CN212321459U - Automatic image identification equipment of fibre - Google Patents
Automatic image identification equipment of fibre Download PDFInfo
- Publication number
- CN212321459U CN212321459U CN202021923976.3U CN202021923976U CN212321459U CN 212321459 U CN212321459 U CN 212321459U CN 202021923976 U CN202021923976 U CN 202021923976U CN 212321459 U CN212321459 U CN 212321459U
- Authority
- CN
- China
- Prior art keywords
- image
- identification
- industrial camera
- fiber
- server
- 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.)
- Active
Links
Images
Landscapes
- Microscoopes, Condenser (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The utility model discloses an automatic image identification equipment of fibre, this equipment including: the image acquisition device is used for acquiring a fiber image for the sample slide; the identification computer is used for controlling the work of the image acquisition device and automatically analyzing the fiber image to obtain an identification report of the fibers contained in the sample slide; the authentication computer comprises a front-end operator and a server; the server interacts with the front-end operator, and the server interacts with the image acquisition device. The utility model discloses it is reliable to have equipment framework, and the device operates steadily, equipment degree of automation is high, the controllability is strong, the discrimination accuracy grade technological effect high.
Description
Technical Field
The utility model belongs to the technical field of the fibre is distinguished, in particular to identification equipment, identification system and identification method thereof.
Background
In the clothing industry, in order to facilitate production management and product analysis, scientific identification of textile fibers is required, wherein identification of morphological characteristics of fibers and measurement and calculation of fiber diameters are the most important identification items.
In the prior art, in order to realize specific test items such as fiber morphological characteristic identification, fiber diameter measurement and calculation and the like, the specific test items are usually carried out in a manual mode by using a microscope for assistance.
The traditional method for artificially identifying textile fibers is low in efficiency, high in repeatability, boring and tedious in detection process, quite high in requirement on the specialty of an identifier, rich in experience and strong in knowledge reserve, and for textile samples with unknown components, an identification conclusion can be obtained and an authoritative identification report can be issued according to the experience of the identifier. The defects greatly restrict the development of the textile industry in the clothing industry, so that the automatic identification equipment is created, and the technical problem which needs to be solved by the technical personnel in the field is to make automatic identification on the textile fibers to be detected by utilizing the automatic identification equipment.
SUMMERY OF THE UTILITY MODEL
In order to solve the above problem, an object of the present invention is to provide an automatic fiber image identification device, which is capable of realizing automatic fiber identification by setting an image acquisition device and an identification computer and cooperating the two tight connections. The utility model provides an identification equipment uses the image that image acquisition device collected the sample slide, conveys this image to the identification computer in, and the identification computer uses this image as research material, obtains the discrimination result based on the fibre that digital image processing technique and convolution neural network technique contained in the automatic identification sample slide.
In order to achieve the above purpose, the technical scheme of the utility model is as follows:
an automated image authentication apparatus for fibers, the apparatus comprising:
the image acquisition device is used for acquiring a fiber image for the sample slide;
the identification computer is used for controlling the work of the image acquisition device and automatically analyzing the fiber image to obtain an identification report of the fibers contained in the sample slide;
the authentication computer comprises a front-end operator and a server; the server is mutual with the front end operation ware, and the server is mutual with image acquisition device the utility model discloses when specifically using in the actual scene, technical staff can be according to using the scene demand, need to constitute the front end operation ware with one or more combinations in specific parts such as keyboard, mouse, display or touch screen, realizes human-computer interaction.
Further, the image acquisition device comprises a microscope and an industrial camera;
the industrial camera is arranged at the microscopic imaging position of the microscope and is connected with the microscope;
both the industrial camera and the microscope interact with the server.
Further, the microscope includes:
base: the device is used for carrying other parts in the equipment and playing a supporting role;
three-axis objective table: the device is provided with a carrying plane, is used for carrying a sample slide and has three freedom degrees of movement in x, y and z directions;
observing the collecting head: the device is provided with a microscopic imaging observation port and a microscopic image acquisition port, and is convenient for operators to observe microscopic imaging of a sample slide and install an industrial camera;
the three-axis objective table is arranged above the base and is movably connected with the base; the observation collecting head is arranged above the three-axis objective table, and the industrial camera is movably connected with the observation collecting head through a microscopic image collecting port of the industrial camera;
the three-axis objective table is interacted with the server, and the degrees of freedom of movement in the x direction, the y direction and the z direction are controlled by the server.
