CN114354632A - Assembly line quality detection equipment based on machine vision - Google Patents
Assembly line quality detection equipment based on machine vision Download PDFInfo
- Publication number
- CN114354632A CN114354632A CN202210030594.5A CN202210030594A CN114354632A CN 114354632 A CN114354632 A CN 114354632A CN 202210030594 A CN202210030594 A CN 202210030594A CN 114354632 A CN114354632 A CN 114354632A
- Authority
- CN
- China
- Prior art keywords
- goods
- conveying mechanism
- image
- host
- machine
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 16
- 230000007246 mechanism Effects 0.000 claims abstract description 46
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 230000007723 transport mechanism Effects 0.000 claims description 3
- 239000012855 volatile organic compound Substances 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000012372 quality testing Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 208000032544 Cicatrix Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 230000037387 scars Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Health & Medical Sciences (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to an assembly line quality detection device based on machine vision, in particular to the technical field of quality detection devices, which comprises a frame body, a conveying mechanism and a control mechanism, wherein the frame body is used for supporting the conveying mechanism; the conveying mechanism is provided with a rotating mechanism which is white. The infrared transceiver is arranged above the conveying mechanism and used for detecting that the goods pass by and suspending the conveying mechanism; the light source is arranged right below the infrared transceiver and is an annular lamp; the industrial camera is arranged on the side edge of the conveying mechanism and used for obtaining images; the image processing device comprises a host, wherein a quality image processing module, a color image processing module and a shape and size image recognition module are arranged in the host. The invention has the technical effects of intelligently identifying the quality of the second-hand or imported luxury goods and classifying the color and the size of the luxury goods.
Description
Technical Field
The invention relates to the technical field of quality detection equipment, in particular to assembly line quality detection equipment based on machine vision.
Background
In the prior art of importing or second-hand luxury goods, such as shoes, bags and the like, professional identification technical training is generally carried out on workers, and then the workers are enabled to carry out size, color classification and quality (including scars and defects) identification on luxury shoes and bags on a production line, so that the identification process is very labor-consuming and inefficient, and many workers are not very good at eye sight and are difficult to find that the machine cannot find flaws.
Disclosure of Invention
It is an object of the present invention to provide a machine vision based pipeline quality detection apparatus with the effect of intelligently authenticating the genuineness of a second-hand luxury good and classifying the color and size of the luxury good.
The above object of the present invention is achieved by the following technical solutions:
a machine vision-based pipeline quality detection apparatus comprising:
the frame body is used for supporting the conveying mechanism;
the conveying mechanism is provided with a rotating mechanism which is white.
The infrared transceiver is arranged above the conveying mechanism and used for detecting that the goods pass by and suspending the conveying mechanism;
the light source is arranged right below the infrared transceiver and is an annular lamp;
the industrial camera is arranged on the side edge of the conveying mechanism and used for obtaining images;
the system comprises a host, wherein a quality image processing module is arranged in the host, and is used for filtering an image through a filter, performing gray processing on the image, performing binarization processing on the image after the gray processing, and performing noise reduction processing on the image to determine whether different color lumps exist or not;
the method comprises the following steps that a color image processing module is further connected inside a host, firstly, R.G.B value extraction is carried out on an image and the image is converted into an HIS mode, a chromaticity histogram is obtained, 7 chromaticity domains of a chromaticity component H are used as 7 color features, and then a particle swarm optimization neural network is applied to carry out color grading on goods;
the host is also internally connected with a shape and size image recognition module, a Fourier operator is used for describing the shape of the goods, the edges of the goods are graded according to the shape through a neural network of an L-M algorithm, and then the largest radial direction of the goods is obtained according to a plurality of images obtained from the rotating mechanism so as to determine the size of the goods.
Preferably, the conveying mechanism terminal is provided with a marking machine, the marking machine is connected with a host, and the marking machine generates a two-dimensional code with cargo information and prints and fixes the two-dimensional code on the cargo.
Preferably, an ejection module is arranged between the marking machine and the conveying mechanism, the ejection module comprises an electric cylinder and an ejector rod which are connected to the host machine, and the ejector rod is located at the output end of the electric cylinder.
Preferably, a peculiar smell detector is further arranged between the conveying mechanism and the ejection module, and the peculiar smell detector can perform online detection on volatile organic compounds and odor concentration through various high-precision and high-resolution high-performance sensors.
Preferably, a plurality of cameras are arranged on the conveying mechanism and connected with the host, and the cameras are kept in a working state for 24 hours and used for preventing people from falling off packages of goods.
In conclusion, the invention has the beneficial effects that:
by adopting the structure, the goods can be stopped by the position measuring driving transmission mechanism of the infrared transceiver in the process of being detected, meanwhile, the industrial camera and the rotating mechanism are opened, photos of the goods around one circle of the goods under the annular lamp are shot, then whether the goods have defects and stains or not is determined according to the quality image processing module, then the goods are classified according to the color number of the color processing module, and finally the goods are classified into large size, medium size and small size according to the size and shape determined by the shape and size image recognition module.
