CN100501312C - Gem tri-dimensional cut detection device based on machine vision - Google Patents
Gem tri-dimensional cut detection device based on machine vision Download PDFInfo
- Publication number
- CN100501312C CN100501312C CNB2007100727726A CN200710072772A CN100501312C CN 100501312 C CN100501312 C CN 100501312C CN B2007100727726 A CNB2007100727726 A CN B2007100727726A CN 200710072772 A CN200710072772 A CN 200710072772A CN 100501312 C CN100501312 C CN 100501312C
- Authority
- CN
- China
- Prior art keywords
- jewel
- image
- parameter
- cut
- measured
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a detecting device and a method of the jewel three-dimensional cutting based on a machine vision, and relates to the jewel cutting detecting field. The invention solves the disadvantages in the prior technology that the working procedure is complicated, the efficiency is lower, the practicability is bad, and the equipment cost is high. The invention has the detecting device that an acquisition device signal output end is connected with an image acquisition card signal input end, the image acquisition card signal output end is connected with a processing system signal input end, an acquisition device, a lighting device an the jewel to be measured are arranged in the same straight line, the processing system signal output end is connected with an equipment control card signal input end, a first control end of an equipment control card is connected with the controlled end of a drive motor, the driving output end of the drive motor is connected to a platform machine body. The invention has the method and procedure that: 1. a system is started up; 2. an image is acquainted; 3. the pre-treatment and the analysis are performed to the image; 4. the acquisition finish is judged; 5. the three-dimensional image is calculated and detected; 6. the comparison is performed; 7. the type and the cutting parameter are obtained. The invention has the advantages that the automation is complete, the detection time is short, the parameter is derived directly, and the cost is cheap.
Description
Technical field
The present invention relates to a kind of jewel cut detection range, be specifically related to a kind of machine vision method and carry out the method that gem tri-dimensional cut detects.
Background technology
The cut grade directly influences this jewel commercial value in the evaluation of jewel, and cut is measured very important, but difficulty is also very big simultaneously.Jewel cut detection system need accurately be measured physical dimension, angle and the ratio of cutting grinding stone, and its cut quality is made evaluation.At present the jewel measuring system that exists mainly contains two classes: a class is carried out labor measurement with engineer's scale to the projected image of jewel, calculate lower, the poor practicability of measuring of efficient, and whole process is loaded down with trivial details, length consuming time, generally need dozens of minutes even a few hours just can finish, and the result seriously relies on tester's experience, is difficult to reach the degree of accuracy of detection.Another kind of system places jewel on the high-precision two-dimensional mobile platform, use microscope to amplify jewel, regulating two-dimensional stage makes the wedge angle of jewel be in microscopical crosshair place, the two-dimensional coordinate of each wedge angle by the position transducer on platform record jewel uses signal processing apparatus to calculate the angle and distance between each wedge angle and then the parameter of definite jewel then.There is inefficient shortcoming equally in this method, owing to only write down jewel wedge angle coordinate, this system can not truly reflect the three-dimensional information of each face of jewel simultaneously.
Summary of the invention
The operation of calculating measurement in the prior art is numerous and diverse, efficient is lower, the shortcoming of poor practicability in order to solve in the present invention, and has proposed a kind of gem tri-dimensional cut detection method based on machine vision.
The inventive system comprises image capturing system 1, rotatable platform equipment 2 and disposal system 3, described image capturing system 1 is by harvester 1-1, image pick-up card 1-2 and lighting device 1-3 form, the signal output part of harvester 1-1 connects the signal input part of image pick-up card 1-2, the signal input part of the signal output part connection processing system 3 of image pick-up card 1-2, described harvester 1-1, jewel A to be measured and lighting device 1-3 are successively set on same the axis, described rotatable platform equipment 2 is by platform body 2-1, drive motor 2-2 and device control card 2-3 form, the signal input part of the signal output part connection device control card 2-3 of described disposal system 3, first control end of device control card 2-3 connects the controlled end of drive motor 2-2, the transmission output terminal of drive motor 2-2 connects on the platform body 2-1, has an image capturing system 1 in the described device at least.