Furthermore, the server comprises a control module and an AI identification model;
the control module is connected with the AI identification model and interacts with the industrial camera to control the industrial camera to collect the image of the sample slide at a fixed point; the control module is also interactive with the three-axis objective table to control the three-axis objective table to move in the x, y and z directions.
Further, the AI identification model comprises an image preprocessing module for receiving the image collected by the industrial camera and performing gray scale adjustment and size adjustment on the image; the image pre-processing module interacts with the industrial camera.
Furthermore, the AI identification model also comprises a diameter measuring module used for respectively measuring and calculating the diameter of the single fiber according to the imaging of the single fiber in the image; the diameter measuring and calculating module is interactive with the image preprocessing module.
Further, the AI identification model also comprises an identification convolution neural network used for obtaining the identification result of the type of the fiber according to the external morphological characteristics of the fiber contained in the sample slide; the discriminatory convolutional neural network interacts with an image preprocessing module.
The utility model discloses in provide automatic image identification equipment of fibre and use and be, work according to following step:
s1: installation preparation: preparing a sample slide, clamping the sample slide on a three-axis objective table, and controlling the movement of the three-axis objective table in the x direction, the y direction and the z direction by an identification computer to make the sample slide stop at a proper observation position
S2: and (3) creating a report: creating a blank report for the current sample slide, and adjusting the industrial camera and the microscope to enter a standby state;
s3: operation identification: the industrial camera works, the image of the sample slide is transmitted to the server, the server calculates and obtains the diameter of a single fiber according to the image, analyzes the morphological characteristics of each fiber in the sample slide, fills the morphological characteristics into an original blank report, and comprehensively obtains an identification report of the fibers contained in the sample slide.
Wherein, S2: creating a report specifically comprises the following substeps:
s21: creating a blank report for the current sample slide;
s23: inputting configuration parameters into the blank report;
s23: the control module controls the three-axis objective table to move, adjusts the visual field of the industrial camera to the initial shooting position, and keeps the industrial camera and the microscope in standby.
Wherein, S3: the operation identification specifically comprises the following substeps:
s31: the control module controls the three-axis object stage to move so as to change the visual field of the industrial camera;
s32: an industrial camera takes an image of a sample slide under a specified field of view;
s33: repeating S31-S32; until the industrial camera shoots images under all the visual fields of the sample slide, the industrial camera transmits the images to an image preprocessing module;
s32: the image preprocessing module performs gray level adjustment and size adjustment on the image to obtain a proper usable image; and positioning the fibers in the image to obtain a single fiber image group.
S34: the image preprocessing module transmits a proper available image into the diameter measuring and calculating module to obtain the diameter of a single fiber to be measured and calculated;
s35: the image preprocessing module transmits a proper available image into an identification convolution neural network to obtain an identification result of the fiber type;
s36: and recording the motion parameters of the three-axis mobile platform, correspondingly filling the identification results of the diameter and the type of the single fiber into the original blank report, and comprehensively obtaining the identification report of the fiber contained in the sample slide.
Compared with the prior art, the utility model discloses following beneficial effect has:
the equipment framework is reliable, and the device operates stably: on one hand, once the image acquisition device consisting of the microscope and the industrial computer is manufactured and put into use, the image acquisition device is quite stable in the working process and is not easily influenced by external interference factors; on the other hand, once the components such as the server and the front-end operator in the identification computer, the control module, the diameter measuring and calculating module and the identification convolutional neural network in the server are developed and put into use, the operation process of the components is very reliable.
The equipment has high automation degree and strong controllability: the microscope and the industrial camera are interacted with the identification computer, the identification computer can easily obtain working parameters and working result feedback information thereof through a port connected with the identification computer, and the whole performance of the equipment is highly controllable; under the control of the identification computer, all parts in the equipment can automatically complete the work content, and the automation degree is high.
The accuracy of the identification result is high: firstly, the control module is used for controlling the work of the industrial camera and the microscope, on one hand, the control module can accurately control the actions of the industrial camera and the microscope to obtain an accurate action effect, and on the other hand, the diameter measuring module and the identification convolutional neural network in the server can be adjusted and tested before being put into use to confirm that the diameter measuring module and the identification convolutional neural network can be started after obtaining higher accuracy, so that the identification accuracy of the whole equipment is ensured to a greater extent.
Drawings
Fig. 1 is a system block diagram of an automated fiber image authentication apparatus provided in an embodiment.
Fig. 2 is a schematic diagram of an overall structure of a microscope in an automated fiber image identification apparatus according to an embodiment.
Fig. 3 is a flowchart of the operation of an automated fiber image authentication device according to an embodiment.
Fig. 4 is a flowchart illustrating operation S2 of an automated fiber image recognition apparatus according to an embodiment.
Fig. 5 is a flowchart illustrating operation S3 of an automated fiber image recognition apparatus according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In order to achieve the above purpose, the technical scheme of the utility model is as follows:
please refer to fig. 1-5.
In this embodiment, an automated fiber image identification device is provided, comprising:
an image acquisition device 1 for acquiring a fiber image of a sample slide;
an identification computer 2 for controlling the operation of the image acquisition device and automatically analyzing the fiber image to obtain an identification report of the fibers contained in the sample slide;
the authentication computer 2 includes a front-end operator 21 and a server 22; server 22 is mutual with front end operation ware 21, and server 22 is mutual with image acquisition device 1 the utility model discloses when specifically using in the actual scene, technical staff can be according to using the scene demand, need to constitute front end operation ware 21 with one or more combinations in specific parts such as keyboard, mouse, display or touch screen, realizes human-computer interaction.
In the present embodiment, the image capturing device 1 includes a microscope 11 and an industrial camera 12;
the industrial camera 12 is arranged at the microscopic imaging position of the microscope 11, and the industrial camera 12 is connected with the microscope 11;
both the industrial camera 12 and the microscope 11 interact with the server 22.
In the present embodiment, the microscope 11 includes:
base 111: the device is used for carrying other parts in the equipment and playing a supporting role;
three-axis stage 112: the device is provided with a carrying plane, is used for carrying a sample slide and has three freedom degrees of movement in x, y and z directions;
observation of the pick head 113: the device is provided with a microscopic imaging observation port and a microscopic image acquisition port A, and is used for facilitating the observation of microscopic imaging of a sample slide by an operator and the installation of an industrial camera 12;
the three-axis object stage 112 is arranged above the base 111 and is movably connected with the base 111; the observation collecting head 113 is arranged above the triaxial object stage 112, and the industrial camera 12 is movably connected with the observation collecting head 113 through a microscopic image collecting port of the industrial camera;
the three-axis stage 112 interacts with the server 22, and its three degrees of freedom of movement in x, y, and z directions are controlled by the server 22.
In the present embodiment, the server 22 includes a control module 221 and an AI identification model 222;
the control module 221 is connected with the AI identification model 222, the control module 221 interacts with the industrial camera 12, and the industrial camera 12 is controlled to collect the image of the sample slide at a fixed point; the control module 221 further interacts with the three-axis stage 112 to control the three degrees of freedom of movement of the three-axis stage 112 in x, y, and z directions.
In this embodiment, the AI identification model 222 includes an image preprocessing module 2221 for receiving the image collected by the industrial camera 12 and performing gray scale adjustment and size adjustment on the image; the image pre-processing module 2221 interacts with the industrial camera 12.
In this embodiment, the AI identification model 222 further includes a diameter calculating module 2222 for calculating the diameters of the individual fibers according to the images of the individual fibers in the image; the diameter estimation module 2222 interacts with an image pre-processing module 2221.
In this embodiment, the AI identification model 222 further includes an identification convolutional neural network 2223 for obtaining an identification result of a type of fiber from an external morphological feature of the fiber contained in the sample slide; the discriminatory convolutional neural network 2223 interacts with an image pre-processing module 2221.
The fiber automatic image identification device provided in the embodiment works according to the following steps:
s1: installation preparation: preparing a sample slide, clamping the sample slide on the three-axis object stage 112, and controlling the three-axis object stage 112 to move in the x, y and z directions by the identification computer 2 so that the sample slide stops at a proper observation position
S2: and (3) creating a report: creating a blank report for the current sample slide, and adjusting the industrial camera and the microscope 11 to enter a standby state;
s3: operation identification: the industrial camera 12 works to transmit the image of the sample slide to the server 22, and the server 22 calculates the diameter of the single fiber according to the image, analyzes the morphological characteristics of each fiber in the sample slide, fills the original blank report, and obtains the identification report of the fiber contained in the sample slide comprehensively.
Further, S2: creating a report specifically comprises the following substeps:
s21: creating a blank report for the current sample slide;
s23: inputting configuration parameters into the blank report, wherein the specific parameters comprise the types of fibers, execution standard bases, dates, time, report names, sample names, instrument numbers and the like;
s23: the control module 221 controls the movement of the three-axis stage 112 to adjust the visual field of the industrial camera 12 to the initial shooting position, and keeps the industrial camera and the microscope in standby.
Further, S3: the operation identification specifically comprises the following substeps:
s31: the control module 221 controls the three-axis object stage 112 to move, and changes the visual field of the industrial camera 12;
s32: the industrial camera 12 takes an image of the sample slide under a specified field of view;
s33: repeating S31-S32; until the industrial camera 12 captures images of all the fields of view of the sample slide, the industrial camera 12 transmits the images to the image preprocessing module 2221;
s32: the image preprocessing module 2221 performs gray scale adjustment and size adjustment on the image to obtain a suitable usable image; and positioning the fibers in the image to obtain a single fiber image group.
S34: the image preprocessing module 2221 transmits a suitable usable image to the diameter calculating module 2222 to obtain the diameter of a single fiber;
s35: the image preprocessing module 2221 transmits a suitable usable image into the identification convolutional neural network 2223 to obtain an identification result of the type of the fiber;
s36: recording the motion parameters of the triaxial moving platform 112, correspondingly filling the identification results of the diameter of the single fiber and the type of the fiber into a blank report configured with the parameters, and comprehensively obtaining the identification report of the fiber contained in the sample slide.
The above description is only exemplary of the present invention and should not be construed as limiting the present invention, and any modifications, equivalents and improvements made within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. An automated image authentication apparatus for fibers, the apparatus comprising:
the image acquisition device is used for acquiring a fiber image for the sample slide;
the identification computer is used for controlling the work of the image acquisition device and automatically analyzing the fiber image to obtain an identification report of the fibers contained in the sample slide;
the authentication computer comprises a front-end operator and a server; the server interacts with the front-end operator, and the server interacts with the image acquisition device.
2. The automated fiber optic image screening apparatus of claim 1, wherein said image capturing device comprises a microscope and an industrial camera;
the industrial camera is arranged at the microscopic imaging position of the microscope and is connected with the microscope;
the industrial camera and the microscope both interact with the server.
3. The automated fiber optic image recognition apparatus of claim 2, wherein the microscope comprises:
base: the device is used for carrying other parts in the equipment and playing a supporting role;
three-axis objective table: the device is provided with a carrying plane, is used for carrying a sample slide and has three freedom degrees of movement in x, y and z directions;
observing the collecting head: the device is provided with a microscopic imaging observation port and a microscopic image acquisition port, and is convenient for operators to observe microscopic imaging of a sample slide and install an industrial camera;
the three-axis objective table is arranged above the base and is movably connected with the base; the observation collecting head is arranged above the three-axis object stage, and the industrial camera is movably connected with the observation collecting head through a microscopic image collecting port of the industrial camera;
the three-axis object stage interacts with the server, and the three degrees of freedom of movement in the x direction, the y direction and the z direction are controlled by the server.