Drawings
FIG. 1 is a schematic view of the overall structure of the present invention;
fig. 2 is a schematic diagram of the principle of the present invention.
The marks in the figure are respectively 1 and a frame body; 2. a transport mechanism; 21. a rotating mechanism; 3. an infrared transceiver; 4. an annular lamp; 5. an industrial camera; 6. a host; 61. a quality image processing module; 62. a color image processing module; 63. a shape and size image recognition module; 7. marking machine; 8. ejecting the module; 9. a peculiar smell detector; 10. a camera is provided.
Detailed Description
In order to facilitate understanding of those skilled in the art, the present invention will be further described with reference to the following examples and drawings, which are not intended to limit the present invention. The present invention is described in detail below with reference to the attached drawings.
The present invention will be described in further detail with reference to the accompanying drawings.
Referring to fig. 1 to 2, a machine vision-based pipeline quality detection apparatus includes:
the frame body 1 is used for supporting the conveying mechanism 2;
the conveying mechanism 2 is provided with a rotating mechanism, and the rotating mechanism is white.
An infrared transceiver 3 installed above the conveying mechanism 2 for detecting the passing of the goods and suspending the conveying mechanism 2;
a light source arranged right below the infrared transceiver 3, wherein the light source is an annular lamp 4;
an industrial camera 5 mounted on the side of the conveying mechanism 2 for obtaining an image;
the image processing device comprises a host machine 6, wherein a quality image processing module 61 is arranged in the host machine 6, firstly, filtering processing is carried out on an image through a filter, then, gray processing is carried out on the image, then, binarization processing is carried out on the image after the gray processing, and then, noise reduction processing is carried out on the image so as to determine whether different color lumps exist or not;
the host 6 is also internally connected with a color image processing module 62, firstly, the R.G.B value of the image is extracted and converted into an HIS mode to obtain a chromaticity histogram, 7 chromaticity domains of the chromaticity component H are used as 7 color features, and then, a particle swarm optimization neural network is applied to carry out color grading on the goods;
the host machine 6 is also internally connected with a shape and size image recognition module 63, a Fourier operator is used for describing the shape of the goods, the edges of the goods are graded according to the shape through a neural network of an L-M algorithm, and then the maximum radial direction of the goods is obtained according to a plurality of images obtained from the rotating mechanism so as to determine the size of the goods.
The working principle is as follows: by adopting the structure, the goods can be stopped by the position measuring driving transmission mechanism 2 of the infrared transceiver 3 in the process of being detected, the industrial camera 5 and the rotating mechanism are opened at the same time, the photos of the goods round the ring lamp 4 under the ring lamp are shot, then whether the goods have defects and dirt or not is determined according to the quality image processing module 61, then the goods are classified according to the color number of the color processing module, and finally the goods are classified into large size, medium size and small size according to the size and shape determined by the shape size image recognition module 63.
The terminal of the conveying mechanism 2 is provided with a marking machine 7, the marking machine 7 is connected with a host machine 6, the marking machine 7 generates a two-dimensional code with goods information and prints and fixes the two-dimensional code on the goods, and the qualified goods after being detected can be timely marked by adopting the structure, so that the qualified goods can be prevented from being fallen out of the package.
An ejection module 8 is arranged between the marking machine 7 and the conveying mechanism 2, the ejection module 8 comprises an electric cylinder and an ejector rod which are connected to the host machine 6, the ejector rod is positioned at the output end of the electric cylinder, and by adopting the structure, the rejected goods in the quality image processing process can be eliminated, so that the detected goods only have differences in color and size.
Still be provided with peculiar smell detector 9 between transport mechanism 2 and the ejecting module 8, peculiar smell detector 9 can be through multiple high accuracy, and high performance sensor is got to the high resolution, carries out on-line measuring to volatile organic compounds, foul smell concentration, adopts such structure can make and carry out the quality detection back of colour size and surface quality to the goods, then carries out peculiar smell detection to the goods, prevents that some second-hand goods from filling with one another, carries out the secondary sale.
The conveying mechanism 2 is provided with a plurality of cameras 10, the cameras 10 are connected with the host 6, and the cameras keep working for 1024 hours and are used for preventing people from falling off packages of goods.
Although the present invention has been described with reference to the above preferred embodiments, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. The utility model provides a production line quality testing equipment based on machine vision which characterized in that: the method comprises the following steps:
the frame body (1) is used for supporting the conveying mechanism (2);
the conveying mechanism (2) is provided with a rotating mechanism, and the rotating mechanism is white.
