CN104807834A - Tile pattern defect detection device based on machine vision - Google Patents

Tile pattern defect detection device based on machine vision Download PDF

Info

Publication number
CN104807834A
CN104807834A CN201510092326.6A CN201510092326A CN104807834A CN 104807834 A CN104807834 A CN 104807834A CN 201510092326 A CN201510092326 A CN 201510092326A CN 104807834 A CN104807834 A CN 104807834A
Authority
CN
China
Prior art keywords
ceramic tile
switch contacts
spring sheet
module
push rod
Prior art date
Application number
CN201510092326.6A
Other languages
Chinese (zh)
Other versions
CN104807834B (en
Inventor
陈从平
黄正
黄杰光
聂葳
王小云
郭世杰
Original Assignee
三峡大学
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 三峡大学 filed Critical 三峡大学
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 invention relates to a tile pattern defect detection system based on machine vision. The system comprises a tile conveying module, a centering module and a vision detection module, wherein the tile conveying module comprises two parallel conveying belts; the centering module comprises a front spring piece and contact switch, two low-speed motors, two motor drivers, eccentric wheels and push rods; the vision detection module comprises a back spring piece and contact switch, a CCD (charge coupled device) camera, an LED coaxial light source and an image processing system. The system firstly centers to-be-detected tiles, then shoots the tiles and matches shot images with a standard image template stored in the system to judge whether the tiles have pattern defects or not. The system has the characteristics of high automation degree, high reliability and flexibility in use and can accurately detect the pattern defects of the tiles.

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, be specifically related to a kind of ceramic tile patterns defect detecting system based on machine vision.
Background technology
Vision-based detection has been successfully applied to the defects detection of ceramic tile aberration, profile etc., but ceramic tile patterns is being carried out in the process of production and processing, the pattern defects such as easy generation pattern contour distortion, disappearance, colorant cross flow, if rely on, manual detection easily produces fatigue, efficiency is low, loss is high, therefore, need to develop a kind of novel ceramic tile patterns defect detecting system based on machine vision.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of ceramic tile patterns defect detecting device based on machine vision, this device is first by ceramic tile centering to be detected, after take, again the image photographed is mated with the standard picture template stored in system, to judge whether ceramic tile has pattern defect.
The object of the present invention is achieved like this:
Based on a ceramic tile patterns defect detecting device for machine vision, comprise ceramic tile transport module, centering module and vision-based detection module;
Described transport module comprises two parallel travelling belts, have certain level spacing, and coaxial drive makes to be synchronized with the movement between two bands;
Described centering module comprises front spring sheet and switch contacts, front spring sheet and switch contacts are arranged on the pedestal in gap between two travelling belts, two cover slow-speed motors and motor driver and front spring sheet and switch contacts are in series, two eccentric wheels are connected with the main shaft of slow-speed motor respectively, one end of two push rods is contacted with eccentric outline by roller, the other end is vertical welding one piece of push pedal respectively, and push rod is through handspike bearing, and when eccentric wheel rotates, pushing rolling wheels makes push rod level stretch out.
Described vision-based detection module comprises rear spring sheet and switch contacts, and rear spring sheet and switch contacts are arranged on the pedestal in gap between two travelling belts, and CCD camera, LED coaxial light source and image processing system and rear spring sheet and switch contacts are in series;
Described front spring sheet and switch contacts and rear spring sheet and switch contacts are made up of spring leaf and contact two parts.
Described push rod is socketed by two hollow metal tubes and forms, two metal tube joint portions are processed with chute, and two pipes are connected firmly by bolt at runner position, telescopic adjustment push rod physical length is got final product by unclamping bolt, push rod is provided with nut, between nut and handspike bearing, spring is installed, push rod automatic retraction can be made to reset by spring, and roller is contacted with eccentric wheel all the time.
Taken tile image is rotated 0 °, 90 °, 180 ° with the tile image that stores in system by described image processing system respectively, standard form after 270 ° mates, if matching degree is greater than setting threshold value, then think ceramic tile pattern-free defect, otherwise think there is pattern defect.
The present invention can obtain following beneficial effect:
When there being ceramic tile to arrive centering station along travelling belt, the spring leaf pressurized of front spring sheet and switch contacts, to be connected with contact, now circuit communication, two slowspeed machine synchronous averaging, respective band movable eccentric wheel rotates, and eccentric wheel promotes push rod makes ceramic tile complete the operation of ceramic tile centering; When ceramic tile leaves spring leaf, spring leaf and contact disconnect, Circuit Interrupt, and slow-speed motor stops the rotation, and by regulating slowspeed machine rotating speed and travelling belt travelling speed, eccentric wheel can be made just to rotate a circle within the time period that spring leaf A is communicated with contact.
Ceramic tile after correcting continues to move ahead with travelling belt, the spring leaf of rear spring sheet and switch contacts is depressed and is connected with contact, circuit ON, CCD camera will be triggered and take, and by the image transmitting that photographs to image processing system, the template image of image to be detected with the pattern-free defect ceramic tile of system storage enters to mate, if matching degree is greater than setting threshold value by image processing system, then think ceramic tile zero defect, otherwise think ceramic tile defectiveness.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described.
Fig. 1 is one-piece construction schematic diagram of the present invention.
Fig. 2 is the structural drawing of push rod.
In figure: CCD camera 1, LED coaxial light source 2, travelling belt 3, rear spring sheet and switch contacts 4, ceramic tile 5, push rod 6, eccentric wheel 7, handspike bearing 8, spring 9, bolt 10, slow-speed motor 11, front spring sheet and switch contacts 12, motor driver 13, image processing system 14, nut 15.
Embodiment
Below in conjunction with accompanying drawing, embodiments of the present invention are described further.
See Fig. 1, a kind of ceramic tile patterns defect detecting device based on machine vision, comprise ceramic tile transport module, centering module and vision-based detection module, transport module comprises two parallel travelling belts 3, certain level spacing is had between two bands, and coaxial drive makes to be synchronized with the movement, thus ensure that the stationarity that ceramic tile transmits and synchronism.
See Fig. 1, preferred scheme, described centering module comprises front spring sheet and switch contacts 12, front spring sheet and switch contacts 12 are arranged on the pedestal in gap between two travelling belts 3, two cover slow-speed motors 11 and motor driver 13 are in series with front spring sheet and switch contacts 12, two eccentric wheels 7 are connected with the main shaft of slow-speed motor 11 respectively, one end of two push rods 6 is contacted by the outline of roller with eccentric wheel 7, the one piece of push pedal of other end vertical welding, push rod 6 is through handspike bearing 8, when eccentric wheel 7 rotates, pushing rolling wheels makes push rod 6 level stretch out, thus ensure that the centering operation being completed ceramic tile by centering module, facilitate follow-up vision-based detection.
See Fig. 1, preferred scheme, described vision-based detection module comprises rear spring sheet and switch contacts 4, rear spring sheet and switch contacts 4 are arranged on the pedestal in gap between two travelling belts 3, CCD camera 1, LED coaxial light source 2 and image processing system 14 is in series with rear spring sheet and switch contacts 4, thus can be completed the detection of ceramic tile patterns by vision-based detection module.
See Fig. 1, preferred scheme, described front spring sheet and switch contacts 12 and rear spring sheet and switch contacts 4 are made up of spring leaf and contact two parts, the position of ceramic tile 5 on travelling belt 3 can be detected by above-mentioned structure, facilitate the centering of ceramic tile to operate.
See Fig. 2, preferred scheme, described push rod 6 is socketed by two hollow metal tubes and forms, two metal tube joint portions are processed with chute, and two pipes are connected firmly by bolt 10 at runner position, regulating pushing rod 6 physical length is got final product by unclamping bolt 10, push rod 6 is provided with nut 15, spring 9 is installed between nut 15 and handspike bearing 8, push rod 6 can be made to automatically reset by spring 9, and roller is contacted with eccentric wheel 7 all the time, can be regulated easily by above-mentioned structure, thus the testing of different size ceramic tile can be realized.
See Fig. 1, preferred scheme, taken tile image is rotated 0 ° with the tile image that stores in system by described image processing system 14 respectively, 90 °, 180 °, the standard form after 270 ° mates, if matching degree is greater than setting threshold value, then think ceramic tile pattern-free defect, otherwise think there is pattern defect.
Device specific works process of the present invention and principle of work are:
First, ceramic tile to be detected is placed on two travelling belts 3, ceramic tile 5 with travelling belt 3 run the spring leaf pushing down front spring sheet and switch contacts 12 make itself and contact time, motor driver 13 obtains electric, controlling slowspeed machine 11 is with movable eccentric wheel 7 to rotate, eccentric wheel promotes push rod 6 and stretches out the pose correcting ceramic tile 5, make ceramic tile 5 arbitrarily while be parallel to the edge of travelling belt 3, when ceramic tile 5 leaves spring leaf and contact, spring leaf rebounds, and circuit disconnects, and slowspeed machine 11 quits work, now eccentric wheel 7 just rotates one week, and push rod 6 is retracted under spring 9 acts on.
Then, the ceramic tile 5 after rectification continues to move ahead with travelling belt, and the spring leaf pushing down rear spring sheet and switch contacts 4 makes it be connected with contact, circuit ON, and CCD camera 1 will be triggered and take, and by the image transmitting that photographs to image processing system 14.
Finally, by image processing system 14, the template image of image to be detected with the pattern-free defect ceramic tile of system storage is entered to mate, if matching degree is greater than setting threshold value, then think ceramic tile 5 zero defect, otherwise think ceramic tile 5 defectiveness, and then complete the defects detection of whole ceramic tile patterns.

Claims (4)

1. based on a ceramic tile patterns defect detecting device for machine vision, it is characterized in that: comprise ceramic tile transport module, centering module and vision-based detection module;
Described transport module comprises two parallel travelling belts (3), have certain level spacing, and coaxial drive makes to be synchronized with the movement between two bands;
Described centering module comprises front spring sheet and switch contacts (12), front spring sheet and switch contacts (12) are arranged on the pedestal in gap between two travelling belts (3), two covers slow-speed motor (11) and motor driver (13) are in series with front spring sheet and switch contacts (12), two eccentric wheels (7) are connected with the main shaft of slow-speed motor (11) respectively, one end of two push rods (6) is contacted by the outline of roller with eccentric wheel (7), the one piece of push pedal of other end vertical welding, push rod (6) is through handspike bearing (8), when eccentric wheel (7) rotates, pushing rolling wheels makes push rod (6) level stretch out.
2. the vision-based detection module described in comprises rear spring sheet and switch contacts (4), rear spring sheet and switch contacts (4) are arranged on the pedestal in gap between two travelling belts (3), and CCD camera (1), LED coaxial light source (2) and image processing system (14) are in series with rear spring sheet and switch contacts (4);
A kind of ceramic tile patterns defect detecting device based on machine vision according to claim 1, is characterized in that: described front spring sheet and switch contacts (12) and rear spring sheet and switch contacts (4) are made up of spring leaf and contact two parts.
3. a kind of ceramic tile patterns defect detecting device based on machine vision according to claim 1, it is characterized in that: described described push rod (6) is socketed by two hollow metal tubes and forms, two metal tube joint portions are processed with chute, and two pipes are connected firmly by bolt (10) at runner position, telescopic adjustment push rod (6) physical length is got final product by unclamping bolt (10), push rod (6) is provided with nut (15), spring (9) is installed between nut (15) and handspike bearing (8), push rod (6) automatic retraction can be made to reset by spring (9), and roller is contacted with eccentric wheel (7) all the time.
4. a kind of ceramic tile patterns defect detecting device based on machine vision according to claim 1, it is characterized in that: taken tile image is rotated 0 ° with the tile image that stores in system by described image processing system (14) respectively, 90 °, 180 °, standard form after 270 ° mates, if matching degree is greater than setting threshold value, then think 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 true CN104807834A (en) 2015-07-29
CN104807834B 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)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105904112A (en) * 2016-05-30 2016-08-31 中国计量大学 On-line detection device for weld defects of red copper pipe joint part based on machine vision technology

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
李温温: "瓷砖色差在线检测系统的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105904112A (en) * 2016-05-30 2016-08-31 中国计量大学 On-line detection device for weld defects of red copper pipe joint part based on machine vision technology
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

Also Published As

Publication number Publication date
CN104807834B (en) 2018-04-10

Similar Documents

Publication Publication Date Title
CN104792788B (en) A kind of gluing visible detection method and its device
CN103323457B (en) Fruit appearance defect real-time online detection system and detection method
CN103785627B (en) Lithium battery pole slice blemish on-line checkingi sorting system and method for sorting thereof
CN103170459B (en) Spectacle lens flaw detection system
CN104889075B (en) A kind of roller open defect vision inspection apparatus
CN101690933B (en) Device for automatically sorting feathers and sorting method
CN102338751B (en) Equipment for detecting circuit board defects based on visual detection method
CN104148920A (en) Steering knuckle bearing material press-fitting production line
EP2767927A3 (en) Face information detection apparatus, vehicle device control system employing face information detection apparatus, and carrier medium of face information detection program
CN103090804A (en) Automatic detection system and detection method of finished product magnet ring image
CN202330294U (en) Surface defect detection device based on machine vision
CN102636490A (en) Method for detecting surface defects of dustproof cover of bearing based on machine vision
CN104018850A (en) Binocular-vision-based segment positioning and capturing system of segment erector
CN203705352U (en) Magnetic shoe online detecting device based on machine vision
CN106272426B (en) The positioning of solar battery sheet series welding anterior optic and angle sensing device and detection method
CN104010190B (en) Method for automatically detecting dead pixels of mobile phone screen before assembling
CN103743752B (en) A kind of magnetic shoe online detection instrument based on machine vision
CN210347490U (en) Appearance detection equipment
CN104502356A (en) Automatic detection method for defects of inner surface of sliding bearing on basis of computer vision
CN202548066U (en) Printing product quality detecting machine
CN203245133U (en) Lens defect detecting system
CN104048607A (en) Visual identification and grabbing method of mechanical arms
CN101900636B (en) Detection device of bearing collar
CN201711420U (en) Waveform retainer combination processing device
CN205240886U (en) Permanent tension automatic control device

Legal Events

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