CN109215022A - Cloth inspection method, device, terminal device, server, storage medium and system - Google Patents
Cloth inspection method, device, terminal device, server, storage medium and system Download PDFInfo
- Publication number
- CN109215022A CN109215022A CN201811037108.2A CN201811037108A CN109215022A CN 109215022 A CN109215022 A CN 109215022A CN 201811037108 A CN201811037108 A CN 201811037108A CN 109215022 A CN109215022 A CN 109215022A
- Authority
- CN
- China
- Prior art keywords
- detected
- fault
- fabric
- server
- image
- 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
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
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
This application discloses cloth inspection method, device, terminal device, server, storage medium and system, this method includes the image to be detected for receiving cloth inspecting machine and sending, and generates defect detection request;Described image to be detected and defect detection request are sent to server, the server includes the neural network model for detecting fabric defects;If receiving the fabric that described image to be detected that the server is sent is included, there are the testing results of fault, the instruction of fault marking of control is generated according to the testing result, the testing result includes the type information and location information of fault;Fault marking of control instruction is sent to the cloth inspecting machine.The cloth inspection method, device, terminal device, server, storage medium and system can reduce the operation cost in provider's later period.
Description
Technical field
This application involves Fabric Detection technical fields, in particular to cloth inspection method, device, terminal device, server, storage
Medium and system.
Background technique
On the production line of the fabrics such as woven fabric, looped fabric, non-woven cloth, need whether to detect produced fabric
There are faults, for example, whether having spot, broken hole, fluffing etc. on fabric.
There are mainly two types of modes for current detection method: the first is pure manual detection mode, i.e., is stood by testing staff
Fabric defects is found in such a way that naked eyes detect before perching equipment and fault is marked or is recorded;Second auxiliary for machine
The detection mode helped is mainly found fabric defects by machine vision and computer program analysis and realizes classification.
In the case where the yield of fabric is very big, being detected by testing staff will have high labor costs the first detection mode,
Moreover, testing staff is easy fatigue after a period of time that works, to there is a possibility that erroneous detection occurs.Therefore, by detecting
Personnel are not high come the overall fault detection efficiency detected and accuracy in detection is not sufficiently stable.
Second of detection mode generally by program Solidification into terminal device, the later period need respectively to each terminal device into
Row maintenance, and detection program provider can not be managed collectively, and cause operation cost high.
Summary of the invention
In view of problem above, the embodiment of the present invention provides a kind of cloth inspection method, device, terminal device, server and is
System, can solve the technical issues of above-mentioned background technology part is mentioned.
In a first aspect, the cloth inspection method of embodiment according to the invention, comprising: receive the mapping to be checked that cloth inspecting machine is sent
Picture, and generate defect detection request;Described image to be detected and defect detection request are sent to server, the server packet
Include the neural network model for detecting fabric defects;If receiving described image to be detected that the server is sent to be wrapped
There are the testing results of fault for the fabric contained, then generate the instruction of fault marking of control, the detection knot according to the testing result
Fruit includes the type information and location information of fault;Fault marking of control instruction is sent to the cloth inspecting machine.
Second aspect, the cloth inspection method of embodiment according to the invention, comprising: receive image to be detected and defect detection is asked
It asks;It is requested according to the defect detection, described image to be detected is examined using the neural network model of detection fabric defects
It surveys;If there are faults for the fabric that described image to be detected is included, generate testing result and export, the testing result includes
The type information and location information of fault.
The third aspect, the cloth examination device of embodiment according to the invention, comprising: request generation module, for receiving perching
Image to be detected that machine is sent, and generate defect detection request;Request sending module is used for described image to be detected and fault
Detection request is sent to server, and the server includes the neural network model for detecting fabric defects;Instruction generates mould
Block, if there are the detection knots of fault for receiving the fabric that described image to be detected that the server is sent is included
Fruit then generates the instruction of fault marking of control according to the testing result, and the testing result includes type information and the position of fault
Confidence breath;Instruction sending module, for fault marking of control instruction to be sent to the cloth inspecting machine.
Fourth aspect, the cloth examination device of embodiment according to the invention, comprising: request receiving module, it is to be checked for receiving
Altimetric image and defect detection request;Defect detection module utilizes detection fabric defects for requesting according to the defect detection
Neural network model detects described image to be detected;As a result output module, if being included for described image to be detected
Fabric there are faults, then generate testing result and export, the testing result includes the type information and location information of fault.
5th aspect, the terminal device of embodiment according to the invention, including processor, memory, communication interface and logical
Believe bus, the processor, the memory and the communication interface complete mutual communication by the communication bus;Institute
It states memory and is stored with executable instruction, wherein the executable instruction makes the processor execute first upon being performed
Method described in aspect.
6th aspect, the server of embodiment according to the invention, including processor, memory, communication interface and communication
Bus, the processor, the memory and the communication interface complete mutual communication by the communication bus;It is described
Memory is stored with executable instruction, wherein the executable instruction wants the processor perform claim
Seek method described in second aspect.
7th aspect, the storage medium of embodiment according to the invention are stored thereon with computer executable instructions,
In, the executable instruction makes computer execute method described in first aspect, side described in second aspect upon being performed
Method.
It can be seen from the above that the scheme of the embodiment of the present invention will be used to detect the neural network of fabric defects
Model is mounted in cloud server, by the communication of terminal device and server, realizes cloud detection and result passback, finally exists
The label to fault is realized on cloth inspecting machine.The neural network model provider of detection fabric defects can be managed collectively and tie up beyond the clouds
Shield, reduces later period operation cost.
Detailed description of the invention
Fig. 1 is the hardware structure schematic diagram of fabric inspecting system provided in an embodiment of the present invention;
Fig. 2 is the signaling process figure of cloth inspection method provided in an embodiment of the present invention;
Fig. 3 is the flow chart of cloth inspection method provided in an embodiment of the present invention;
Fig. 4 is the another flow chart of cloth inspection method provided in an embodiment of the present invention;
Fig. 5 is the method flow diagram provided in an embodiment of the present invention detected to image to be detected;
Fig. 6 is the structural block diagram of cloth examination device provided in an embodiment of the present invention;
Fig. 7 is the schematic diagram of terminal device provided in an embodiment of the present invention;
Fig. 8 is the another structural block diagram of cloth examination device provided in an embodiment of the present invention;
Fig. 9 is the structural block diagram of defect detection module provided in an embodiment of the present invention;
Figure 10 is the schematic diagram of server provided in an embodiment of the present invention.
Specific embodiment
Theme described herein is discussed referring now to example embodiment.It should be understood that discussing these embodiments only
It is in order to enable those skilled in the art can better understand that being not to claim to realize theme described herein
Protection scope, applicability or the exemplary limitation illustrated in book.It can be in the protection scope for not departing from present disclosure
In the case of, the function and arrangement of the element discussed are changed.Each example can according to need, omit, substitute or
Add various processes or component.For example, described method can be executed according to described order in a different order, with
And each step can be added, omits or combine.In addition, feature described in relatively some examples is in other examples
It can be combined.
As used in this article, term " includes " and its modification indicate open term, are meant that " including but not limited to ".
Term "based" indicates " being based at least partially on ".Term " one embodiment " and " embodiment " expression " at least one implementation
Example ".Term " another embodiment " expression " at least one other embodiment ".Term " first ", " second " etc. may refer to not
Same or identical object.Here may include other definition, either specific or implicit.Unless bright in context
It really indicates, otherwise the definition of a term is consistent throughout the specification.
It referring to Fig.1, is the hardware structure schematic diagram of fabric inspecting system provided by the embodiments of the present application, which can use
In implementing cloth inspection method provided by the embodiments of the present application, as shown in Figure 1, framework 100 may include: cloth inspecting machine 102, terminal device
104, network 106 and server 108.Network 106 is to provide communication link between terminal device 104 and server 108
Medium.Network 106 may include various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 104 and be interacted by network 106 with server 108, to receive or send message, number
According to etc., alternatively, terminal device 104 is interacted by network 106 with server 108 according to preset instructions, on terminal device 104
Perching application program can be installed.Terminal device 104, which can be such as computer or other, suitably has the electricity of computing capability
Sub- equipment.
Server 108 can be to provide the server of detection service, equipped with the nerve net for detecting fabric defects
Network model.Server 108 can receive the detection request of terminal device 104, and will test result and feed back to terminal device 104.
Cloth inspecting machine 102 usually may include real-time acquisition device, control device, labelling apparatus and devices for taking-up.In real time
Acquisition device can use CCD industrial camera, be used to acquire the textile image on cloth inspecting machine in real time by predeterminated frequency.Its
In, above-mentioned CCD (Charge Coupled Device, photosensitive coupling component) is in digital camera for recording light variation
Semiconductor subassembly.When it is implemented, real-time acquisition device can be connect by the network switch with terminal device, will adopt in real time
Image to be detected of collection is sent to terminal device.Control device can use PLC control cabinet, control device respectively with labelling apparatus
It is connected with devices for taking-up, carries out fault label and control devices for taking-up startup-shutdown for controlling labelling apparatus.When it is implemented,
Control device can be connect in such a way that serial ports connects with terminal device, the information sent with receiving terminal apparatus.Label dress
Fault label can be carried out in the corresponding position of fabric under control of the control means using ink-jet marking device by setting.Devices for taking-up
It usually may include cloth beam, batch rotation axis and batch driving motor, control device is connect with driving motor is batched, control dress
It sets and driving motor realization startup-shutdown operation is batched by control, devices for taking-up can be by fabric to be detected continually by real-time
The acquisition range of acquisition device, to realize the continuous acquisition to fabric surface.
It should be understood that the number of cloth inspecting machine, terminal device, network and server in Fig. 1 is only schematical.According to
Actual needs, can have any number of cloth inspecting machine, terminal device, network and server.
Based on fabric inspecting system shown in FIG. 1, Fig. 2 shows the signaling processes of cloth inspection method provided in an embodiment of the present invention
Figure, referring to figs. 1 and 2, this method 200 may include:
Step S202, cloth inspecting machine acquires image to be detected.
In the present embodiment, cloth inspecting machine acquires image to be detected by real-time acquisition device, when it is implemented, adopting in real time
Acquisition means can use CCD industrial camera.Real-time acquisition device is arranged above cloth beam, acquires fabric surface image in real time
As image to be detected.
Step S204, image to be detected of acquisition is sent to terminal device by cloth inspecting machine.
In the present embodiment, the real-time acquisition device of cloth inspecting machine can be by wired or wireless mode by mapping to be checked
As being sent to terminal device.
Step S206, terminal device executes pretreatment to image to be detected, and such as, but not limited to, image T is converted to
Gray level image etc..
Step S208, terminal device executes image enhancement and normalized to pretreated image to be detected, thus
Enhance useful information in image and is converted to satisfactory canonical form.Image enhancement and normalized are known skills
Art omits descriptions thereof herein.
Step S210, terminal device generates defect detection request.
Step S212, terminal device by through image enhancement and normalized image to be detected and defect detection request hair
It send to server.
Step S214, server requests to detect image to be detected using neural network model according to defect detection.
Optionally, neural network model can use single type neural network model, such as, but not limited to, backpropagation
Neural network (BP:back propagation Neural Network) model, convolutional neural networks (CNN:
Convolutional Neural Network) model, Recognition with Recurrent Neural Network (RNN:Recurrent Neural Network)
Model, LSTM (Long Short-Term Memory, shot and long term memory) model, GRU (Gated Recurrent Unit, door
Control cycling element) model;Can also use combined neural network model, such as, but not limited to, CNN model+classifier,
CNN model+CNN model, BP model+classifier;It is also possible to other kinds of neural network model.
If step S216, server is not detected the fabric surface that image to be detected is included there are faults, it is determined that
Fault is not present in the fabric surface that image to be detected is included, and then process terminates.
If step S218, server detects fabric surface that image to be detected is included there are faults, inspection is generated
It surveys as a result, testing result includes fault type information and defect position information.
Optionally, fault type is such as, but not limited to spot, yarn defect, float, printing and dyeing fault, side defect, fold, skew of weft, breaks
Hole hooks silk, sanding unevenness, blur, fluffing, scratch, roll line, stop Mark.Wherein, spot includes greasy dirt, rust spot, color dot, dirt
Stain, mildew, auxiliary agent spot;Yarn defect includes dead cotton, slubbing, flyings, thick young yarn, soiled yarn, the dry unevenness of item;Float include broken yarn, knot,
Dropped stitch, rotten needle, try to stop people from fighting each other it is elastic, disconnected try to stop people from fighting each other, spacing is unstable, cloth cover plays snake, filling is shown up, color fibre, needle path, mistake yarn, yarn trace, tries to stop people from fighting each other
It is show-through, try to stop people from fighting each other and show up;Printing and dyeing fault include bite, stamp displacement, stamp staining, stamp cross bottom, stamp is bad, dyeing flower, yin-yang
Color loses colour, difference;When defect includes pin hole, double needle hole, crimping, rotten side, narrow envelope, wealthy envelope;Fold includes intermediate catcher mark, cloth cover
Corrugation, folding line;Skew of weft includes twill, arch.
Step S220, server will test result and be sent to terminal device.
Step S222, terminal device generates the instruction of fault marking of control, fault marking of control instruction packet according to testing result
Include fault type information and defect position information.
Step S224, the instruction of fault marking of control is sent to cloth inspecting machine by terminal device.
In the present embodiment, the instruction of fault marking of control is sent to the control device of cloth inspecting machine by terminal device.
Step S226, cloth inspecting machine instructs according to fault marking of control and carries out fault label on the fabric.
In the present embodiment, cloth inspecting machine controls labelling apparatus by control device and carries out fault label on the fabric.
Optionally, cloth inspecting machine can select the labeling method label different type of different instruction information according to fault type information
Fault different fault types is such as, but not limited to corresponded to using the ink-jet of different colours.
The scheme that process can be seen that the embodiment of the present invention offer as shown in Figure 2 will be used to detect the mind of fabric defects
It is mounted in cloud server through network model, by the communication of terminal device and server, realizes cloud detection and result passback,
The label to fault is finally realized on cloth inspecting machine.The neural network model provider of detection fabric defects can unify pipe beyond the clouds
Reason and maintenance, reduce later period operation cost.
Other modifications
It will be understood by those skilled in the art that although in the above embodiments, method 200 includes executing to image to be detected
Pretreated step S206, however, the present invention is not limited thereto.In other embodiments of the invention, method 200 can also be with
It does not include that pretreated step S206 is executed to image to be detected.
It will be understood by those skilled in the art that although in the above embodiments, method 200 includes executing to image to be detected
The step S208 of image enhancement and normalized, however, the present invention is not limited thereto.In the other embodiment of the present invention
In, method 200 can not also include the steps that executing image enhancement and normalized S208 to image to be detected.
Below with the angle of terminal device, cloth inspection method provided in an embodiment of the present invention is introduced, it is described below
Cloth inspection method can correspond to each other reference with signaling process content above.
Fig. 3 is the flow chart for the cloth inspection method that the embodiment of the present invention provides, and this method 300 can be applied to terminal device,
Referring to Fig. 3, this method 300 may include:
Step S302, image to be detected that cloth inspecting machine is sent is received, and generates defect detection request.
Optionally, after receiving image to be detected that cloth inspecting machine is sent, image can be executed to image to be detected and located in advance
Reason and/or image enhancement and normalized.
Step S304, described image to be detected and defect detection request are sent to server, the server includes using
In the neural network model of detection fabric defects.
Optionally, the fabric surface that neural network model is used to detect that image to be detected to be included whether there is fault, with
And type and the position of fault.
If step S306, receiving the fabric that described image to be detected that the server is sent is included, there are faults
Testing result, then according to the testing result generate fault marking of control instruction, the testing result includes the type of fault
Information and location information.
Step S308, fault marking of control instruction is sent to the cloth inspecting machine.
Fig. 4 is the another flow chart for the cloth inspection method that the embodiment of the present invention provides, and this method 400 can be applied to service
Device, referring to Fig. 4, this method 400 may include:
Step S402, image to be detected and defect detection request are received.
Step S404, according to the defect detection request, using detection fabric defects neural network model to it is described to
Detection image is detected.
If there are faults for the fabric that step S406, described image to be detected is included, generates testing result and export, institute
State the type information and location information that testing result includes fault.
Corresponding, Fig. 5 shows the neural network model provided in an embodiment of the present invention using detection fabric defects to institute
The method flow diagram that image to be detected is detected is stated, referring to Fig. 5, this method 500 may include:
Step S502, the one or more for obtaining the specified image using the first nerves network model trained is candidate
The fabric attributes feature of object corresponding to region.
Wherein, one or more candidate regions of the specified image can be obtained by identification positioning and image segmentation algorithm
Domain, identification positioning and image segmentation algorithm are the prior art, omit descriptions thereof herein.Object packet corresponding to candidate region
Fabric defects and/or fabric attributes are included, first nerves network model obtains the fabric attributes for wherein belonging to the object of fabric attributes
Feature.
First nerves network model is trained in advance for obtaining the deep learning model of fabric attributes feature, optional
, first nerves network model can be timing neural network model, such as RNN model, LSTM model or GRU model.
Step S504, according to the fabric attributes feature and the candidate region, nervus opticus network that utilization has been trained
Model determines in the candidate region with the presence or absence of fault effective coverage, is with the fabric that the described image to be detected of determination is included
It is no that there are faults.
Wherein, nervus opticus network model is trained in advance for carrying out fabric attributes/fault discriminant classification depth
Learning model is spent, attribute/fault is carried out to candidate region according to the fabric attributes feature that first nerves network model obtains
Two discriminant classifications, then exclude the attribute inactive area for being identified as fabric attributes, and the fault that reservation is identified as fault is effective
Region.If image to be detected whole region is identified as inactive area, it is determined that the fabric that image to be detected is included is not deposited
In fault, if differentiating result, there are effective coverages, it is determined that there are faults for the fabric that image to be detected is included.Optionally,
Two neural network models can be used with attribute/fault discriminant classification network CNN model, be in original convolutional Neural net
Increase by one attribute/fault discriminant classification network neural network model in network, CNN model described in present embodiment may include most
Basic CNN model, or, the improved model on CNN such as R-CNN, Fast R-CNN, Faster R-CNN.
Specifically, having attribute/fault discriminant classification network CNN model includes convolution feature extraction network, attribute/defect
Point discriminant classification network and target classification Recurrent networks.Wherein, convolution feature extraction network is used to extract the feature of candidate region
Figure, specific convolution feature extraction network can be using AlexNet, ZFnet, GoogleNet, VGG as convolution feature extraction
Network.Wherein, attribute/fault discriminant classification network input layer is a pond layer, and output layer is one Softmax layers, in
Between be several hidden layers, all layers of cascade connection, when it is implemented, attribute/fault discriminant classification network can be using including one
Pond layer, three full articulamentums (hidden layer) and one Softmax layers.Wherein, target classification Recurrent networks are according to attribute/fault point
Class differentiates the fault effective coverage of network output, extracts provincial characteristics from the characteristic pattern that convolution feature extraction network extracts, from
And it determines in fault effective coverage and returns amendment with the presence or absence of fault and target fault bounding box.If image to be detected whole area
Domain is identified as inactive area, it is determined that the fabric that image to be detected is included be not present fault, if differentiate result there are
Imitate region, it is determined that there are faults for the fabric that image to be detected is included.
When it is implemented, attribute/fault discriminant classification network network parameter can be used as shown in table 1.
Table 1, the present embodiment attribute/fault discriminant classification network parameter
When it is implemented, the network parameter of target classification Recurrent networks can be using as shown in table 2.
Table 2, the present embodiment target classification Recurrent networks parameter
When the present embodiment carries out defect detection to image to be detected, fabric attributes feature is obtained first, for determining defect
Comprehensively considered when point, to eliminate interference of the fabric attributes feature to testing result, is realized to the accurate of fabric defects
Detection, improves accuracy in detection.
Cloth examination device provided in an embodiment of the present invention is introduced below, cloth examination device described below can with it is above
Reference is corresponded to each other with the cloth inspection method of terminal device angle description.
Fig. 6 is a structural block diagram of cloth examination device provided in an embodiment of the present invention, which can be applied to terminal and set
It is standby, referring to Fig. 6, the device 600 may include request generation module 602, request sending module 604, directive generation module 606,
Instruction sending module 608.Request generation module 602 is used to receive image to be detected of cloth inspecting machine transmission, and generates defect detection
Request.Request sending module 604 is used to described image to be detected and defect detection request being sent to server, the server
Including the neural network model for detecting fabric defects.If directive generation module 606 is for receiving the server hair
There are the testing results of fault for the fabric that the described image to be detected sent is included, then generate fault mark according to the testing result
Remember control instruction, the testing result includes the type information and location information of fault.Instruction sending module 608 is used for will be described
The instruction of fault marking of control is sent to the cloth inspecting machine.
The embodiment of the present invention also provides a kind of terminal device, which may include cloth examination device described above.
It, can be to the neural network model equipped with detection fabric defects using terminal device provided in an embodiment of the present invention
Server sends defect detection request, and the testing result sent according to server generates the instruction of fault marking of control and tested with controlling
Cloth machine carries out fault label.
Fig. 7 shows the schematic diagram of the terminal device of one embodiment according to the invention.As shown in fig. 7, terminal device
700 may include processor 702, memory 704, communication interface 706 and communication bus 708, processor 702,704 and of memory
Communication interface 706 completes mutual communication by communication bus 708.
Memory 704 is stored with executable instruction, wherein the executable instruction makes processor 702 upon being performed
Execute method 300 shown in Fig. 3.
Below with the angle of server, cloth examination device provided in an embodiment of the present invention is introduced, it is described below to test
Cloth apparatus can with above with server side describe cloth inspection method correspond to each other reference.
The another structural block diagram of the position Fig. 8 cloth examination device provided in an embodiment of the present invention, the device 800 can be applied to service
Device, referring to Fig. 8, which may include request receiving module 802, defect detection module 804 and result output module 806.
Request receiving module 802 is for receiving image to be detected and defect detection request.Defect detection module 804 is used for according to the defect
Point detection request, detects described image to be detected using the neural network model of detection fabric defects.As a result mould is exported
If block 806 is used for the fabric that described image to be detected is included, there are faults, generate testing result and export, the detection knot
Fruit includes the type information and location information of fault.
Fig. 9 shows a kind of alternative construction block diagram of defect detection module 804 provided in an embodiment of the present invention, referring to Fig. 9,
Defect detection module 804 may include the first taxon 8042, the second taxon 8044 and third taxon 8046.The
One taxon 8042 is for classifying to described image to be detected using the first nerves network model trained, wherein
The first nerves network model is the Abnormal Map for belonging to fabric included in it and there may be fault for detection image
There can not be the normal picture of fault as still falling within fabric included in it.If the second taxon 8044 is used for institute
It states first nerves network model and described image to be detected is classified as the abnormal image, then there is memory energy using what is trained
The nervus opticus network model of power classifies to described image to be detected, wherein the nervus opticus network model is for examining
Altimetric image is to belong to fabric included in it to there are problems that fault image still falls within the normal picture.Third grouping sheet
If described image to be detected is classified as described problem image for the nervus opticus network model by member 8046, using
Trained classifier determines fault type and defect position existing for fabric that described image to be detected is included.
The embodiment of the present invention also provides a kind of server, which may include above-mentioned to test described in server side
Cloth apparatus.
Figure 10 shows the schematic diagram of the server of one embodiment according to the invention.As shown in Figure 10, server 900
It may include processor 902, memory 904, communication interface 906 and communication bus 908, processor 902, memory 904 and logical
Letter interface 906 completes mutual communication by communication bus 908.
Memory 904 is stored with executable instruction, wherein the executable instruction makes processor 902 upon being performed
Execute method 400 shown in Fig. 4, method shown in fig. 5 500.
The communication bus that above-mentioned terminal device and server are mentioned can be Peripheral Component Interconnect standard (Peripheral
Pomponent Interconnect, abbreviation PCI) bus or expanding the industrial standard structure (Extended Industry
Standard Architecture, abbreviation EISA) bus etc..The communication bus can be divided into address bus, data/address bus, control
Bus processed etc..Only to be indicated with a thick line in figure convenient for indicating, it is not intended that an only bus or a type of total
Line.
Communication interface is for the communication between above-mentioned electronic equipment and other equipment.
Memory may include random access memory (Random Access Memory, abbreviation RAM), also may include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be storage device that at least one is located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
Abbreviation CPU), network processing unit (Network Processor, abbreviation NP) etc.;It can also be digital signal processor
(Digital Signal Processing, abbreviation DSP), specific integrated circuit (Application Specific
Integrated Circuit, abbreviation ASIC), field programmable gate array (Field-Programmable Gate Array,
Abbreviation FPGA), graphics processor (Graphics Processing Unit, abbreviation GPU) or other programmable logic device,
Discrete gate or transistor logic, discrete hardware components.
The present invention also provides a kind of storage mediums, are stored thereon with computer executable instructions, wherein the executable finger
Order makes computer execute method 300, method shown in Fig. 4 400 or method shown in fig. 5 shown in Fig. 3 upon being performed
500。
The embodiment of the present invention also provides a kind of fabric inspecting system, and specific structure can refer to shown in Fig. 1, including cloth inspecting machine 102, end
End equipment 104 and server 108, cloth inspecting machine 102 are connect with terminal device 104, and terminal device 104 is with server 108 by having
Gauze network or wireless network connection, terminal device 104 can be using terminal devices described in above-described embodiment, and server 108 can
Using server described in above-described embodiment.
The specific embodiment illustrated above in conjunction with attached drawing describes exemplary embodiment, it is not intended that may be implemented
Or fall into all embodiments of the protection scope of claims." exemplary " meaning of the term used in entire this specification
Taste " be used as example, example or illustration ", be not meant to than other embodiments " preferably " or " there is advantage ".For offer pair
The purpose of the understanding of described technology, specific embodiment include detail.However, it is possible in these no details
In the case of implement these technologies.In some instances, public in order to avoid the concept to described embodiment causes indigestion
The construction and device known is shown in block diagram form.
The foregoing description of present disclosure is provided so that any those of ordinary skill in this field can be realized or make
Use present disclosure.To those skilled in the art, the various modifications carried out to present disclosure are apparent
, also, can also answer generic principles defined herein in the case where not departing from the protection scope of present disclosure
For other modifications.Therefore, present disclosure is not limited to examples described herein and design, but disclosed herein with meeting
Principle and novel features widest scope it is consistent.
Claims (10)
1. cloth inspection method, comprising:
Image to be detected that cloth inspecting machine is sent is received, and generates defect detection request;
Described image to be detected and defect detection request are sent to server, the server includes for detecting fabric defects
Neural network model;
If receiving fabric that described image to be detected that the server is sent is included there are the testing result of fault,
The instruction of fault marking of control is generated according to the testing result, the testing result includes the type information and position letter of fault
Breath;
Fault marking of control instruction is sent to the cloth inspecting machine.
2. cloth inspection method, comprising:
Receive image to be detected and defect detection request;
It is requested according to the defect detection, described image to be detected is examined using the neural network model of detection fabric defects
It surveys;
If there are faults for the fabric that described image to be detected is included, generates testing result and export, the testing result packet
Include the type information and location information of fault.
3. according to the method described in claim 2, wherein, the neural network model using detection fabric defects to it is described to
Detection image is detected, comprising:
It is obtained corresponding to one or more candidate regions of the specified image using the first nerves network model trained
The fabric attributes feature of object;
According to the fabric attributes feature and the candidate region, the time is determined using the nervus opticus network model trained
It whether there is fault effective coverage in favored area, the fabric for being included with the described image to be detected of determination is with the presence or absence of fault.
4. cloth examination device, comprising:
Generation module is requested, for receiving image to be detected of cloth inspecting machine transmission, and generates defect detection request;
Request sending module, for described image to be detected and defect detection request to be sent to server, the server packet
Include the neural network model for detecting fabric defects;
Directive generation module, if existed for receiving the fabric that described image to be detected that the server is sent is included
The testing result of fault then generates the instruction of fault marking of control according to the testing result, and the testing result includes fault
Type information and location information;
Instruction sending module, for fault marking of control instruction to be sent to the cloth inspecting machine.
5. cloth examination device, comprising:
Request receiving module, for receiving image to be detected and defect detection request;
Defect detection module, for being requested according to the defect detection, using the neural network model of detection fabric defects to institute
Image to be detected is stated to be detected;
As a result output module, if the fabric for being included for described image to be detected there are fault, generates testing result and defeated
Out, the testing result includes the type information and location information of fault.
6. device according to claim 5, wherein the defect detection module includes:
Acquiring unit, the one or more for obtaining the specified image using the first nerves network model trained are candidate
The fabric attributes feature of object corresponding to region;
Determination unit, for the nervus opticus network that according to the fabric attributes feature and the candidate region, utilization has been trained
Model determines in the candidate region with the presence or absence of fault effective coverage, is with the fabric that the described image to be detected of determination is included
It is no that there are faults.
7. terminal device, comprising:
Processor, memory, communication interface and communication bus, the processor, the memory and the communication interface pass through
The communication bus completes mutual communication;
The memory is stored with executable instruction, wherein the executable instruction holds the processor
Row method described in claim 1.
8. server, comprising:
Processor, memory, communication interface and communication bus, the processor, the memory and the communication interface pass through
The communication bus completes mutual communication;
The memory is stored with executable instruction, wherein the executable instruction holds the processor
Row method described in claim 2 or 3.
9. storage medium is stored thereon with computer executable instructions, wherein the executable instruction makes to succeed in one's scheme upon being performed
Method described in calculation machine perform claim requirement 1, method described in claim 2 or 3.
10. fabric inspecting system, comprising:
Cloth inspecting machine, terminal device and server, wherein
The terminal device is terminal device as claimed in claim 7;
The server is server according to any one of claims 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811037108.2A CN109215022A (en) | 2018-09-05 | 2018-09-05 | Cloth inspection method, device, terminal device, server, storage medium and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811037108.2A CN109215022A (en) | 2018-09-05 | 2018-09-05 | Cloth inspection method, device, terminal device, server, storage medium and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109215022A true CN109215022A (en) | 2019-01-15 |
Family
ID=64987729
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811037108.2A Pending CN109215022A (en) | 2018-09-05 | 2018-09-05 | Cloth inspection method, device, terminal device, server, storage medium and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109215022A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110188833A (en) * | 2019-06-04 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Method and apparatus for training pattern |
WO2020048248A1 (en) * | 2018-09-05 | 2020-03-12 | 深圳灵图慧视科技有限公司 | Textile defect detection method and apparatus, and computer device and computer-readable medium |
CN111595237A (en) * | 2020-05-13 | 2020-08-28 | 广西大学 | Machine vision-based fabric size measurement distributed system and method |
CN112102224A (en) * | 2019-06-18 | 2020-12-18 | 浙江工业大学 | Cloth defect identification method based on deep convolutional neural network |
CN114004819A (en) * | 2021-11-04 | 2022-02-01 | 中国联合网络通信集团有限公司 | Cloth inspection processing method, device, equipment, system and medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1721600A (en) * | 2001-04-20 | 2006-01-18 | 皮卡诺股份有限公司 | Method for optimizing a textile production process and devices applying this method |
CN101510085A (en) * | 2009-03-13 | 2009-08-19 | 东华大学 | Fluoroplastic film defect on-line detecting control system based on process control machine |
CN102507607A (en) * | 2011-11-30 | 2012-06-20 | 明基材料有限公司 | System and method for integrating defect detection results |
CN103207186A (en) * | 2013-04-08 | 2013-07-17 | 北京经纬纺机新技术有限公司 | Identification method for defect detection of automatic cloth inspecting machine and system thereof |
CN106996935A (en) * | 2017-02-27 | 2017-08-01 | 华中科技大学 | A kind of multi-level fuzzy judgment Fabric Defects Inspection detection method and system |
CN107123114A (en) * | 2017-04-21 | 2017-09-01 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of cloth defect inspection method and device based on machine learning |
CN108242054A (en) * | 2018-01-09 | 2018-07-03 | 北京百度网讯科技有限公司 | A kind of steel plate defect detection method, device, equipment and server |
-
2018
- 2018-09-05 CN CN201811037108.2A patent/CN109215022A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1721600A (en) * | 2001-04-20 | 2006-01-18 | 皮卡诺股份有限公司 | Method for optimizing a textile production process and devices applying this method |
CN101510085A (en) * | 2009-03-13 | 2009-08-19 | 东华大学 | Fluoroplastic film defect on-line detecting control system based on process control machine |
CN102507607A (en) * | 2011-11-30 | 2012-06-20 | 明基材料有限公司 | System and method for integrating defect detection results |
CN103207186A (en) * | 2013-04-08 | 2013-07-17 | 北京经纬纺机新技术有限公司 | Identification method for defect detection of automatic cloth inspecting machine and system thereof |
CN106996935A (en) * | 2017-02-27 | 2017-08-01 | 华中科技大学 | A kind of multi-level fuzzy judgment Fabric Defects Inspection detection method and system |
CN107123114A (en) * | 2017-04-21 | 2017-09-01 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of cloth defect inspection method and device based on machine learning |
CN108242054A (en) * | 2018-01-09 | 2018-07-03 | 北京百度网讯科技有限公司 | A kind of steel plate defect detection method, device, equipment and server |
Non-Patent Citations (1)
Title |
---|
刘祥惠: "基于深度学习的织物图像疵点区域定位算法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020048248A1 (en) * | 2018-09-05 | 2020-03-12 | 深圳灵图慧视科技有限公司 | Textile defect detection method and apparatus, and computer device and computer-readable medium |
CN110188833A (en) * | 2019-06-04 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Method and apparatus for training pattern |
CN110188833B (en) * | 2019-06-04 | 2021-06-18 | 北京字节跳动网络技术有限公司 | Method and apparatus for training a model |
CN112102224A (en) * | 2019-06-18 | 2020-12-18 | 浙江工业大学 | Cloth defect identification method based on deep convolutional neural network |
CN112102224B (en) * | 2019-06-18 | 2025-01-10 | 浙江工业大学 | A cloth defect recognition method based on deep convolutional neural network |
CN111595237A (en) * | 2020-05-13 | 2020-08-28 | 广西大学 | Machine vision-based fabric size measurement distributed system and method |
CN114004819A (en) * | 2021-11-04 | 2022-02-01 | 中国联合网络通信集团有限公司 | Cloth inspection processing method, device, equipment, system and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109215022A (en) | Cloth inspection method, device, terminal device, server, storage medium and system | |
CN110175988A (en) | Cloth defect inspection method based on deep learning | |
CN107123114A (en) | A kind of cloth defect inspection method and device based on machine learning | |
CN108009591A (en) | A kind of contact network key component identification method based on deep learning | |
CN109035248A (en) | Defect detection method, apparatus, terminal device, server and storage medium | |
CN109815998A (en) | A kind of AI dress dimension method for inspecting and system based on YOLO algorithm | |
CN110275958A (en) | Site information recognition methods, device and electronic equipment | |
CN109187579A (en) | Fabric defect detection method and device, computer equipment and computer-readable medium | |
CN107369155A (en) | A kind of cloth surface defect detection method and its system based on machine vision | |
CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
CN108416774A (en) | A kind of fabric types recognition methods based on fine granularity neural network | |
CN106530284A (en) | Welding spot type detection and device based on image recognition | |
CN111401419A (en) | Improved RetinaNet-based employee dressing specification detection method | |
CN108038843A (en) | A kind of method, apparatus and equipment for defects detection | |
CN112712516B (en) | High-speed rail bottom rubber strip fault detection method and system based on YOLOv5 | |
CN107808358A (en) | Image watermark automatic testing method | |
CN103279744B (en) | Imitation fingerprint detection methods based on multiple dimensioned three mode texture feature and system | |
CN101739570A (en) | Cotton foreign fiber online classifying method and system | |
CN113996556B (en) | Cloud-integrated product sorting system and method | |
CN109829881A (en) | Bird's Nest detection method and system based on deep learning | |
CN116415506A (en) | Industrial robot fault diagnosis method and system based on federal learning | |
CN110263680A (en) | Image processing method, device and system and storage medium | |
CN110020691A (en) | LCD screen defect inspection method based on the training of convolutional neural networks confrontation type | |
Sayed | Robust fabric defect detection algorithm using entropy filtering and minimum error thresholding | |
KR100234593B1 (en) | Method for high inspection of fabric |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190115 |
|
WD01 | Invention patent application deemed withdrawn after publication |