CN111008965A - System and method for identifying morphological characteristics of cotton-flax blended fibers - Google Patents
System and method for identifying morphological characteristics of cotton-flax blended fibers Download PDFInfo
- Publication number
- CN111008965A CN111008965A CN201911192043.3A CN201911192043A CN111008965A CN 111008965 A CN111008965 A CN 111008965A CN 201911192043 A CN201911192043 A CN 201911192043A CN 111008965 A CN111008965 A CN 111008965A
- Authority
- CN
- China
- Prior art keywords
- fiber
- cotton
- fibers
- module
- identification system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention discloses a system for identifying morphological characteristics of cotton-flax blended fibers, which comprises: the fiber sample acquisition module is used for acquiring a fiber sample; the fiber edge cutting module is used for carrying out fiber edge detection on each fiber sample to obtain a fiber area; the single fiber cutting module is used for cutting a plurality of fibers in each fiber area; the fiber quantity counting module is used for counting the fiber quantity; the fiber quantity standard-reaching judging module is used for judging whether the fiber quantity reaches the standard or not; the fiber attitude adjusting module is used for adjusting the fiber attitude of each fiber to be a preset reasonable attitude; the fiber type judging module is used for judging the fiber type of each fiber; the cotton and linen blended fiber classification result output module is used for outputting the fiber type judgment result, the fiber type judgment result made by the method is more objective, scientific and accurate, and the identification speed is greatly improved. The invention also provides a method for identifying the morphological characteristics of the cotton-flax blended fiber.
Description
Technical Field
The invention relates to the technical field of morphological characteristic identification, in particular to a system and a method for identifying morphological characteristics of cotton-flax blended fibers.
Background
In the apparel industry, scientific identification of textile fibers is required for ease of production management and product analysis. The fiber identification mainly comprises the morphological characteristic identification and the physical and chemical characteristic identification of the fiber. Morphological feature identification is usually achieved by microscopic observation. The physical and chemical property identification method mainly comprises a combustion method, a dissolution method, a reagent coloring method, a melting point method, a specific gravity method, a birefringence method, an X-ray diffraction method, an infrared absorption spectrum method and the like.
At present, various garment manufacturers usually adopt a traditional microscopic observation method to collect fiber samples manually, determine morphological characteristic detection targets by human eyes to identify and detect the morphological characteristics of the fibers, but the whole manual detection process is high in work repeatability, boring and inefficient, and depends on manual detection experience, so that the detection result is not scientific and objective enough, and the automatic identification requirement of markets on the cotton-hemp blended fibers is difficult to meet.
Disclosure of Invention
The invention aims to provide a system for identifying morphological characteristics of cotton-flax blended fibers, so as to solve the technical problems.
The invention also provides a method for identifying the morphological characteristics of the cotton-flax blended fiber.
In order to achieve the purpose, the invention adopts the following technical scheme:
the provided system for identifying morphological characteristics of cotton and linen blended fibers is used for identifying morphological characteristics of various textile fibers in cotton and linen blending and comprises the following steps:
the fiber sample acquisition module is used for acquiring a fiber sample of the hemp-cotton blended fiber plectrum manufactured by a user;
the fiber edge cutting module is connected with the fiber sample acquisition module and used for carrying out fiber edge detection on each fiber sample and carrying out picture cutting on each fiber sample according to a fiber edge detection result to obtain a fiber area with a reserved fiber edge;
a single fiber slitting module connected to the fiber edge cutting module for slitting a plurality of fibers in the fiber region associated with each of the fiber samples;
the fiber quantity counting module is connected with the single fiber cutting module and is used for counting the quantity of the cut fibers;
the fiber quantity standard-reaching judging module is connected with the fiber quantity counting module and is used for judging whether the quantity of the split fibers meets the identification requirement or not to obtain and store a first quantity judging result;
the fiber attitude adjusting module is connected with the fiber quantity standard-reaching judging module and is used for adjusting the fiber attitude of each fiber to be a preset reasonable attitude when the quantity of the fibers meets the identification requirement;
the fiber type judging module is connected with the fiber posture adjusting module and is used for judging the fiber type of each fiber after posture adjustment to obtain and store a fiber type judging result;
the fiber type judging module is used for judging the type of the fibers, and judging the type of the fibers according to the type of the fibers;
the fiber quantity standard-reaching judging module of each category is connected with the fiber quantity counting module of each category and is used for judging whether the quantity of the fibers belonging to each category meets the identification requirement or not to obtain and store a second quantity judging result;
the cotton-flax blended fiber classification result output module is connected with the fiber type judging module, the various fiber quantity counting module and the various fiber quantity standard judging module and is used for integrating the fiber type judging result and the quantity counting result of the fibers belonging to various types to form a cotton-flax blended fiber classification result and outputting the cotton-flax blended fiber classification result after the quantity of the fibers belonging to various types meets the identification requirement;
and the fiber sample re-collection control module is respectively connected with the fiber sample collection module, the fiber quantity standard-reaching judgment module and the various fiber quantity standard-reaching judgment module and is used for controlling the fiber sample collection module to re-collect the fiber sample when the fiber quantity standard-reaching judgment module judges that the quantity of the split fibers does not meet the identification requirement or when the various fiber quantity standard-reaching judgment module judges that the quantity of the fibers belonging to various categories does not meet the identification requirement.
