CN104807834B - A kind of ceramic tile patterns defect detecting device based on machine vision - Google Patents

A kind of ceramic tile patterns defect detecting device based on machine vision Download PDF

Info

Publication number
CN104807834B
CN104807834B CN201510092326.6A CN201510092326A CN104807834B CN 104807834 B CN104807834 B CN 104807834B CN 201510092326 A CN201510092326 A CN 201510092326A CN 104807834 B CN104807834 B CN 104807834B
Authority
CN
China
Prior art keywords
ceramic tile
spring leaf
switch contacts
push rod
module
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
CN201510092326.6A
Other languages
Chinese (zh)
Other versions
CN104807834A (en
Inventor
陈从平
黄正
黄杰光
聂葳
王小云
郭世杰
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.)
China Three Gorges University
Original Assignee
China Three Gorges University
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 China Three Gorges University filed Critical China Three Gorges University
Priority to CN201510092326.6A priority Critical patent/CN104807834B/en
Publication of CN104807834A publication Critical patent/CN104807834A/en
Application granted granted Critical
Publication of CN104807834B publication Critical patent/CN104807834B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The present invention relates to a kind of ceramic tile patterns defect detecting system based on machine vision, including ceramic tile transport module, centering module, vision-based detection module.Ceramic tile transport module is made up of two parallel conveyer belts, and centering module is by preceding spring leaf and switch contacts, two sets of slow-speed motors and motor driver, eccentric wheel and push rod composition;Vision-based detection module is made up of rear spring leaf and switch contacts, CCD camera, LED coaxial light sources, image processing system.System by ceramic tile centering to be detected, is then shot first, then the image photographed is matched with the standard picture template stored in system, to judge whether ceramic tile has pattern defect.The present invention has that automaticity is high, good reliability, the characteristics of using flexible, can accurately detect the pattern defect of ceramic tile.

