CN106845481A - A kind of goods and materials shape recognition process based on binocular image vision - Google Patents
A kind of goods and materials shape recognition process based on binocular image vision Download PDFInfo
- Publication number
- CN106845481A CN106845481A CN201710037352.8A CN201710037352A CN106845481A CN 106845481 A CN106845481 A CN 106845481A CN 201710037352 A CN201710037352 A CN 201710037352A CN 106845481 A CN106845481 A CN 106845481A
- Authority
- CN
- China
- Prior art keywords
- goods
- gray level
- level image
- materials
- ampuliform
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to waste and old ampuliform recycle technology, specifically a kind of goods and materials shape recognition process based on binocular image vision.The present invention solves the problems, such as that the existing waste and old ampuliform goods and materials identification technology scope of application is limited, cost of implementation is high, technical difficulty is big, recognition efficiency is low, identification accuracy is low.A kind of goods and materials shape recognition process based on binocular image vision, the method is realized using following steps：Step S1：The upright ampuliform goods and materials placed are carried out overlooking shooting and eyelevel shot simultaneously；Step S2：Gray level image A and gray level image B are corrected respectively；Step S3：Medium filtering is carried out to the gray level image A and gray level image B after correction respectively；Step S4：Identify the circular feature region and rectangular characteristic region of ampuliform goods and materials；Step S5：Identify the edge in the circular feature region of ampuliform goods and materials and the edge in rectangular characteristic region；Step S6：Reconstruct the image of ampuliform goods and materials.The present invention is applied to waste and old ampuliform recycle.
Description
Technical field
The present invention relates to waste and old ampuliform recycle technology, specifically a kind of goods and materials shape based on binocular image vision is known
Other method.
Background technology
The identification of waste and old ampuliform goods and materials is the primary link during waste and old ampuliform recycle.In prior art condition
Under, the identification of waste and old ampuliform goods and materials is generally carried out using following several identification technologies：First, radio frequency identification：Using scanning bar shaped
The technology of code recognizes the species of waste and old ampuliform goods and materials.2nd, Material Identification：The material of waste and old ampuliform goods and materials is recognized using sensor
Matter.3rd, ultrasonic ranging+identification of weighing：The length and diameter of waste and old ampuliform goods and materials are substantially calculated using ultrasonic measuring distance technology,
And the weight of waste and old ampuliform goods and materials is recognized using weighing technology.4th, normal image identification：Recognized using background subtraction useless
Old ampuliform goods and materials.But practice have shown that, above-mentioned waste and old ampuliform goods and materials identification technology is limited by itself principle, and generally existing is as follows
Problem：First, the waste and old ampuliform goods and materials of radio frequency identification technical requirements must carry bar code, once the bar code of waste and old ampuliform goods and materials takes off
Fall, thus its identification that just cannot carry out waste and old ampuliform goods and materials cause its scope of application to be limited.2nd, Material Identification technology is present
The problem that cost of implementation is high, technical difficulty is big, recognition efficiency is low.3rd, there is identification accurately in ultrasonic ranging+identification technology of weighing
The low problem of degree.4th, the background of normal image identification technology requirement image is uniform and constant, causes it to there is technical difficulty
Greatly, the low problem of recognition efficiency.It is existing to solve based on this, it is necessary to invent a kind of brand-new waste and old ampuliform goods and materials identification technology
With the presence of the above mentioned problem of waste and old ampuliform goods and materials identification technology.
The content of the invention
The existing waste and old ampuliform goods and materials identification technology scope of application is limited, cost of implementation is high, technology is difficult in order to solve for the present invention
Degree is big, the problem that recognition efficiency is low, identification accuracy is low, there is provided a kind of goods and materials shape recognition side based on binocular image vision
Method.