4. The fiber-automated image authentication apparatus according to claim 3, wherein the server includes therein a control module and an AI authentication model;
the control module is connected with the AI identification model, interacts with the industrial camera and controls the industrial camera to collect the image of the sample slide at a fixed point; the control module is also interactive with the three-axis objective table and controls the three-axis objective table to move in the x, y and z directions.
5. The fiber automatic image identification device according to claim 4, wherein the AI identification model comprises an image preprocessing module for receiving the image collected by the industrial camera and performing gray scale adjustment and size adjustment on the image; the image pre-processing module interacts with the industrial camera.
6. The automated fiber image identification device according to claim 5, wherein the AI identification model further comprises a diameter measurement module for measuring diameters of the individual fibers respectively according to images of the individual fibers in the image; the diameter measuring and calculating module is interactive with the image preprocessing module.
7. The automated fiber image discrimination apparatus according to claim 5, wherein the AI discrimination model further includes a discrimination convolutional neural network for deriving a discrimination result of a kind of the fiber based on an external morphological feature of the fiber contained in the sample slide; the discriminatory convolutional neural network interacts with the image pre-processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202021923976.3U CN212321459U (en) | 2020-09-07 | 2020-09-07 | Automatic image identification equipment of fibre |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202021923976.3U CN212321459U (en) | 2020-09-07 | 2020-09-07 | Automatic image identification equipment of fibre |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212321459U true CN212321459U (en) | 2021-01-08 |
Family
ID=74035975
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202021923976.3U Active CN212321459U (en) | 2020-09-07 | 2020-09-07 | Automatic image identification equipment of fibre |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212321459U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111982907A (en) * | 2020-09-07 | 2020-11-24 | 中纺标(深圳)检测有限公司 | Automatic fiber image identification device and identification method thereof |
-
2020
- 2020-09-07 CN CN202021923976.3U patent/CN212321459U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111982907A (en) * | 2020-09-07 | 2020-11-24 | 中纺标(深圳)检测有限公司 | Automatic fiber image identification device and identification method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107463789B (en) | Integrated automatic calibration device and calibration method for medical display | |
| CN110383038A (en) | System and method for being automatically analyzed to air sample | |
| CN103499301B (en) | A kind of bast-fibre fineness automatic analyzer and application thereof | |
| CN102288607A (en) | Woven fabric count detector based on digital microscope | |
| CN212321459U (en) | Automatic image identification equipment of fibre | |
| CN108663380A (en) | Probe card detection method and system | |
| CN109470698A (en) | Across scale field trash quick analytic instrument device and method based on microphotograph matrix | |
| CN101782527A (en) | Full-automatic fracture image analyzer | |
| CN101178396A (en) | Cashmere fibre, fleece fibre blended spinning quantitative determination instrument and method | |
| CN112825622A (en) | Sample image capturing method and sample image capturing apparatus | |
| CN101839691B (en) | Image-based test sieve automatic calibrator | |
| CN111982908A (en) | Fiber automatic analysis equipment based on visual analysis technology and analysis method thereof | |
| CN209247652U (en) | Rivet surface defect on-line measuring device on a kind of big shell | |
| CN101806749B (en) | Device and method for analyzing fiber composition content in fabrics | |
| CN111982907A (en) | Automatic fiber image identification device and identification method thereof | |
| CN213456679U (en) | Automatic fiber analysis equipment based on visual analysis technology | |
| CN104483317A (en) | High-throughput digital full-field metallographic in-situ statistic characterization analyzer and analysis method | |
| CN109115685B (en) | Auxiliary positioning system for ultrathin section of electron microscope | |
| CN111626333A (en) | Intelligent detection equipment and method for cement substrate hole structure | |
| CN106197515A (en) | The detecting system of a kind of instrument pointer amount of jitter and detection method thereof | |
| CN214894884U (en) | Portable multidirectional adjustable biological sample fine treatment device | |
| CN113418919A (en) | Textile fiber component qualitative and quantitative online analysis system and method | |
| CN212569866U (en) | Automatic acquisition system for drilling core correlation data | |
| CN213336587U (en) | Multi-model electric connector contact holding force testing system | |
| CN114877810A (en) | Cotton fiber length detection device based on machine vision and application method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |