CN112730445A - Tobacco shred sundry visual image detection system - Google Patents
Tobacco shred sundry visual image detection system Download PDFInfo
- Publication number
- CN112730445A CN112730445A CN202110071374.2A CN202110071374A CN112730445A CN 112730445 A CN112730445 A CN 112730445A CN 202110071374 A CN202110071374 A CN 202110071374A CN 112730445 A CN112730445 A CN 112730445A
- Authority
- CN
- China
- Prior art keywords
- sundry
- tobacco shred
- image
- tobacco
- personal computer
- 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
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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
-
- 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
- G01N2021/845—Objects on a conveyor
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
- G01N2021/8908—Strip illuminator, e.g. light tube
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N2021/8909—Scan signal processing specially adapted for inspection of running sheets
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
- G01N2021/8925—Inclusions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
- G01N2201/1296—Using chemometrical methods using neural networks
Landscapes
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Textile Engineering (AREA)
- Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a tobacco shred sundry video detection system, which comprises: industrial cameras, industrial personal computers, PLC controllers and speed sensors. The industrial personal computer is respectively in signal connection with the industrial camera and the PLC, and the PLC is in signal connection with the speed sensor. The speed sensor is used for detecting the conveying speed of the tobacco shred conveying belt, and the PLC judges the running state of the tobacco shred conveying belt according to the conveying speed and sends the running state to the industrial personal computer. And the industrial personal computer controls the industrial camera to photograph the cut tobacco on the cut tobacco conveyer belt when the cut tobacco conveyer belt is in the running state to obtain a cut tobacco image. And an image processing algorithm is operated on the industrial personal computer, and the tobacco shred images are subjected to image processing and sundry identification. The invention can improve the accuracy and the working efficiency of the tobacco shred sundries detection and improve the production quality of cigarettes.
Description
Technical Field
The invention relates to the technical field of cigarette production management, in particular to a tobacco shred sundry video detection system.
Background
During the production process of the cigarette, paper or plastic packaging scraps in the transportation process are mixed in tobacco shreds inevitably, and the quality of the cigarette is affected. The tobacco shreds with different brands have obvious color difference in the production process, and the distribution and the shape of the tobacco shreds are always changed on a conveying belt, so that the accurate detection of the sundries cannot be realized by simply using detection means such as color, shape, texture, patterns and the like. In addition, impurity foreign matters in the tobacco shreds are manually selected, are influenced by individual subjective consciousness, waste time and labor, are easy to cause visual fatigue after long-time work, and cannot ensure the working efficiency. Therefore, how to realize the accuracy and the intellectualization of the detection of the sundries on the surfaces of the cut tobaccos on the conveying belt in the production process of the tobacco-making thread has important significance.
Disclosure of Invention
The invention provides a tobacco shred sundry visual image detection system, which solves the problems of low identification accuracy and high labor cost in the conventional tobacco shred sundry detection, can improve the tobacco shred sundry detection accuracy and working efficiency, and improves the cigarette production quality.
In order to realize the following purposes, the invention provides the following technical scheme:
a tobacco shred sundry visual image detection system comprises: the system comprises an industrial camera, an industrial personal computer, a PLC (programmable logic controller) and a speed sensor;
the industrial personal computer is respectively in signal connection with the industrial camera and the PLC controller, and the PLC controller is in signal connection with the speed sensor;
the speed sensor is used for detecting the transmission speed of the tobacco shred conveying belt, and the PLC judges the running state of the tobacco shred conveying belt according to the transmission speed and sends the running state to the industrial personal computer;
the industrial personal computer controls the industrial camera to photograph the cut tobacco on the cut tobacco conveyer belt when the cut tobacco conveyer belt is in a running state to obtain a cut tobacco image;
and an image processing algorithm is operated on the industrial personal computer, and the tobacco shred images are subjected to image processing and sundry identification.
Preferably, the method further comprises the following steps: an imaging spectrometer;
the imaging spectrometer is in signal connection with the industrial personal computer and is used for detecting tobacco shred spectral images of tobacco shreds on the tobacco shred conveying belt and sending the tobacco shred spectral images to the industrial personal computer;
and the industrial personal computer identifies impurities according to the tobacco shred spectral image.
Preferably, the method further comprises the following steps: a manipulator;
the manipulator is in signal connection with the PLC, and the industrial personal computer determines the position of the sundries according to the tobacco shred images or the tobacco shred spectral images and sends the position of the sundries to the PLC;
and the PLC controls the tobacco shred conveying belt to stop running when receiving the sundry information sent by the industrial personal computer, and controls the manipulator to remove sundries according to the sundry position.
Preferably, the method further comprises the following steps: an alarm device;
the alarm device is in signal connection with the PLC, and the PLC controls the alarm device to give an alarm when the cut tobacco conveyer belt stops running.
Preferably, the alarm device is at least one of the following: alarm indicator lamp, audible and visual alarm and buzzer.
Preferably, the method further comprises the following steps: an LED light source;
the LED light source is in signal connection with the PLC, and is used for providing illumination brightness for the industrial camera;
and the PLC controls the LED light source to illuminate when the tobacco shred conveying belt is in operation.
Preferably, be provided with pipe tobacco debris image recognition platform on the industrial computer, pipe tobacco debris image recognition platform includes: a clutter image dataset, a Yolo V3 model, and a PyTorch network;
the Yolo V3 model is loaded on the PyTorch network, and GPU accelerated training is carried out in the Yolo V3 model by calling parameter setting and the sundry image data set, so that the trained Yolo V3 model carries out sundry identification on the cut tobacco images shot by the industrial camera;
the PyTorch network is used for building a deep learning acceleration platform.
Preferably, the tobacco shred sundry image recognition platform performs sundry recognition, and comprises:
collecting pictures of different types of sundries and marking the pictures to form a tobacco shred sundry image data set;
performing image cutting, scaling, overturning, shifting, rotating, brightness adjusting and stretching on the sundry image of the sundry image data set;
fusing the tobacco shred images and the sundry images through an image segmentation algorithm, an image enhancement algorithm or an image fusion algorithm to obtain tobacco shred sundry training images;
performing model training by taking the tobacco shred sundry training image as a training sample of the Yolo V3 model;
and carrying out sundry target detection on the tobacco shred image by using a trained Yolo V3 model.
The invention provides a tobacco shred sundry video detection system, which comprises: the system comprises an industrial camera, an industrial personal computer, a PLC (programmable logic controller) and a speed sensor; the industrial personal computer controls the industrial camera to shoot the tobacco shred conveying belt according to the running state of the tobacco shred conveying belt sent by the PLC, and carries out sundry identification on the tobacco shred image. The problems of low identification accuracy and high labor cost in the existing tobacco shred impurity detection can be solved, the tobacco shred impurity detection accuracy and the working efficiency can be improved, and the cigarette production quality can be improved.
Drawings
In order to more clearly describe the specific embodiments of the present invention, the drawings to be used in the embodiments will be briefly described below.
FIG. 1 is a schematic view of a tobacco shred sundry image detection system provided by the invention.
Fig. 2 is a schematic diagram of a cut tobacco impurity detection process provided by the embodiment of the invention.
Detailed Description
In order to make the technical field of the invention better understand the scheme of the embodiment of the invention, the embodiment of the invention is further described in detail with reference to the drawings and the implementation mode.
The method aims at solving the problems of low identification accuracy and high labor cost in the impurity detection of the current tobacco shred production line. The invention provides a tobacco shred sundry visual image detection system, which solves the problems of low identification accuracy and high labor cost in the conventional tobacco shred sundry detection, can improve the tobacco shred sundry detection accuracy and working efficiency, and improves the cigarette production quality.
As shown in fig. 1, a tobacco shred sundry visual image detection system comprises: industrial cameras, industrial personal computers, PLC controllers and speed sensors. The industrial personal computer is respectively in signal connection with the industrial camera and the PLC, and the PLC is in signal connection with the speed sensor. The speed sensor is used for detecting the conveying speed of the tobacco shred conveying belt, and the PLC judges the running state of the tobacco shred conveying belt according to the conveying speed and sends the running state to the industrial personal computer. And the industrial personal computer controls the industrial camera to photograph the cut tobacco on the cut tobacco conveyer belt when the cut tobacco conveyer belt is in the running state to obtain a cut tobacco image. And an image processing algorithm is operated on the industrial personal computer, and the tobacco shred images are subjected to image processing and sundry identification.
Specifically, after the system is started, the light source of the industrial camera is in a normally-on state, the state of the tobacco shred conveying belt is read through the industrial personal computer, and when the conveying belt runs, the industrial camera is controlled to shoot in real time. The system automatically captures the next image from the image stream of the industrial camera for detection after the current image is processed by the industrial personal computer. The industrial computer obtains the running state of pipe tobacco conveyer belt through the PLC controller, and after detecting debris, the PLC controller control pipe tobacco conveyer belt is shut down, realizes the auto-stop function. The industrial personal computer mainly completes the functions of reading image stream, storing sundry images, counting, converting image formats, detecting tobacco shred sundries, storing detection results, controlling communication and the like. The running state of the cut tobacco conveying belt is detected through the speed sensor, the conveying belt is determined to be in a starting state when the speed is larger than a set threshold value, and the conveying belt is determined to be in a stopping state when the speed is smaller than the set threshold value.
In one embodiment, the cut tobacco impurity detection process is shown in fig. 2: (1) and after the system is started, opening the industrial camera and calling a camera image stream capture program to start capturing the image stream. (2) And reading the running state of the cut tobacco conveyer belt in the PLC, transmitting the camera stream picture to a variable to be detected if the cut tobacco conveyer belt runs, and continuing to read the running state of the cut tobacco conveyer belt if the cut tobacco conveyer belt stops. (3) And after the picture is read, executing a detection program and outputting a detection result. (4) And if sundries are detected, the industrial personal computer writes a cut tobacco conveyer belt stop signal into the PLC, and the PLC drives the starting equipment to alarm and stop to wait for the inspection and processing of an operator. Checking and processing by an operator, if the sundries are really present, processing the sundries, confirming the sundries processing, and storing sundries pictures and detection results by the system; and if the operator checks that no sundries exist, carrying out false detection processing confirmation, storing a false detection picture by the system, and storing a detection result. (5) And if the sundries are not detected, continuing the next detection period and continuously executing detection. It should be noted that the image processing algorithm run on the industrial personal computer can be realized by adopting a neural network algorithm, and can also be realized by other algorithms. The system can improve the accuracy and the working efficiency of tobacco shred sundries detection and improve the production quality of cigarettes.
The system further comprises: an imaging spectrometer. The imaging spectrometer is in signal connection with the industrial personal computer and is used for detecting tobacco shred spectral images of tobacco shreds on the tobacco shred conveying belt and sending the tobacco shred spectral images to the industrial personal computer. And the industrial personal computer identifies impurities according to the tobacco shred spectral image.
In practical application, the spectral image of the tobacco shred is detected by an imaging spectrometer to obtain the spectral image of the tobacco shred. A neural network model is built on an industrial personal computer, a training sample is input for training, and then sundry identification is carried out on tobacco shred spectral images so as to distinguish paper scraps, plastics, tobacco shreds and other sundries in the tobacco shreds. The system can improve the false detection rate and the missing detection rate of the sundries and effectively reduce the influence of illumination change on sundry identification.
The system further comprises: and the industrial personal computer determines the position of the sundries according to the tobacco shred images or the tobacco shred spectral images and sends the position of the sundries to the PLC. And the PLC controls the tobacco shred conveying belt to stop running when receiving the sundry information sent by the industrial personal computer, and controls the manipulator to remove sundries according to the sundry position.
In practical application, the manipulator can be arranged on the guide rail, the guide rail is arranged on the periphery of the cut tobacco conveying belt, and the manipulator can move along the guide rail to grab the cut tobacco containing sundries and send the cut tobacco into the collecting box, so that an operator can pick the cut tobacco manually. The manipulator can improve the working efficiency and reduce the potential safety hazard of manual operation.
The system further comprises: an alarm device; the alarm device is in signal connection with the PLC, and the PLC controls the alarm device to give an alarm when the cut tobacco conveyer belt stops running.
Further, the alarm device is at least one of the following: alarm indicator lamp, audible and visual alarm and buzzer.
The system further comprises: an LED light source; the LED light source is in signal connection with the PLC, and is used for providing illumination brightness for the industrial camera; and the PLC controls the LED light source to illuminate when the tobacco shred conveying belt is in operation.
Be provided with pipe tobacco debris image recognition platform on the industrial computer, pipe tobacco debris image recognition platform includes: a clutter image dataset, a Yolo V3 model, and a PyTorch network. The Yolo V3 model is loaded on the PyTorch network, and GPU accelerated training is carried out in the Yolo V3 model by calling parameter setting and the sundry image data set, so that the trained Yolo V3 model carries out sundry identification on the cut tobacco images shot by the industrial camera; the PyTorch network is used for building a deep learning acceleration platform.
Further, the tobacco shred sundry image recognition platform performs sundry recognition and comprises:
collecting pictures of different types of sundries and marking the pictures to form a tobacco shred sundry image data set;
performing image cutting, scaling, overturning, shifting, rotating, brightness adjusting and stretching on the sundry image of the sundry image data set;
fusing the tobacco shred images and the sundry images through an image segmentation algorithm, an image enhancement algorithm or an image fusion algorithm to obtain tobacco shred sundry training images;
performing model training by taking the tobacco shred sundry training image as a training sample of the Yolo V3 model;
and carrying out sundry target detection on the tobacco shred image by using a trained Yolo V3 model.
Specifically, the building of yolov3 network model is realized on the pytorech platform, and the realization mode is as follows:
(1) and installing and configuring the pytorech platform.
(2) Loading a yolov3 model through a pytorech platform, calling parameter setting, carrying out GPU accelerated training on an image data set in a yolov3 model, and outputting a weight file in a pt format after the training is finished. It should be noted that Yolo V3 is a single-stage target detection algorithm proposed by Joseph Redmon and others in a method of fusing ResNET, FPN, binary cross entropy loss and the like. Yolo V3 adopts a new feature extraction network Darknet-53, and Darknet-53 is mainly composed of 5 residual blocks. In the aspect of predicting the class result of the Yolo V3, an upsampling and fusion method is adopted, targets are independently detected through fusion feature maps of 13 × 13, 26 × 26 and 52 × 52 in different scales, the detection effect on objects with different sizes and shielded objects is effectively enhanced, and jump layer connection is introduced to strengthen the convergence effect.
(3) And calling the weight file and the real-time image of the industrial camera in the pytore platform through a program.
Therefore, the invention provides a tobacco shred sundry visual image detection system.A commercial control computer controls an industrial camera to shoot a tobacco shred conveying belt according to the running state of the tobacco shred conveying belt sent by a PLC (programmable logic controller) and performs sundry identification on a tobacco shred image. The problems of low identification accuracy and high labor cost in the existing tobacco shred impurity detection can be solved, the tobacco shred impurity detection accuracy and the working efficiency can be improved, and the cigarette production quality can be improved.
The construction, features and functions of the present invention have been described in detail with reference to the embodiments shown in the drawings, but the present invention is not limited to the embodiments shown in the drawings, and all equivalent embodiments modified or modified by the spirit and scope of the present invention should be protected without departing from the spirit of the present invention.
Claims (8)
1. A tobacco shred sundry visual image detection system is characterized by comprising: the system comprises an industrial camera, an industrial personal computer, a PLC (programmable logic controller) and a speed sensor;
the industrial personal computer is respectively in signal connection with the industrial camera and the PLC controller, and the PLC controller is in signal connection with the speed sensor;
the speed sensor is used for detecting the transmission speed of the tobacco shred conveying belt, and the PLC judges the running state of the tobacco shred conveying belt according to the transmission speed and sends the running state to the industrial personal computer;
the industrial personal computer controls the industrial camera to photograph the cut tobacco on the cut tobacco conveyer belt when the cut tobacco conveyer belt is in a running state to obtain a cut tobacco image;
and an image processing algorithm is operated on the industrial personal computer, and the tobacco shred images are subjected to image processing and sundry identification.
2. The tobacco shred sundry visual image detection system according to claim 1, further comprising: an imaging spectrometer;
the imaging spectrometer is in signal connection with the industrial personal computer and is used for detecting tobacco shred spectral images of tobacco shreds on the tobacco shred conveying belt and sending the tobacco shred spectral images to the industrial personal computer;
and the industrial personal computer identifies impurities according to the tobacco shred spectral image.
3. The tobacco shred sundry visual image detection system according to claim 2, further comprising: a manipulator;
the manipulator is in signal connection with the PLC, and the industrial personal computer determines the position of the sundries according to the tobacco shred images or the tobacco shred spectral images and sends the position of the sundries to the PLC;
and the PLC controls the tobacco shred conveying belt to stop running when receiving the sundry information sent by the industrial personal computer, and controls the manipulator to remove sundries according to the sundry position.
4. The tobacco shred sundry visual image detection system according to claim 3, further comprising: an alarm device;
the alarm device is in signal connection with the PLC, and the PLC controls the alarm device to give an alarm when the cut tobacco conveyer belt stops running.
5. The tobacco shred sundry visual image detection system according to claim 4, wherein the alarm device is at least one of the following: alarm indicator lamp, audible and visual alarm and buzzer.
6. The tobacco shred sundry visual image detection system according to claim 5, further comprising: an LED light source;
the LED light source is in signal connection with the PLC, and is used for providing illumination brightness for the industrial camera;
and the PLC controls the LED light source to illuminate when the tobacco shred conveying belt is in operation.
7. The tobacco shred sundry image detection system according to claim 6, wherein a tobacco shred sundry image recognition platform is arranged on the industrial personal computer, and the tobacco shred sundry image recognition platform comprises: a clutter image dataset, a Yolo V3 model, and a PyTorch network;
the Yolo V3 model is loaded on the PyTorch network, and GPU accelerated training is carried out in the Yolo V3 model by calling parameter setting and the sundry image data set, so that the trained Yolo V3 model carries out sundry identification on the cut tobacco images shot by the industrial camera;
the PyTorch network is used for building a deep learning acceleration platform.
8. The tobacco shred sundry image detection system according to claim 7, wherein the tobacco shred sundry image identification platform is used for identifying sundries and comprises the following steps:
collecting pictures of different types of sundries and marking the pictures to form a tobacco shred sundry image data set;
performing image cutting, scaling, overturning, shifting, rotating, brightness adjusting and stretching on the sundry image of the sundry image data set;
fusing the tobacco shred images and the sundry images through an image segmentation algorithm, an image enhancement algorithm or an image fusion algorithm to obtain tobacco shred sundry training images;
performing model training by taking the tobacco shred sundry training image as a training sample of the Yolo V3 model;
and carrying out sundry target detection on the tobacco shred image by using a trained Yolo V3 model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110071374.2A CN112730445A (en) | 2021-01-19 | 2021-01-19 | Tobacco shred sundry visual image detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110071374.2A CN112730445A (en) | 2021-01-19 | 2021-01-19 | Tobacco shred sundry visual image detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112730445A true CN112730445A (en) | 2021-04-30 |
Family
ID=75593337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110071374.2A Pending CN112730445A (en) | 2021-01-19 | 2021-01-19 | Tobacco shred sundry visual image detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112730445A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113533349A (en) * | 2021-07-19 | 2021-10-22 | 吴玉生 | Intelligent automatic tobacco shred impurity detecting and removing system |
| CN113650089A (en) * | 2021-09-15 | 2021-11-16 | 红云红河烟草(集团)有限责任公司 | Filament cutter running piece imaging detection alarm device |
| CN115410077A (en) * | 2022-11-02 | 2022-11-29 | 杭州首域万物互联科技有限公司 | Method for realizing cut tobacco impurity detection and identification based on YOLOV7 target detection algorithm |
| CN115984636A (en) * | 2023-03-21 | 2023-04-18 | 杭州书微信息科技有限公司 | Foreign matter impurity removal system and method |
| WO2024028971A1 (en) * | 2022-08-02 | 2024-02-08 | 日本たばこ産業株式会社 | Foreign substance inspection device |
-
2021
- 2021-01-19 CN CN202110071374.2A patent/CN112730445A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113533349A (en) * | 2021-07-19 | 2021-10-22 | 吴玉生 | Intelligent automatic tobacco shred impurity detecting and removing system |
| CN113650089A (en) * | 2021-09-15 | 2021-11-16 | 红云红河烟草(集团)有限责任公司 | Filament cutter running piece imaging detection alarm device |
| WO2024028971A1 (en) * | 2022-08-02 | 2024-02-08 | 日本たばこ産業株式会社 | Foreign substance inspection device |
| CN115410077A (en) * | 2022-11-02 | 2022-11-29 | 杭州首域万物互联科技有限公司 | Method for realizing cut tobacco impurity detection and identification based on YOLOV7 target detection algorithm |
| CN115984636A (en) * | 2023-03-21 | 2023-04-18 | 杭州书微信息科技有限公司 | Foreign matter impurity removal system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112730445A (en) | Tobacco shred sundry visual image detection system | |
| US20140247347A1 (en) | Methods and Apparatus for Video Based Process Monitoring and Control | |
| CA3152907A1 (en) | System and method for ai visual inspection | |
| CN107084992B (en) | Capsule detection method and system based on machine vision | |
| JP6188571B2 (en) | Waste stirring state detection device and waste stirring state detection method | |
| CN214844880U (en) | Tobacco shred sundry visual image detection system | |
| CN107891012A (en) | Pearl size and circularity sorting equipment based on equivalent algorithm | |
| CN112800909A (en) | Self-learning type tobacco shred sundry visual image detection method | |
| CN105195442B (en) | A kind of fresh-water fishes freshness hierarchy system and method based on machine vision | |
| CN115128033A (en) | Tobacco leaf detection method, device and system and storage medium | |
| CN113834814B (en) | Glove surface defect detection device | |
| US20160253856A1 (en) | Coin recognition and removal from a material stream | |
| CN113333329A (en) | Cigarette defect detection system based on deep learning | |
| CN214398645U (en) | Cigarette carton flow monitoring system | |
| CN111353432B (en) | Rapid clean selection method and system for honeysuckle medicinal materials based on convolutional neural network | |
| CN114119583A (en) | Industrial visual inspection system, method, network model selection method and warp knitting machine | |
| CN113558287A (en) | Control method and system for cigarette tobacco end face detection | |
| CN113390884A (en) | Cigarette abnormity monitoring method and device for cigarette conveying channel of cigarette equipment | |
| CN111617971A (en) | Bobbin yarn detection system, method and device | |
| CN113642572B (en) | Image target detection method, system and device based on multi-level attention | |
| CN116933409B (en) | Digital twinning-oriented coal mine underground equipment model compression design method | |
| JP7469731B2 (en) | Monitoring system, monitoring method, and program | |
| CN117686424B (en) | Meat broken bone intelligent detection system and method based on machine vision | |
| CN215736849U (en) | Control system for detecting end face of tobacco shred of cigarette | |
| JP7029201B1 (en) | Object inspection equipment, inspection programs, and systems |
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 |