CN102980893A - Classification detection system and method of ingot surface defect - Google Patents
Classification detection system and method of ingot surface defect Download PDFInfo
- Publication number
- CN102980893A CN102980893A CN2012104548872A CN201210454887A CN102980893A CN 102980893 A CN102980893 A CN 102980893A CN 2012104548872 A CN2012104548872 A CN 2012104548872A CN 201210454887 A CN201210454887 A CN 201210454887A CN 102980893 A CN102980893 A CN 102980893A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- collecting device
- ingot
- order
- 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
Landscapes
- Image Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
Disclosed are a classification detection system and a method of an ingot surface defect. The system comprises an image collecting device, an upper computer module and a power source. The image collecting device is connected with the upper computer module and is used for real-time collection of the ingot image on an assembly line. The upper computer module is used for processing and analyzing the collected image and extracting defect area. The power source is respectively connected with the image collecting device and the upper computer module so as to supply electric power. The classification detection system and the method of the ingot surface defect have the advantages of being high in detection precision, high in accuracy degree of defect statistics, convenient to inquire and high in production efficiency.
Description
Technical field
The present invention relates to the ingot surface defect detection field, be specifically related to a kind of ingot surface defect classified detection system and method.
Background technology
In recent years, along with growing continuously and fast of Chinese national economy, driven increasing substantially of domestic steel consumption.Steel ingot is a kind of in numerous steel, and a lot of rolling shapes all form by steel ingot is rolling.Therefore in today of steel industry develop rapidly, be the target that large-scale iron and steel enterprise is pursued to the pursuit of ingot quality always.In the production run of steel ingot, it is a most important link that ingot quality detects.Enterprise only has promptly and accurately and product is carried out quality testing, adjustment production strategy that can be correct according to the concrete condition of production.Effectively the quality testing of steel ingot can guarantee its production efficiency and product quality, also is simultaneously the powerful guarantee that enterprise obtains economic benefit.
Steel ingot is solidified through Sheng ladle injection mold by molten steel and forms.Steel ingot casting divides two kinds of downhill casting and bottom castings, and the general inner structure of upper caststeel ingot is better, and snotter is less, and operation cost is lower; Lower caststeel ingot surface quality is good, but owing to by feed trumpet and Tang Dao steel inclusion is increased.In addition, cast temperature should strictly be controlled, and the casting temperature is excessively low, and molten steel can cause ingot surface defect after entering mould, even molten steel just begins to solidify in ladle, causes metal loss or whole stove steel to scrap; Cast warmly when too high, will delay the formation time on steel ingot top layer, cause steel ingot fire check to occur.Common Ingot defects has: the scabbing of surface of steel ingot, pipe and longitudinal and transverse crackle, inner remaining shrinkage cavity, rimhole, loose and segregation are mingled with etc.These defectives reduce the billet yield of steel ingot greatly, even whole steel ingot is scrapped.These defectives are divided into Four types: corner crack, shrinkage cavity, center segregation, center porosity.
At present, the ingot surface defect classification and Detection means that generally adopt comprise that ultrasound wave or X ray detect.Because it is convenient and swift that ultrasound examination has, low cost and other advantages, thereby compared to the X ray detection, ultrasound examination is used more extensive.Yet the conventional sense method obtains the data of waveform and has only utilized sub-fraction, for defective, especially the actual defects at center is carried out the qualitative evaluation aspect and is but had sizable difficulty, detect identification and take time and effort, accuracy of identification is low, and poor accuracy, detection efficiency are low.
Summary of the invention
The object of the present invention is to provide a kind of ingot surface defect classified detection system, exist detection identification to take time and effort to solve existing ultrasound wave ingot surface defect classification and Detection mode, accuracy of identification is low, poor accuracy, the technical matters that detection efficiency is low.
Another object of the present invention is to provide a kind of ingot surface defect classification and Detection method, exist detection identification to take time and effort to solve existing ultrasound wave ingot surface defect classification and Detection mode, accuracy of identification is low, poor accuracy, the technical matters that detection efficiency is low.
For achieving the above object, the invention provides a kind of ingot surface defect classified detection system, comprise: image collecting device, upper computer module and power supply, image collecting device is connected with upper computer module, in order to the steel ingot image on the Real-time Collection streamline, upper computer module extracts defect area in order to the image that collects is carried out Treatment Analysis; Power supply is connected with upper computer module with image collecting device respectively, in order to electric power to be provided; Wherein, upper computer module further comprises:
Man-machine interaction processing unit: in order to accept user's operation, realize initial work and parameter setting, and show in real time detection information and testing result;
Image acquisition units: be connected with image collecting device with the man-machine interaction processing unit respectively, in order to user's operation of accepting according to the man-machine interaction processing unit, drive the steel ingot image on the image collecting device Real-time Collection streamline, and the image that collects is sent to image pretreatment unit and man-machine interaction processing unit;
Image pretreatment unit: be connected with image acquisition units, process operation in order to the image that collects is carried out gray processing processing, image enhancement processing, image denoising and self-adaption binaryzation, highlight the defect characteristic information in the image.
Image analyzing unit: be connected with the image pretreatment unit, in order to according to pretreated image calculation texture statistics and morphological operation, strengthen and extract defect area and be sent to the classification of defects statistic unit;
Classification of defects statistic unit: be connected with image analyzing unit, in order to being strengthened image, divides defect area, obtain different defective classifications, add up defect kind and the related defects rate of one batch steel ingot product, and be sent to database and man-machine interaction processing unit; And,
Database: in order to store defect kind and the related defects rate of one batch steel ingot product.
According to the described ingot surface defect classified detection system of preferred embodiment of the present invention, this image collecting device adopts the CCD color camera.
According to the described ingot surface defect classified detection system of preferred embodiment of the present invention, this classification of defects statistic unit is sent to database and man-machine interaction processing unit with the form of excel chart with one batch Steel Structure Weld defect situation generating report forms.
For achieving the above object, the present invention also provides a kind of ingot surface defect classification and Detection method, may further comprise the steps:
(1) accepts user's operation, realize initial work and parameter setting;
(2) according to user's operation, drive the steel ingot image on the image collecting device Real-time Collection streamline;
(3) image that collects is carried out gray processing processing, image enhancement processing, image denoising and self-adaption binaryzation and process operation, highlight the defect characteristic information in the image;
(4) according to pretreated image calculation texture statistics and morphological operation, strengthen and extract defect area;
(5) defect area is strengthened image and divide, obtain different defective classifications, add up defect kind and the related defects rate of one batch steel ingot product, show and the storage statistics.
Can be found out by above, ingot surface defect classified detection system of the present invention and method are processed by collection and the image of steel ingot image, obtain classification and the statistics of Ingot defects, show in real time detection information and statistics and statistics is stored in the database.System running speed is fast, and, adopt the method for image to realize the intelligent classification Ingot defects, accuracy of detection is high, and real-time is high, practical, simple to operate, has greatly improved production efficiency.In addition, the query processing by the interaction process of database can be provided convenience makes things convenient for subsequent query, has further improved accuracy.Therefore, compared with prior art, the present invention has the accuracy of detection height, and the defect statistics accuracy is high, inquiry is convenient and the high advantage of production efficiency.
Description of drawings
Fig. 1 is the structure principle chart of ingot surface defect classified detection system of the present invention;
Fig. 2 is the defect situation statistical representation intention that the embodiment of the invention is added up one batch the steel ingot product that obtains.
Embodiment
Below in conjunction with accompanying drawing, specify the present invention.
See also Fig. 1, a kind of ingot surface defect classified detection system comprises: image collecting device 1, upper computer module 2 and power supply 3, and image collecting device 1 adopts the CCD color camera, it is connected with upper computer module 2, in order to the steel ingot image on the Real-time Collection streamline; Upper computer module 2 extracts defect area in order to the image that collects is carried out Treatment Analysis; Power supply is connected with upper computer module with image collecting device 1 respectively and is connected, in order to electric power to be provided; Wherein, upper computer module 2 further comprises:
Man-machine interaction processing unit 21: in order to accept user's operation, realize initial work and parameter setting, and show in real time detection information and testing result.
Parameter is provided for arranging segmentation threshold, linear classifier coefficient, the parameters such as connected domain operator.
The initial work of man-machine interaction processing unit 21 main completion systems, realize the parameter setting, accept user's operation and show various data etc.
Image acquisition units 22: is connected with image collecting device with man-machine interaction processing unit 21 respectively and is connected, in order to user's operation of accepting according to man-machine interaction processing unit 21, drive the steel ingot image on the image collecting device 1 Real-time Collection streamline, and the image that collects is sent to image pretreatment unit 23 and man-machine interaction processing unit 21.
Steel ingot image on the image acquisition units 22 driven CCD color camera Real-time Collection streamlines, and can adjust the parameters such as the exposure of camera and gain.
Image pretreatment unit 23: be connected with image acquisition units 22, process operation in order to the image that collects is carried out gray processing processing, image enhancement processing, image denoising and self-adaption binaryzation, highlight the defect characteristic information in the image.
Particularly, adopt medium filtering and Gassian low-pass filter to carry out the image denoising operation.
Image analyzing unit 24: be connected with image pretreatment unit 23, in order to according to pretreated image calculation texture statistics and morphological operation, strengthen and extract defect area and be sent to classification of defects statistic unit 25.
Classification of defects statistic unit 25: be connected with image analyzing unit 24, in order to being strengthened image, divides defect area, obtain different defective classifications, add up defect kind and the related defects rate of one batch steel ingot product, and be sent to database 26 and man-machine interaction processing unit 21.
The defective that classification of defects statistic unit 25 obtains image analyzing unit 24 strengthens image divides, and utilizes linear classifier to be divided into different defective classifications.And, with the form of excel chart one batch Steel Structure Weld defect situation generating report forms is sent to database and man-machine interaction processing unit and stores and show.
The defective of steel ingot mainly comprises four kinds: center segregation, center porosity, shrinkage cavity and corner crack.As shown in Figure 2, defect recognition result of the present invention is divided into 5 kinds of situations: defect kind is shown as 0 expression normally; 1 expression shrinkage cavity defect; 2 expression center porosities; 3 expression center segregations; 4 expression corner cracks.
Database 26: in order to store defect kind and the related defects rate of one batch steel ingot product.
Ingot surface defect classified detection system of the present invention can be finished the sampling and processing of the steel ingot image on the streamline, automatically detect the Ingot defects kind on the streamline, and the statistical dependence ratio of defects, generating report forms is input in the correspondence database, system is simple to operate, and is convenient easy-to-use.System adopts digital image processing method that ingot surface defect is carried out evaluation of classification, at first by CCD color camera Real-time Collection steel ingot image, then strengthen the characteristic information of defective by the image pre-service, then the Four types defective is carried out signature analysis, by the texture statistics component analysis, the signature analysis of shrinkage cavity class defective out, carrying out the morphology processing displays crack defect again, the feature of ultimate analysis center segregation and two kinds of defectives of center porosity detects classification of defects one by one; Generating report forms afterwards, defect kind and the related defects rate of adding up the steel ingot product of this batch with the form of excel chart; At last, the result of statistics is imported to store and be sent to the man-machine interaction processing unit in the database of appointment and show.
Based on above-mentioned system, the present invention also provides a kind of ingot surface defect classification and Detection method, may further comprise the steps:
(1) accepts user's operation, realize initial work and parameter setting.
The parameter setting comprises the parameters such as segmentation threshold, linear classifier coefficient and connected domain operator are set.
(2) according to user's operation, drive the steel ingot image on the image collecting device Real-time Collection streamline.
Steel ingot image on the image acquisition units driven CCD color camera Real-time Collection streamline, and the parameters such as the exposure of adjustment camera and gain.
(3) image that collects is carried out gray processing processing, image enhancement processing, image denoising and self-adaption binaryzation and process operation, highlight the defect characteristic information in the image.
The image pretreatment unit carries out above associated picture pretreatment operation to the image that collects, and highlights the defect characteristic information in the image.Wherein, the image denoising operation adopts medium filtering and Gassian low-pass filter to realize.
(4) image analyzing unit is according to pretreated image calculation texture statistics and morphological operation, strengthens and extracts defect area.
(5) defect area is strengthened image and divide, obtain different defective classifications, add up defect kind and the related defects rate of one batch steel ingot product, show and the storage statistics.
