of the aluminum cover in an off-line manner, and radially dividing the annular detection template into a plurality of sector ring blocks with the same size. When the aluminum cover is detected on line, the annular detection template is translated to enable the center of the annular detection template to be overlapped with the circle center of the cover surface of the aluminum cover to be detected, the brightness value of the aluminum cover surface sector ring block covered by the annular detection template is calculated, and whether the defect of the six bridges of the cover surface of the aluminum cover exists or not is judged according to the brightness value. Because the template is established off-line, when the aluminum cover is detected in real time, only the annular detection template needs to be moved, and the six-bridge position of the aluminum cover does not need to be searched, so that the six-bridge position of the cover surface of the aluminum cover can be quickly positioned, the image searching range is reduced, and the detection efficiency is improved.
In order to achieve the purpose, the application adopts the following technical scheme:
(1) assembling an industrial camera to a station to be detected on an aluminum cover detection line, selecting a qualified aluminum cover, and acquiring an image of the qualified aluminum cover through the industrial camera.
(2) Positioning the qualified aluminum cover image acquired in the step (1) to obtain the inner radius R of the six-bridge annular area of the cover surface of the aluminum cover1And an outer radius R2。
(3) Establishing an annular detection template, which comprises the following specific steps:
(3-1) establishing a circle with the origin as the center of a circle and the inner radius as R1An outer radius of R2The annular region of (a).
And (3-2) the annular area is radially and equally divided into m fan-shaped ring blocks with equal size, and the value of m enables the arc width of each fan-shaped ring block to be not larger than the arc width of a single bridging part of the six-bridge aluminum cover.
(3-3) storing the coordinate values of the inner points of the sector ring blocks in (3-2) in a three-dimensional array P [ i, j, k ], wherein i is the serial number of the sector ring block, the value of i is 1,2, … …, m, j is the serial number of the inner points of the sector ring block, k is the coordinate of the inner points of the sector ring block, when k is 0, the value of the horizontal coordinate of the point is obtained, when k is 1, the value of the vertical coordinate of the point is obtained, and the three-dimensional array P [ i, j, k ] is the annular detection template inner point coordinate set which is radially divided into m sector ring blocks with equal size.
(4) And acquiring an image of the aluminum cover to be detected by an industrial camera.
(5) And establishing a six-bridge detection array according to the annular detection template and the brightness value of the cover surface of the aluminum cover in the image to be detected. The method comprises the following specific steps:
(5-1) positioning the circle center position of the aluminum cover surface of the image of the aluminum cover to be detected, translating the annular detection template to enable the center of the annular detection template to be overlapped with the circle center of the aluminum cover surface in the image of the aluminum cover to be detected, and respectively counting the brightness value of the aluminum cover surface covered by each sector ring block in the annular detection template, wherein the calculation formula is as follows:
Figure BDA0002000266790000031
wherein E isiAnd (3) the brightness value of the aluminum cover surface covered by the sector ring block, i is the serial number of the sector ring block, phi (-) is the brightness value of the pixel point of the aluminum cover surface, and S is the set of the inner points of the ith sector ring block.
(5-2) establishing a six-bridge detection array G [ i ], wherein i is 1,2, … …, m, and the length of the six-bridge detection array G [ i ] is equal to the number of fan rings of the ring-shaped detection template.
(5-3) setting a distinguishing threshold U so that the distinguishing threshold U can distinguish the fan ring block of the ring-shaped detection template into a part containing the bridge and a part not containing the bridge, and storing the result of the distinguishing two parts into the six-bridge detection array G [ i ] in the step (5-2), wherein the calculation formula is as follows:
Figure BDA0002000266790000032
(6) operating the six-bridge detection array Gi, and judging whether the six-bridge defect of the cover surface of the aluminum cover exists or not, wherein the method comprises the following specific steps:
(6-1) setting the pass threshold interval of the bridging part to be [ amin,amax]Setting the qualified threshold interval of the hollow part as [ bmin,bmax]The calculation formula of the threshold interval is as follows:
Figure BDA0002000266790000033
Figure BDA0002000266790000034
α＝360/m
wherein the content of the first and second substances,
Figure BDA0002000266790000041
which represents the rounding-down of the whole,
Figure BDA0002000266790000042
and representing rounding up, wherein α is a central angle corresponding to a single sector ring block of the detection template, β is a central angle corresponding to a single bridging part of a six-bridge area of the aluminum cover surface, and gamma is a central angle corresponding to a single hollow part of the six-bridge area of the aluminum cover surface.
(6-2) detecting the array G [ i ] for the six bridges]Searching the elements in the array according to the serial number, and if the six-bridge detection array G [ i ]]The value of the first element in the six-bridge detection array is 0 when the six-bridge detection array G [ i]When the number 1 appears, the number of the consecutive numbers 1 is recorded, denoted by a, if a satisfies the condition amin≤a≤amaxAnd if not, determining that the bridging part of the six-bridge area of the cover surface of the aluminum cover is qualified, otherwise determining that the defect exists.
(6-3) detecting the six-bridge array G [ i]Searching the elements in the array according to the serial number, and if the six-bridge detection array G [ i ]]The value of the first element in the six-bridge detection array is 1, when the six-bridge detection array G [ i ]]When the number 0 appears, the number of consecutive 0 is recorded and is represented by b, if b satisfies the condition bmin≤b≤bmaxAnd if not, determining that the hollow part of the six-bridge area of the cover surface of the aluminum cover is qualified, otherwise, determining that the defect exists.
Drawings
FIG. 1 is a collected image of a qualified aluminum cap;
FIG. 2 is a graph showing the inner radius R of the six-bridge annular region of the cover surface of the aluminum cover1And an outer radius R2A schematic diagram;
FIG. 3 is a schematic view of an annular inspection template that is radially divided into a plurality of equal-sized ring segments;
FIG. 4 is an overlapped view of the center of the annular detection template and the center of the cover surface of the aluminum cover;
FIG. 5 is an aluminum lid with a six-bridge hollow defect;
fig. 6 is a flow chart of a method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a template matching detection method for six-bridge defects of an aluminum cover based on machine vision, which can be realized by the flow shown in figure 6 and comprises the following steps:
and S111, assembling an industrial camera to a station to be detected on an aluminum cover detection line, selecting a qualified aluminum cover, and acquiring an image of the qualified aluminum cover by the industrial camera, wherein the image of the qualified aluminum cover is shown in figure 1.
Step S112, operating the qualified aluminum cover image acquired in the step S111, and measuring the inner radius R of the six-bridge annular area of the cover surface of the aluminum cover1And an outer radius R2See fig. 2.
Step S113, referring to fig. 3, an annular detection template radially divided into a plurality of equal-sized sector ring blocks is established. The method comprises the following specific steps:
(3-1) establishing a circle with the origin as the center of a circle and the inner radius as R1An outer radius of R2The annular area is radially and equally divided into m fan-shaped ring blocks with equal size, the value of m ensures that the arc width of the fan-shaped ring block is not larger than the arc width of a single bridging part of the six-bridge of the aluminum cover, and the annular area with the m fan-shaped ring blocks is used as a six-bridge detection template, which is shown in fig. 3.
(3-2) storing the coordinate values of the inner points of the sector ring blocks in (3-1) in a three-dimensional array P [ i, j, k ], wherein i is the serial number of the sector ring block, and the value of i is 1,2, … …, and m, j is the serial number of the inner points of the sector ring block; k is the coordinate of the point in the sector ring block, and when k is 0, the k is the value of the abscissa of the point; when k is 1, it is the value of the ordinate of the point.
And step S114, acquiring an image of the aluminum cover to be detected by the industrial camera.
And S115, establishing a six-bridge detection array according to the detection template established in the step S113 and the brightness value of the cover surface of the aluminum cover in the image of the aluminum cover to be detected. The method comprises the following specific steps:
(5-1) positioning the circle center position of the aluminum cover surface of the image of the aluminum cover to be detected, and translating the detection template to enable the center of the detection template to be overlapped with the circle center of the aluminum cover surface to be detected, as shown in fig. 4. And counting the brightness value in the sector ring area in the detection template. The calculation formula is as follows:
Figure BDA0002000266790000061
wherein E isiAnd (3) the brightness value of the aluminum cover surface covered by the sector ring block, i is the serial number of the sector ring block, phi (-) is the brightness value of the pixel point of the aluminum cover surface, and S is the set of the inner points of the ith sector ring block.
(5-2) establishing a six-bridge detection array G [ i ], wherein i is 1,2, … …, m, and the length of the six-bridge detection array G [ i ] is equal to the number of fan rings of the ring-shaped detection template.
(5-3) setting a distinguishing threshold U so that the distinguishing threshold U can distinguish the fan ring block of the ring-shaped detection template into a part containing the bridge and a part not containing the bridge, and storing the result of the distinguishing two parts into the six-bridge detection array G [ i ] in the step (5-2), wherein the calculation formula is as follows:
Figure BDA0002000266790000062
step S116, operating the six-bridge detection array G [ i ], and judging the six-bridge defect of the cover surface of the aluminum cover according to the six-bridge detection array, which comprises the following specific steps:
(6-1) setting the pass threshold interval of the bridging part to [ amin,amax]Setting the qualified threshold interval of the hollow part as [ bmin,bmax]The calculation formula of the threshold interval is as follows:
Figure BDA0002000266790000063
Figure BDA0002000266790000064
α＝360/m
wherein the content of the first and second substances,
Figure BDA0002000266790000065
which represents the rounding-down of the whole,
Figure BDA0002000266790000066
and representing rounding up, wherein α is a central angle corresponding to a single sector ring block of the detection template, β is a central angle corresponding to a single bridging part of a six-bridge area of the aluminum cover surface, and gamma is a central angle corresponding to a single hollow part of the six-bridge area of the aluminum cover surface.
(6-2) detecting the array G [ i ] for the six bridges]Searching the elements in the array according to the serial number, and if the six-bridge detection array G [ i ]]The value of the first element in the six-bridge detection array is 0 when the six-bridge detection array G [ i]When the number 1 appears, the number of the consecutive numbers 1 is recorded, denoted by a, if a satisfies the condition amin≤a≤amaxAnd if not, determining that the bridging part of the six-bridge area of the cover surface of the aluminum cover is qualified, otherwise determining that the defect exists.
(6-3) detecting the six-bridge array G [ i]Searching the elements in the array according to the serial number, and if the six-bridge detection array G [ i ]]The value of the first element in the six-bridge detection array is 1, when the six-bridge detection array G [ i ]]When the number 0 appears, the number of consecutive 0 is recorded and is represented by b, if b satisfies the condition bmin≤b≤bmaxIf the hollowed-out part of the six-bridge area on the cover surface of the aluminum cover is qualified, otherwise, the aluminum cover has a defect, and fig. 5 shows an aluminum cover sample with the six-bridge hollowed-out defect.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention.

Claims (3)

1. A template matching detection method for six bridge defects of an aluminum cover based on machine vision is characterized by comprising the following steps:
A. collecting a qualified aluminum cover image;
B. measuring the inner radius and the outer radius of the six-bridge annular area of the cover surface of the aluminum cover in the qualified aluminum cover image;
C. establishing an annular detection template which is radially divided into a plurality of sector ring blocks with equal size;
D. collecting an image of an aluminum cover to be detected;
E. establishing a six-bridge detection array according to the annular detection template and the brightness value of the cover surface of the aluminum cover in the image to be detected;
F. judging whether the defects of the six bridges on the cover surface of the aluminum cover exist or not according to the six-bridge detection array;
the step F comprises the following steps:
F1. setting the qualified threshold interval of the bridging part as [ amin,amax]Setting the qualified threshold interval of the hollow part as [ bmin,bmax]The calculation formula of the threshold interval is as follows:
Figure FDA0002501305210000011
Figure FDA0002501305210000012
α＝360/m
wherein the content of the first and second substances,
Figure FDA0002501305210000013
in order to get the whole downwards,
Figure FDA0002501305210000014
for rounding up, α is a central angle corresponding to a single sector ring block of the detection template, β is a central angle corresponding to a single bridging part of a six-bridge area of the aluminum cover surface, and γ is a central angle corresponding to a single hollow part of the six-bridge area of the aluminum cover surface;
F2. detecting an array G [ i ] for the six bridges]If the six-bridge detection array G [ i ] is searched]The value of the first element in the six-bridge detection array is 0 when the six-bridge detection array G [ i]When the number 1 appears, the number of the consecutive numbers 1 is recorded, denoted by a, if a satisfies the condition amin≤a≤amaxIf the bridging part of the six-bridge area of the cover surface of the aluminum cover is qualified, otherwise, the defect exists;
F3. detecting an array G [ i ] for the six bridges]If the six-bridge detection array G [ i ] is searched]The value of the first element in the six-bridge detection array is 1, when the six-bridge detection array G [ i ]]When the number 0 appears, the number of consecutive 0 is recorded and is represented by b, if b satisfies the condition bmin≤b≤bmaxAnd if not, determining that the hollow part of the six-bridge area of the cover surface of the aluminum cover is qualified, otherwise, determining that the defect exists.
2. The template matching detection method for the six-bridge defect of the aluminum cover based on the machine vision as claimed in claim 1, wherein the step of establishing an annular detection template which is radially divided into a plurality of equal-size sector ring blocks comprises:
C1. establishing an annular area by taking the original point as the center of a circle, wherein the inner radius and the outer radius of the annular area are respectively the inner radius R of the six-bridge annular area of the cover surface of the aluminum cover in the qualified aluminum cover image1And an outer radius R2；
C2. Equally dividing the annular region in the step C1 into m fan-shaped ring blocks with equal size in the radial direction, wherein the value of m ensures that the arc width of each fan-shaped ring block is not larger than that of the six-bridge bridging part;
C3. and D, storing the coordinate values of the inner points of the sector ring blocks in the step C2 in a three-dimensional array P [ i, j, k ], wherein i is the serial number of the sector ring block, the value of i is 1,2, … …, m, j is the serial number of the inner points of the sector ring block, and k is the coordinate of the inner points of the sector ring block.
3. The template matching detection method for the six-bridge defect of the aluminum cover based on the machine vision as claimed in claim 1, wherein the step of establishing the six-bridge detection array according to the annular detection template and the brightness value of the cover surface of the aluminum cover in the image to be detected comprises the following steps:
E1. positioning the circle center position of the cover surface of the aluminum cover in the image of the aluminum cover to be detected;
E2. translating the annular detection template to enable the center of the annular detection template to be overlapped with the circle center of the cover surface of the aluminum cover in the image of the aluminum cover to be detected;
E3. and respectively counting the brightness value of the aluminum cover surface covered by each fan ring block in the annular detection template, wherein the calculation formula is as follows:
Figure FDA0002501305210000031
wherein E isiThe brightness value of the aluminum cover surface covered by the sector ring block, i is the serial number of the sector ring block, phi (-) is the brightness value of the pixel point of the aluminum cover surface, and S is the set of the inner point of the ith sector ring block;
E4. establishing a six-bridge detection array G [ i ], wherein i is 1,2, … …, m, and the length of the six-bridge detection array G [ i ] is equal to the number of fan-ring blocks of the ring-shaped detection template;
E5. setting a distinguishing threshold U so that the distinguishing threshold U can distinguish the fan ring block of the detection template into a part including the bridge and a part not including the bridge, and storing the result of distinguishing the two parts into a six-bridge detection array G [ i ] in the step E4, wherein the calculation formula is as follows:
Figure FDA0002501305210000032
CN201910210273.1A 2019-03-20 2019-03-20 Template matching detection method for six-bridge defects of aluminum cover based on machine vision Active CN109975309B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910210273.1A CN109975309B (en) 2019-03-20 2019-03-20 Template matching detection method for six-bridge defects of aluminum cover based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910210273.1A CN109975309B (en) 2019-03-20 2019-03-20 Template matching detection method for six-bridge defects of aluminum cover based on machine vision

Publications (2)

Publication Number Publication Date
CN109975309A CN109975309A (en) 2019-07-05
CN109975309B true CN109975309B (en) 2020-08-25

Family

ID=67079585

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910210273.1A Active CN109975309B (en) 2019-03-20 2019-03-20 Template matching detection method for six-bridge defects of aluminum cover based on machine vision

Country Status (1)

Country Link
CN (1) CN109975309B (en)

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006170635A (en) * 2004-12-13 2006-06-29 Hitachi Engineering & Services Co Ltd Detector of flaw by image processing and flaw detecting method using it
JP2011069771A (en) * 2009-09-28 2011-04-07 Kirin Techno-System Co Ltd Lighting system of resin cap
CN101799431B (en) * 2010-04-08 2012-01-04 湖南大学 Machine visual on-line detection method and equipment for tank cover quality in high-speed production line
CN102169093B (en) * 2010-12-20 2012-10-10 湖南大学 Multi-station machine vision imaging detection method and system based on graphics processor
JP5959430B2 (en) * 2012-12-21 2016-08-02 倉敷紡績株式会社 Bottle cap appearance inspection device and appearance inspection method
CN103424409B (en) * 2013-04-12 2015-06-17 安徽工业大学 Vision detecting system based on DSP
CN103604808B (en) * 2013-12-04 2016-03-02 天津普达软件技术有限公司 A kind of bottle cap defective vision detection method
CN104438126A (en) * 2014-12-10 2015-03-25 天津普达软件技术有限公司 Removal method of defective bottle parisons
CN106981060A (en) * 2017-02-27 2017-07-25 湖南大学 A kind of Empty Bottle Inspector bottom of bottle localization method
CN109146874B (en) * 2018-09-05 2020-08-18 中冶赛迪重庆信息技术有限公司 Machine vision-based overflow slag detection method

Also Published As

Publication number Publication date
CN109975309A (en) 2019-07-05

Similar Documents

Publication Publication Date Title
CN105548216A (en) Visual detection method for appearance of semi-finished battery
CN104123542A (en) Device and method for positioning wheel hub work piece
CN105865329A (en) Vision-based acquisition system for end surface center coordinates of bundles of round steel and acquisition method thereof
JP2013531262A5 (en) Method of analyzing OCT image and method of analyzing optic nerve
CN103886294A (en) Method and system for recognizing number of movement times of arrester for convertor station based on images
CN110108712A (en) Multifunctional visual sense defect detecting system
JP5695821B2 (en) Color code target, color code discrimination device, and color code discrimination method
CN106886989A (en) The automatic optical detection method of keyboard
CN114463296A (en) Light-weight part defect detection method based on single sample learning
US20220099530A1 (en) Circumferential main groove detection method and circumferential main groove detection device
CN109975309B (en) Template matching detection method for six-bridge defects of aluminum cover based on machine vision
CN109584208B (en) Inspection method for intelligent identification model of industrial structure defects
CN104259110A (en) Detection method of ceramic valve element
JP5350943B2 (en) Color code target, color code discrimination device, and color code discrimination method
CN112036391A (en) Electronic inspection method and system based on shale gas field production station
CN106546605A (en) A kind of medicated beer bottle mouth defect detection method for utilizing 4 circumferential registrations and hysteresis threshold
CN115937555A (en) Industrial defect detection algorithm based on standardized flow model
KR0130950B1 (en) Method for recognizing circular hole
CN116052041A (en) Indicating lamp state identification method based on depth network
CN108827974A (en) A kind of ceramic tile defect inspection method and system
CN210071691U (en) Check standard bottle
CN109127462B (en) Intelligent sausage sorting method based on visual guidance
JP5812284B2 (en) Belt-like structure detecting device, method and program
CN112907665B (en) Micro-fluidic blood type detection card micro-cavity reaction tank precise positioning method based on RGB color space
CN101048784B (en) Method for assigning a digital image to a class of a classification system

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
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20220105

Address after: 264003 No. 3, No. 39, Keji Avenue, high tech Zone, Yantai City, Shandong Province

Patentee after: Shandong Chuangdian Intelligent Technology Co.,Ltd.

Address before: 200444 No. 99, upper road, Shanghai, Baoshan District

Patentee before: Shanghai University

Patentee before: Shandong Chuangdian Intelligent Technology Co.,Ltd.

Patentee before: LUDONG University

TR01 Transfer of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: A Template Matching Detection Method for Aluminum Cover Six Bridge Defects Based on Machine Vision

Effective date of registration: 20230804

Granted publication date: 20200825

Pledgee: Yantai Rural Commercial Bank Co.,Ltd.

Pledgor: Shandong Chuangdian Intelligent Technology Co.,Ltd.

Registration number: Y2023980051126

PE01 Entry into force of the registration of the contract for pledge of patent right