CN110909649A - Fabric weft straightening method and device, computer equipment and storage medium - Google Patents
Fabric weft straightening method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110909649A CN110909649A CN201911119724.7A CN201911119724A CN110909649A CN 110909649 A CN110909649 A CN 110909649A CN 201911119724 A CN201911119724 A CN 201911119724A CN 110909649 A CN110909649 A CN 110909649A
- Authority
- CN
- China
- Prior art keywords
- fabric
- preset parameters
- image
- template
- vectors
- 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
- 239000004744 fabric Substances 0.000 title claims abstract description 380
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 239000013598 vector Substances 0.000 claims abstract description 185
- 238000013145 classification model Methods 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 239000000284 extract Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 239000004753 textile Substances 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 239000002759 woven fabric Substances 0.000 description 5
- 238000013136 deep learning model Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000004043 dyeing Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007639 printing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000009941 weaving Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004061 bleaching Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000009991 scouring Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Manufacturing & Machinery (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for fabric weft straightening, a computer device, and a storage medium. The method comprises the following steps: acquiring a fabric image, and extracting a characteristic vector corresponding to the fabric image; matching the characteristic vectors with the characteristic vectors in a fabric template, wherein the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters; acquiring the preset parameters associated with the feature vectors which are successfully matched; and inputting the preset parameters into a weft straightening model to perform weft straightening treatment on the fabric. By adopting the method, the parameter acquisition efficiency can be improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a fabric weft straightening method, apparatus, computer device, and storage medium.
Background
With the progress and development of society, people have higher requirements on the types and quality of textiles. However, many kinds of textiles are subjected to mechanical tension for many times in the production processes of scouring, bleaching, printing, dyeing and the like, so that the textiles are deformed undesirably, and the deformation degrees of different kinds of textiles are different.
In order to ensure the printing and dyeing quality of textiles such as fabrics, the fabrics need to pass through a weft straightening machine, and the fabrics are shaped by the weft straightening machine. However, in the prior art, various fabrics and fabrics with different deformation degrees are mostly set with different weft straightening machine adjustment parameters through manual work, so that the acquisition efficiency of the adjustment parameters is low.
Disclosure of Invention
In view of the above, it is necessary to provide a fabric weft straightening method, apparatus, computer device and storage medium capable of improving parameter acquisition efficiency.
A method of fabric weft finishing, the method comprising:
acquiring a fabric image, and extracting a characteristic vector corresponding to the fabric image;
matching the characteristic vectors with the characteristic vectors in a fabric template, wherein the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters;
acquiring the preset parameters associated with the feature vectors which are successfully matched;
and inputting the preset parameters into a weft straightening model to perform weft straightening treatment on the fabric.
In one embodiment, the method for generating the fabric template comprises the following steps:
acquiring fabric images of the fabric in various states;
extracting a plurality of features corresponding to the fabric image, and generating a feature vector according to the plurality of features;
acquiring preset parameters corresponding to the fabric image;
and associating each characteristic vector, the fabric category and the preset parameters to generate a fabric template.
In one embodiment, the extracting a plurality of features corresponding to the fabric image and generating a feature vector according to the plurality of features includes:
extracting local texture features of the fabric image;
obtaining multi-scale images of the fabric image under multiple scales, and extracting multi-scale features of the fabric image according to the multi-scale images;
and generating a feature vector according to the local texture feature and the multi-scale feature.
In one embodiment, the extracting a plurality of features corresponding to the fabric image and generating a feature vector according to the plurality of features includes:
and inputting the fabric images into a classification model, and identifying the fabric images through the classification model according to pre-trained pattern characteristic parameters to obtain characteristic vectors corresponding to the patterns of the fabric images.
In one embodiment, the obtaining the preset parameters associated with the feature vectors successfully matched includes:
acquiring preset parameters associated with the feature vectors which are successfully matched from the fabric template;
inputting the preset parameters into a weft straightening model so that the weft straightening model adjusts the preset parameters according to the obtained preset threshold value, and calculating weft straightening precision values corresponding to the adjusted preset parameters;
and extracting the preset parameter corresponding to the maximum weft straightening precision value.
In one embodiment, the matching the feature vectors with the feature vectors in the fabric template includes:
calculating a distance value between the feature vector and each feature vector in the fabric template;
and when the distance value is smaller than a preset threshold value, the feature vector is successfully matched.
In one embodiment, the method further comprises:
acquiring an image of the newly added fabric;
extracting new characteristic vectors and new preset parameters corresponding to the new fabric images;
and adding each newly added feature vector, the newly added fabric category and the newly added preset parameters to the fabric template.
A fabric straightening device, the device comprising:
the vector acquisition module is used for acquiring a fabric image and extracting a characteristic vector corresponding to the fabric image;
the matching module is used for matching the characteristic vectors with the characteristic vectors in the fabric template, and the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters;
the parameter acquisition module is used for acquiring the preset parameters associated with the feature vectors which are successfully matched;
and the processing module is used for inputting the preset parameters into a weft straightening model so as to carry out weft straightening processing on the fabric.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the above method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
The fabric weft straightening method, the device, the computer equipment and the storage medium acquire the fabric image and extract the characteristic vector corresponding to the fabric image; matching the characteristic vectors with the characteristic vectors in the fabric template, wherein the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters, so that the preset parameters associated with the characteristic vectors which are successfully matched can be obtained from the fabric template; and then, the preset parameters are input into the weft straightening model, so that weft straightening treatment is carried out on the fabric according to the obtained preset parameters without manually setting parameters for the fabric, and the parameter obtaining efficiency is improved.
Drawings
FIG. 1 is a diagram of an application scenario of a fabric weft straightening method in one embodiment;
FIG. 2 is a schematic flow diagram of a fabric weft straightening process in one embodiment;
FIG. 3 is a schematic diagram of a process for obtaining feature vectors of a fabric image in one embodiment;
FIG. 4 is a schematic diagram illustrating a process of obtaining preset parameters according to an embodiment;
FIG. 5 is a block diagram of the fabric weft straightener in one embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further 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 present application and are not intended to limit the present application.
The fabric weft straightening method provided by the application can be applied to the application environment as shown in figure 1. Wherein image capture device 102 communicates with server 104 over a network. The image acquisition equipment 102 shoots the fabric to obtain a fabric image, the server 104 obtains the fabric image and extracts a feature vector corresponding to the fabric image; matching the characteristic vectors with all characteristic vectors in a fabric template, wherein the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters; the server 104 acquires preset parameters associated with the feature vectors which are successfully matched; and inputting preset parameters into a weft straightening model to perform weft straightening treatment on the fabric.
The image capturing device 102 may be, but not limited to, various cameras and devices with image capturing functions, and the server 104 may be implemented by a separate server or a server cluster composed of a plurality of servers. When the server 104 is an independent server, a plurality of databases may be deployed in the server 104, and each database may store a fabric image corresponding to a specific type of fabric; when the server 104 is a server cluster formed by a plurality of servers, a database deployed in each server may store a fabric image set corresponding to a particular type of fabric.
In one embodiment, as shown in fig. 2, a flow chart of a fabric weft straightening method is provided, which is illustrated by taking the method as an example applied to the server 104 in fig. 1, and in other embodiments, the method can also be applied to a terminal, and the method includes the following steps:
The fabric is a flat soft piece block formed by crossing, winding and connecting fine and flexible objects, and comprises fabrics such as textile fabrics, braided fabrics, towels and the like. In order to extract the characteristics of the fabric, the fabric needs to be shot by image acquisition equipment to obtain a fabric image, and then the characteristic vector corresponding to the fabric image is extracted by using an image processing algorithm.
The feature vector is a vector for characterizing the fabric feature, and can be used for identifying the fabric. The types of the fabric are various, and for example, the fabric may be classified into a pure woven fabric, a blended woven fabric, an interwoven fabric, and the like according to the types of the raw materials, and may be classified into a rib fabric, a lattice pattern fabric, and the like according to the types of patterns. Specifically, the server can extract pattern feature vectors corresponding to the fabric images, and the type of the fabric is judged by using the pattern feature vectors.
And step 220, matching the characteristic vectors with the characteristic vectors in the fabric template, wherein the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters.
The fabric template stores the association among the feature vector, the fabric category and the preset parameter in advance, for example, the feature vector, the fabric category and the preset parameter are associated and bound to generate an association, and the fabric template is generated according to at least one association. The server matches in the fabric template according to the feature vectors extracted from the fabric images, and then the fabric category or preset parameters associated with the feature vectors can be obtained.
And step 230, acquiring preset parameters associated with the feature vectors successfully matched.
And when the server correctly matches the characteristic vector in the fabric template, acquiring the fabric category or preset parameters associated with the characteristic vector.
The preset parameter may be an algorithm parameter corresponding to processing the category of fabric, for example, when the fabric is subjected to weft straightening processing, the preset parameter may be a weft straightening parameter corresponding to the category of fabric. The preset parameters may be manually input experience parameters, for example, the light source parameters corresponding to the fabric are manually selected and processed according to the type of the fabric, such that automatic selection of the transmission light source and the reflection light source is achieved, or the algorithm parameters corresponding to the fabric are manually selected and processed according to the type of the fabric, and the like, and the manual experience parameters are recorded in the fabric template, so that one-time setting and recycling are achieved, and the efficiency of parameter acquisition is improved.
In other embodiments, the server may also match preset parameters from the fabric template according to the obtained fabric category.
And 240, inputting preset parameters into a weft straightening model to perform weft straightening treatment on the fabric.
When the preset parameters are input parameters in the weft straightening model, the server performs weft straightening processing on the fabric by acquiring the preset parameters, so that the weft straightening parameters are automatically acquired, and the acquisition efficiency and the acquisition accuracy of the weft straightening parameters are improved.
Specifically, a camera is used for shooting a fabric to obtain a fabric image, a server is used for extracting the fabric image features by using a feature extraction algorithm, and then the fabric category is identified, so that the problem that the fabric category cannot be automatically and accurately identified by the traditional scheme is solved. The weft straightening processing is carried out on the fabric according to the matching of the fabric type from the fabric template to the preset parameters, and the intelligent matching algorithm is combined, so that the method has the advantages of high identification precision, quick identification response, large data and large fabric types, and the automatic parameter setting is realized. In addition, after the parameters are set by adopting an intelligent matching algorithm, the workload of field workers can be greatly reduced, and the normal production progress is not influenced; secondly, based on intelligent matching algorithm efficiency, precision are very high, have improved and have set up the parameter efficiency automatically according to the fabric type, have improved product quality, especially in the field of weaving, after taking place to change the type of weaving, can match the preset parameter automatically, have improved work efficiency.
In this embodiment, because the types of the fabrics are various, and when different types of fabrics are processed, the corresponding weft straightening parameters are also different, in order to improve the efficiency of acquiring the weft straightening parameters, the server associates the fabric types with the preset parameters in advance, and then when the server acquires the fabric types corresponding to the fabrics, the preset parameters associated with the feature vectors successfully matched can be extracted from the fabric template, so that the efficiency of acquiring the parameters is improved.
In one embodiment, a method of generating a fabric template includes: acquiring fabric images of the fabric in various states; extracting a plurality of characteristics corresponding to the fabric image, and generating a characteristic vector according to the plurality of characteristics; acquiring preset parameters corresponding to the fabric image; and associating the characteristic vectors, the fabric categories and preset parameters to generate a fabric template.
In the process of processing the fabric, the fabric is in a traction state continuously and is influenced by various mechanical movements and production operations, so that the fabric generates weft skew and bending, namely the weft skew. Therefore, for the same category of fabrics, different states of deformation, stretching, distortion, different illumination and various inclination angles may be provided, and the accurate identification of the category of the fabrics in the different states has a certain influence.
In order to improve the identification robustness of the fabric type and realize that the fabric type can still be correctly identified when the fabric is in different states, the server extracts a plurality of characteristics of the fabric image and generates a characteristic vector according to the plurality of characteristics of the fabric image. The extracted fabric characteristics should have the following properties: the fabric type can be identified, and particularly, the fabric type can still be identified when the acquired fabric image is in a deformed state, a stretched state, a light state, a twisted state and the like.
Specifically, the server acquires fabric images of the fabric in different states, acquires a feature vector of the fabric according to the fabric images in the different states, and generates the feature vector according to a plurality of features.
The server acquires preset parameters corresponding to the fabric, and then associates the acquired characteristic vectors, the fabric categories and the preset parameters to generate a fabric template.
In the embodiment, a fabric template is established in advance, preset parameters such as corresponding light source parameters and algorithm parameters are solidified in the fabric template, and characteristic parameters of various woven fabrics are also solidified in the fabric template, the server generates characteristic vectors from a plurality of characteristics of an identified fabric image so as to identify the type of the fabric by using the characteristic vectors, and the preset parameters are matched from the fabric template according to the type of the fabric, so that the robustness of fabric identification and the efficiency of acquiring the preset parameters are improved.
In one embodiment, as shown in fig. 3, a flow diagram for obtaining feature vectors of a fabric image is provided. Specifically, extracting a plurality of features corresponding to the fabric image, and generating a feature vector according to the plurality of features includes:
in step 310, local texture features of the fabric image are extracted.
The texture features of the fabric image can be used to identify the fabric class. For example, local texture features of a fabric image can be extracted by using a local binary Pattern (LBP-local binary Pattern), wherein the LBP is an operator for describing local features of the image, and the LBP features have the significant advantages of gray scale invariance, rotation invariance and the like, and can cope with changes of illumination, that is, fabric categories can be still identified under different illumination changes.
And 320, acquiring multi-scale images of the fabric image under multiple scales, and extracting multi-scale features of the fabric image according to the multi-scale images.
To cope with deformation, stretching and distortion of the fabric, an algorithm of histogram of oriented gradient (HOG-histogram of oriented gradient) and LBP multi-feature fusion may be used. Firstly, cutting and scaling an input fabric image to obtain a fabric image with multiple scales, and then extracting multi-scale features of the fabric image according to the multi-scale image.
The server represents the feature vector of the fabric image by a one-dimensional vector formed by the multi-scale LBP feature and one HOG feature. And (4) performing related binding on the fabric type and the characteristic vector to establish a characteristic template. Further, preset parameters corresponding to the woven cloth of each category are obtained, the preset parameters, the fabric categories and the characteristic vectors are related and bound, and a fabric template is established.
In the embodiment, the identification of the fabric category is realized by acquiring the multi-scale features of the fabric image, and the multi-scale features have anti-interference capability and can realize the identification of the fabric in different states.
In one embodiment, extracting a plurality of features corresponding to the fabric image, and generating a feature vector according to the plurality of features includes: and inputting the fabric images into a classification model, and identifying the fabric images through the classification model according to the pre-trained pattern characteristic parameters to obtain characteristic vectors corresponding to the patterns of the fabric images.
The image classification model can be a machine learning model trained in advance, the machine learning model already learns the classification parameters for classifying the fabric images, and the identification of the fabric image classes is realized according to the classification parameters. Specifically, the server inputs the acquired fabric images in various states into a pre-trained fabric image classification model, the fabric image classification model extracts feature vectors of the fabric images according to pre-learned classification parameters, and classification of the fabric images is achieved according to the feature vectors. Furthermore, the pattern features in the fabric images can be used for representing the categories of the fabrics, and the fabric image classification model realizes the category identification of the fabric images according to the pattern feature vectors by extracting the pattern feature vectors corresponding to the patterns in the fabric images.
The fabric image classification model can be a pre-trained deep learning model, and the training process for the fabric image classification model can include: and taking the fabric images in different states and the pattern classes corresponding to the patterns in the fabric images of various types as training samples, inputting the training samples into a deep learning model, and learning the relationship between the fabric images and the pattern classes by using the deep learning model to obtain a fabric image classification model.
For example, the deep learning model may be a CNN network model, and in particular may be a VGG16 model, trained in a VGG16 model using a loss function driven model. Further, the server sequentially passes the acquired fabric images through the trained VGG16 model to obtain the fabric types.
In the embodiment, automatic extraction of the pattern characteristic vectors is realized through the image and fabric image classification model, so that the characteristic vectors of the fabric image are quickly and accurately acquired, and the fabric is identified in the category.
Furthermore, the obtained fabric image classification model can be suitable for the existing fabrics of any type, and when the fabrics of unknown type are encountered, the corresponding type data are added into the fabric image classification model for training, and the fabric image classification model is updated, so that the fabric image classification model is easy to maintain and has high practical value.
In one embodiment, as shown in fig. 4, a schematic flow chart for obtaining the preset parameter is provided. Specifically, obtaining preset parameters associated with feature vectors that are successfully matched includes:
and step 410, acquiring preset parameters associated with the feature vectors successfully matched from the fabric template.
The server firstly obtains preset parameters corresponding to the type of fabric from the fabric template, namely obtains corresponding experience values from the fabric template, inputs the experience values into an image detection algorithm such as a weft straightening model, detects the angles of the weft or the weft of the fabric, and then performs weft straightening operation on the woven fabric, wherein the experience values can be parameters in the weft straightening model algorithm, such as binarization threshold parameters, texture extraction parameters, angle detection parameters, limit values such as maximum and minimum value parameters and the like corresponding to different types of woven fabrics.
It should be noted that the preset parameter is an empirical parameter, that is, a parameter commonly used for processing the fabric of the category, but there are slight differences in fabric color or fabric material for the same category of fabric, and in these differences, even if the optimal preset parameters adapted for the same category of fabric are not completely the same, the preset parameter obtained by the server from the fabric template is sometimes not the optimal processing parameter applicable to all the fabrics of the category.
And step 420, inputting preset parameters into the weft straightening model so that the weft straightening model adjusts the preset parameters according to the obtained preset threshold value, and calculating weft straightening precision values corresponding to the adjusted preset parameters.
The method comprises the steps that a server provides a simulation environment, the size of a preset parameter obtained from a fabric template is continuously adjusted in the simulation environment, specifically, the preset parameter is input into a weft straightening model, a preset threshold value is obtained by the weft straightening model, the size of the preset parameter is adjusted according to the preset threshold value, so that the weft straightening model performs weft straightening on the fabric according to the adjusted preset parameter, and a weft straightening precision value corresponding to weft straightening processing performed by utilizing each adjusted preset parameter is calculated. It should be noted that the server may provide a simulation environment in the fabric template to perform tuning and adaptation of preset parameters, so as to set the algorithm of each fabric template.
And 430, extracting a preset parameter corresponding to the maximum weft straightening precision value.
And the server extracts the preset parameter corresponding to the maximum weft finishing precision value as the optimal preset parameter corresponding to the fabric of the category. And the optimal preset parameters and the preset parameters obtained from the fabric template can be the same or different in size.
And the server can also perform associated binding on the acquired optimal preset parameters, the fabric type and the characteristic vector to form a fabric template.
In the embodiment, the obtained preset parameters are automatically adjusted and optimized by providing a simulation environment, so that the obtained preset parameters are more accurate, and the precision of weft straightening of the fabric is improved.
In one embodiment, matching the feature vectors to the feature vectors in the fabric template comprises: calculating a distance value between the characteristic vector and each characteristic vector in the fabric template; and when the distance value is smaller than the preset threshold value, the feature vector is successfully matched.
Specifically, the server matches the obtained feature vectors with feature vectors in a fabric template, calculates cosine distances or Euclidean distances between the feature vectors to obtain matching degrees, and judges whether the feature vectors are successfully matched according to the calculated matching degree value. And when the matching degree is smaller than a preset threshold value, judging that the matching of the feature vectors is successful, otherwise, judging that no proper matching feature vector is found, and at the moment, manually setting parameters and further updating the fabric template.
In one embodiment, the method further comprises: acquiring an image of the newly added fabric; extracting new feature vectors and new preset parameters corresponding to the new fabric images; and adding each newly added feature vector, the newly added fabric category and the newly added preset parameters to the fabric template.
In this embodiment, the obtained image classification model can be adapted to any existing fabric, and when an unknown fabric category is encountered, only corresponding fabric data needs to be added to the fabric image classification model for training, and the fabric image classification model is updated, so that the method is easy to maintain and has high practical value. The problem of adopt the mode of manual input parameter to set up machine mode among the traditional art to if meet new variety new classification, need artifical resetting parameter, very big increase field work personnel's work load like this, it is poor to adjust the real-time simultaneously, leads to whole latitude to appear the problem.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided a fabric weft straightener comprising:
the vector obtaining module 510 is configured to obtain a fabric image and extract a feature vector corresponding to the fabric image.
The matching module 520 is configured to match the feature vectors with feature vectors in a fabric template, where the fabric template is generated in advance according to the feature vectors, the fabric category, and preset parameters.
A parameter obtaining module 530, configured to obtain preset parameters associated with the feature vectors that are successfully matched.
And the processing module 540 is used for inputting preset parameters into the weft straightening model so as to carry out weft straightening processing on the fabric.
In one embodiment, the apparatus further comprises:
the image acquisition module is used for acquiring fabric images of the fabric in various states.
And the vector acquisition modules are used for extracting a plurality of characteristics corresponding to the fabric image and generating characteristic vectors according to the characteristics.
And the preset parameter acquisition module is used for acquiring preset parameters corresponding to the fabric image.
And the template generation module is used for associating each characteristic vector, the fabric category and the preset parameters to generate a fabric template.
In one embodiment, a plurality of vector acquisition modules, comprising:
and the texture feature extraction unit is used for extracting the local texture features of the fabric image.
And the multi-scale feature acquisition unit is used for acquiring multi-scale images of the fabric image under multiple scales and extracting the multi-scale features of the fabric image according to the multi-scale images.
And the first vector generation unit is used for generating a feature vector according to the local texture feature and the multi-scale feature.
In one embodiment, a plurality of vector acquisition modules, comprising:
and the second vector generation unit is used for inputting the fabric images into the classification model so as to identify the fabric images according to the pre-trained pattern characteristic parameters through the classification model to obtain the characteristic vectors corresponding to the patterns of the fabric images.
In one embodiment, the parameter obtaining module 530 includes:
and the preset parameter acquisition unit is used for acquiring the preset parameters associated with the feature vectors which are successfully matched from the fabric template.
And the precision value calculation unit is used for inputting the preset parameters into the weft straightening model so as to adjust the preset parameters according to the acquired preset threshold value and calculate the weft straightening precision value corresponding to each adjusted preset parameter.
And the parameter extraction unit is used for extracting a preset parameter corresponding to the maximum weft straightening precision value.
In one embodiment, the matching module 520 includes:
and the distance calculation unit is used for calculating the distance value between the characteristic vector and each characteristic vector in the fabric template.
And the matching judgment unit is used for successfully matching the characteristic vectors when the distance value is smaller than a preset threshold value.
In one embodiment, the apparatus further comprises:
and the newly added image acquisition module is used for acquiring the newly added fabric image.
And the newly added parameter acquisition module is used for extracting newly added characteristic vectors and newly added preset parameters corresponding to the newly added fabric images.
And the adding module is used for adding each newly added feature vector, each newly added fabric category and each newly added preset parameter to the fabric template.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for searching application data processing related data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a fabric weft finishing method.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: acquiring a fabric image, and extracting a characteristic vector corresponding to the fabric image; matching the characteristic vectors with all characteristic vectors in a fabric template, wherein the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters; acquiring preset parameters associated with the feature vectors which are successfully matched; and inputting preset parameters into a weft straightening model to perform weft straightening treatment on the fabric.
In one embodiment, the processor when executing the computer program performs the steps of the method for generating a fabric template further for: acquiring fabric images of the fabric in various states; extracting a plurality of characteristics corresponding to the fabric image, and generating a characteristic vector according to the plurality of characteristics; acquiring preset parameters corresponding to the fabric image; and associating the characteristic vectors, the fabric categories and preset parameters to generate a fabric template.
In one embodiment, the processor, when executing the computer program, performs the steps of extracting a plurality of features corresponding to the fabric image, and generating a feature vector according to the plurality of features, further configured to: extracting local texture features of the fabric image; obtaining multi-scale images of the fabric image under multiple scales, and extracting multi-scale features of the fabric image according to the multi-scale images; and generating a feature vector according to the local texture features and the multi-scale features.
In one embodiment, the processor, when executing the computer program, performs the steps of extracting a plurality of features corresponding to the fabric image, and generating a feature vector according to the plurality of features, further configured to: and inputting the fabric images into a classification model, and identifying the fabric images through the classification model according to the pre-trained pattern characteristic parameters to obtain characteristic vectors corresponding to the patterns of the fabric images.
In one embodiment, the processor when executing the computer program further performs the step of obtaining the preset parameters associated with the feature vectors successfully matched, for: acquiring preset parameters associated with the feature vectors which are successfully matched from the fabric template; inputting preset parameters into a weft straightening model so that the weft straightening model adjusts the preset parameters according to the obtained preset threshold value, and calculating weft straightening precision values corresponding to the adjusted preset parameters; and extracting a preset parameter corresponding to the maximum weft straightening precision value.
In one embodiment, the processor when executing the computer program further performs the step of matching the feature vectors to the feature vectors in the fabric template for: calculating a distance value between the characteristic vector and each characteristic vector in the fabric template; and when the distance value is smaller than the preset threshold value, the feature vector is successfully matched.
In one embodiment, the processor, when executing the computer program, further implements: acquiring an image of the newly added fabric; extracting new feature vectors and new preset parameters corresponding to the new fabric images; and adding each newly added feature vector, the newly added fabric category and the newly added preset parameters to the fabric template.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring a fabric image, and extracting a characteristic vector corresponding to the fabric image; matching the characteristic vectors with all characteristic vectors in a fabric template, wherein the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters; acquiring preset parameters associated with the feature vectors which are successfully matched; and inputting preset parameters into a weft straightening model to perform weft straightening treatment on the fabric.
In one embodiment, the computer program when executed by the processor performs the steps of the method for generating a fabric template further for: acquiring fabric images of the fabric in various states; extracting a plurality of characteristics corresponding to the fabric image, and generating a characteristic vector according to the plurality of characteristics; acquiring preset parameters corresponding to the fabric image; and associating the characteristic vectors, the fabric categories and preset parameters to generate a fabric template.
In one embodiment, the computer program when executed by the processor performs the steps of extracting a plurality of features corresponding to the fabric image, and generating a feature vector from the plurality of features further comprises: extracting local texture features of the fabric image; obtaining multi-scale images of the fabric image under multiple scales, and extracting multi-scale features of the fabric image according to the multi-scale images; and generating a feature vector according to the local texture features and the multi-scale features.
In one embodiment, the computer program when executed by the processor performs the steps of extracting a plurality of features corresponding to the fabric image, and generating a feature vector from the plurality of features further comprises: and inputting the fabric images into a classification model, and identifying the fabric images through the classification model according to the pre-trained pattern characteristic parameters to obtain characteristic vectors corresponding to the patterns of the fabric images.
In one embodiment, the computer program when executed by the processor further performs the step of obtaining the preset parameters associated with the feature vectors successfully matched, further: acquiring preset parameters associated with the feature vectors which are successfully matched from the fabric template; inputting preset parameters into a weft straightening model so that the weft straightening model adjusts the preset parameters according to the obtained preset threshold value, and calculating weft straightening precision values corresponding to the adjusted preset parameters; and extracting a preset parameter corresponding to the maximum weft straightening precision value.
In one embodiment, the computer program when executed by the processor performs the step of matching the feature vectors to the feature vectors in the fabric template is further configured to: calculating a distance value between the characteristic vector and each characteristic vector in the fabric template; and when the distance value is smaller than the preset threshold value, the feature vector is successfully matched.
In one embodiment, the computer program when executed by the processor further implements: acquiring an image of the newly added fabric; extracting new feature vectors and new preset parameters corresponding to the new fabric images; and adding each newly added feature vector, the newly added fabric category and the newly added preset parameters to the fabric template.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of fabric weft finishing, the method comprising:
acquiring a fabric image, and extracting a characteristic vector corresponding to the fabric image;
matching the characteristic vectors with the characteristic vectors in a fabric template, wherein the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters;
acquiring the preset parameters associated with the feature vectors which are successfully matched;
and inputting the preset parameters into a weft straightening model to perform weft straightening treatment on the fabric.
2. The method of claim 1, wherein the method of generating the fabric template comprises:
acquiring fabric images of the fabric in various states;
extracting a plurality of features corresponding to the fabric image, and generating a feature vector according to the plurality of features;
acquiring preset parameters corresponding to the fabric image;
and associating each characteristic vector, the fabric category and the preset parameters to generate a fabric template.
3. The method according to claim 2, wherein the extracting a plurality of features corresponding to the fabric image and generating a feature vector according to the plurality of features comprises:
extracting local texture features of the fabric image;
obtaining multi-scale images of the fabric image under multiple scales, and extracting multi-scale features of the fabric image according to the multi-scale images;
and generating a feature vector according to the local texture feature and the multi-scale feature.
4. The method according to claim 2, wherein the extracting a plurality of features corresponding to the fabric image and generating a feature vector according to the plurality of features comprises:
and inputting the fabric images into a classification model, and identifying the fabric images through the classification model according to pre-trained pattern characteristic parameters to obtain characteristic vectors corresponding to the patterns of the fabric images.
5. The method according to claim 1, wherein the obtaining the preset parameters associated with the feature vectors successfully matched comprises:
acquiring preset parameters associated with the feature vectors which are successfully matched from the fabric template;
inputting the preset parameters into a weft straightening model so that the weft straightening model adjusts the preset parameters according to the obtained preset threshold value, and calculating weft straightening precision values corresponding to the adjusted preset parameters;
and extracting the preset parameter corresponding to the maximum weft straightening precision value.
6. The method of claim 1, wherein matching the feature vectors to each of the feature vectors in the fabric template comprises:
calculating a distance value between the feature vector and each feature vector in the fabric template;
and when the distance value is smaller than a preset threshold value, the feature vector is successfully matched.
7. The method of claim 1, further comprising:
acquiring an image of the newly added fabric;
extracting new characteristic vectors and new preset parameters corresponding to the new fabric images;
and adding each newly added feature vector, the newly added fabric category and the newly added preset parameters to the fabric template.
8. A fabric straightening device, characterized in that it comprises:
the vector acquisition module is used for acquiring a fabric image and extracting a characteristic vector corresponding to the fabric image;
the matching module is used for matching the characteristic vectors with the characteristic vectors in the fabric template, and the fabric template is generated in advance according to the characteristic vectors, the fabric category and preset parameters;
the parameter acquisition module is used for acquiring the preset parameters associated with the feature vectors which are successfully matched;
and the processing module is used for inputting the preset parameters into a weft straightening model so as to carry out weft straightening processing on the fabric.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911119724.7A CN110909649A (en) | 2019-11-15 | 2019-11-15 | Fabric weft straightening method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911119724.7A CN110909649A (en) | 2019-11-15 | 2019-11-15 | Fabric weft straightening method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110909649A true CN110909649A (en) | 2020-03-24 |
Family
ID=69817859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911119724.7A Pending CN110909649A (en) | 2019-11-15 | 2019-11-15 | Fabric weft straightening method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110909649A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105421012A (en) * | 2015-11-03 | 2016-03-23 | 顾金华 | Automatic fabric pattern finishing method based on machine vision |
| CN108664588A (en) * | 2018-05-07 | 2018-10-16 | 中山市元目图像科技有限公司 | Automatic method for online detection and control of cloth skewing |
| CN109137448A (en) * | 2018-11-13 | 2019-01-04 | 王鹂辉 | Fabric based on machine vision is intelligently whole to spend whole latitude system |
| CN110110129A (en) * | 2019-05-13 | 2019-08-09 | 江南大学 | A kind of textile image search method based on fine textures characterization |
| US20190279352A1 (en) * | 2016-11-30 | 2019-09-12 | Rakuten, Inc. | Image processing device, image processing method, server, and computer program |
| CN110390675A (en) * | 2019-07-26 | 2019-10-29 | 常州弘仁智能科技有限公司 | A kind of fabric weft inclination detection method based on image analysing computer |
-
2019
- 2019-11-15 CN CN201911119724.7A patent/CN110909649A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105421012A (en) * | 2015-11-03 | 2016-03-23 | 顾金华 | Automatic fabric pattern finishing method based on machine vision |
| US20190279352A1 (en) * | 2016-11-30 | 2019-09-12 | Rakuten, Inc. | Image processing device, image processing method, server, and computer program |
| CN108664588A (en) * | 2018-05-07 | 2018-10-16 | 中山市元目图像科技有限公司 | Automatic method for online detection and control of cloth skewing |
| CN109137448A (en) * | 2018-11-13 | 2019-01-04 | 王鹂辉 | Fabric based on machine vision is intelligently whole to spend whole latitude system |
| CN110110129A (en) * | 2019-05-13 | 2019-08-09 | 江南大学 | A kind of textile image search method based on fine textures characterization |
| CN110390675A (en) * | 2019-07-26 | 2019-10-29 | 常州弘仁智能科技有限公司 | A kind of fabric weft inclination detection method based on image analysing computer |
Non-Patent Citations (2)
| Title |
|---|
| TANG-JUN LV 等: "Feature matching of fancy weft knitted stitch based on modified SURF algorithm", 《TEXTILE RESEARCH JOURNAL》 * |
| 蔡海军: "跟踪印花***视觉检测算法研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Azizah et al. | Deep learning implementation using convolutional neural network in mangosteen surface defect detection | |
| CN107463965B (en) | Deep learning-based fabric attribute picture acquisition and recognition method and recognition system | |
| CN108090470B (en) | Face alignment method and device | |
| US8224039B2 (en) | Separating a directional lighting variability in statistical face modelling based on texture space decomposition | |
| CN111368758B (en) | Face ambiguity detection method, face ambiguity detection device, computer equipment and storage medium | |
| CN109871821B (en) | Pedestrian re-identification method, device, equipment and storage medium of self-adaptive network | |
| CN104778481A (en) | Method and device for creating sample library for large-scale face mode analysis | |
| CN111008643B (en) | Picture classification method and device based on semi-supervised learning and computer equipment | |
| CN110889838A (en) | Fabric defect detection method and device | |
| CN110969193B (en) | Fabric image acquisition method and device, computer equipment and storage medium | |
| JP2009069996A (en) | Image processing device and image processing method, recognition device and recognition method, and program | |
| US20200364878A1 (en) | Patch expansion for segmentation network training | |
| CN110791944B (en) | Weft straightener control method, weft straightener control device, computer equipment and storage medium | |
| CN112949693A (en) | Training method of image classification model, image classification method, device and equipment | |
| CN113449704A (en) | Face recognition model training method and device, electronic equipment and storage medium | |
| CN110909649A (en) | Fabric weft straightening method and device, computer equipment and storage medium | |
| CN108876776A (en) | A kind of method of generating classification model, eye fundus image classification method and device | |
| CN116994049A (en) | Full-automatic flat knitting machine and method thereof | |
| CN115311248A (en) | Defect model matching method based on gray fabric texture, medium, and electronic device | |
| CN210864814U (en) | Fabric edge aligning device | |
| CN115937107A (en) | Two-stage gray fabric defect detection method, system, medium and computer | |
| CN110796658A (en) | Fabric edge aligning method and device, computer equipment and storage medium | |
| CN113610026A (en) | Pedestrian re-identification method and device based on mask attention | |
| US20220366248A1 (en) | Learning apparatus, a learning method, object detecting apparatus, object detecting method, and recording medium | |
| Siegmund et al. | Rapid classification of textile fabrics arranged in piles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200324 |
|
| RJ01 | Rejection of invention patent application after publication |