The infrared transceiver (3) is arranged above the conveying mechanism (2) and is used for detecting the passing of the goods and suspending the conveying mechanism (2);
the light source is arranged right below the infrared transceiver (3), and is an annular lamp (4);
the industrial camera (5) is arranged on the side edge of the conveying mechanism (2) and is used for obtaining images;
the image processing device comprises a host (6), wherein a quality image processing module (61) is arranged in the host (6), firstly, filtering processing is carried out on an image through a filter, then, gray processing is carried out on the image, then, binarization processing is carried out on the image after the gray processing, and then, noise reduction processing is carried out on the image to determine whether different color lumps exist or not;
the host (6) is also internally connected with a color image processing module (62), firstly, R.G.B value extraction is carried out on the image and the image is converted into an HIS mode to obtain a chromaticity histogram, 7 chromaticity domains of a chromaticity component H are used as 7 color features, and then, a particle swarm optimization neural network is applied to carry out color grading on the goods;
the main machine (6) is also internally connected with a shape and size image recognition module (63), a Fourier operator is used for describing the shape of the goods at first, the edges of the goods are graded according to the shape through a neural network of an L-M algorithm, and then the maximum radial direction of the goods is obtained according to a plurality of images obtained from the rotating mechanism so as to determine the size of the goods.
2. The machine-vision-based pipeline quality detection device of claim 1, wherein: the conveying mechanism (2) terminal is provided with marking machine (7), marking machine (7) are connected with host computer (6), marking machine (7) generate have the two-dimensional code that has goods information and print and fix to the goods.
3. The machine-vision-based pipeline quality detection device of claim 2, wherein: an ejection module (8) is arranged between the marking machine (7) and the conveying mechanism (2), the ejection module (8) comprises an electric cylinder and an ejector rod which are connected to the host (6), and the ejector rod is located at the output end of the electric cylinder.
4. The machine-vision-based pipeline quality detection device of claim 3, wherein: still be provided with peculiar smell detector (9) between transport mechanism (2) and ejecting module (8), peculiar smell detector (9) can be through multiple high accuracy, high performance sensor is got to high resolution, carries out on-line measuring to volatile organic compounds, foul smell concentration.
5. The machine-vision-based pipeline quality detection device of claim 4, wherein: the conveying mechanism (2) is provided with a plurality of cameras (10), the cameras (10) are connected with the host (6), and the cameras (10) keep working for 24 hours and are used for preventing people from falling off packages from goods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210030594.5A CN114354632A (en) | 2022-01-12 | 2022-01-12 | Assembly line quality detection equipment based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210030594.5A CN114354632A (en) | 2022-01-12 | 2022-01-12 | Assembly line quality detection equipment based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114354632A true CN114354632A (en) | 2022-04-15 |
Family
ID=81108444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210030594.5A Pending CN114354632A (en) | 2022-01-12 | 2022-01-12 | Assembly line quality detection equipment based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114354632A (en) |
-
2022
- 2022-01-12 CN CN202210030594.5A patent/CN114354632A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102579783B1 (en) | Vision inspection system by using remote learning of product defects image | |
| CN109550712B (en) | Chemical fiber filament tail fiber appearance defect detection system and method | |
| CN110314854B (en) | Workpiece detecting and sorting device and method based on visual robot | |
| CN109454006B (en) | Detection and classification method based on device for online detection and classification of chemical fiber spindle tripping defects | |
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN109724984B (en) | Defect detection and identification device and method based on deep learning algorithm | |
| CN106706653A (en) | High-speed wide board detection method | |
| CN110246122A (en) | Small size bearing quality determining method, apparatus and system based on machine vision | |
| CN104483320B (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN110403232B (en) | Cigarette quality detection method based on secondary algorithm | |
| CN110567976B (en) | Mobile phone cover plate silk-screen defect detection device and detection method based on machine vision | |
| Eshkevari et al. | Automatic dimensional defect detection for glass vials based on machine vision: A heuristic segmentation method | |
| CN109142509B (en) | Round steel magnetic powder flaw detection method and device | |
| CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
| CN110554052A (en) | artificial board surface defect detection method and system | |
| CN108414531A (en) | A kind of fexible film defect detecting device and its detection method based on machine vision | |
| CN111239142A (en) | Paste appearance defect detection device and method | |
| CN114549493A (en) | Magnetic core defect detection system and method based on deep learning | |
| CN114820626A (en) | Intelligent detection method for automobile front part configuration | |
| CN111426693A (en) | Quality defect detection system and detection method thereof | |
| CN109622404B (en) | Automatic sorting system and method for micro-workpieces based on machine vision | |
| Gong et al. | Adaptive visual inspection method for transparent label defect detection of curved glass bottle | |
| CN102609699A (en) | Device and method for recognizing number of cast workpiece scanned by laser | |
| CN115947066B (en) | Belt tearing detection method, device and system | |
| CN109063738B (en) | Automatic online detection method for compressed sensing ceramic water valve plate |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220415 |