Description

A kind of ceramic tile patterns defect detecting device based on machine vision
Technical field
The present invention relates to ceramic tile detection technique field, and in particular to a kind of ceramic tile patterns defect based on machine vision Detecting system.
Background technology
Vision-based detection has been successfully applied to the defects of ceramic tile aberration, profile etc. and detected, but is produced to ceramic tile patterns During processing, the pattern defects such as pattern contour deformation, missing, colorant cross flow are also easy to produce, if being also easy to produce by artificial detection Fatigue, efficiency is low, loss is high, therefore, it is necessary to develops a kind of new ceramic tile patterns defects detection system based on machine vision System.
The content of the invention
The technical problems to be solved by the invention are to provide a kind of ceramic tile patterns defect detecting device based on machine vision, This device first by ceramic tile centering to be detected, after shot, then by the image photographed and the standard picture stored in system Template is matched, to judge whether ceramic tile has pattern defect.
The object of the present invention is achieved like this:
A kind of ceramic tile patterns defect detecting device based on machine vision, including ceramic tile transport module, centering module and regard Feel detection module;
Described transport module includes two parallel conveyer belts, has certain level spacing, and Driven by Coaxial between two bands Make to be synchronized with the movement;
Described centering module includes preceding spring leaf and switch contacts, and preceding spring leaf and switch contacts are arranged on two conveyer belts Between gap pedestal on, two sets of slow-speed motors and motor driver are in series with preceding spring leaf and switch contacts, two partially Heart wheel is connected with the main shaft of slow-speed motor respectively, and one end of two push rods is contacted by roller with the outline of eccentric wheel, separately One end is respectively perpendicular one piece of push pedal of welding, and push rod passes through handspike bearing, and pushing rolling wheels protrude horizontally up push rod when eccentric wheel rotates.
Described vision-based detection module includes rear spring leaf and switch contacts, and rear spring leaf and switch contacts are arranged on two and passed Send between on the pedestal in gap, CCD camera, LED coaxial light sources and image processing system and rear spring leaf and switch contacts phase Series connection;
Described preceding spring leaf and switch contacts and rear spring leaf and switch contacts, it is by spring leaf and contact two parts structure Into.
Described push rod is made up of two hollow metal tube sockets, and two metal tube joint portions are machined with chute, and in cunning Groove location is connected firmly two pipes by bolt, by unclamping the i.e. telescopically adjustable push rod physical length of bolt, is provided with push rod Nut, spring is installed between nut and handspike bearing, by spring push rod can be made to retract automatically reset, and roller is begun It is in contact eventually with eccentric wheel.
Taken tile image is rotated 0 ° by described image processing system with the tile image stored in system respectively, Standard form after 90 °, 180 °, 270 ° is matched, if matching degree is more than given threshold, then it is assumed that ceramic tile pattern-free defect, Otherwise it is assumed that there is pattern defect.
The present invention can obtain following beneficial effect:
When there is ceramic tile to reach centering station along conveyer belt, the spring leaf of preceding spring leaf and switch contacts is pressurized and contact Connection, now circuit communication, two slowspeed machine synchronous averagings, each band movable eccentric wheel rotation, eccentric wheel promotion push rod make ceramic tile Complete ceramic tile centering operation;When ceramic tile leaves spring leaf, spring leaf disconnects with contact, Circuit Interrupt, and slow-speed motor stops Rotation, by adjusting slowspeed machine rotating speed and transmission tape running speed, the time that eccentric wheel can be made to be connected in spring leaf A with contact Rotated a circle just in section.
Ceramic tile after correction continues to move ahead with conveyer belt, and the spring leaf of rear spring leaf and switch contacts is depressed and contact Connection, circuit are connected, and CCD camera will be triggered and be shot, and by the image transmitting photographed to image processing system, image The template image for the pattern-free defect ceramic tile that processing system stores image to be detected with system enters to match, and is set if matching degree is more than Determine threshold value, then it is assumed that ceramic tile zero defect, otherwise it is assumed that ceramic tile is defective.
Brief description of the drawings
The invention will be further described with reference to the accompanying drawings and examples.
Fig. 1 is the overall structure diagram of the present invention.
Fig. 2 is the structure chart of push rod.
In figure:CCD camera 1, LED coaxial light sources 2, conveyer belt 3, rear spring leaf and switch contacts 4, ceramic tile 5, push rod 6, partially Heart wheel 7, handspike bearing 8, spring 9, bolt 10, slow-speed motor 11, preceding spring leaf and switch contacts 12, motor driver 13, Image processing system 14, nut 15.
Embodiment
Embodiments of the present invention are described further below in conjunction with the accompanying drawings.
Referring to Fig. 1, a kind of ceramic tile patterns defect detecting device based on machine vision, including ceramic tile transport module, centering Module and vision-based detection module, transport module include two parallel conveyer belts 3, have certain level spacing between two bands, and together Axle driving makes to be synchronized with the movement, so as to ensure that the stationarity and synchronism of ceramic tile transmission.
Referring to Fig. 1, preferable scheme, described centering module includes preceding spring leaf and switch contacts 12, preceding spring leaf and Switch contacts 12 are between two conveyer belts 3 on the pedestal in gap, and two sets of slow-speed motors 11 and motor driver 13 are with before Spring leaf and switch contacts 12 are in series, and main shaft of two eccentric wheels 7 respectively with slow-speed motor 11 is connected, two push rods 6 One end is contacted by roller with the outline of eccentric wheel 7, and one piece of push pedal of other end vertical welding, push rod 6 passes through handspike bearing 8, Pushing rolling wheels protrude horizontally up push rod 6 when eccentric wheel 7 rotates, so as to ensure that the centering that ceramic tile is completed by centering module is grasped Make, facilitate follow-up vision-based detection.
Referring to Fig. 1, preferable scheme, described vision-based detection module includes rear spring leaf and switch contacts 4, rear spring leaf And switch contacts 4 be arranged on two conveyer belts 3 between gap pedestal on, CCD camera 1, LED coaxial light sources 2 and image procossing system System 14 is in series with rear spring leaf and switch contacts 4, so as to complete the detection of ceramic tile patterns by vision-based detection module.
Referring to Fig. 1, preferable scheme, described preceding spring leaf and switch contacts 12 and rear spring leaf and switch contacts 4 are It is made up of spring leaf and contact two parts, position of the ceramic tile 5 on conveyer belt 3 is able to detect that by above-mentioned structure, it is convenient The centering operation of ceramic tile.
Referring to Fig. 2, preferable scheme, the push rod 6 is made up of two hollow metal tube sockets, two metal tube joint portions Chute is machined with, and is connected firmly two pipes by bolt 10 in runner position, by unclamping the i.e. adjustable actual (tube) length of push rod 6 of bolt 10 Degree, nut 15 is provided with push rod 6, spring 9 is provided between nut 15 and handspike bearing 8, can make push rod by spring 9 6 automatically reset, and roller is in contact all the time with eccentric wheel 7, can easily be adjusted by above-mentioned structure, so as to Realize the detection work of different size ceramic tiles.
Referring to Fig. 1, preferable scheme, described image processing system 14 by taken tile image respectively with system The standard form that the tile image of storage rotates after 0 °, 90 °, 180 °, 270 ° is matched, if matching degree is more than given threshold, Ceramic tile pattern-free defect is then thought, otherwise it is assumed that there is pattern defect.
The present invention device specific work process and operation principle be:
First, ceramic tile to be detected is placed on two conveyer belts 3, ceramic tile 5 with conveyer belt 3 operation push down before spring leaf and When the spring leaf of switch contacts 12 makes it with contact, motor driver 13 must be electric, and control slowspeed machine 11 is with movable eccentric wheel 7 Rotating, eccentric wheel, which promotes push rod 6 to stretch out, to correct the pose of ceramic tile 5, makes ceramic tile 5 any while edge parallel to conveyer belt 3, When ceramic tile 5 leaves spring leaf and contact, spring leaf rebounds, and circuit disconnects, and slowspeed machine 11 is stopped, now eccentric wheel 7 Just rotate one week, push rod 6 is retracted under the effect of spring 9.
Then, the ceramic tile 5 after correction continues to move ahead with conveyer belt, pushes down the spring leaf of rear spring leaf and switch contacts 4 and makes It is connected with contact, and circuit is connected, and CCD camera 1 will be triggered and be shot, and by the image transmitting photographed to image procossing System 14.
Finally, the Prototype drawing of the pattern-free defect ceramic tile stored image to be detected and system by image processing system 14 As entering matching, if matching degree is more than given threshold, then it is assumed that the zero defect of ceramic tile 5, otherwise it is assumed that ceramic tile 5 is defective, and then complete The defects of whole ceramic tile patterns, is detected.

Claims (2)

  1. A kind of 1. ceramic tile patterns defect detecting device based on machine vision, it is characterised in that:Including ceramic tile transport module, centering Module and vision-based detection module;
    Described transport module includes two parallel conveyer belts(3), two have certain level spacing between, and Driven by Coaxial makes It is synchronized with the movement;
    Described centering module includes preceding spring leaf and switch contacts(12), preceding spring leaf and switch contacts(12)Passed installed in two Send band(3)Between gap pedestal on, two sets of slow-speed motors(11)And motor driver(13)Opened with preceding spring leaf and contact Close(12)It is in series, two eccentric wheels(7)Respectively with slow-speed motor(11)Main shaft be connected, two push rods(6)One end lead to Cross roller and eccentric wheel(7)Outline contact, the one piece of push pedal of other end vertical welding, push rod(6)Through handspike bearing(8), Eccentric wheel(7)Pushing rolling wheels make push rod during rotation(6)Protrude horizontally up;
    Described vision-based detection module includes rear spring leaf and switch contacts(4), rear spring leaf and switch contacts(4)Installed in two Conveyer belt(3)Between gap pedestal on, CCD camera(1), LED coaxial light sources(2)And image processing system(14)With rear spring Piece and switch contacts(4)It is in series;
    Described preceding spring leaf and switch contacts(12)With rear spring leaf and switch contacts(4), it is by spring leaf and contact two Divide and form;
    The push rod(6)It is made up of two hollow metal tube sockets, two metal tube joint portions are machined with chute, and in chute position Put and pass through bolt(10)Two pipes are connected firmly, by unclamping bolt(10)I.e. telescopically adjustable push rod(6)Physical length, in push rod (6)On nut is installed(15), nut(15)With handspike bearing(8)Between spring is installed(9), pass through spring(9)It can make Push rod(6)Automatic retract resets, and make roller all the time with eccentric wheel(7)It is in contact.
  2. A kind of 2. ceramic tile patterns defect detecting device based on machine vision according to claim 1, it is characterised in that:Institute State image processing system(14)Taken tile image is rotated 0 ° with the tile image that is stored in system respectively, 90 °, Standard form after 180 °, 270 ° is matched, if matching degree is more than given threshold, then it is assumed that ceramic tile pattern-free defect, otherwise Think there is pattern defect.
CN201510092326.6A 2015-03-02 2015-03-02 A kind of ceramic tile patterns defect detecting device based on machine vision Active CN104807834B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510092326.6A CN104807834B (en) 2015-03-02 2015-03-02 A kind of ceramic tile patterns defect detecting device based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510092326.6A CN104807834B (en) 2015-03-02 2015-03-02 A kind of ceramic tile patterns defect detecting device based on machine vision

Publications (2)

Publication Number Publication Date
CN104807834A CN104807834A (en) 2015-07-29
CN104807834B true CN104807834B (en) 2018-04-10

Family

ID=53692848

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510092326.6A Active CN104807834B (en) 2015-03-02 2015-03-02 A kind of ceramic tile patterns defect detecting device based on machine vision

Country Status (1)

Country Link
CN (1) CN104807834B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105904112B (en) * 2016-05-30 2018-01-19 中国计量大学 Red copper pipe connecting piece weld defect on-line measuring device based on machine vision technique

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2374284Y (en) * 1999-06-01 2000-04-19 佛山市康思达液压机械总公司 Building material positioning detecting and selecting appts.
CN2419595Y (en) * 2000-04-28 2001-02-14 欧汝登 Color difference determiner for color, weins and patterns of tiles
CN2795852Y (en) * 2005-05-12 2006-07-12 佛山市德科机电设备有限公司 Automatic detector for glazed tile surface property
CN103529039A (en) * 2013-10-25 2014-01-22 成都四星液压制造有限公司 Magnetic shoe detection device
CN204422436U (en) * 2015-03-02 2015-06-24 三峡大学 A kind of ceramic tile patterns defect detecting device based on machine vision

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2374284Y (en) * 1999-06-01 2000-04-19 佛山市康思达液压机械总公司 Building material positioning detecting and selecting appts.
CN2419595Y (en) * 2000-04-28 2001-02-14 欧汝登 Color difference determiner for color, weins and patterns of tiles
CN2795852Y (en) * 2005-05-12 2006-07-12 佛山市德科机电设备有限公司 Automatic detector for glazed tile surface property
CN103529039A (en) * 2013-10-25 2014-01-22 成都四星液压制造有限公司 Magnetic shoe detection device
CN204422436U (en) * 2015-03-02 2015-06-24 三峡大学 A kind of ceramic tile patterns defect detecting device based on machine vision

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
瓷砖色差在线检测系统的研究;李温温;《中国优秀硕士学位论文全文数据库 信息科技辑》;20111215(第S2期);详见正文第8-14页"2.2 视觉系统硬件选择""2.4 系统机构设计""2.5 系统软件" *

Also Published As

Publication number Publication date
CN104807834A (en) 2015-07-29

Similar Documents

Publication Publication Date Title
CN103738680B (en) Feeding machine
CN203495341U (en) Plate cutting machine
CN102338751B (en) Equipment for detecting circuit board defects based on visual detection method
PH12019500977A1 (en) Image-based vehicle damage determining method, apparatus, and electronic device
CN101690933B (en) Device for automatically sorting feathers and sorting method
CN104386329B (en) A kind of full-automatic PCB labelling machines and implementation method
CN201289466Y (en) Appearance inspection machine for printed circuit board
CN102221549B (en) Fully-automatic board feeding optical image detecting device for PCB (printed circuit board)
CN203750868U (en) Computer vision-based burr detection device
CN203869671U (en) Wood contour detection device
CN204718970U (en) Product appearance inspection device
CN202330294U (en) Surface defect detection device based on machine vision
CN201769429U (en) Sticking film machine capable of automatically detecting products
CN103785627A (en) On-line lithium battery pole piece surface defect detection sorting system and method
US5175930A (en) Method and apparatus for attaching belt-shaped member to forming drum
CN107252908B (en) A kind of automatic drilling device of turning of electric motor end cap
CN106423894B (en) Wheel hub appearance automatic sorting device, method for sorting and sorting system based on machine vision
CN103529039B (en) A kind of magnetic shoe detection device
CN101659062B (en) Processing method and device for volume to volume fully-automatic deviation-rectifying die-cutting
CN102490523B (en) Automatic laser engraving system based on computer vision and service method of automatic laser engraving system
CN104209272B (en) A kind of equipment carrying out product sorting according to image information
CN203455286U (en) Cell phone outer shell edge quality detection device based on machine vision
CN203705352U (en) Magnetic shoe online detecting device based on machine vision
CN105728339B (en) A kind of ceramic cartridge vision automatic checkout system
CN103743752B (en) A kind of magnetic shoe online detection instrument based on machine vision

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant