CN107194916A - A kind of vision measurement system of feature based Point matching - Google Patents
A kind of vision measurement system of feature based Point matching Download PDFInfo
- Publication number
- CN107194916A CN107194916A CN201710267845.0A CN201710267845A CN107194916A CN 107194916 A CN107194916 A CN 107194916A CN 201710267845 A CN201710267845 A CN 201710267845A CN 107194916 A CN107194916 A CN 107194916A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- described image
- measurement system
- vision measurement
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Library & Information Science (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of vision measurement system of feature based Point matching of technical field of visual measurement, the vision measurement system of the feature based Point matching includes image capture module, image pre-processing module, interpretation of result module, characteristic extracting module, image data base, image retrieval module, user's input module and result output module, effective avoid of the invention manually detects that identification labor intensity is big, efficiency is low, fatigability and traditional detection function are relatively simple, automation, the not high shortcoming of intelligence degree, accuracy of identification and real-time are high, the correctness and accuracy of matching can be improved, and the workload of matching can be reduced, so as to improve calculating speed, use vision measurement system more closing to reality production.
Description
Technical field
The present invention relates to technical field of visual measurement, specially a kind of vision measurement system of feature based Point matching.
Background technology
Machine vision is a cross discipline, be related to artificial intelligence, Neurobiology, psychophysics, computer science,
The subjects such as image procossing, pattern-recognition, have a wide range of applications basis.With electronic technology, computer hardware technique,
Image procossing and developed rapidly with human vision correlation technique, machine vision technique all achieves great in theory and practice
Development, the application in the field such as China's industry, agricultural, medical science, robot navigation, satellite remote sensing is more and more extensive.Large quantities of
In the industrial production of amount, the increasingly raising of the increasingly automated and product quality of production process, it is desirable to have it is more effective, more accurate and
The detection means of high speed, machine vision technique ensure that the reliability under industrial environment, improve production automation journey
Degree, greatly improves production efficiency.Therefore, in the production process of modernization, NI Vision Builder for Automated Inspection is widely used in product
The fields such as measurement, inspection, quality control.The concrete application of machine vision in the industry mainly has:Automobile full car size measurement, zero
Part edge and planar dimension detection etc..Therefore, making we have proposed a kind of vision measurement system of feature based Point matching input
With to solve the above problems.
The content of the invention
It is an object of the invention to provide a kind of vision measurement system of feature based Point matching, to solve above-mentioned background skill
The problem of being proposed in art.
To achieve the above object, the present invention provides following technical scheme:A kind of vision measurement system of feature based Point matching
System, the vision measurement system of the feature based Point matching includes image capture module, image pre-processing module, interpretation of result mould
Block, characteristic extracting module, image data base, image retrieval module, user's input module and result output module;
Described image acquisition module carries out visual image collection to examined object using the two groups of CCD cameras in left and right, and
The image of collection is uploaded in described image pretreatment module;
Described image pretreatment module is used to be converted into being calculated by the visual image and internal characteristicses of testee
The data of machine processing;
The interpretation of result module be used for the data that handle described image pretreatment module with described image database
Standard value be compared;
The characteristic extracting module is used to carry out rim detection to the image of the testee in described image database, and
Extract edge feature;
Described image database is used for the visual image for storing testee, and provides the model standard ginseng of testee
Number;
Described image retrieval module is used for the port for providing user search, and receives the inspection of the user input unit write-in
Rope information;
User's input module receives user input instruction, and input instruction is uploaded into described image retrieval module;
The result output module provides the result output channel of the interpretation of result resume module.
It is preferred that, the resolution ratio of the CCD camera in described image acquisition module is 2448pixel × 2050pixel, pixel
3.45 μm of (H) × 3.34 μm (V) of size, lens focus is 8mm.
It is preferred that, described image database is managed collectively by data base management system, and insertion, modification and the retrieval of data are equal
To be carried out by data base management system.
It is preferred that, user's input module is the personal PC machine of built-in multi-point touch control type capacitance plate.
Compared with prior art, the beneficial effects of the invention are as follows:Effective avoid of the invention manually detects identification work
Intensity is big, and efficiency is low, and fatigability and traditional detection function are relatively simple, automation, the not high shortcoming of intelligence degree, identification
Precision and real-time are high, it is possible to increase the correctness and accuracy of matching, and can reduce the workload of matching, so as to improve
Calculating speed, uses vision measurement system more closing to reality production.
Brief description of the drawings
Fig. 1 is principle of the invention block diagram.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Referring to Fig. 1, the present invention provides a kind of technical scheme:A kind of vision measurement system of feature based Point matching, should
The vision measurement system of feature based Point matching includes image capture module, image pre-processing module, interpretation of result module, feature
Extraction module, image data base, image retrieval module, user's input module and result output module;
Described image acquisition module carries out visual image collection to examined object using the two groups of CCD cameras in left and right, and
The image of collection is uploaded in described image pretreatment module;
Described image pretreatment module is used to be converted into being calculated by the visual image and internal characteristicses of testee
The data of machine processing;
The interpretation of result module be used for the data that handle described image pretreatment module with described image database
Standard value be compared;
The characteristic extracting module is used to carry out rim detection to the image of the testee in described image database, and
Extract edge feature;
Described image database is used for the visual image for storing testee, and provides the model standard ginseng of testee
Number;
Described image retrieval module is used for the port for providing user search, and receives the inspection of the user input unit write-in
Rope information;
User's input module receives user input instruction, and input instruction is uploaded into described image retrieval module;
The result output module provides the result output channel of the interpretation of result resume module.
Wherein, the resolution ratio of the CCD camera in described image acquisition module is 2448pixel × 2050pixel, pixel chi
Very little 3.45 μm of (H) × 3.34 μm (V), lens focus is 8mm, and described image database is managed collectively by data base management system,
Insertion, modification and the retrieval of data are intended to carry out by data base management system, and user's input module is that built-in multiple spot is touched
The personal PC machine of control formula capacitance plate.
Specifically, assuming that template is t (k, 1), size is n × m, and real-time figure is f (u, v), then similarity function isWherein (u, v) represents pixel coordinate, due to only doing plus and minus calculation,
If pair correlation function sets threshold value again, calculating the midway on most of positions will terminate, therefore arithmetic speed is very fast, template
After matching, the φ (u, v) of generation can regard a width gray level image as, can obtain binary image after being selected through threshold value, and by this two
Value image carries out Object Operations.In bianry image, change of scale is carried out to binary image using Gaussian kernel, image is obtained
Metric space under multiple dimensioned represents sequence, and these sequences are carried out with the feature extraction of metric space, wherein, two-dimensional Gaussian kernel
Shown in being defined as follows,Wherein σ represents the variance that Gauss is just being distributed very much, for two dimension
Image I (x, y), the metric space under different scale represents that L (x, y, σ) can be by image I's (x, y) and Gaussian kernel G (x, y, σ)
Convolution obtains L (x, y, σ)=G (x, y, σ) × I (x, y), wherein, L represents metric space, and (x, y) represents the point on image I, σ
It is scale factor, its value is smaller, represents that the image is smoothed smaller;Its value is more big, and characterize that the image is smoothed is bigger,
Large scale corresponds to the general picture feature of image, and small yardstick corresponds to the minutia of image.
Generally, there are numerous structural motifs of the same name, a certain matching particularly in piece image in match window
Feature primitive might have many candidate targets in another piece image, and really structural motif of the same name can only have one, head
First by matching characteristic sorting primitives, to determine which feature primitive as matching object, then to same in another sub-picture
One class formation primitive carries out the search of matching object, and the priori and constraints finally according to actual object differentiate matching
Statistical information in accuracy, the method extracted in the present invention using statistical nature, description image on a region, these letters
Breath be able to can also not included with inclusion region positional information, and a kind of the most frequently used statistical nature is invariant moment features, and bending moment is not special
Levy with rotation translation invariance, can be used in the images steganalysis with rigid body translation.During target identification,
Because figure is different from matching figure acquisition modes in real time, the time is different with the position in space, therefore real-time figure is relative to matching figure just
The geometric distortions such as certain translation, rotation and ratio change can be produced, the consistency of the geometric distortion of image moment just overcomes
This problem, reflects the intrinsic property of image, and its advantage is that process is simple, and with the tangible explanation to boundary shape.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of changes, modification can be carried out to these embodiments, replace without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (4)
1. a kind of vision measurement system of feature based Point matching, it is characterised in that:The vision measurement of the feature based Point matching
System includes image capture module, image pre-processing module, interpretation of result module, characteristic extracting module, image data base, image
Retrieve module, user's input module and result output module;
Described image acquisition module carries out visual image collection using the two groups of CCD cameras in left and right to examined object, and will adopt
The image of collection is uploaded in described image pretreatment module;
Described image pretreatment module is used for that be converted into the visual image and internal characteristicses of testee can be by computer
The data of reason;
The interpretation of result module is used for the data for handling described image pretreatment module and the mark in described image database
Quasi- value is compared;
The characteristic extracting module is used to carry out rim detection to the image of the testee in described image database, and extracts
Edge feature;
Described image database is used for the visual image for storing testee, and provides the model canonical parameter of testee;
Described image retrieval module is used for the port for providing user search, and receives the retrieval letter of the user input unit write-in
Breath;
User's input module receives user input instruction, and input instruction is uploaded into described image retrieval module;
The result output module provides the result output channel of the interpretation of result resume module.
2. a kind of vision measurement system of feature based Point matching according to claim 1, it is characterised in that:Described image
The resolution ratio of CCD camera in acquisition module is 2448pixel × 2050pixel, 3.45 μm of (H) × 3.34 μm of pixel dimension
(V), lens focus is 8mm.
3. a kind of vision measurement system of feature based Point matching according to claim 1, it is characterised in that:Described image
Database is managed collectively by data base management system, and insertion, modification and the retrieval of data are intended to enter by data base management system
OK.
4. a kind of vision measurement system of feature based Point matching according to claim 1, it is characterised in that:The user
Input module is the personal PC machine of built-in multi-point touch control type capacitance plate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710267845.0A CN107194916A (en) | 2017-04-22 | 2017-04-22 | A kind of vision measurement system of feature based Point matching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710267845.0A CN107194916A (en) | 2017-04-22 | 2017-04-22 | A kind of vision measurement system of feature based Point matching |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107194916A true CN107194916A (en) | 2017-09-22 |
Family
ID=59872326
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710267845.0A Pending CN107194916A (en) | 2017-04-22 | 2017-04-22 | A kind of vision measurement system of feature based Point matching |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107194916A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109766391A (en) * | 2019-01-21 | 2019-05-17 | 武汉裕量信息科技有限公司 | Detection system, detection method and computer-readable medium |
CN110110542A (en) * | 2019-05-23 | 2019-08-09 | 武汉神算云信息科技有限责任公司 | Image data management system, equipment and storage medium |
CN110239232A (en) * | 2019-04-08 | 2019-09-17 | 上海泰威技术发展股份有限公司 | A kind of intelligent identification Method for the more change in pattern printings of plate |
CN112769229A (en) * | 2020-12-11 | 2021-05-07 | 国网浙江省电力有限公司绍兴供电公司 | Disconnecting link state identification and analysis method based on fusion of object ID and image system |
CN114676957A (en) * | 2022-01-27 | 2022-06-28 | 福建瑞达精工股份有限公司 | Clock and watch product assembly quality data analysis system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030071908A1 (en) * | 2001-09-18 | 2003-04-17 | Masato Sannoh | Image pickup device, automatic focusing method, automatic exposure method, electronic flash control method and computer program |
CN101762253A (en) * | 2009-12-11 | 2010-06-30 | 北京科技大学 | System and method for multi-sensor-based on-line multi-dimension measurement of special-shaped shaft-type workpieces |
JP2013233639A (en) * | 2012-05-10 | 2013-11-21 | Hitachi Zosen Fukui Corp | Workpiece position detection method and workpiece conveyance method using same |
CN104112269A (en) * | 2014-05-12 | 2014-10-22 | 北京联合大学 | Solar cell laser-marking parameter detection method based on machine vision and system thereof |
CN104198013A (en) * | 2014-08-14 | 2014-12-10 | 青岛海诚自动化设备有限公司 | Water level measuring device based on machine vision technology |
-
2017
- 2017-04-22 CN CN201710267845.0A patent/CN107194916A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030071908A1 (en) * | 2001-09-18 | 2003-04-17 | Masato Sannoh | Image pickup device, automatic focusing method, automatic exposure method, electronic flash control method and computer program |
CN101762253A (en) * | 2009-12-11 | 2010-06-30 | 北京科技大学 | System and method for multi-sensor-based on-line multi-dimension measurement of special-shaped shaft-type workpieces |
JP2013233639A (en) * | 2012-05-10 | 2013-11-21 | Hitachi Zosen Fukui Corp | Workpiece position detection method and workpiece conveyance method using same |
CN104112269A (en) * | 2014-05-12 | 2014-10-22 | 北京联合大学 | Solar cell laser-marking parameter detection method based on machine vision and system thereof |
CN104198013A (en) * | 2014-08-14 | 2014-12-10 | 青岛海诚自动化设备有限公司 | Water level measuring device based on machine vision technology |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109766391A (en) * | 2019-01-21 | 2019-05-17 | 武汉裕量信息科技有限公司 | Detection system, detection method and computer-readable medium |
CN109766391B (en) * | 2019-01-21 | 2024-01-23 | 武汉易万科技有限公司 | Detection system, detection method, and computer-readable medium |
CN110239232A (en) * | 2019-04-08 | 2019-09-17 | 上海泰威技术发展股份有限公司 | A kind of intelligent identification Method for the more change in pattern printings of plate |
CN110110542A (en) * | 2019-05-23 | 2019-08-09 | 武汉神算云信息科技有限责任公司 | Image data management system, equipment and storage medium |
CN112769229A (en) * | 2020-12-11 | 2021-05-07 | 国网浙江省电力有限公司绍兴供电公司 | Disconnecting link state identification and analysis method based on fusion of object ID and image system |
CN114676957A (en) * | 2022-01-27 | 2022-06-28 | 福建瑞达精工股份有限公司 | Clock and watch product assembly quality data analysis system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fan et al. | A performance evaluation of local features for image-based 3D reconstruction | |
CN107194916A (en) | A kind of vision measurement system of feature based Point matching | |
CN102704215B (en) | Automatic cutting method of embroidery cloth based on combination of DST file parsing and machine vision | |
CN113160285B (en) | Point cloud matching method based on local depth image criticality | |
CN103093191A (en) | Object recognition method with three-dimensional point cloud data and digital image data combined | |
CN112132886A (en) | Circular hole center rapid positioning and roundness detection method for aviation part | |
CN106327534A (en) | Tire inner wall texture identification method based on locating block | |
Ma et al. | Binocular vision object positioning method for robots based on coarse-fine stereo matching | |
CN115690803A (en) | Digital image recognition method and device, electronic equipment and readable storage medium | |
Li et al. | A novel hand gesture recognition based on high-level features | |
Xing et al. | 3dtnet: Learning local features using 2d and 3d cues | |
Liu et al. | Improved image matching algorithm based on LK optical flow and grid motion statistics | |
Wang et al. | Real-time visual static hand gesture recognition system and its FPGA-based hardware implementation | |
Sowah et al. | An intelligent instrument reader: using computer vision and machine learning to automate meter reading | |
CN113657339A (en) | Instrument pointer counting and reading method and medium based on machine vision | |
CN113705564A (en) | Pointer type instrument identification reading method | |
Dong et al. | Superpixel-based local features for image matching | |
AUGMENTED | Grayscale image enhancement for enhancing features detection in marker-less augmented reality technology | |
Li et al. | Online workpieces recognition for the robotic spray-painting production line with a low-cost RGB-D camera | |
CN109858353A (en) | Facial image feature extracting method based on mark transformation and LBP | |
CN114743257A (en) | Method for detecting and identifying image target behaviors | |
Liu et al. | New anti-blur and illumination-robust combined invariant for stereo vision in human belly reconstruction | |
Wang et al. | A Pointer Instrument Reading Approach Based On Mask R-CNN Key Points Detection | |
Li et al. | A Fourier Descriptor for Bone Point Segmentation using inner distance in remote sensing images | |
Liu et al. | Identification and reading method of pointer meter based on CBAM D2-Net |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170922 |
|
RJ01 | Rejection of invention patent application after publication |