The present invention adopts the following technical scheme that realization：
A kind of goods and materials shape recognition process based on binocular image vision, the method is realized using following steps：
Step S1：Using orthogonal binocular camera, the upright ampuliform goods and materials placed are carried out overlooking shooting and eyelevel shot simultaneously,
Thus gray level image A and gray level image B is respectively obtained；The gray level image A and eyelevel shot that vertical view shooting is obtained are obtained
Gray level image B simultaneously include ampuliform goods and materials and background；
Step S2：Using perspective transform algorithm, gray level image A and gray level image B are corrected respectively, thus respectively from
Distortion is eliminated in gray level image A and gray level image B；
Step S3：Medium filtering is carried out to the gray level image A and gray level image B after correction respectively, thus respectively from gray scale
Noise is eliminated in change image A and gray level image B；
Step S4：Using maximum cross correlation algorithm, the circular feature area of ampuliform goods and materials is on the one hand identified from gray level image A
Domain, the circular feature region is made up of bottom of bottle and bottleneck, and the rectangle of ampuliform goods and materials is on the other hand identified from gray level image B
Characteristic area, the rectangular characteristic region is made up of bottleneck and body；
Step S5：Using Sobel operators, the circular feature region of ampuliform goods and materials is on the one hand identified from gray level image A
Edge, on the other hand identifies the edge in the rectangular characteristic region of ampuliform goods and materials from gray level image B；
Step S6：The size in the circular feature region of bottle shaped article money is calculated from gray level image A, from gray level image B
The size in the rectangular characteristic region of ampuliform goods and materials is calculated, the image of ampuliform goods and materials is thus reconstructed.
Compared with existing waste and old ampuliform goods and materials identification technology, a kind of goods and materials based on binocular image vision of the present invention
Shape recognition process by use brand-new recognition principle, realize and waste and old ampuliform goods and materials be identified, thus possess as
Lower advantage：First, compared with radio frequency identification technology, the present invention carries bar code without waste and old ampuliform goods and materials, you can carry out Waste bottle
The identification of shape goods and materials, therefore its scope of application is no longer limited.2nd, compared with Material Identification technology, cost of implementation of the present invention is lower,
Technical difficulty is smaller, recognition efficiency is higher.3rd, compared with ultrasonic ranging+identification technology of weighing, identification accuracy of the present invention is more
It is high.4th, compared with normal image identification technology, the background that the present invention is no longer required for image is uniform and constant, therefore its skill
Art difficulty is smaller, recognition efficiency is higher.
The present invention efficiently solves that the existing waste and old ampuliform goods and materials identification technology scope of application is limited, cost of implementation is high, technology
The problem that difficulty is big, recognition efficiency is low, identification accuracy is low, it is adaptable to waste and old ampuliform recycle.
Brief description of the drawings
Fig. 1 is schematic flow sheet of the invention.
Specific embodiment
A kind of goods and materials shape recognition process based on binocular image vision, the method is realized using following steps：
Step S1：Using orthogonal binocular camera, the upright ampuliform goods and materials placed are carried out overlooking shooting and eyelevel shot simultaneously,
Thus gray level image A and gray level image B is respectively obtained；The gray level image A and eyelevel shot that vertical view shooting is obtained are obtained
Gray level image B simultaneously include ampuliform goods and materials and background；
Step S2：Using perspective transform algorithm, gray level image A and gray level image B are corrected respectively, thus respectively from
Distortion is eliminated in gray level image A and gray level image B；
Step S3：Medium filtering is carried out to the gray level image A and gray level image B after correction respectively, thus respectively from gray scale
Noise is eliminated in change image A and gray level image B；
Step S4：Using maximum cross correlation algorithm, the circular feature area of ampuliform goods and materials is on the one hand identified from gray level image A
Domain, the circular feature region is made up of bottom of bottle and bottleneck, and the rectangle of ampuliform goods and materials is on the other hand identified from gray level image B
Characteristic area, the rectangular characteristic region is made up of bottleneck and body；
Step S5：Using Sobel operators, the circular feature region of ampuliform goods and materials is on the one hand identified from gray level image A
Edge, on the other hand identifies the edge in the rectangular characteristic region of ampuliform goods and materials from gray level image B；
Step S6：The size in the circular feature region of bottle shaped article money is calculated from gray level image A, from gray level image B
The size in the rectangular characteristic region of ampuliform goods and materials is calculated, the image of ampuliform goods and materials is thus reconstructed.
In the step S5, the template that Sobel operators are used is。
Claims (2)
1. a kind of goods and materials shape recognition process based on binocular image vision, it is characterised in that：The method is to use following steps
Realize：
Step S1：Using orthogonal binocular camera, the upright ampuliform goods and materials placed are carried out overlooking shooting and eyelevel shot simultaneously,
Thus gray level image A and gray level image B is respectively obtained；The gray level image A and eyelevel shot that vertical view shooting is obtained are obtained
Gray level image B simultaneously include ampuliform goods and materials and background；
Step S2：Using perspective transform algorithm, gray level image A and gray level image B are corrected respectively, thus respectively from
Distortion is eliminated in gray level image A and gray level image B；
Step S3：Medium filtering is carried out to the gray level image A and gray level image B after correction respectively, thus respectively from gray scale
Noise is eliminated in change image A and gray level image B；
Step S4：Using maximum cross correlation algorithm, the circular feature area of ampuliform goods and materials is on the one hand identified from gray level image A
Domain, the circular feature region is made up of bottom of bottle and bottleneck, and the rectangle of ampuliform goods and materials is on the other hand identified from gray level image B
Characteristic area, the rectangular characteristic region is made up of bottleneck and body；
Step S5：Using Sobel operators, the circular feature region of ampuliform goods and materials is on the one hand identified from gray level image A
Edge, on the other hand identifies the edge in the rectangular characteristic region of ampuliform goods and materials from gray level image B；
Step S6：The size in the circular feature region of bottle shaped article money is calculated from gray level image A, from gray level image B
The size in the rectangular characteristic region of ampuliform goods and materials is calculated, the image of ampuliform goods and materials is thus reconstructed.
2. a kind of goods and materials shape recognition process based on binocular image vision according to claim 1, it is characterised in that：Institute
State in step S5, the template that Sobel operators are used is 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710037352.8A CN106845481A (en) | 2017-01-19 | 2017-01-19 | A kind of goods and materials shape recognition process based on binocular image vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710037352.8A CN106845481A (en) | 2017-01-19 | 2017-01-19 | A kind of goods and materials shape recognition process based on binocular image vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106845481A true CN106845481A (en) | 2017-06-13 |
Family
ID=59124523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710037352.8A Pending CN106845481A (en) | 2017-01-19 | 2017-01-19 | A kind of goods and materials shape recognition process based on binocular image vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106845481A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368802A (en) * | 2020-03-28 | 2020-07-03 | 河南工业职业技术学院 | Material shape recognition method based on binocular image vision |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279785A (en) * | 2014-06-24 | 2016-01-27 | 北京鸿合智能系统股份有限公司 | Display platform three-dimensional modeling method and device |
-
2017
- 2017-01-19 CN CN201710037352.8A patent/CN106845481A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279785A (en) * | 2014-06-24 | 2016-01-27 | 北京鸿合智能系统股份有限公司 | Display platform three-dimensional modeling method and device |
Non-Patent Citations (1)
| Title |
|---|
| 陆志敏: "玻璃瓶罐外形尺寸的计算机视觉检测", 《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368802A (en) * | 2020-03-28 | 2020-07-03 | 河南工业职业技术学院 | Material shape recognition method based on binocular image vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022027949A1 (en) | Machine vision-based detecting method and system for glass bottle bottom defects | |
| CN104764746B (en) | A kind of detection method of comprehensive PET bottle lid anti-theft ring defect | |
| CN105865570A (en) | Machine vision-based glass bottle liquid level detection method | |
| CN104535586B (en) | Strip steel edge defect detection identification method | |
| CN106952257A (en) | A kind of curved surface label open defect detection method based on template matches and Similarity Measure | |
| CN110246122A (en) | Small size bearing quality determining method, apparatus and system based on machine vision | |
| CN106290382A (en) | Bubble-cap tablet package defective vision detection device and method | |
| CN104574353B (en) | The surface defect decision method of view-based access control model conspicuousness | |
| EP2278260A3 (en) | Method and apparatus for measuring dents | |
| CL2021001855A1 (en) | System and method to detect scanning irregularities in self-checkout terminals | |
| EP3214603A3 (en) | Image processing | |
| EP3002712A3 (en) | Horizontal and vertical line detection and removal for document images | |
| ATE548707T1 (en) | METHOD AND DEVICE FOR FINGERPRINT COMPARISON | |
| EP3006370A3 (en) | Sealed fibrous container | |
| EP2259224A3 (en) | Image processing apparatus, image processing method, and program | |
| EP2500177A3 (en) | Printed layer formation processing device and printed layer formation processing method | |
| CN106981060A (en) | A kind of Empty Bottle Inspector bottom of bottle localization method | |
| WO2019001191A1 (en) | Method and device for detecting spliced banknote | |
| CN106845481A (en) | A kind of goods and materials shape recognition process based on binocular image vision | |
| EP3832522A1 (en) | Method for reading ultra high frequency rfid tag | |
| KR101188696B1 (en) | Method for inspecting shape of rolled coil | |
| Hobson et al. | Characterisation and identification of rice grains through digital image analysis | |
| CN108805854B (en) | Method for rapidly counting tablets and detecting completeness of tablets in complex environment | |
| Yao et al. | Exterior quality inspection of rice based on computer vision | |
| WO2006093532A3 (en) | Microwave transmission/reception element structure with distance-to-subject relative motion, and related methodology |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |