CN109001211A - Welds seam for long distance pipeline detection system and method based on convolutional neural networks - Google Patents
Welds seam for long distance pipeline detection system and method based on convolutional neural networks Download PDFInfo
- Publication number
- CN109001211A CN109001211A CN201810585115.XA CN201810585115A CN109001211A CN 109001211 A CN109001211 A CN 109001211A CN 201810585115 A CN201810585115 A CN 201810585115A CN 109001211 A CN109001211 A CN 109001211A
- Authority
- CN
- China
- Prior art keywords
- layers
- feature mapping
- neural networks
- convolutional neural
- mapping module
- 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
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of welds seam for long distance pipeline detection system and method based on convolutional neural networks, including C1 layers of Feature Mapping module, S2 layers of Feature Mapping module, C3 layers of Feature Mapping module;Image of the C1 layers of Feature Mapping module for input passes through and three trainable filters progress convolution, in three Feature Mapping figures of C1 layers of generation after convolution;S2 layers of Feature Mapping module are used to obtain three S2 layers of Feature Mapping figure by a sigmoid number for after above-mentioned C1 layers of Feature Mapping figure weighted value and biasing;C3 layers of Feature Mapping module are used to the mapping graph of above-mentioned S2 layers of Feature Mapping module obtaining C3 layers of Feature Mapping figure using filtering.The present invention uses convolutional neural networks, improves weld seam judging nicety rate;Welds seam for long distance pipeline is detected using convolutional neural networks equipment is carried, to avoid artificial detection risk.
Description
Technical field
The present invention relates to pipeline weld inspection systems, relate more specifically to a kind of long distance pipeline based on convolutional neural networks
Weld inspection system.
Background technique
In recent years, the mass data and computer hardware (CPU, GPU etc.) generated with the fast development of internet
Rapid development and various machine learning algorithms continue to optimize, deep learning neural network based is in computer vision and figure
As the fields achievements such as identification classification, natural language processing, speech recognition are distinguished.Convolutional neural networks (cnn) are used as deep learning
A pith achieve and be widely applied in terms of image procossing with its unique structural advantage.Convolutional neural networks
(convolutional neuron networks, CNN) is made of the full-mesh layer on one or more convolutional layers and top, and
And including related weight and pond layer (pooling layer), this structure enables CNN to utilize the two dimension knot of input data
Structure.Compared with other deep structures, convolutional neural networks show excellent result in image and voice application.Convolution
Neural network can also use the back-propagation algorithm of standard to be trained, also, due to comparing with less parameter Estimation
Other depth structures are easier to train.
Summary of the invention
1, the purpose of the present invention.
The present multi-purpose artificial investigation mode of long distance pipeline welding line detection, there are three big drawbacks: first is that some position pipelines
Very narrow, operating personnel can not reach;Second is that workload is big, artificial detection time-consuming expend it is high;Third is that many places are in closed black
Dark job space, the situations such as operating personnel's anoxic, dizzy, tired take place frequently, and there are high life dangers.And it uses and carries convolution mind
Welds seam for long distance pipeline detection system equipment through network, avoids testing staff from entering pipeline, to effectively evade detection risk.
2, the technical solution adopted in the present invention.
The welds seam for long distance pipeline detection system based on convolutional neural networks that the invention proposes a kind of, including C1 layers of feature are reflected
Penetrate module, S2 layers of Feature Mapping module, C3 layers of Feature Mapping module;
Image of the C1 layers of Feature Mapping module for input passes through and three trainable filters carry out convolution, convolution
Afterwards in three Feature Mapping figures of C1 layers of generation;
S2 layers of Feature Mapping module are used to pass through one for after above-mentioned C1 layers of Feature Mapping figure weighted value and biasing
Sigmoid number obtains three S2 layers of Feature Mapping figure;
C3 layers of Feature Mapping module are for obtaining the mapping graph of above-mentioned S2 layers of Feature Mapping module using filtering
C3 layers of Feature Mapping figure.
It further include S4 layers of Feature Mapping module in further specific embodiment, again and S2 by this hierarchical structure
Equally, after being weighted value and biasing, the activation primitive by a sigmoid function as convolutional network obtains three S4
The Feature Mapping figure of layer.
It further include rasterizer module, by the pixel value of S4 layers of Feature Mapping module in further specific embodiment
It is rasterized.
In further specific embodiment, further includes neural network module, by the rasterizer module and connect into
One vector inputs traditional neural network, finally obtains output.
In further specific embodiment, the C1 Feature Mapping module, C2 layers of Feature Mapping module are spy
Extract layer is levied, the input of each neuron is connected with the local receptor field of preceding layer, and extracts the feature of the part, once the office
After portion's feature is extracted, its positional relationship between other features is also decided therewith.
In further specific embodiment, the S1 layer Feature Mapping module, S4 layers of Feature Mapping module are
Each computation layer of down-sampled layer, network is made of multiple Feature Mappings, and each Feature Mapping is a plane, is owned in plane
The weight of neuron is equal.
A kind of welds seam for long distance pipeline detection method based on convolutional neural networks proposed by the present invention, including convolutional Neural net
Network training process, identification process;
Convolutional neural networks training process: to the mark defect grading of elementary training sample, welding normal sample is added, establishes
Standard exercise data set and test assessment data set are established in Different categories of samples mark mapping;Training dataset is for training nerve net
Network is fitted rating model;Test data set reaches for assessing every wheel training accuracy, auxiliary adjusting training intensity and wheel number
Training and preservation model can be completed in target accuracy rate.
Identification process: using the whole figure heavy duty technology heavy duty network of neural network, and recalls " the defect grading " of training completion
Neural network parameter configuration is completed model and is restored.
Further, the identification process further includes the picture sample tensor to be graded for completing real-time acquisition pretreatment
Change, cuts tensor specification by neural network input size, input the queue of neural network pending data.
Further, further include establishing neural network dialogue, be loaded into the network of recovery and to ratings data, run nerve net
Network simultaneously obtains each rank weight and output, determines sample quality classification according to each rank weight and gap, assesses image deflects grade
Not.
3, technical effect caused by the present invention.
(1) present invention uses convolutional neural networks, improves weld seam judging nicety rate.
(2) present invention detects welds seam for long distance pipeline using carrying convolutional neural networks equipment, to avoid artificial detection
Risk.
Detailed description of the invention
Fig. 1 is schematic structural view of the invention.
Fig. 2 is the schematic diagram of convolutional neural networks of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
To further illustrate the technical scheme of the present invention below with reference to the accompanying drawings and specific embodiments.
It is as shown in Figure 1 the schematic diagram of convolutional neural networks.The image of input pass through and three trainable filters into
Row convolution then after Feature Mapping figure weighted value and biasing, passes through one in three Feature Mapping figures of C1 layers of generation after convolution
Sigmoid number obtains three S2 layers of Feature Mapping figure.These mapping graphs obtain C3 layers using filtering.This hierarchical structure is again
S4 is generated as S2.Finally, these pixel values are rasterized, and are connected into a vector and inputted traditional neural network, most
After exported.Wherein, it is characterized extract layer for C layers, the input of each neuron is connected with the local receptor field of preceding layer, and mentions
The feature for taking the part, after the local feature is extracted, its positional relationship between other features is also decided therewith;
S layers are down-sampled layer, and each computation layer of network is made of multiple Feature Mappings, and each Feature Mapping is a plane, plane
The weight of upper all neurons is equal.Feature Mapping structure is using the lesser sigmoid function of influence function core as convolution net
The activation primitive of network, so that Feature Mapping has shift invariant.
Convolutional neural networks training process: to the mark defect grading of elementary training sample, welding normal sample is added, establishes
Standard exercise data set and test assessment data set are established in Different categories of samples mark mapping;Training dataset is for training nerve net
Network is fitted rating model;Test data set reaches for assessing every wheel training accuracy, auxiliary adjusting training intensity and wheel number
Training and preservation model can be completed in target accuracy rate.
Identification process: using the whole figure heavy duty technology heavy duty network of neural network, and recalls " the defect grading " of training completion
Neural network parameter configuration is completed model and is restored.Then the picture sample tensor to be graded real-time acquisition pretreatment completed,
Tensor specification is cut by neural network input size, inputs the queue of neural network pending data.Neural network dialogue is established, is carried
Enter the network of recovery and to ratings data, run neural network and obtain each rank " weight and " output, according to each rank " weight
With " gap judgement sample quality classification, assess image deflects rank.
Claims (9)
1. a kind of welds seam for long distance pipeline detection system based on convolutional neural networks, it is characterised in that: including C1 layers of Feature Mapping
Module, S2 layers of Feature Mapping module, C3 layers of Feature Mapping module;
The image of C1 layers of Feature Mapping module for input passes through and three trainable filters carry out convolution, after convolution
Three Feature Mapping figures of C1 layers of generation;
S2 layers of Feature Mapping module are used to pass through one for after above-mentioned C1 layers of Feature Mapping figure weighted value and biasing
Sigmoid number obtains three S2 layers of Feature Mapping figure;
C3 layers of Feature Mapping module are used to the mapping graph of above-mentioned S2 layers of Feature Mapping module obtaining C3 layers using filtering
Feature Mapping figure.
2. the welds seam for long distance pipeline detection system according to claim 1 based on convolutional neural networks, it is characterised in that: also
Including S4 layers of Feature Mapping module, by this hierarchical structure again as S2, after being weighted value and biasing, pass through one
Activation primitive of the sigmoid function as convolutional network obtains three S4 layers of Feature Mapping figure.
3. the welds seam for long distance pipeline detection system according to claim 2 based on convolutional neural networks, it is characterised in that: also
Including rasterizer module, the pixel value of S4 layers of Feature Mapping module is rasterized.
4. the welds seam for long distance pipeline detection system according to claim 3 based on convolutional neural networks, it is characterised in that: also
Including neural network module, by the rasterizer module and connects into a vector and input traditional neural network, finally
To output.
5. the welds seam for long distance pipeline detection system according to claim 1 based on convolutional neural networks, it is characterised in that: institute
C1 Feature Mapping module, the C2 layers of Feature Mapping module stated are characterized extract layer, the input and preceding layer of each neuron
Local receptor field be connected, and extract the feature of the part, after the local feature is extracted, its position between other features
Relationship is set also to decide therewith.
6. the welds seam for long distance pipeline detection system according to claim 1 or 2 based on convolutional neural networks, feature exist
In: the S1 layer Feature Mapping module, S4 layers of Feature Mapping module are down-sampled layer, and each computation layer of network is by more
A Feature Mapping composition, each Feature Mapping are a plane, and the weight of all neurons is equal in plane.
7. a kind of welds seam for long distance pipeline detection method based on convolutional neural networks, it is characterised in that: including convolutional neural networks
Training process, identification process;
Convolutional neural networks training process: to the mark defect grading of elementary training sample, welding normal sample is added, establishes all kinds of
Standard exercise data set and test assessment data set are established in sample mark mapping;Training dataset is intended for training neural network
Close rating model;Test data set reaches target standard for assessing every wheel training accuracy, auxiliary adjusting training intensity and wheel number
Training and preservation model can be completed in true rate.
Identification process: using the whole figure heavy duty technology heavy duty network of neural network, and recalls " defect grading " nerve of training completion
Network parameter configuration is completed model and is restored.
8. the welds seam for long distance pipeline detection method according to claim 7 based on convolutional neural networks, it is characterised in that: institute
The identification process stated further includes the picture sample tensor to be graded for completing real-time acquisition pretreatment, inputs ruler by neural network
It is very little to cut tensor specification, input the queue of neural network pending data.
9. the welds seam for long distance pipeline detection method according to claim 8 based on convolutional neural networks, it is characterised in that: also
Including establishing neural network dialogue, being loaded into the network of recovery and to ratings data, running neural network and obtain each rank weight
And output, sample quality classification is determined according to each rank weight and gap, assesses image deflects rank.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810585115.XA CN109001211A (en) | 2018-06-08 | 2018-06-08 | Welds seam for long distance pipeline detection system and method based on convolutional neural networks |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810585115.XA CN109001211A (en) | 2018-06-08 | 2018-06-08 | Welds seam for long distance pipeline detection system and method based on convolutional neural networks |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109001211A true CN109001211A (en) | 2018-12-14 |
Family
ID=64600347
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810585115.XA Pending CN109001211A (en) | 2018-06-08 | 2018-06-08 | Welds seam for long distance pipeline detection system and method based on convolutional neural networks |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109001211A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109886298A (en) * | 2019-01-16 | 2019-06-14 | 江苏大学 | A kind of detection method for quality of welding line based on convolutional neural networks |
CN110047073A (en) * | 2019-05-05 | 2019-07-23 | 北京大学 | A kind of X-ray weld image fault grading method and system |
CN110108783A (en) * | 2019-05-14 | 2019-08-09 | 上海市特种设备监督检验技术研究院 | A kind of pipeline defect detection method and apparatus based on convolutional neural networks |
CN110163859A (en) * | 2019-05-29 | 2019-08-23 | 广东工业大学 | Weld seam welding method, device and equipment based on PoseCNN |
CN111383328A (en) * | 2020-02-27 | 2020-07-07 | 西安交通大学 | 3D visualization method and system for breast cancer focus |
CN113256620A (en) * | 2021-06-25 | 2021-08-13 | 南京思飞捷软件科技有限公司 | Vehicle body welding quality information judging method based on difference convolution neural network |
TWI762047B (en) * | 2020-11-26 | 2022-04-21 | 樹德科技大學 | Image-based weld bead defect detection method and the device |
CN115625571A (en) * | 2022-12-19 | 2023-01-20 | 江苏卓远半导体有限公司 | Monitoring method and system for diamond disk |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104977313A (en) * | 2014-04-09 | 2015-10-14 | 四川省特种设备检验研究院 | Method and device for detecting and identifying X-ray image defects of welding seam |
CN105891215A (en) * | 2016-03-31 | 2016-08-24 | 浙江工业大学 | Welding visual detection method and device based on convolutional neural network |
CN106530284A (en) * | 2016-10-21 | 2017-03-22 | 广州视源电子科技股份有限公司 | Welding spot type detection and device based on image recognition |
CN107123117A (en) * | 2017-04-26 | 2017-09-01 | 广东工业大学 | A kind of IC pin quality of welding spot detection method and device based on deep learning |
CN107133960A (en) * | 2017-04-21 | 2017-09-05 | 武汉大学 | Image crack dividing method based on depth convolutional neural networks |
CN107316064A (en) * | 2017-06-26 | 2017-11-03 | 长安大学 | A kind of asphalt pavement crack classifying identification method based on convolutional neural networks |
JP2018005639A (en) * | 2016-07-04 | 2018-01-11 | タカノ株式会社 | Image classification device, image inspection device, and program |
CN107609602A (en) * | 2017-09-28 | 2018-01-19 | 吉林大学 | A kind of Driving Scene sorting technique based on convolutional neural networks |
CN108038850A (en) * | 2017-12-08 | 2018-05-15 | 天津大学 | A kind of drainage pipeline Exception Type automatic testing method based on deep learning |
US20180157933A1 (en) * | 2016-12-07 | 2018-06-07 | Kla-Tencor Corporation | Data Augmentation for Convolutional Neural Network-Based Defect Inspection |
-
2018
- 2018-06-08 CN CN201810585115.XA patent/CN109001211A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104977313A (en) * | 2014-04-09 | 2015-10-14 | 四川省特种设备检验研究院 | Method and device for detecting and identifying X-ray image defects of welding seam |
CN105891215A (en) * | 2016-03-31 | 2016-08-24 | 浙江工业大学 | Welding visual detection method and device based on convolutional neural network |
JP2018005639A (en) * | 2016-07-04 | 2018-01-11 | タカノ株式会社 | Image classification device, image inspection device, and program |
CN106530284A (en) * | 2016-10-21 | 2017-03-22 | 广州视源电子科技股份有限公司 | Welding spot type detection and device based on image recognition |
US20180157933A1 (en) * | 2016-12-07 | 2018-06-07 | Kla-Tencor Corporation | Data Augmentation for Convolutional Neural Network-Based Defect Inspection |
CN107133960A (en) * | 2017-04-21 | 2017-09-05 | 武汉大学 | Image crack dividing method based on depth convolutional neural networks |
CN107123117A (en) * | 2017-04-26 | 2017-09-01 | 广东工业大学 | A kind of IC pin quality of welding spot detection method and device based on deep learning |
CN107316064A (en) * | 2017-06-26 | 2017-11-03 | 长安大学 | A kind of asphalt pavement crack classifying identification method based on convolutional neural networks |
CN107609602A (en) * | 2017-09-28 | 2018-01-19 | 吉林大学 | A kind of Driving Scene sorting technique based on convolutional neural networks |
CN108038850A (en) * | 2017-12-08 | 2018-05-15 | 天津大学 | A kind of drainage pipeline Exception Type automatic testing method based on deep learning |
Non-Patent Citations (4)
Title |
---|
刘梦溪: "深度卷积神经网络的X射线焊缝缺陷研究", 《传感器与微系统》 * |
刘涵: "基于X 射线图像和卷积神经网络的石油钢管焊缝缺陷检测与识别", 《仪器仪表学报》 * |
褚慧慧: "基于视觉的焊缝质量检测技术研究", 《中国知网》 * |
韦鹏程: "《基于R语言数据挖掘的统计与分析》", 31 December 2017, 电子科技大学出版社 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109886298A (en) * | 2019-01-16 | 2019-06-14 | 江苏大学 | A kind of detection method for quality of welding line based on convolutional neural networks |
CN110047073A (en) * | 2019-05-05 | 2019-07-23 | 北京大学 | A kind of X-ray weld image fault grading method and system |
CN110047073B (en) * | 2019-05-05 | 2021-07-06 | 北京大学 | X-ray weld image defect grading method and system |
CN110108783A (en) * | 2019-05-14 | 2019-08-09 | 上海市特种设备监督检验技术研究院 | A kind of pipeline defect detection method and apparatus based on convolutional neural networks |
CN110163859A (en) * | 2019-05-29 | 2019-08-23 | 广东工业大学 | Weld seam welding method, device and equipment based on PoseCNN |
CN110163859B (en) * | 2019-05-29 | 2023-05-05 | 广东工业大学 | PoseCNN-based weld joint welding method, device and equipment |
CN111383328A (en) * | 2020-02-27 | 2020-07-07 | 西安交通大学 | 3D visualization method and system for breast cancer focus |
TWI762047B (en) * | 2020-11-26 | 2022-04-21 | 樹德科技大學 | Image-based weld bead defect detection method and the device |
CN113256620A (en) * | 2021-06-25 | 2021-08-13 | 南京思飞捷软件科技有限公司 | Vehicle body welding quality information judging method based on difference convolution neural network |
CN115625571A (en) * | 2022-12-19 | 2023-01-20 | 江苏卓远半导体有限公司 | Monitoring method and system for diamond disk |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109001211A (en) | Welds seam for long distance pipeline detection system and method based on convolutional neural networks | |
Hou et al. | Deep features based on a DCNN model for classifying imbalanced weld flaw types | |
Petricca et al. | Corrosion detection using AI: a comparison of standard computer vision techniques and deep learning model | |
CN106980858A (en) | The language text detection of a kind of language text detection with alignment system and the application system and localization method | |
CN108830188A (en) | Vehicle checking method based on deep learning | |
Zheng et al. | A generic semi-supervised deep learning-based approach for automated surface inspection | |
CN107818302A (en) | Non-rigid multi-scale object detection method based on convolutional neural network | |
CN104977313A (en) | Method and device for detecting and identifying X-ray image defects of welding seam | |
CN108052881A (en) | The method and apparatus of multiclass entity object in a kind of real-time detection construction site image | |
CN106897738A (en) | A kind of pedestrian detection method based on semi-supervised learning | |
CN107563431A (en) | A kind of image abnormity detection method of combination CNN transfer learnings and SVDD | |
CN108615046A (en) | A kind of stored-grain pests detection recognition methods and device | |
CN114565579A (en) | Aircraft skin surface damage detection method and system based on deep learning | |
Savino et al. | Automated classification of civil structure defects based on convolutional neural network | |
CN111145145B (en) | Image surface defect detection method based on MobileNet | |
CN106997373A (en) | A kind of link prediction method based on depth confidence network | |
Hu et al. | Automatic defect detection from X-ray scans for aluminum conductor composite core wire based on classification neutral network | |
CN115131503A (en) | Health monitoring method and system for iris three-dimensional recognition | |
CN113902710A (en) | Method and system for detecting surface defects of industrial parts based on anomaly detection algorithm | |
CN115048537A (en) | Disease recognition system based on image-text multi-mode collaborative representation | |
CN115527098A (en) | Infrared small target detection method based on global mean contrast space attention | |
Monigari et al. | Plant leaf disease prediction | |
Shadrach et al. | Anomaly Detection in Vitis Vinifera Using Neural Networks and Radon Transform | |
CN112150344A (en) | Method for determining a confidence value of an object of a class | |
CN117011274A (en) | Automatic glass bottle detection system and method thereof |
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: 20181214 |
|
RJ01 | Rejection of invention patent application after publication |