The step of detection method of the present invention is as follows:
Step 1: start-up system: jewel A to be measured is placed on the rotatable platform equipment 2, disposal system 3 is sent steering order, start image capturing system 1 and rotatable platform equipment 2, drive platform body 2-1 by device control card 2-3 controlling and driving motor 2-2 with assigned rate and carry out the high precision rotation;
Step 2: images acquired: at the appointed time gather the jewel image of current angle at interval by harvester 1-1, the image of collection is converted into the multiframe digital picture by image pick-up card 1-2 and imports in the disposal system 3;
Step 3: image pre-service and analysis: every frame of digital image in the multiframe digital picture of gathering and corresponding angle parameter are carried out pre-service through in the disposal system 3, will handle back multiframe digital picture afterwards and carry out the graphical analysis of each aspect;
Step 4: judge to gather whether finish: judge whether platform body 2-1 rotates a circle; Be, image acquisition process is finished, and enters step 5; , do not return step 2 and continue images acquired;
Step 5: 3-D view calculates and detects: the three-dimensional surface and the form parameter that obtain jewel A to be measured by three-dimensional detection algorithm;
Step 6: contrast: the three-dimensional surface of jewel A to be measured and form parameter be kept at disposal system 3 in the parameter of jewel type in the standard database compare, further calculate jewel A shape to be measured and cut parameter;
Step 7: obtain type and cut parameter: the type and the cut parameter result that obtain final jewel A to be measured.
Characteristics of the present invention are:
(1) the whole testing process full automation of jewel cut need not manual intervention.System is short detection time, and every jewel detection time is only about 10 seconds; It is convenient to measure, and only needs jewel is arbitrarily placed on the rotation platform, need not manual calibrating position, thereby can carry out the jewel batch detection easily.
(2) directly calculate the three-dimensional cut and the form parameter of jewel, and show testing result intuitively with three dimensional constitution, the user checks conveniently.Same picture, 3-D display detect jewel and standard jewel, and the user can carry out the cut and the parameter comparison of jewel integral body and any local facet intuitively.
(3) system uses component equipments such as business-like video camera, control card, secondary light source based on the machine vision principle, and homogeneous system need not special measuring appliance relatively, thereby easy to use, the cost performance height.
(4) can detect the small-sized polyhedron shape workpiece of other any type.
(5) have preservation, inquiry, and the function of the generation of form and printing is used and is inquired about thereby provide to access in the future.
Description of drawings
Fig. 1 is the structural representation of apparatus of the present invention; Fig. 2 is the process flow diagram of inventive method; Fig. 3 is the process flow diagram of inventive method step 3; Fig. 4 is the process flow diagram of inventive method step 5.
Embodiment
Embodiment one: present embodiment is described in conjunction with Fig. 1, the device of present embodiment is by image capturing system 1, rotatable platform equipment 2 and disposal system 3 are formed, described image capturing system 1 is by harvester 1-1, image pick-up card 1-2 and lighting device 1-3 form, the signal output part of harvester 1-1 connects the signal input part of image pick-up card 1-2, the signal input part of the signal output part connection processing system 3 of image pick-up card 1-2, described harvester 1-1, jewel A to be measured and lighting device 1-3 are successively set on same the axis, described rotatable platform equipment 2 is by platform body 2-1, drive motor 2-2 and device control card 2-3 form, the signal input part of the signal output part connection device control card 2-3 of described disposal system 3, first control end of device control card 2-3 connects the controlled end of drive motor 2-2, the transmission output terminal of drive motor 2-2 connects on the platform body 2-1, has an image capturing system 1 in the described device at least.
Embodiment two: present embodiment is described in conjunction with Fig. 1, present embodiment and embodiment one difference are that harvester 1-1 is made up of camera lens 1-1-1 and video camera 1-1-2, the imaging plane of video camera 1-1-2 is arranged on the focal plane of camera lens 1-1-1, and video camera 1-1-2 is SONY 1/3 " 600 line high-resolution video cameras.Other composition is identical with embodiment one with connected mode.By camera lens 1-1-1 information is converged on the video camera 1-1-2, make the image information that collects more accurate.
Embodiment three: present embodiment is described in conjunction with Fig. 1, present embodiment and embodiment one difference are that lighting device 1-3 is made up of secondary light source 1-3-1 and Fresnel Lenses 1-3-2, and secondary light source 1-3-1 is arranged on the focus of Fresnel Lenses 1-3-2.Other composition is identical with embodiment one with connected mode.In image acquisition process, the jewel detection directional light that becomes backlight that secondary light source 1-3-1 is provided by Fresnel Lenses 1-3-2.
Embodiment four: in conjunction with Fig. 1 present embodiment is described, present embodiment is that with embodiment three differences second control end of device control card 2-3 is connected the controlled end of secondary light source 1-3-1, reaches the purpose of automatic control.Other composition is identical with embodiment three with connected mode.
Embodiment five: present embodiment is described in conjunction with Fig. 1, present embodiment and embodiment one difference are that rotatable platform equipment 2 has increased air pump 2-4, air pump 2-4 is arranged on the platform body 2-1, the 3rd control end of device control card 2-3 connects the controlled end of air pump 2-4, take out the function of stream by the gas of air pump 2-4, between the crown of platform body 2-1 and jewel A to be measured, produce negative pressure, keep jewel A to be measured and platform body 2-1 relative fixed in the rotary course.Other composition is identical with embodiment one with connected mode.
Embodiment six: in conjunction with Fig. 1 present embodiment is described, present embodiment and embodiment one difference are to have increased display device 4, and the output terminal of disposal system 3 connects the input end of display device 4.Other composition is identical with embodiment one with connected mode.
Embodiment seven: in conjunction with Fig. 2 present embodiment is described, the method step of present embodiment is as follows:
Step 1: start-up system: jewel A to be measured is placed on the rotatable platform equipment 2, disposal system 3 is sent steering order, start image capturing system 1 and rotatable platform equipment 2, drive platform body 2-1 by device control card 2-3 controlling and driving motor 2-2 with assigned rate and carry out the high precision rotation;
Step 2: images acquired: at the appointed time gather the jewel image of current angle at interval by harvester 1-1, the image of collection is converted into the multiframe digital picture by image pick-up card 1-2 and imports in the disposal system 3;
Step 3: image pre-service and analysis: every frame of digital image in the multiframe digital picture of gathering and corresponding angle parameter are carried out pre-service through in the disposal system 3, will handle back multiframe digital picture afterwards and carry out the graphical analysis of each aspect;
Step 4: judge to gather whether finish: judge whether platform body 2-1 rotates a circle; Be, image acquisition process is finished, and enters step 5; , do not return step 2 and continue images acquired;
Step 5: 3-D view calculates and detects: the three-dimensional surface and the form parameter that obtain jewel A to be measured by three-dimensional detection algorithm;
Step 6: contrast: the three-dimensional surface of jewel A to be measured and form parameter be kept at disposal system 3 in the parameter of jewel type in the standard database compare, further calculate jewel A shape to be measured and cut parameter;
Step 7: obtain type and cut parameter: the type and the cut parameter result that obtain final jewel A to be measured.
Embodiment eight: present embodiment is described in conjunction with Fig. 3, present embodiment and embodiment seven differences are step 3: image pre-service and analysis, and the step of image pre-service and analysis is as follows: steps A: carry out the image pre-service: by removing noise, thresholding and image segmentation every frame of digital image of different angles is handled; Step B: jewel profile fitting a straight line: from handle the every frame of digital image in back, extract the jewel profile, use the Douglas-Peucker algorithm to carry out fitting a straight line; Step C: cut apart each aspect: with the numbering of the profile straight line case preface after the match, grouping-hierarchy then.Other step is identical with embodiment seven.
Embodiment nine: present embodiment is described in conjunction with Fig. 4, present embodiment and embodiment seven differences are step 5: 3-D view calculates and detects, and 3-D view calculates as follows with the step that detects: step a: mate each aspect profile: carry out profile fitting a straight line identical on each aspect of multiframe digital picture corresponding; Step b: data filtering and cut apart each space plane: the data filtering of the profile fitting a straight line of correspondence being carried out the minimax value judges, thereby judges the intersection between the space plane, is combined into each space plane by intersection; Step c: calculate jewel reference center and each space plane physical dimension; Steps d: calculate each space plane parameter, step e: result optimizing: delete too small space plane, revise the linking plane, thereby obtain three-dimensional surface and the form parameter of jewel A to be measured.Other step is identical with embodiment seven.
Embodiment ten: present embodiment and embodiment seven differences are that the 3D shape of the jewel A to be measured in the step 7 and the 3D shape and the cut parameter of cut parameter and standard jewel are presented on the display device 4, reach 3D shape and be rotated and local amplification, conveniently check and the contrast effect.And by disposal system 3 with report form output with store all data, use and inquire about for access in the future.Other step is identical with embodiment seven.
Claims (4)
1,, it is characterized in that its step is as follows based on the gem tri-dimensional cut detection method of machine vision:
Step 1: start-up system: jewel to be measured (A) is placed on the rotatable platform equipment (2), disposal system (3) is sent steering order, start image capturing system (1) and rotatable platform equipment (2), drive platform body (2-1) by device control card (2-3) controlling and driving motor (2-2) with assigned rate and carry out the high precision rotation;
Step 2: images acquired: at the appointed time gather the jewel image of current angle at interval by harvester (1-1), the image of collection is converted into the multiframe digital picture by image pick-up card (1-2) and imports in the disposal system (3);
Step 3: image pre-service and analysis: will carry out pre-service in every frame of digital image in the multiframe digital picture of gathering and the corresponding angle parameter process disposal system (3), will handle back multiframe digital picture afterwards and carry out the graphical analysis of each aspect;
Step 4: judge to gather whether finish: judge whether platform body (2-1) rotates a circle; Be, image acquisition process is finished, and enters step 5; , do not return step 2 and continue images acquired;
Step 5: 3-D view calculates and detects: the three-dimensional surface and the form parameter that obtain jewel to be measured (A) by three-dimensional detection algorithm;
Step 6: contrast: the three-dimensional surface of jewel to be measured (A) and form parameter are compared with the parameter of jewel type in being kept at the middle standard database of disposal system (3), further calculate jewel to be measured (A) shape and cut parameter;
Step 7: obtain type and cut parameter: the type and the cut parameter result that obtain final jewel to be measured (A).
2, the gem tri-dimensional cut detection method based on machine vision according to claim 1, it is characterized in that step 3: image pre-service and analysis, the step of image pre-service and analysis is as follows: steps A: carry out the image pre-service: by removing noise, thresholding and image segmentation every frame of digital image of different angles is handled; Step B: jewel profile fitting a straight line: from handle the every frame of digital image in back, extract the jewel profile, use the Douglas-Peucker algorithm to carry out fitting a straight line; Step C: cut apart each aspect: with the numbering of the profile straight line case preface after the match, grouping-hierarchy then.
3, the gem tri-dimensional cut detection method based on machine vision according to claim 1, it is characterized in that step 5: 3-D view calculates and detects, and 3-D view calculates as follows with the step that detects: step a: mate each aspect profile: carry out profile fitting a straight line identical on each aspect of multiframe digital picture corresponding; Step b: data filtering and cut apart each space plane: the data filtering of the profile fitting a straight line of correspondence being carried out the minimax value judges, thereby judges the intersection between the space plane, is combined into each space plane by intersection; Step c: calculate jewel reference center and each space plane physical dimension; Steps d: calculate each space plane parameter, step e: result optimizing: delete too small space plane, revise the linking plane, thereby obtain the three-dimensional surface and the form parameter of jewel to be measured (A).
4, the gem tri-dimensional cut detection method based on machine vision according to claim 1, it is characterized in that the 3D shape of the jewel to be measured (A) in the step 7 and the 3D shape and the cut parameter of cut parameter and standard jewel are presented on the display device (4), and export and store all data with report form by disposal system (3).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2007100727726A CN100501312C (en) | 2007-09-06 | 2007-09-06 | Gem tri-dimensional cut detection device based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2007100727726A CN100501312C (en) | 2007-09-06 | 2007-09-06 | Gem tri-dimensional cut detection device based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101144704A CN101144704A (en) | 2008-03-19 |
CN100501312C true CN100501312C (en) | 2009-06-17 |
Family
ID=39207351
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2007100727726A Expired - Fee Related CN100501312C (en) | 2007-09-06 | 2007-09-06 | Gem tri-dimensional cut detection device based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN100501312C (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8270719B2 (en) * | 2008-10-14 | 2012-09-18 | Gemological Appraisal Association, Inc. | Gem pattern matching algorithm to determine the percentage match of a target gem pattern to a database of gem patterns |
CA2788068C (en) | 2010-01-26 | 2019-09-10 | De Beers Centenary AG | Gemstone sparkle analysis |
FR2993191B1 (en) * | 2012-07-16 | 2015-01-16 | Snecma | METHODS AND CUTTING SYSTEM |
CN103472064B (en) * | 2013-10-12 | 2015-11-18 | 梧州学院 | A kind of method of justifying the qualification of bright cut jewel cut |
CN104197833B (en) * | 2014-08-25 | 2017-01-25 | 华东泰克西汽车铸造有限公司 | Automatic detection control method for checking core support of sand core |
CN108692678A (en) * | 2018-05-30 | 2018-10-23 | 中国地质大学(武汉) | A kind of accurate gem three-dimensional measuring device based on laser |
CN108846403B (en) * | 2018-06-04 | 2023-04-07 | 武汉恒宇科教仪器设备研发有限公司 | Method for extracting facet gem image features |
CN109099867A (en) * | 2018-06-26 | 2018-12-28 | 无锡新吉凯氏测量技术有限公司 | A kind of jewel certification and identifying system and method based on geometric shape information |
CN109040712A (en) * | 2018-09-27 | 2018-12-18 | 深圳市完美爱钻石有限公司 | Fiery coloured silk cutting scope |
CN110095080A (en) * | 2018-12-11 | 2019-08-06 | 上海大学 | A kind of small parts fast two-dimensional overall size measuring device |
CN111351429B (en) * | 2018-12-20 | 2021-07-30 | 武汉永能智翔自动化系统有限公司 | Hexahedron size measuring system and method based on motion control and machine vision |
-
2007
- 2007-09-06 CN CNB2007100727726A patent/CN100501312C/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN101144704A (en) | 2008-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100501312C (en) | Gem tri-dimensional cut detection device based on machine vision | |
CN109859272B (en) | Automatic focusing binocular camera calibration method and device | |
JP7037876B2 (en) | Use of 3D vision in automated industrial inspection | |
CA2724495C (en) | Accurate image acquisition for structured-light system for optical shape and positional measurements | |
CN107014321B (en) | Rapid field flatness measuring device and measuring method | |
US9215453B2 (en) | Method for calibrating a measurement system and device for carrying out the method | |
CN103824298B (en) | A kind of intelligent body 3 D visual positioner based on twin camera and method | |
WO2021185220A1 (en) | Three-dimensional model construction and measurement method based on coordinate measurement | |
TW201026428A (en) | System for positioning micro tool of micro machine and method thereof | |
CN102353349B (en) | Machine vision based micro-sound film concentricity online testing system and testing method | |
CN107084671B (en) | A kind of recessed bulb diameter measuring system and measurement method based on three wire configuration light | |
CN113267141B (en) | Microscopic three-dimensional information acquisition equipment | |
WO2014011182A1 (en) | Convergence/divergence based depth determination techniques and uses with defocusing imaging | |
CN106918306A (en) | Industrial products three-dimensional appearance real-time detecting system based on light field one camera | |
CN109636857B (en) | Alignment method and calibration system | |
CN112254680B (en) | Multi freedom's intelligent vision 3D information acquisition equipment | |
CN100462672C (en) | Image measuring system and method | |
CN111811431A (en) | Three-dimensional scanner, three-dimensional scanning system and method | |
CN110044266B (en) | Photogrammetry system based on speckle projection | |
CN201082573Y (en) | Jewel three-dimensional autodesign and detecting device based on machine vision | |
JP3696336B2 (en) | How to calibrate the camera | |
TW202147050A (en) | System and method for controlling automatic inspection of articles | |
CN110657750B (en) | Detection system and method for passivation of cutting edge of cutter | |
CN111351429B (en) | Hexahedron size measuring system and method based on motion control and machine vision | |
CN206583440U (en) | A kind of projected image sighting distance detecting system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090617 Termination date: 20150906 |
|
EXPY | Termination of patent right or utility model |