The defective that classification of defects statistic unit 25 obtains image analyzing unit 24 strengthens image divides, and utilizes linear classifier to be divided into different defective classifications.And, with the form of excel chart one batch Steel Structure Weld defect situation generating report forms is sent to database and man-machine interaction processing unit and stores and show.
The defective of steel ingot mainly comprises four kinds: center segregation, center porosity, shrinkage cavity and corner crack.As shown in Figure 2, defect recognition result of the present invention is divided into 5 kinds of situations: defect kind is shown as 0 expression normally; 1 expression shrinkage cavity defect; 2 expression center porosities; 3 expression center segregations; 4 expression corner cracks.
The present invention at first inputs correlation parameter, start-up system, and beginning Real-time Collection steel ingot image and real-time analysis defective, the result shows by the man-machine interaction processing unit, wherein, 0 expression is normal, 1 expression shrinkage cavity defect, 2 expression center porosities, 3 expression center segregations, 4 expression corner cracks.Process to be detected finishes, generating report forms, generate one batch the defect kind of steel ingot product and related defects rate result's excel chart (as shown in Figure 2), and import to and store in the corresponding database and show by the man-machine interaction processing unit.
Ingot surface defect classified detection system of the present invention and method collection and the image by the steel ingot image processed, and obtains classification and the statistics of Ingot defects, shows in real time detection information and statistics and statistics is stored in the database.System running speed is fast, and, adopt the method for image to realize the intelligent classification Ingot defects, accuracy of detection is high, and real-time is high, practical, simple to operate, has greatly improved production efficiency.In addition, the query processing by the interaction process of database can be provided convenience makes things convenient for subsequent query, has further improved accuracy.Therefore, compared with prior art, the present invention has the accuracy of detection height, and the defect statistics accuracy is high, inquiry is convenient and the high advantage of production efficiency.
The above, it only is better embodiment of the present invention, be not that the present invention is done any pro forma restriction, any content that does not break away from technical solution of the present invention, according to any simple modification, equivalent variations and the modification that technical spirit of the present invention is done above embodiment, all belong to the scope of technical solution of the present invention.
Claims (4)
1. ingot surface defect classified detection system, it is characterized in that, comprise: image collecting device, upper computer module and power supply, described image collecting device is connected with described upper computer module, in order to the steel ingot image on the Real-time Collection streamline, described upper computer module extracts defect area in order to the image that collects is carried out Treatment Analysis; Described power supply is connected with upper computer module with described image collecting device respectively, in order to electric power to be provided; Wherein, described upper computer module further comprises:
Man-machine interaction processing unit: in order to accept user's operation, realize initial work and parameter setting, and show in real time detection information and testing result;
Image acquisition units: be connected with image collecting device with described man-machine interaction processing unit respectively, in order to user's operation of accepting according to described man-machine interaction processing unit, drive the steel ingot image on the image collecting device Real-time Collection streamline, and the image that collects is sent to image pretreatment unit and man-machine interaction processing unit;
Image pretreatment unit: be connected with described image acquisition units, process operation in order to the image that collects is carried out gray processing processing, image enhancement processing, image denoising and self-adaption binaryzation, highlight the defect characteristic information in the image;
Image analyzing unit: be connected with described image pretreatment unit, in order to according to pretreated image calculation texture statistics and morphological operation, strengthen and extract defect area and be sent to the classification of defects statistic unit;
Classification of defects statistic unit: be connected with described image analyzing unit, in order to being strengthened image, divides defect area, obtain different defective classifications, add up defect kind and the related defects rate of one batch steel ingot product, and be sent to database and man-machine interaction processing unit; And,
Database: in order to store defect kind and the related defects rate of one batch steel ingot product.
2. ingot surface defect classified detection system as claimed in claim 1 is characterized in that, described image collecting device adopts the CCD color camera.
3. ingot surface defect classified detection system as claimed in claim 1, it is characterized in that described classification of defects statistic unit is sent to database and man-machine interaction processing unit with the form of excel chart with one batch Steel Structure Weld defect situation generating report forms.
4. an ingot surface defect classification and Detection method is characterized in that, may further comprise the steps:
(1) accepts user's operation, realize initial work and parameter setting;
(2) according to user's operation, drive the steel ingot image on the image collecting device Real-time Collection streamline;
(3) image that collects is carried out gray processing processing, image enhancement processing, image denoising and self-adaption binaryzation and process operation, highlight the defect characteristic information in the image;
(4) according to pretreated image calculation texture statistics and morphological operation, strengthen and extract defect area;
(5) defect area is strengthened image and divide, obtain different defective classifications, add up defect kind and the related defects rate of one batch steel ingot product, show and the storage statistics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104548872A CN102980893A (en) | 2012-11-13 | 2012-11-13 | Classification detection system and method of ingot surface defect |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104548872A CN102980893A (en) | 2012-11-13 | 2012-11-13 | Classification detection system and method of ingot surface defect |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102980893A true CN102980893A (en) | 2013-03-20 |
Family
ID=47855113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012104548872A Pending CN102980893A (en) | 2012-11-13 | 2012-11-13 | Classification detection system and method of ingot surface defect |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102980893A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103264019A (en) * | 2013-04-25 | 2013-08-28 | 洛阳久德轴承模具技术有限公司 | Tapered roller surface defect detection system |
| CN103383361A (en) * | 2013-08-02 | 2013-11-06 | 湖州职业技术学院 | Steel wire core conveyer belt detection device and method |
| CN104259110A (en) * | 2014-09-26 | 2015-01-07 | 浙江大学台州研究院 | Detection method of ceramic valve element |
| CN104778684A (en) * | 2015-03-06 | 2015-07-15 | 江苏大学 | Method and system thereof for automatically measuring, representing and classifying heterogeneous defects on surface of steel |
| CN108337900A (en) * | 2015-06-30 | 2018-07-27 | 倍耐力轮胎股份公司 | The method and apparatus of the defect on surface for detecting tire |
| CN108508023A (en) * | 2018-03-30 | 2018-09-07 | 深圳市益鑫智能科技有限公司 | The defect detecting system of end puller bolt is contacted in a kind of railway contact line |
| CN109690289A (en) * | 2016-09-12 | 2019-04-26 | 株式会社Posco | It is segregated analytical equipment and method |
| CN111402190A (en) * | 2018-12-28 | 2020-07-10 | 上海尤图智能科技有限公司 | Image processing device and system for wire rod on-line detection |
| WO2022117118A1 (en) * | 2021-01-06 | 2022-06-09 | 大冶特殊钢有限公司 | Machine vision-based automatic identification and rating method and system for low-magnification acid etching defect |
| CN115791804A (en) * | 2022-12-20 | 2023-03-14 | 中国航发贵州黎阳航空动力有限公司 | Stripe defect detection method for compressor blade |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030122731A1 (en) * | 2000-07-04 | 2003-07-03 | Atsushi Miyake | Image processing system |
| CN101424645A (en) * | 2008-11-20 | 2009-05-06 | 上海交通大学 | Soldered ball surface defect detection device and method based on machine vision |
| CN101726498A (en) * | 2009-12-04 | 2010-06-09 | 河海大学常州校区 | Intelligent detector and method of copper strip surface quality on basis of vision bionics |
-
2012
- 2012-11-13 CN CN2012104548872A patent/CN102980893A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030122731A1 (en) * | 2000-07-04 | 2003-07-03 | Atsushi Miyake | Image processing system |
| CN101424645A (en) * | 2008-11-20 | 2009-05-06 | 上海交通大学 | Soldered ball surface defect detection device and method based on machine vision |
| CN101726498A (en) * | 2009-12-04 | 2010-06-09 | 河海大学常州校区 | Intelligent detector and method of copper strip surface quality on basis of vision bionics |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103264019B (en) * | 2013-04-25 | 2014-06-11 | 洛阳久德轴承模具技术有限公司 | Tapered roller surface defect detection system |
| CN103264019A (en) * | 2013-04-25 | 2013-08-28 | 洛阳久德轴承模具技术有限公司 | Tapered roller surface defect detection system |
| CN103383361A (en) * | 2013-08-02 | 2013-11-06 | 湖州职业技术学院 | Steel wire core conveyer belt detection device and method |
| CN104259110A (en) * | 2014-09-26 | 2015-01-07 | 浙江大学台州研究院 | Detection method of ceramic valve element |
| CN104778684A (en) * | 2015-03-06 | 2015-07-15 | 江苏大学 | Method and system thereof for automatically measuring, representing and classifying heterogeneous defects on surface of steel |
| CN108337900B (en) * | 2015-06-30 | 2020-04-07 | 倍耐力轮胎股份公司 | Method and apparatus for detecting defects on the surface of a tyre |
| CN108337900A (en) * | 2015-06-30 | 2018-07-27 | 倍耐力轮胎股份公司 | The method and apparatus of the defect on surface for detecting tire |
| CN109690289A (en) * | 2016-09-12 | 2019-04-26 | 株式会社Posco | It is segregated analytical equipment and method |
| CN108508023A (en) * | 2018-03-30 | 2018-09-07 | 深圳市益鑫智能科技有限公司 | The defect detecting system of end puller bolt is contacted in a kind of railway contact line |
| CN108508023B (en) * | 2018-03-30 | 2021-06-04 | 苏州阚创检测有限公司 | Defect detection system for contact end jacking bolt in railway contact network |
| CN111402190A (en) * | 2018-12-28 | 2020-07-10 | 上海尤图智能科技有限公司 | Image processing device and system for wire rod on-line detection |
| CN111402190B (en) * | 2018-12-28 | 2023-06-09 | 上海尤图智能科技有限公司 | Image processing device and system for wire rod on-line detection |
| WO2022117118A1 (en) * | 2021-01-06 | 2022-06-09 | 大冶特殊钢有限公司 | Machine vision-based automatic identification and rating method and system for low-magnification acid etching defect |
| CN115791804A (en) * | 2022-12-20 | 2023-03-14 | 中国航发贵州黎阳航空动力有限公司 | Stripe defect detection method for compressor blade |
| CN115791804B (en) * | 2022-12-20 | 2023-06-13 | 中国航发贵州黎阳航空动力有限公司 | Method for detecting stripe defect of compressor blade |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102980893A (en) | Classification detection system and method of ingot surface defect | |
| CN108090423B (en) | Depth license plate detection method based on thermodynamic diagram and key point regression | |
| CN101902617B (en) | Device and method for realizing video structural description by using DSP and FPGA | |
| CN105205821B (en) | A kind of welding image dividing method | |
| CN109859160B (en) | Aluminum magnesium alloy casting internal defect image identification method based on machine vision | |
| EP3385716A3 (en) | Method of using non-rare cells to detect rare cells | |
| CN103499585A (en) | Non-continuity lithium battery thin film defect detection method and device based on machine vision | |
| CN108256260A (en) | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine | |
| CN114549497A (en) | Method for detecting surface defects of walking board based on image recognition and artificial intelligence system | |
| CN102496161A (en) | Method for extracting contour of image of printed circuit board (PCB) | |
| CN106485708A (en) | A kind of round log method of counting based on image recognition | |
| CN105092597A (en) | Detection method for cracks on surface of hard-plastic material | |
| CN105719275A (en) | Parallel combination image defect segmentation method | |
| CN102980892A (en) | On-line examination system and method for steel pipe | |
| CN110555373A (en) | Concrete vibration quality real-time detection method based on image recognition | |
| Fu et al. | Research on image-based detection and recognition technologies for cracks on rail surface | |
| CN109308707B (en) | Non-contact type online measuring method for thickness of aluminum ingot | |
| CN107133952A (en) | A kind of alligatoring recognition methods for merging time-frequency characteristics | |
| Zhu et al. | Multi-classification recognition and quantitative characterization of surface defects in belt grinding based on YOLOv7 | |
| CN113436102A (en) | Method for detecting surface defects of machined part | |
| Hu et al. | Heavy rail surface defects detection based on the morphology of multi-scale and dual-structure elements | |
| CN109916923A (en) | A kind of customization plate automatic defect detection method based on machine vision | |
| Yingyong et al. | Research on algorithm for automatic license plate recognition system | |
| Zhao et al. | A surface defect detection system for railway track based on machine vision | |
| CN108364095B (en) | Molten steel quality diagnosis method in steelmaking production process based on data mining |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130320 |