The invention also provides a method for identifying the morphological characteristics of the cotton-flax blended fiber, which is realized by applying the system for identifying the morphological characteristics of the cotton-flax blended fiber and comprises the following steps:
step S1, the cotton-flax blended fiber morphological characteristic identification system collects a fiber sample of the cotton-flax blended fiber plectrum made by a user;
step S2, the cotton and hemp blended fiber morphological characteristic identification system carries out fiber edge detection on the collected fiber samples, and carries out picture cutting on the fiber samples according to the fiber edge detection result to obtain a fiber area with the fiber edge reserved;
step S3, cutting a plurality of fibers in each fiber area by the cotton-flax blended fiber morphological characteristic identification system;
step S4, the morphological feature identification system of the cotton-flax blended fiber counts the number of the fibers cut out;
step S5, the identification system for morphological characteristics of the cotton-flax blended fiber judges whether the quantity of the fibers meets the identification requirement,
if yes, go to step S6;
if not, the step S1 is repeated, and the fiber sample collection equipment is controlled to continue to collect the fiber sample of the cotton-flax blended fiber plectrum;
step S6, the morphological characteristic identification system of the cotton-flax blended fiber adjusts the fiber attitude of each fiber to a preset reasonable attitude;
step S7, the cotton-flax blended fiber morphological characteristic identification system judges the fiber type of each fiber after the posture adjustment, and a fiber type judgment result is obtained and stored;
step S8, the cotton-flax blended fiber morphological characteristic identification system counts the number of the fibers belonging to each category according to the fiber type judgment result to obtain and store the number counting result of the fibers belonging to each category;
step S9, the identification system for morphological characteristics of cotton-flax blended fiber judges whether the quantity of the fiber belonging to each category meets the identification requirement,
if yes, go to step S10;
if not, the step S1 is repeated, and the fiber sample collection equipment is controlled to continue to collect the fiber sample of the cotton-flax blended fiber plectrum;
and step S10, the cotton-flax blended fiber morphological characteristic identification system integrates the fiber type judgment result and the number statistical result of the fibers belonging to each type to form a cotton-flax blended fiber classification result and outputs the cotton-flax blended fiber classification result.
Preferably, in the step S2, the method for detecting the fiber edge of each fiber sample by the cotton-flax blend fiber morphological feature identification system specifically includes the following steps:
step S21, the cotton and linen blended fiber morphological characteristic identification system carries out image preprocessing on each fiber sample image;
step S22, the cotton-flax blended fiber morphological characteristic identification system converts each fiber sample image after image pretreatment into a corresponding gray image P;
step S23, the cotton-flax blended fiber morphological characteristic identification system carries out image gradient calculation on each gray level image P to obtain an image gradient calculation result corresponding to each gray level image P;
step S24, the cotton-flax blended fiber morphological characteristic identification system carries out image integral scanning on each gray level image P, each pixel point on the image is checked, and the pixel point which has the same gradient direction with the pixel point and has the maximum pixel value around each pixel point is reserved;
step S25, the identification system for morphological characteristics of cotton-flax blended fiber judges whether the gray gradient value of each reserved pixel point is higher than a first threshold value,
if so, taking the pixel points as boundary points of the fibers on the fiber sample image;
if not, go to step S26;
step S26, the identification system for morphological characteristics of cotton-flax blended fiber judges whether the gray gradient value of each reserved pixel point is less than a second threshold value,
if yes, judging that the pixel point is not the boundary point of the fiber on the fiber sample image and discarding;
if not, go to step S27;
step S27, the cotton-flax blended fiber morphological characteristic identification system judges whether another pixel point connected with the pixel point exists,
if yes, taking another pixel point connected with the pixel point as the boundary point and switching to S38;
if not, discarding the pixel point;
and step S38, the cotton-flax blend fiber morphological characteristic identification system takes all the detected boundary points as the fiber edges of the fibers in the fiber sample, and then the fiber areas retaining the fiber edges are obtained through picture cutting.
Preferably, in the step S3, the method for cutting the fibers in each fiber region by the cotton-flax blend fiber characteristic identification system specifically includes the following steps:
step S31, the cotton and linen blended fiber morphological characteristic identification system carries out image scanning on each fiber area to obtain all connected domains in each fiber area;
step S32, the shape and feature identification system of the cotton-flax blended fiber separately saves the communicated domains which are not intersected with each other;
step S33, the identification system for morphological characteristics of the cotton-flax blended fiber detects whether a cavity point exists in each connected domain stored in the step S32,
if yes, filling the hole points with numerical values, and going to step S34;
if not, the process goes directly to step S34;
and S34, the morphological characteristic identification system of the cotton-flax blended fiber compares each connected domain detected in the step S33 with the corresponding fiber sample to obtain a plurality of fibers.
Preferably, in the step S34, the image data comparing method is specifically that the cotton-flax blended fiber morphological feature identification system performs image and operation on each connected domain and the corresponding fiber sample.
Preferably, in the step S5, the number of the fibers meeting the identification requirement is not less than 1500.
Preferably, in the step S6, the method for adjusting the fiber posture of each fiber to the preset reasonable posture by the cotton-flax blend fiber morphological feature identification system specifically includes the following steps:
step S61, the morphological characteristic identification system of the cotton-flax blended fiber obtains the height and width of the picture of a single fiber;
step S62, the identification system for morphological characteristics of the cotton-flax blended fiber judges whether the picture height of the single fiber is larger than or equal to the picture width,
if yes, rotating the fiber picture for 90 degrees;
and if not, not adjusting the posture of the fiber picture.
Preferably, in the step S9, the number of the fibers belonging to each of the categories that satisfy the authentication requirement is not less than 300.
The invention has the beneficial effects that:
1. only need artifical preparation fibre sample plectrum, follow-up fibre morphological feature analysis in the fibre sample has completely realized the machine automation, and whole differentiation process need not artifical the participation, has overcome the defect that relies on artifical differentiation experience in the past, and the differentiation result is more objective, science, accurate.
2. The identification speed is greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic structural diagram of a morphological feature identification system for a cotton-flax blend fiber according to an embodiment of the present invention;
FIG. 2 is a step diagram of a method for identifying morphological characteristics of a cotton-flax blend fiber according to an embodiment of the present invention;
FIG. 3 is a sub-step diagram of step S2 in the method for identifying morphological characteristics of cotton and hemp blended fibers according to an embodiment of the present invention;
FIG. 4 is a sub-step diagram of step S3 in the method for identifying morphological characteristics of cotton and hemp blended fibers according to an embodiment of the present invention;
FIG. 5 is a sub-step diagram of step S6 in the method for identifying morphological characteristics of cotton and hemp blended fibers according to an embodiment of the present invention;
FIG. 6 is a block flow diagram of a method for identifying morphological characteristics of a cotton-flax blend fiber according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a model structure of a fiber type determination model for identifying fiber types by the system for identifying morphological characteristics of a cotton-flax blend fiber according to an embodiment of the present invention;
FIG. 8 is a block diagram of a process for training a fiber type determination model by a morphological feature identification system for cotton and linen blended fibers according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a single cotton fiber cut by the cotton-flax blend fiber morphology feature identification system provided in one embodiment of the present invention;
FIG. 10 is a schematic diagram of single flax fibers cut by a cotton-flax blend fiber morphological feature identification system according to an embodiment of the invention;
FIG. 11 is a schematic diagram of single ramie fibers cut by the morphological characteristics identification system for cotton-flax blend fibers according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further explained by the specific implementation mode in combination with the attached drawings.
Wherein the showings are for the purpose of illustration only and are shown by way of illustration only and not in actual form, and are not to be construed as limiting the present patent; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "inner", "outer", etc. are used for indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not indicated or implied that the referred device or element must have a specific orientation, be constructed in a specific orientation and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and are not to be construed as limitations of the present patent, and the specific meanings of the terms may be understood by those skilled in the art according to specific situations.
In the description of the present invention, unless otherwise explicitly specified or limited, the term "connected" or the like, if appearing to indicate a connection relationship between the components, is to be understood broadly, for example, as being fixed or detachable or integral; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or may be connected through one or more other components or may be in an interactive relationship with one another. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Referring to fig. 1, a system for identifying morphological characteristics of a cotton-hemp blended fiber provided in an embodiment of the present invention is used for identifying morphological characteristics of each textile fiber in a cotton-hemp blend, and includes:
the fiber sample collection module 1 is used for collecting a fiber sample of a cotton-flax blended fiber plectrum made by a user;
the fiber edge cutting module 2 is connected with the fiber sample collecting module 1 and is used for carrying out fiber edge detection on each fiber sample and carrying out picture cutting on each fiber sample according to the fiber edge detection result to obtain a fiber area with a reserved fiber edge;
a single fiber cutting module 3 connected to the fiber edge cutting module 2 for cutting out a plurality of fibers in the fiber area associated with each fiber sample;
the fiber number counting module 4 is connected with the single fiber cutting module 3 and is used for counting the number of the cut fibers;
the fiber quantity standard-reaching judging module 5 is connected with the fiber quantity counting module 4 and is used for judging whether the quantity of the split fibers meets the identification requirement or not, and obtaining and storing a first quantity judging result;
the fiber attitude adjusting module 6 is connected with the fiber quantity standard judging module 5 and used for adjusting the fiber attitude of each fiber to be a preset reasonable attitude when the quantity of the fibers meets the identification requirement;
the fiber type judging module 7 is connected with the fiber posture adjusting module 6 and used for judging the fiber type of each fiber after posture adjustment to obtain and store a fiber type judging result;
the fiber number counting module 8 is connected with the fiber type judging module 7 and used for counting the number of the fibers belonging to each type according to the fiber type judging result to obtain and store the counting result of the number of the fibers belonging to each type;
the standard-reaching judging module 9 for the number of the fibers of each category is connected with the counting module 8 for the number of the fibers of each category and is used for judging whether the number of the fibers belonging to each category meets the identification requirement or not, and obtaining and storing a second number judging result;
the cotton and linen blended fiber classification result output module 10 is connected with the fiber type judging module 7, the various fiber quantity counting module 8 and the various fiber quantity standard-reaching judging module 9 and is used for integrating the fiber type judging result and the fiber quantity counting result belonging to various types to form a cotton and linen blended fiber classification result and outputting the cotton and linen blended fiber classification result when the quantity of the fibers belonging to various types meets the identification requirement;
the fiber sample re-collection control module 11 is respectively connected with the fiber sample collection module 1, the fiber quantity standard-reaching judgment module 5 and the various fiber quantity standard-reaching judgment module 8, and is used for controlling the fiber sample collection module to re-collect the fiber sample when the fiber quantity standard-reaching judgment module judges that the quantity of the segmented fibers does not meet the identification requirement or when the various fiber quantity standard-reaching judgment module judges that the quantity of the fibers belonging to various categories does not meet the identification requirement.
Referring to fig. 2 and fig. 6, an embodiment of the present invention further provides a method for identifying morphological characteristics of a cotton-hemp blended fiber, which is implemented by applying the above system for identifying morphological characteristics of a cotton-hemp blended fiber, and specifically includes the following steps:
step S1, the cotton-flax blended fiber morphological characteristic identification system collects the fiber sample of the cotton-flax blended fiber plectrum made by the user;
step S2, the morphological characteristic identification system of the cotton-flax blended fiber detects the fiber edge of each collected fiber sample, and cuts the image of each fiber sample according to the fiber edge detection result to obtain the fiber area with the fiber edge reserved;
step S3, cutting a plurality of fibers in each fiber area by the cotton-hemp blended fiber morphological characteristic identification system;
step S4, the morphological feature identification system of the cotton-flax blended fiber counts the number of the fibers cut out;
step S5, the morphological characteristics identification system of the cotton-flax blended fiber judges whether the quantity of the cut fiber meets the identification requirement,
if yes, go to step S6;
if not, the step S1 is repeated, and the fiber sample collection equipment is controlled to continue to collect the fiber sample of the cotton-flax blended fiber plectrum;
step S6, the morphological characteristic identification system of the cotton-flax blended fiber adjusts the fiber attitude of each fiber to a preset reasonable attitude;
step S7, the cotton-flax blended fiber morphological characteristic identification system judges the fiber type of each fiber after the posture adjustment, and a fiber type judgment result is obtained and stored;
step S8, the cotton-flax blended fiber morphological characteristic identification system counts the quantity of the fibers belonging to each category according to the fiber type judgment result to obtain and store the quantity counting result of the fibers belonging to each category;
step S9, the morphological characteristics identification system of the cotton-flax blended fiber judges whether the quantity of the fiber belonging to each category meets the identification requirement,
if so, the process proceeds to step S10,
if not, the step S1 is repeated, and the fiber sample collection equipment is controlled to continue to collect the fiber sample of the cotton-flax blended fiber plectrum;
and step S10, the cotton-flax blended fiber morphological characteristic identification system integrates the fiber type judgment result and the number statistical result of the fibers belonging to each type to form a cotton-flax blended fiber classification result and outputs the cotton-flax blended fiber classification result.
In the counting scheme, the cotton-hemp blend fiber plectrum is manufactured according to the national standard and the existing blend fiber plectrum manufacturing method, the blend fiber to be identified is taken, and the plectrum is manufactured manually.
And placing the manufactured shifting sheet at a specified position of an objective table, and controlling a fiber sample collecting device such as a 500-time microscope and an industrial camera to collect the fiber sample by the aid of the cotton-flax blended fiber morphological characteristic identification system to form a sampling picture with the resolution of 1080 x 1920. If the sample pictures need to be collected for multiple times, the system can automatically adjust the position of the shifting piece before the pictures are shot, and the situation that the content of the pictures collected for multiple times is not repeated is ensured.
Referring to fig. 3, in step S2, the method for detecting the fiber edge of each fiber sample by the cotton-flax blended fiber morphological feature identification system specifically includes the following steps:
step S21, the morphological characteristic identification system of the cotton-flax blended fiber carries out picture pretreatment on each fiber sample image;
step S22, the morphological characteristic identification system of the cotton-flax blended fiber converts each fiber sample image after the image pretreatment into a corresponding gray level image P;
step S23, the cotton-flax blended fiber morphological characteristic identification system carries out image gradient calculation on each gray level image P to obtain an image gradient calculation result corresponding to each gray level image P;
step S24, the cotton-flax blended fiber morphological characteristic identification system carries out image integral scanning on each gray level image P, each pixel point on the image is checked, and the pixel point with the maximum pixel value and the same gradient direction as the pixel point around each pixel point is reserved;
step S25, the morphological characteristics identification system of the cotton-flax blended fiber judges whether the gray gradient of each reserved pixel point is higher than a first threshold value,
if yes, the pixel point is used as a boundary point of the fiber on the fiber sample image;
if not, go to step S26;
step S26, the morphological characteristics identification system of the cotton-flax blended fiber judges whether the gray gradient value of each reserved pixel point is less than a second threshold value,
if yes, judging that the pixel point is not a boundary point of the fiber on the fiber sample image and discarding;
if not, the process proceeds to step S27,
step S27, judging whether another pixel point connected with the pixel point exists by the cotton-hemp blended fiber morphological characteristic identification system, if so, taking the other pixel point connected with the pixel point as a boundary point and turning to step S28;
if not, discarding the pixel point;
and step S28, the cotton-flax blend fiber morphological characteristic identification system takes all detected boundary points as fiber edges of the fibers in the fiber sample, and then the fiber areas with the fiber edges reserved are obtained through picture cutting.
In step S2, specifically, for each collected fiber sample image, the cotton-hemp blend fiber morphological feature identification system detects the boundary using an optimized multi-level edge detection algorithm, and then processes and retains the fiber edge; the process of applying the multi-stage edge detection algorithm to the fiber edge detection is as follows:
a) removing image noise of the fiber sample picture by using a Gaussian filter of 3x 3;
b) converting the fiber sample picture into a gray image, and recording the gray image as P;
c) using Sobel operator, calculating image gradient, the calculation formula is as follows:
order to
Using operator Sx、SyRespectively carrying out convolution operation with the gray level image P:
Gx＝Sx⊙P；
Gy＝Sy⊙P；
in the above formula, ⊙ is convolution operation symbol, GxThe image gradient of the gray level image corresponding to the fiber sample picture in the x-axis direction is represented;
Gythe image gradient of the gray level image corresponding to the fiber sample picture in the y-axis direction is represented;
the lateral and longitudinal gray values (edge gradients) for each pixel of the image are calculated by:
in the above formula, Edge _ g (g) is used to represent the Edge gradient of the gray image corresponding to the fiber sample image;
angle (θ) is used to indicate the gradient direction of the gray image corresponding to the fiber sample picture.
d) Non-maxima suppression; after obtaining the magnitude and direction of the gradient, scanning the whole image, checking each pixel point, and reserving the maximum value (point) with the same gradient direction around the pixel point;
e) a hysteresis threshold; setting a minVal (the first threshold value) and a maxVal (the second threshold value) to determine the boundary of the image, wherein the boundary is a real boundary when the gray gradient of the image is higher than the maxVal, the boundary lower than the minVal is discarded, if the gray gradient is between the minVal and the maxVal, the boundary connected with the boundary is a boundary point, and if the gray gradient is not between the minVal and the maxVal, the boundary is;
f) and integrating all boundary points, namely fiber edges, and storing the edge points as mask pictures (fiber areas).
In the above technical solution, it should be noted that the method for cutting the fiber region by the cotton-hemp blended fiber morphological feature identification system is the existing technical method, and the picture cutting process is not described herein.
Referring to fig. 4, in step S3, the method for cutting fibers in each fiber region by the cotton-hemp blend fiber morphological feature identification system specifically includes the following steps:
step S31, the cotton-flax blended fiber morphological characteristic identification system carries out image scanning on each fiber area to obtain all connected domains in each fiber area;
step S32, the morphological characteristic identification system of the cotton-flax blended fiber separately saves the communicated domains which are not intersected with each other;
step S33, the morphological characteristics identification system of the cotton-flax blended fiber detects whether a cavity point exists in each connected domain stored in the step S32,
if yes, filling the hole points with numerical values, and going to step S34;
if not, the process goes directly to step S34;
and step S34, the morphological characteristic identification system of the cotton-flax blended fiber compares the connected domain detected in the step S33 with the corresponding fiber sample to obtain a plurality of fibers.
In the above technical solution, in step S34, the image data comparison method specifically includes that the cotton-flax blended fiber morphological feature identification system performs image and operation on each connected domain and the corresponding fiber sample original image.
See fig. 9, 10 and 11 for images of the cut individual fibers.
In step S3, specifically, the morphological feature identification system for cotton-hemp blended fibers filters out crossing and overlapping fibers according to the edge detection result in step S2, and cuts single fibers from the original sampled image based on the crossing and overlapping fibers; the process is as follows:
a) based on a mask picture (fiber area), scanning each pixel point on the mask picture to obtain a connected domain;
b) storing disjoint connected domains separately;
c) checking whether a hole point exists in the connected domain, and if the hole point exists, filling the hole point with a mask value;
d) according to the single connected domain, carrying out AND operation with a primary fiber image (original sampling image) to cut out single fibers;
e) repeating c) and d) until all fibers are cut.
In step S5, the number of fibers satisfying the identification requirement is preferably not less than 1500.
Referring to fig. 5, in step S6, the method for adjusting the fiber posture of each fiber to the preset reasonable posture by the cotton-hemp blended fiber morphological feature identification system specifically includes the following steps:
step S61, the morphological characteristic identification system of the cotton-flax blended fiber obtains the height and width of the picture of the single fiber;
step S62, the morphological characteristics identification system of the cotton-flax blended fiber judges whether the picture height of the single fiber is larger than or equal to the picture width,
if so, rotating the fiber picture by 90 degrees to enable the width of the fiber picture to be larger than the height of the picture;
and if not, not adjusting the posture of the fiber picture.
In step S9, the number of fibers belonging to each category that satisfy the authentication requirement is preferably not less than 300.
Finally, the cotton-flax blended fiber morphological characteristic identification system outputs a cotton-flax blended fiber classification result, and outputs the proportion of various fibers according to the cotton-flax blended fiber classification result, thereby providing reference data for textile fiber identification. The classification results of the cotton-flax blended fibers are shown in the following table a:
in the above technical solution, it should be noted that, the identification system for morphological characteristics of cotton and hemp blended fibers judges the type of the fibers through a pre-trained fiber type determination model, the structure of the fiber type determination model please refer to fig. 7 specifically, and the process of training the model please refer to fig. 8 specifically.
It should be understood that the above-described embodiments are merely preferred embodiments of the invention and the technical principles applied thereto. It will be understood by those skilled in the art that various modifications, equivalents, changes, and the like can be made to the present invention. However, such variations are within the scope of the invention as long as they do not depart from the spirit of the invention. In addition, certain terms used in the specification and claims of the present application are not limiting, but are used merely for convenience of description.
Claims (8)
1. A cotton-flax blended fiber morphological characteristic identification system is used for identifying morphological characteristics of various textile fibers in cotton-flax blending and is characterized by comprising the following components:
the fiber sample acquisition module is used for acquiring a fiber sample of the hemp-cotton blended fiber plectrum manufactured by a user;
the fiber edge cutting module is connected with the fiber sample acquisition module and used for carrying out fiber edge detection on each fiber sample and carrying out picture cutting on each fiber sample according to a fiber edge detection result to obtain a fiber area with a reserved fiber edge;
a single fiber slitting module connected to the fiber edge cutting module for slitting a plurality of fibers in the fiber region associated with each of the fiber samples;
the fiber quantity counting module is connected with the single fiber cutting module and is used for counting the quantity of the cut fibers;
the fiber quantity standard-reaching judging module is connected with the fiber quantity counting module and is used for judging whether the quantity of the split fibers meets the identification requirement or not to obtain and store a first quantity judging result;
the fiber attitude adjusting module is connected with the fiber quantity standard-reaching judging module and is used for adjusting the fiber attitude of each fiber to be a preset reasonable attitude when the quantity of the fibers meets the identification requirement;
the fiber type judging module is connected with the fiber posture adjusting module and is used for judging the fiber type of each fiber after posture adjustment to obtain and store a fiber type judging result;
the fiber type judging module is used for judging the type of the fibers, and judging the type of the fibers according to the type of the fibers;
the fiber quantity standard-reaching judging module of each category is connected with the fiber quantity counting module of each category and is used for judging whether the quantity of the fibers belonging to each category meets the identification requirement or not to obtain and store a second quantity judging result;
the cotton-flax blended fiber classification result output module is connected with the fiber type judging module, the various fiber quantity counting module and the various fiber quantity standard judging module and is used for integrating the fiber type judging result and the quantity counting result of the fibers belonging to various types to form a cotton-flax blended fiber classification result and outputting the cotton-flax blended fiber classification result after the quantity of the fibers belonging to various types meets the identification requirement;
and the fiber sample re-collection control module is respectively connected with the fiber sample collection module, the fiber quantity standard-reaching judgment module and the various fiber quantity standard-reaching judgment module and is used for controlling the fiber sample collection module to re-collect the fiber sample when the fiber quantity standard-reaching judgment module judges that the quantity of the split fibers does not meet the identification requirement or when the various fiber quantity standard-reaching judgment module judges that the quantity of the fibers belonging to various categories does not meet the identification requirement.
2. A method for identifying morphological characteristics of cotton-flax blended fibers is realized by applying the system for identifying morphological characteristics of cotton-flax blended fibers as the claim 1, and is characterized by comprising the following steps:
step S1, the cotton-flax blended fiber morphological characteristic identification system collects a fiber sample of the cotton-flax blended fiber plectrum made by a user;
step S2, the cotton and hemp blended fiber morphological characteristic identification system carries out fiber edge detection on the collected fiber samples, and carries out picture cutting on the fiber samples according to the fiber edge detection result to obtain a fiber area with the fiber edge reserved;
step S3, cutting a plurality of fibers in each fiber area by the cotton-flax blended fiber morphological characteristic identification system;
step S4, the morphological feature identification system of the cotton-flax blended fiber counts the number of the fibers cut out;
step S5, the identification system for morphological characteristics of the cotton-flax blended fiber judges whether the quantity of the fibers meets the identification requirement,
if yes, go to step S6;
if not, the step S1 is repeated, and the fiber sample collection equipment is controlled to continue to collect the fiber sample of the cotton-flax blended fiber plectrum;
step S6, the morphological characteristic identification system of the cotton-flax blended fiber adjusts the fiber attitude of each fiber to a preset reasonable attitude;
step S7, the cotton-flax blended fiber morphological characteristic identification system judges the fiber type of each fiber after the posture adjustment, and a fiber type judgment result is obtained and stored;
step S8, the cotton-flax blended fiber morphological characteristic identification system counts the number of the fibers belonging to each category according to the fiber type judgment result to obtain and store the number counting result of the fibers belonging to each category;
step S9, the identification system for morphological characteristics of cotton-flax blended fiber judges whether the quantity of the fiber belonging to each category meets the identification requirement,
if yes, go to step S10;
if not, the step S1 is repeated, and the fiber sample collection equipment is controlled to continue to collect the fiber sample of the cotton-flax blended fiber plectrum;
and step S10, the cotton-flax blended fiber morphological characteristic identification system integrates the fiber type judgment result and the number statistical result of the fibers belonging to each type to form a cotton-flax blended fiber classification result and outputs the cotton-flax blended fiber classification result.
3. The method for identifying morphological characteristics of cotton and linen blended fiber according to claim 2, wherein in step S2, the method for detecting fiber edges of each fiber sample by the system for identifying morphological characteristics of cotton and linen blended fiber comprises the following steps:
step S21, the cotton and linen blended fiber morphological characteristic identification system carries out image preprocessing on each fiber sample image;
step S22, the cotton-flax blended fiber morphological characteristic identification system converts each fiber sample image after image pretreatment into a corresponding gray image P;
step S23, the cotton-flax blended fiber morphological characteristic identification system carries out image gradient calculation on each gray level image P to obtain an image gradient calculation result corresponding to each gray level image P;
step S24, the cotton-flax blended fiber morphological characteristic identification system carries out image integral scanning on each gray level image P, each pixel point on the image is checked, and the pixel point which has the same gradient direction with the pixel point and has the maximum pixel value around each pixel point is reserved;
step S25, the identification system for morphological characteristics of cotton-flax blended fiber judges whether the gray gradient value of each reserved pixel point is higher than a first threshold value,
if so, taking the pixel points as boundary points of the fibers on the fiber sample image;
if not, go to step S26;
step S26, the identification system for morphological characteristics of cotton-flax blended fiber judges whether the gray gradient value of each reserved pixel point is less than a second threshold value,
if yes, judging that the pixel point is not the boundary point of the fiber on the fiber sample image and discarding;
if not, go to step S27;
step S27, the cotton-flax blended fiber morphological characteristic identification system judges whether another pixel point connected with the pixel point exists,
if yes, taking another pixel point connected with the pixel point as the boundary point and switching to S28;
if not, discarding the pixel point;
and step S28, the cotton-flax blend fiber morphological characteristic identification system takes all the detected boundary points as the fiber edges of the fibers in the fiber sample, and then the fiber areas retaining the fiber edges are obtained through picture cutting.
4. The method for identifying morphological characteristics of cotton and linen blended fibers according to claim 2, wherein in step S3, the method for cutting the fibers in each fiber area by the system for identifying morphological characteristics of cotton and linen blended fibers comprises the following steps:
step S31, the cotton and linen blended fiber morphological characteristic identification system carries out image scanning on each fiber area to obtain all connected domains in each fiber area;
step S32, the shape and feature identification system of the cotton-flax blended fiber separately saves the communicated domains which are not intersected with each other;
step S33, the identification system for morphological characteristics of the cotton-flax blended fiber detects whether a cavity point exists in each connected domain stored in the step S32,
if yes, filling the hole points with numerical values, and going to step S34;
if not, the process goes directly to step S34;
and S34, the morphological characteristic identification system of the cotton-flax blended fiber compares each connected domain detected in the step S33 with the corresponding fiber sample to obtain a plurality of fibers.
5. The method for identifying morphological characteristics of cotton and linen blended fibers according to claim 4, wherein in step S34, the image data comparison method is specifically that the cotton and linen blended fiber morphological characteristic identification system performs image AND operation on each connected domain and the corresponding fiber sample.
6. The method for identifying morphological characteristics of cotton and hemp blend fibers according to claim 2, wherein in step S5, the number of fibers satisfying the identification requirement is not less than 1500.
7. The method for identifying morphological characteristics of cotton and hemp blended fibers according to claim 2, wherein in the step S6, the method for adjusting the fiber posture of each fiber to the preset reasonable posture by the cotton and hemp blended fiber morphological characteristic identification system specifically comprises the following steps:
step S61, the morphological characteristic identification system of the cotton-flax blended fiber obtains the height and width of the picture of a single fiber;
step S62, the identification system for morphological characteristics of the cotton-flax blended fiber judges whether the picture height of the single fiber is larger than or equal to the picture width,
if yes, rotating the fiber picture for 90 degrees;
and if not, not adjusting the posture of the fiber picture.
8. The method for identifying morphological characteristics of cotton and hemp blend fibers according to claim 2, wherein in step S9, the number of fibers belonging to each of said categories that satisfy the identification requirements is not less than 300.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911192043.3A CN111008965A (en) | 2019-11-28 | 2019-11-28 | System and method for identifying morphological characteristics of cotton-flax blended fibers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911192043.3A CN111008965A (en) | 2019-11-28 | 2019-11-28 | System and method for identifying morphological characteristics of cotton-flax blended fibers |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111008965A true CN111008965A (en) | 2020-04-14 |
Family
ID=70112255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911192043.3A Pending CN111008965A (en) | 2019-11-28 | 2019-11-28 | System and method for identifying morphological characteristics of cotton-flax blended fibers |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111008965A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150488A (en) * | 2020-09-23 | 2020-12-29 | 创新奇智(青岛)科技有限公司 | Fiber diameter measuring method, fiber diameter measuring device, electronic device, and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107860933A (en) * | 2017-10-26 | 2018-03-30 | 信融源大数据科技(北京)有限公司 | The automatic testing method and device of fiber content in textile based on digital picture |
| CN108038838A (en) * | 2017-11-06 | 2018-05-15 | 武汉纺织大学 | A kind of cotton fibriia species automatic testing method and system |
| CN110006898A (en) * | 2019-03-28 | 2019-07-12 | 上海工程技术大学 | The blended ratio measuring method of polyester fiber based on circularity algorithm |
-
2019
- 2019-11-28 CN CN201911192043.3A patent/CN111008965A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107860933A (en) * | 2017-10-26 | 2018-03-30 | 信融源大数据科技(北京)有限公司 | The automatic testing method and device of fiber content in textile based on digital picture |
| CN108038838A (en) * | 2017-11-06 | 2018-05-15 | 武汉纺织大学 | A kind of cotton fibriia species automatic testing method and system |
| CN110006898A (en) * | 2019-03-28 | 2019-07-12 | 上海工程技术大学 | The blended ratio measuring method of polyester fiber based on circularity algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 赵训明: "棉与苎麻纤维的计算机图像识别方法的研究" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150488A (en) * | 2020-09-23 | 2020-12-29 | 创新奇智(青岛)科技有限公司 | Fiber diameter measuring method, fiber diameter measuring device, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112233133B (en) | Power plant high-temperature pipeline defect detection and segmentation method based on OTSU and area growth method | |
| CN111751253B (en) | Forming method and quality detection method of concrete aggregate detection model | |
| CN105139386B (en) | A kind of image processing method of fast automatic detecting electric connector solder joint defective work | |
| CN111402226A (en) | Surface defect detection method based on cascade convolution neural network | |
| CN109948469A (en) | The automatic detection recognition method of crusing robot instrument based on deep learning | |
| CN108562589A (en) | A method of magnetic circuit material surface defect is detected | |
| CN103604937B (en) | Fabric analysis system and method based on biaxial mechanical stretch processing | |
| CN109767422A (en) | Pipe detection recognition methods, storage medium and robot based on deep learning | |
| CN111462075B (en) | Rapid refocusing method and system for full-slice digital pathological image fuzzy region | |
| CN109684938A (en) | It is a kind of to be taken photo by plane the sugarcane strain number automatic identifying method of top view based on crop canopies | |
| CN106056597A (en) | Object visual detection method and device | |
| CN102915432A (en) | Method and device for extracting vehicle-bone microcomputer image video data | |
| CN109182081A (en) | A kind of unicellular separation system based on image processing model | |
| CN109345524A (en) | A kind of bearing open defect detection system of view-based access control model | |
| CN104048966B (en) | The detection of a kind of fabric defect based on big law and sorting technique | |
| CN112070712B (en) | Printing defect detection method based on self-encoder network | |
| CN107958253A (en) | A kind of method and apparatus of image recognition | |
| CN111008965A (en) | System and method for identifying morphological characteristics of cotton-flax blended fibers | |
| CN110813795B (en) | Device and method for detecting breakage of chemical fiber spindle paper tube on line | |
| CN106960424B (en) | Tubercle bacillus image segmentation and identification method and device based on optimized watershed algorithm | |
| CN114463425B (en) | Workpiece surface featureless point positioning method based on probability Hough straight line detection | |
| CN113470041B (en) | Immunohistochemical cell image cell nucleus segmentation and counting method and system | |
| CN202815869U (en) | Vehicle microcomputer image and video data extraction apparatus | |
| CN113378663B (en) | Inspection pointer type circular instrument identification method and device | |
| CN117350967B (en) | Optical detection-based wafer appearance defect detection system and method |
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 |