CN111336954A - Method for automatically classifying fiber cross sections and automatically calculating areas - Google Patents
Method for automatically classifying fiber cross sections and automatically calculating areas Download PDFInfo
- Publication number
- CN111336954A CN111336954A CN202010125563.9A CN202010125563A CN111336954A CN 111336954 A CN111336954 A CN 111336954A CN 202010125563 A CN202010125563 A CN 202010125563A CN 111336954 A CN111336954 A CN 111336954A
- Authority
- CN
- China
- Prior art keywords
- cross
- section
- fiber
- area
- calculate
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
- G01B11/285—Measuring arrangements characterised by the use of optical techniques for measuring areas using photoelectric detection means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention relates to a method for automatically classifying fiber cross sections and automatically calculating areas, which comprises the steps of placing a fiber sample on an objective table, focusing a lens, photographing and collecting clear area images; detecting the cross section of the fiber by adopting a target detection algorithm to obtain the cross section of the single fiber; preprocessing the image by adopting an image processing technology, and obtaining a contour through semantic segmentation; optimize final target, and generate and cover the territory, calculate the profile size according to covering the territory, calculate the area according to profile size and scale, and calculate every type average area, it can effectively improve work efficiency, make it can make things convenient for, quick completion work, can classify and calculate the area to the fibre cross section, effectively solve the problem of artifical recognition fibre cross section and calculate the problem that the average area of fibre cross section need the manual circle of drawing to scan the calculation again, realize full-automatic, need not artificial intervention, greatly save the human cost and saved the time cost.
Description
Technical Field
The invention relates to the fields of computer software, AI, image processing and the like, in particular to a method for automatically classifying fiber cross sections and automatically calculating areas.
Background
In the traditional textile industry, fiber cross-sectional area measurement needs to load prepared fiber samples into a fiber slicer, the fiber slices are coated with soft rubber, the fiber slices with moderate thickness are cut and placed on a glass slide, then a projector needs to be prepared, the cross sections of fiber images are drawn by using pencils in a projection plane, the area is calculated after drawing, the whole process is large in workload, tedious and tedious, more in repetitive labor and low in working efficiency, and the industrial development is not facilitated.
Disclosure of Invention
The invention improves the prior art aiming at the defects, provides a method for automatically classifying the cross section of the fiber and automatically calculating the area of the cross section so as to improve the working efficiency of the industry and conveniently and quickly finish the work, and realizes the automation of drawing and classifying the cross section, and the technical scheme is as follows:
method for automatic classification and area calculation of a fibre cross section, comprising the steps of:
(1) placing the prepared fiber sample on an objective table;
(2) focusing a lens and taking a picture;
(3) collecting a shot clear area image;
(4) detecting the cross section of the fiber in the area by adopting a target detection algorithm, and acquiring the cross section of a single fiber;
(5) preprocessing the cross section of a single fiber by adopting an image processing technology;
(6) performing semantic segmentation on the detected cross section of the single fiber, and acquiring a contour;
(7) optimizing the final target and generating a Mongolian layout, wherein the function formula is as follows:
(8) calculating the size of the outline according to the mask diagram;
(9) calculating the area of the cross section of the fiber according to the size of the outline of the cross section of the fiber and a scale;
(10) the average cross-sectional area of each type of fiber was calculated.
The target detection algorithm is a yolo, SSD or FasterRCNN method and the like.
The semantic segmentation adopts methods such as FCN, Unet or CGAN.
Compared with the prior art, the invention has the beneficial effects that: the invention can classify the fiber cross sections and calculate the area, liberates people from tedious and boring labor, saves the labor cost, improves the working efficiency, effectively solves the problems of manually identifying the fiber cross sections and manually drawing circles and then scanning and calculating the average area of the fiber cross sections, realizes full automation, does not need manual intervention, greatly saves the labor cost and saves the time cost.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced as follows:
FIG. 1 is a schematic diagram of a device client interface for use with the present invention;
FIG. 2 is a cross-sectional view of a fiber of the present invention;
FIG. 3 is a diagram illustrating the effect of contour generation according to the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
Embodiments of the invention will be described in further detail below with reference to the following drawings, in which:
method for automatic classification and area calculation of a fibre cross section, comprising the steps of:
(1) placing the prepared fiber sample on an objective table;
(2) focusing a lens and taking a picture;
(3) collecting a shot clear area image;
(4) detecting the cross section of the fiber in the area by adopting a target detection algorithm, and acquiring the cross section of a single fiber;
(5) preprocessing the cross section of a single fiber by adopting an image processing technology;
(6) performing semantic segmentation on the detected cross section of the single fiber, and acquiring a contour;
(7) optimizing the final target and generating a Mongolian layout, wherein the function formula is as follows:
(8) calculating the size of the outline according to the mask diagram;
(9) calculating the area of the cross section of the fiber according to the size of the outline of the cross section of the fiber and a scale;
(10) the average cross-sectional area of each type of fiber was calculated.
Further, the target detection algorithm is a yolo algorithm, and FCN semantics are adopted for semantic segmentation.
The invention can classify the fiber cross sections and calculate the area, liberates people from tedious and boring labor, saves the labor cost, improves the working efficiency, effectively solves the problems of manually identifying the fiber cross sections and manually drawing circles and then scanning and calculating the average area of the fiber cross sections, realizes full automation, does not need manual intervention, can obtain results within five minutes compared with the time which is about two hours in the prior art, and greatly saves the labor cost and the time cost.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (3)
1. Method for automatic classification and area calculation of a cross section of a fibre, characterized in that it comprises the following steps:
(1) placing the prepared fiber sample on an objective table;
(2) focusing a lens and taking a picture;
(3) collecting a shot clear area image;
(4) detecting the cross section of the fiber in the area by adopting a target detection algorithm, and acquiring the cross section of a single fiber;
(5) preprocessing the cross section of a single fiber by adopting an image processing technology;
(6) performing semantic segmentation on the detected cross section of the single fiber, and acquiring a contour;
(7) optimizing the final target and generating a Mongolian layout, wherein the function formula is as follows:
(8) calculating the size of the outline according to the mask diagram;
(9) calculating the area of the cross section of the fiber according to the size of the outline of the cross section of the fiber and a scale;
(10) the average cross-sectional area of each type of fiber was calculated.
2. The method for automatic classification and area calculation of fiber cross-section according to claim 1, characterized in that the target detection algorithm is yolo, SSD or fasternn method.
3. The method for automatic classification and area calculation of fiber cross-section as claimed in claim 1, wherein the semantic segmentation adopts FCN, Unet or CGAN.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010125563.9A CN111336954B (en) | 2020-02-27 | 2020-02-27 | Method for automatically classifying fiber cross sections and automatically calculating areas |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010125563.9A CN111336954B (en) | 2020-02-27 | 2020-02-27 | Method for automatically classifying fiber cross sections and automatically calculating areas |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111336954A true CN111336954A (en) | 2020-06-26 |
| CN111336954B CN111336954B (en) | 2022-04-12 |
Family
ID=71179675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010125563.9A Active CN111336954B (en) | 2020-02-27 | 2020-02-27 | Method for automatically classifying fiber cross sections and automatically calculating areas |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111336954B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08164521A (en) * | 1994-12-14 | 1996-06-25 | Kobe Steel Ltd | Fiber reinforced resin composition |
| CN1264823A (en) * | 2000-03-31 | 2000-08-30 | 清华大学 | Method and special microscopic device for measuring size of fibre |
| CN101424680A (en) * | 2008-12-11 | 2009-05-06 | 东华大学 | Computer automatic recognition apparatus and method for profile fiber |
| CN101487838A (en) * | 2008-12-11 | 2009-07-22 | 东华大学 | Extraction method for dimension shape characteristics of profiled fiber |
| CN102435153A (en) * | 2011-09-21 | 2012-05-02 | 江苏盛虹科技股份有限公司 | Profile degree testing method for polyester filament yarn |
| CN104330056A (en) * | 2014-10-23 | 2015-02-04 | 西南大学 | Method of accurately measuring cross section area of single silk and application thereof |
| CN107358177A (en) * | 2017-06-27 | 2017-11-17 | 维拓智能科技（深圳）有限公司 | A kind of medium and long distance pedestrian detection method and terminal device based on graphical analysis |
| CN107747919A (en) * | 2017-10-13 | 2018-03-02 | 广东工业大学 | A kind of fiber cross section product measuring method and system |
-
2020
- 2020-02-27 CN CN202010125563.9A patent/CN111336954B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08164521A (en) * | 1994-12-14 | 1996-06-25 | Kobe Steel Ltd | Fiber reinforced resin composition |
| CN1264823A (en) * | 2000-03-31 | 2000-08-30 | 清华大学 | Method and special microscopic device for measuring size of fibre |
| CN101424680A (en) * | 2008-12-11 | 2009-05-06 | 东华大学 | Computer automatic recognition apparatus and method for profile fiber |
| CN101487838A (en) * | 2008-12-11 | 2009-07-22 | 东华大学 | Extraction method for dimension shape characteristics of profiled fiber |
| CN102435153A (en) * | 2011-09-21 | 2012-05-02 | 江苏盛虹科技股份有限公司 | Profile degree testing method for polyester filament yarn |
| CN104330056A (en) * | 2014-10-23 | 2015-02-04 | 西南大学 | Method of accurately measuring cross section area of single silk and application thereof |
| CN107358177A (en) * | 2017-06-27 | 2017-11-17 | 维拓智能科技（深圳）有限公司 | A kind of medium and long distance pedestrian detection method and terminal device based on graphical analysis |
| CN107747919A (en) * | 2017-10-13 | 2018-03-02 | 广东工业大学 | A kind of fiber cross section product measuring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111336954B (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023134793A2 (en) | Machine vision-based machine tool part online inspection method | |
| CN109613002B (en) | Glass defect detection method and device and storage medium | |
| CN110148130B (en) | Method and device for detecting part defects | |
| WO2018000731A1 (en) | Method for automatically detecting curved surface defect and device thereof | |
| CN107085846B (en) | Workpiece surface defect image identification method | |
| CN111982916A (en) | Welding seam surface defect detection method and system based on machine vision | |
| CN115063409B (en) | Method and system for detecting surface material of mechanical cutter | |
| CN102261892A (en) | Rapid width measurement system for tobacco shreds | |
| CN112967285B (en) | Chloasma image recognition method, system and device based on deep learning | |
| CN117237646B (en) | PET high-temperature flame-retardant adhesive tape flaw extraction method and system based on image segmentation | |
| CN111724358A (en) | Concrete quality detection method and system based on image and convolutional neural network | |
| CN113781458A (en) | Artificial intelligence based identification method | |
| CN111579466B (en) | Household sperm detection device and detection method | |
| CN110648312A (en) | Method for identifying wool and cashmere fibers based on scale morphological characteristic analysis | |
| CN111178405A (en) | Similar object identification method fusing multiple neural networks | |
| CN111336954B (en) | Method for automatically classifying fiber cross sections and automatically calculating areas | |
| CN114894808A (en) | Device and method for detecting defects of heat pipe orifice based on machine vision | |
| CN114049490A (en) | Intelligent occupational health early warning method and system | |
| CN103900499A (en) | Cigarette packing warning zone area measuring method based on computer visual technology | |
| CN116843687A (en) | Communication optical cable surface flaw detection method and device | |
| CN110930393A (en) | Chip material pipe counting method, device and system based on machine vision | |
| CN115908301A (en) | Defect detection method and device based on enhanced input and storage medium | |
| CN109916923A (en) | A kind of customization plate automatic defect detection method based on machine vision | |
| CN111881932B (en) | FasterRCNN target detection algorithm for military aircraft | |
| TWI777307B (en) | Method, computer program, and computer readable medium of using electroluminescence images to identify defect of solar cell based on deep learning technology |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Fu Guangwei Inventor after: Chen Hua Inventor after: Zhang Zhenzhu Inventor after: Li Hongying Inventor after: Han Wenxia Inventor after: Chen Jinjian Inventor after: Zhang Zhirong Inventor after: Wang Jing Inventor after: Lin Jiapeng Inventor after: Wang Wen Inventor before: Li Hongying Inventor before: Han Wenxia Inventor before: Wang Jing Inventor before: Chen Jinjian Inventor before: Lin Jiapeng Inventor before: Wang Wen Inventor before: Chen Hua |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210427 Address after: 100025, Beijing, Chaoyang District Jing Jing Li street, No. 3 main building, 6 floor Applicant after: CHINA TEXTILE ENGINEERING SOCIETY Applicant after: FOSHAN ZHONGFANGLIAN INSPECTION TECHNOLOGY SERVICE Co.,Ltd. Applicant after: Guangzhou guantu Vision Technology Co.,Ltd. Address before: 528211 South Technology Innovation Center, Xiqiao Textile City, Nanhai District, Foshan City, Guangdong Province Applicant before: FOSHAN ZHONGFANGLIAN INSPECTION TECHNOLOGY SERVICE Co.,Ltd. Applicant before: Guangzhou guantu Vision Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100025 6th floor, main building, No.3 yanjingli middle street, Chaoyang District, Beijing Patentee after: China Textile Engineering Society Patentee after: FOSHAN ZHONGFANGLIAN INSPECTION TECHNOLOGY SERVICE CO.,LTD. Patentee after: Guangzhou guantu Technology Co.,Ltd. Address before: 100025 6th floor, main building, No.3 yanjingli middle street, Chaoyang District, Beijing Patentee before: China Textile Engineering Society Patentee before: FOSHAN ZHONGFANGLIAN INSPECTION TECHNOLOGY SERVICE CO.,LTD. Patentee before: Guangzhou guantu Vision Technology Co.,Ltd. |