CN110110726A - Power equipment nameplate identification method and device, computer equipment and storage medium - Google Patents
Power equipment nameplate identification method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110110726A CN110110726A CN201910405844.7A CN201910405844A CN110110726A CN 110110726 A CN110110726 A CN 110110726A CN 201910405844 A CN201910405844 A CN 201910405844A CN 110110726 A CN110110726 A CN 110110726A
- Authority
- CN
- China
- Prior art keywords
- nameplate
- text
- region
- image
- type
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000004590 computer program Methods 0.000 claims description 30
- 230000015654 memory Effects 0.000 claims description 22
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 238000013145 classification model Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 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
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a method and a device for identifying a nameplate of electrical equipment, computer equipment and a storage medium. The method comprises the following steps: acquiring a nameplate image; identifying a nameplate type in the nameplate image; and determining a corresponding character recognition model according to the nameplate type, and recognizing the nameplate characters by using the character recognition model. By the method, the identification accuracy of the nameplate of the power equipment can be improved.
Description
Technical field
This application involves field of power systems, more particularly to a kind of power equipment nameplate recognition methods, device, computer
Equipment and storage medium.
Background technique
With the fast development of south electric network business scope (southern five provinces) interior social economy, production and living field is to electric power
The demand used increases rapidly, and power equipment involved by transmission of electricity, power transformation and distribution links also increases rapidly.Electric power is set
Standby nameplate records the basic parameter and identity information of equipment, power equipment is counted, is managed, inspection when usually need to obtain
Take the name plate information of equipment.
In recent years with the development of artificial intelligence technology, begin to use intelligent image identification to carry out the knowledge of name plate information
Other typing.Existing intelligence nameplate identifies method, carries out nameplate Text region to nameplate image generally by neural network.But
It is that when using deep neural network to nameplate region progress Text region is carried out, the accuracy of identification is not high.
Therefore, existing nameplate recognition methods has that recognition accuracy is not high.
Summary of the invention
Based on this, the invention proposes a kind of power equipment nameplate recognition methods, device, computer equipment and storages to be situated between
Matter, to solve the problems, such as conventional electric power equipment nameplate identification inaccuracy.
A kind of power equipment nameplate recognition methods, comprising steps of
Obtain nameplate image；
Identify the nameplate type in the nameplate image；
According to the nameplate type, corresponding Text region model is determined, and utilize Text region model identification inscription
Board text.
Nameplate type in the identification nameplate image in one of the embodiments, comprising:
By nameplate disaggregated model, the characteristics of image in described image region is extracted from the nameplate image；
According to the characteristics of image in described image region, nameplate region is identified；The nameplate region be include nameplate feature
Image-region；
According to the nameplate region, the nameplate type is determined.
It is described according to the nameplate region in one of the embodiments, determine nameplate type, comprising:
According to the characteristics of image in the nameplate region, the nameplate region is evaluated, obtains nameplate region scoring；
It is scored according to the nameplate region, classifies to the nameplate region, obtain the nameplate type.
It is described by nameplate disaggregated model in one of the embodiments, identify the nameplate type in the nameplate image
Before, further includes:
Obtain a large amount of nameplate images；
Mark the nameplate region and the nameplate type in the nameplate image；
It will be trained in nameplate image input deep neural network model after mark, obtain the nameplate classification
Model.
It is described according to the nameplate type in one of the embodiments, determine corresponding Text region model, comprising:
Obtain multiple candidate identification models；Candidate's identification model has corresponding nameplate type；
In the multiple candidate identification model, candidate identification model corresponding with the nameplate type is extracted, as
The Text region model.
It is described in one of the embodiments, to identify nameplate text using Text region model, comprising:
Obtain text candidate frame；
Obtain the text confidence level of the text candidate frame；
The text candidate frame is filtered according to the text confidence level, obtains the Text region frame；
According to the Text region frame, the nameplate text is obtained.
It is described according to the Text region frame in one of the embodiments, obtain the nameplate text, comprising:
It identifies the Text region frame, obtains candidate character；
Obtain the matching degree of the candidate character Yu the nameplate text；
According to the matching degree, determine that the candidate character is the nameplate text.
A kind of power equipment nameplate identification device, described device include:
Image collection module, for obtaining nameplate image；
Type identification module, for identification the nameplate type of the nameplate image；
Text region module for determining corresponding Text region model according to the nameplate type, and utilizes the text
Word identification model identifies nameplate text.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Obtain nameplate image；
Identify the nameplate type in the nameplate image；
According to the nameplate type, corresponding Text region model is determined, and utilize Text region model identification inscription
Board text.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Obtain nameplate image；
Identify the nameplate type in the nameplate image；
According to the nameplate type, corresponding Text region model is determined, and utilize Text region model identification inscription
Board text.
Above-mentioned power equipment nameplate recognition methods, device, computer equipment and storage medium, are known by nameplate disaggregated model
Nameplate type in other nameplate image determines corresponding Text region mould according to nameplate type from candidate character identification model
Type, and nameplate text is identified using the Text region model, it avoids using same depth recognition network to variety classes
The problem that the nameplate of type is identified, and causes identification inaccurate, to improve power equipment nameplate recognition accuracy.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of power equipment nameplate recognition methods of one embodiment；
Fig. 2 is a kind of applied environment figure of power equipment nameplate recognition methods of one embodiment；
Fig. 3 is a kind of idiographic flow schematic diagram of power equipment nameplate recognition methods of one embodiment；
Fig. 4 is a kind of specific method schematic diagram of power equipment nameplate identification of one embodiment；
Fig. 5 is a kind of structural block diagram of power equipment nameplate identification device of one embodiment；
Fig. 6 is a kind of internal structure chart of computer equipment of one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
In one embodiment, as shown in Figure 1, providing a kind of power equipment nameplate recognition methods.It is provided by the present application
Power equipment nameplate recognition methods, can be applied in application environment as shown in Figure 2.
Application environment shown in Fig. 2 includes image collecting device 210, power equipment nameplate 220, nameplate identification server
230 and terminal 240, wherein after image collecting device 210 acquires the image of power equipment nameplate 220, by network by nameplate figure
Text region is carried out as being transmitted in nameplate identification server 230, the nameplate text after identification is shown by terminal 240, terminal
240 identify that server 230 is communicated with nameplate by network.Wherein, image collecting device 210 can be specially camera,
Nameplate identification server 230 can be realized with the server cluster of the either multiple server compositions of independent server, whole
End 240 can be, but not limited to be various personal computers, laptop, smart phone, tablet computer and portable wearable
Equipment.The power equipment nameplate recognition methods of the embodiment of the present application, may comprise steps of:
Step S110 obtains nameplate image.
Wherein, nameplate image can be the image shot for nameplate.Nameplate can be on power equipment, record
The label of the technical parameters such as manufacturer and nominal operation situation.
In the specific implementation, user acquires initial nameplate image by image collecting device 210, and by initial nameplate image into
The pretreatment such as row noise reduction, correction, obtains nameplate image, and nameplate image is input in nameplate identification server 230 and is handled.
Step S120 identifies the nameplate type in the nameplate image.
In the specific implementation, after nameplate identification server 230 gets nameplate image, by nameplate image input nameplate classification
The processing of convolution pondization is carried out in model, obtains the image-region of multiple scale calibrations, characteristics of image is extracted from image-region,
According to characteristics of image, image-region is filtered, so that it is determined that nameplate region；The characteristics of image of nameplate region is subjected to convolution
Pondization processing obtains nameplate region scoring, is scored according to nameplate region, classified to nameplate region, obtain nameplate type.
Step S130 determines corresponding Text region model according to the nameplate type, and utilizes the Text region mould
Type identifies nameplate text.
In the specific implementation, the nameplate type is sent in configuration file and is matched, is obtained after getting nameplate type
To corresponding Text region model；By nameplate region input Text region model, generate Text region frame, to Text region frame into
Row Text region obtains nameplate text information.
According to the technical solution of the embodiment of the present application, the nameplate type in nameplate image is identified by nameplate disaggregated model,
According to nameplate type, corresponding Text region model is determined from candidate character identification model, and know using Text region model
Not Chu nameplate text, avoid and the nameplate of different types identified using same depth recognition network, cause to identify
Inaccurate problem, to improve power equipment nameplate recognition accuracy.
In another embodiment, the nameplate image includes image-region, the nameplate in the identification nameplate image
Type, comprising:
By nameplate disaggregated model, the characteristics of image in described image region is extracted from the nameplate image；According to institute
The characteristics of image of image-region is stated, identifies nameplate region；The nameplate region is the image-region for including nameplate feature；According to
The nameplate region determines the nameplate type.
In the specific implementation, nameplate image is inputted convolutional Neural after nameplate identification server 230 gets nameplate image
Convolution algorithm is carried out in network layer, generates the image-region of multiple dimensional standards, and the image in interception image region obtains region
Image obtains the characteristics of image of area image by area image after the processing of convolution pondization.Characteristics of image is matrix, matrix
The pixel of element correspondence image characteristic area, by being filtered according to the pixel number of pixel to area image, thus really
Determine nameplate region.According to the nameplate region, nameplate type is determined.
The technical solution of the present embodiment, by extracting the characteristics of image of image-region, and by characteristics of image to image district
Domain is filtered, and determines nameplate region, so that identification range when nameplate identification server 230 identifies nameplate region is reduced,
And then improve power equipment nameplate recognition efficiency.
It is described according to the nameplate region in another embodiment, determine nameplate type, comprising:
According to the characteristics of image in the nameplate region, the nameplate region is evaluated, obtains nameplate region scoring；
It is scored according to the nameplate region, classifies to the nameplate region, obtain the nameplate type.
In the specific implementation, characteristics of image is carried out after nameplate identification server 230 gets the characteristics of image of nameplate region
Convolution algorithm obtains nameplate region scoring, nameplate scoring input decision function is judged, to obtain nameplate type.
For example, extracting the characteristics of image in nameplate region, such as nameplate material feature, nameplate color characteristic, nameplate size
Feature input neural network in handled, according in nameplate disaggregated model network weight and Node B threshold calculate network it is defeated
Out, network is exported and kind judging is carried out by decision function, to obtain nameplate type.
The technical solution of the present embodiment scores to the nameplate region by the characteristics of image in nameplate region, and
Classified according to scoring to nameplate region, obtain the nameplate type, so that nameplate identification server 230 can be accurate
It identifies nameplate classification, and then improves power equipment nameplate recognition accuracy.
It is described by nameplate disaggregated model in another embodiment, before identifying the nameplate type in the nameplate image,
Further include:
Obtain a large amount of nameplate images；Mark the nameplate region and the nameplate type in the nameplate image；It will mark
It is trained in nameplate image input deep neural network model after note, obtains the nameplate disaggregated model.
In the specific implementation, a sample (Ai, Bi) of selection nameplate sample set, Ai is data, Bi is label, is sent into mind
Through network, the reality output Y of network is calculated, is calculated D=Bi-Y (i.e. predicted value is differed with actual value), according to error D tune
Whole weight matrix W, repeats the above process each sample, and until for entire sample set, error is no more than prescribed limit, from
And obtain nameplate disaggregated model.
It is described according to the nameplate type in another embodiment, determine corresponding Text region model, comprising:
Obtain multiple candidate identification models；Candidate's identification model has corresponding nameplate type；In the multiple time
It selects in identification model, candidate identification model corresponding with the nameplate type is extracted, as the Text region model.
In the specific implementation, the type is inputted in configuration file and is matched, from nameplate type after obtaining nameplate type
Corresponding identification model is obtained in corresponding Text region relationship model table.
In practical application, configuration file can be initially set up, nameplate type is recorded in configuration file and corresponds to Text region
Relationship model table.
It is described to identify nameplate text using Text region model in another embodiment, comprising:
Obtain text candidate frame；Obtain the text confidence level of the text candidate frame；According to the text confidence level to institute
It states text candidate frame to be filtered, obtains the Text region frame；According to the Text region frame, the nameplate text is obtained.
Wherein, text confidence level can be the probability that index text selects frame to have nameplate character features.
It handles, obtains in the specific implementation, nameplate identifies that server 230 inputs nameplate region in Text region model
Text candidate frame is introduced into a two-way long short-term memory Recognition with Recurrent Neural Network layer and calculates by text candidate frame.Specifically,
Two-way long short-term memory Recognition with Recurrent Neural Network layer by two standards one layer of LSTM (Long Short-Term Memory, length
Memory network) module composition, coordinate central point and text candidate frame of one of LSTM module for predictive text candidate frame
Length and width drift correction value, another LSTM module is used to predict the text confidence level of the candidate frame.It is right according to text confidence level
All text candidate frames are filtered, and obtain the Text region frame with nameplate text information, according to Text region frame, obtain inscription
Board text.
The technical solution of the present embodiment, by obtaining the text candidate frame of nameplate region and the text confidence level of candidate frame,
Text candidate frame is filtered according to text confidence level, Text region frame is obtained, so that nameplate text be recognized accurately, improves electric power
Equipment nameplate recognition accuracy.
It is described according to the Text region frame in another embodiment, obtain the nameplate text, comprising:
It identifies the Text region frame, obtains candidate character；Obtain the matching of the candidate character Yu the nameplate text
Degree；According to the matching degree, determine that the candidate character is the nameplate text.
In the specific implementation, nameplate identification server is mentioned by calling corresponding Text region model to obtain Text region frame
The alphabetic character morphological feature in Text region frame is taken, initial text is obtained.The character features in Text region frame may at this time
Can because nameplate get rusty, the reasons such as nameplate image exposure, cause character features incomplete, therefore initial text at this time and be not allowed
Really.For example, " voltmeter " character features become " electricity soil table " text after there is the nameplate of " voltmeter " character features to get rusty
Word feature, the initial text that Text region model is got at this time are " electricity soil table ".Nameplate identification server 230 is pre-established with
Device name database, nameplate identify that server 230 obtains the candidate character with initial characters matching from device name database,
And the matching degree of candidate character Yu initial text is calculated, according to matching degree, determine that candidate character is nameplate text.
The technical solution of the present embodiment obtains initial text, passes through the acquisition pair of initial text by identifying Text region frame
The candidate character answered determines nameplate text, to improve identification by calculating the matching degree of candidate character and initial text
The order of accuarcy of power equipment nameplate text.
The embodiment of the present application is deeply understood for the ease of those skilled in the art, is said below with reference to specific example
It is bright.Fig. 3 is a kind of specific method flow diagram of power equipment nameplate identification of one embodiment.As shown, image is adopted
Collect electric power nameplate image, and nameplate image is transmitted in nameplate identification server 230, using nameplate disaggregated model to being transmitted to
Nameplate image in server carries out nameplate classification, and sorted nameplate image is transmitted to corresponding Text region model, text
Word identification model determines nameplate text by extracting nameplate character features.
The embodiment of the present application is deeply understood for the ease of those skilled in the art, is said below with reference to specific example
It is bright.Fig. 4 is a kind of specific method schematic diagram of power equipment nameplate identification of one embodiment.As shown, because different inscriptions
The text point of board and content difference, so needing to classify to nameplate region, initially set up nameplate disaggregated model, to collection
The various nameplate images arrived carry out nameplate signature, and the nameplate image input deep neural network after label is trained,
Obtain nameplate disaggregated model；Then the model for establishing word area detection and identification carries out text to the various nameplate images of collection
The frame of word field selects label, and frame is selected the nameplate marked because field difference needs frame choosing label respectively by different nameplate types
Image input deep neural network is trained, and obtains the model of word area detection and identification；Nameplate image to be measured is inputted
Nameplate classification and Detection is carried out in nameplate disaggregated model, obtains nameplate type, and the corresponding text of nameplate type is inquired according to configuration file
Word identification model, Text region model determine nameplate text by extracting nameplate character features.
It should be understood that although each step in the flow chart of Fig. 1 is successively shown according to the instruction of arrow, this
A little steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these steps
It executes there is no the limitation of stringent sequence, these steps can execute in other order.Moreover, at least part in Fig. 1
Step may include that perhaps these sub-steps of multiple stages or stage are executed in synchronization to multiple sub-steps
It completes, but can execute at different times, the execution sequence in these sub-steps or stage, which is also not necessarily, successively to be carried out,
But it can be executed in turn or alternately at least part of the sub-step or stage of other steps or other steps.
In one embodiment, as shown in figure 5, providing a kind of power equipment nameplate identification device, comprising:
Image collection module 510, for obtaining nameplate image；
Type identification module 520, for identification the nameplate type of the nameplate image；
Text region module 530 for determining corresponding Text region model according to the nameplate type, and utilizes institute
State Text region model identification nameplate text.
In one embodiment, the type identification module 520, comprising:
Image characteristics extraction submodule, for extracting characteristics of image from the image-region in the nameplate image；
Type determination module, for determining the nameplate type according to the nameplate region.
In one embodiment, the type determination module, comprising:
Score unit in region, for evaluating the nameplate region according to the characteristics of image in the nameplate region,
Obtain nameplate region scoring；
Territorial classification unit is classified to the nameplate region, is obtained described for being scored according to the nameplate region
Nameplate type.
In one embodiment, the power equipment nameplate identification device, further includes:
Nameplate image obtains module, for obtaining a large amount of nameplate images；
Labeling module, for marking the nameplate region in the nameplate image and the nameplate type；
Training module is obtained for will be trained in the nameplate image input deep neural network model after mark
To the nameplate disaggregated model.
In one embodiment, the Text region module 530, comprising:
Identification model acquisition submodule, for obtaining multiple candidate identification models；Candidate's identification model, which has, to be corresponded to
Nameplate type；
Text region model acquisition submodule, for extracting and the nameplate in the multiple candidate identification model
The corresponding candidate identification model of type, as the Text region model.
In one embodiment, the Text region model acquisition submodule, comprising:
Text candidate frame acquiring unit, for obtaining text candidate frame；
Text confidence computation unit, for obtaining the text confidence level of the text candidate frame；
Text region frame acquiring unit is obtained for being filtered according to the text confidence level to the text candidate frame
To the Text region frame；
Nameplate text acquiring unit, for obtaining the nameplate text according to the Text region frame.
Specific restriction about power equipment nameplate identification device may refer to identify above for power equipment nameplate
The restriction of method, details are not described herein.Modules in above-mentioned power equipment nameplate identification device can be fully or partially through
Software, hardware and combinations thereof are realized.Above-mentioned each module can be embedded in the form of hardware or independently of the place in computer equipment
It manages in device, can also be stored in a software form in the memory in computer equipment, in order to which processor calls execution or more
The corresponding operation of modules.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 6.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of power equipment nameplate recognition methods.The display screen of the computer equipment can be liquid crystal display or electric ink
Display screen, the input unit of the computer equipment can be the touch layer covered on display screen, be also possible to outside computer equipment
Key, trace ball or the Trackpad being arranged on shell can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain nameplate image；
Identify the nameplate type in the nameplate image；
According to the nameplate type, corresponding Text region model is determined, and utilize Text region model identification inscription
Board text.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Obtain nameplate image；
Identify the nameplate type in the nameplate image；
According to the nameplate type, corresponding Text region model is determined, and utilize Text region model identification inscription
Board text.
In one embodiment, it is also performed the steps of when processor executes computer program
By nameplate disaggregated model, the characteristics of image in described image region is extracted from the nameplate image；
According to the characteristics of image in described image region, nameplate region is identified；The nameplate region be include nameplate feature
Image-region；
According to the nameplate region, the nameplate type is determined.
In one embodiment, it is also performed the steps of when processor executes computer program
According to the characteristics of image in the nameplate region, the nameplate region is evaluated, obtains nameplate region scoring；
It is scored according to the nameplate region, classifies to the nameplate region, obtain the nameplate type.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain a large amount of nameplate images；
Mark the nameplate region and the nameplate type in the nameplate image；
It will be trained in nameplate image input deep neural network model after mark, obtain the nameplate classification
Model.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain multiple candidate identification models；Candidate's identification model has corresponding nameplate type；
In the multiple candidate identification model, candidate identification model corresponding with the nameplate type is extracted, as
The Text region model.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain text candidate frame；
Obtain the text confidence level of the text candidate frame；
The text candidate frame is filtered according to the text confidence level, obtains the Text region frame；
According to the Text region frame, the nameplate text is obtained.
In one embodiment, it is also performed the steps of when processor executes computer program
It identifies the Text region frame, obtains candidate character；
Obtain the matching degree of the candidate character Yu the nameplate text；
According to the matching degree, determine that the candidate character is the nameplate text.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Obtain nameplate image；
Identify the nameplate type in the nameplate image；
According to the nameplate type, corresponding Text region model is determined, and utilize Text region model identification inscription
Board text.
In one embodiment, it is also performed the steps of when processor executes computer program
By nameplate disaggregated model, the characteristics of image in described image region is extracted from the nameplate image；
According to the characteristics of image in described image region, nameplate region is identified；The nameplate region be include nameplate feature
Image-region；
According to the nameplate region, the nameplate type is determined.
In one embodiment, it is also performed the steps of when processor executes computer program
According to the characteristics of image in the nameplate region, the nameplate region is evaluated, obtains nameplate region scoring；
It is scored according to the nameplate region, classifies to the nameplate region, obtain the nameplate type.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain a large amount of nameplate images；
Mark the nameplate region and the nameplate type in the nameplate image；
It will be trained in nameplate image input deep neural network model after mark, obtain the nameplate classification
Model.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain multiple candidate identification models；Candidate's identification model has corresponding nameplate type；
In the multiple candidate identification model, candidate identification model corresponding with the nameplate type is extracted, as
The Text region model.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain text candidate frame；
Obtain the text confidence level of the text candidate frame；
The text candidate frame is filtered according to the text confidence level, obtains the Text region frame；
According to the Text region frame, the nameplate text is obtained.
In one embodiment, it is also performed the steps of when processor executes computer program
It identifies the Text region frame, obtains candidate character；
Obtain the matching degree of the candidate character Yu the nameplate text；
According to the matching degree, determine that the candidate character is the nameplate text.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of power equipment nameplate recognition methods characterized by comprising
Obtain nameplate image；
Identify the nameplate type in the nameplate image；
According to the nameplate type, corresponding Text region model is determined, and utilize Text region model identification nameplate text
Word.
2. the method according to claim 1, wherein the nameplate image includes image-region, the identification institute
State the nameplate type in nameplate image, comprising:
By nameplate disaggregated model, the characteristics of image in described image region is extracted from the nameplate image；
According to the characteristics of image in described image region, nameplate region is identified；The nameplate region is the figure for including nameplate feature
As region；
According to the nameplate region, the nameplate type is determined.
3. according to the method described in claim 2, it is characterized in that, described determine nameplate type according to the nameplate region, packet
It includes:
According to the characteristics of image in the nameplate region, the nameplate region is evaluated, obtains nameplate region scoring；
It is scored according to the nameplate region, classifies to the nameplate region, obtain the nameplate type.
4. according to claim 1 to method described in 3, which is characterized in that it is described by nameplate disaggregated model, identify the nameplate
Before nameplate type in image, further includes:
Obtain a large amount of nameplate images；
Mark the nameplate region and the nameplate type in the nameplate image；
It will be trained in nameplate image input deep neural network model after mark, obtain the nameplate classification mould
Type.
5. determining corresponding text the method according to claim 1, wherein described according to the nameplate type
Identification model, comprising:
Obtain multiple candidate identification models；Candidate's identification model has corresponding nameplate type；
In the multiple candidate identification model, candidate identification model corresponding with the nameplate type is extracted, as described
Text region model.
6. the method according to claim 1, wherein described identify nameplate text, packet using Text region model
It includes:
Obtain text candidate frame；
Obtain the text confidence level of the text candidate frame；
The text candidate frame is filtered according to the text confidence level, obtains the Text region frame；
According to the Text region frame, the nameplate text is obtained.
7. according to the method described in claim 6, obtaining the nameplate it is characterized in that, described according to the Text region frame
Text, comprising:
It identifies the Text region frame, obtains candidate character；
Obtain the matching degree of the candidate character Yu the nameplate text；
According to the matching degree, determine that the candidate character is the nameplate text.
8. a kind of power equipment nameplate identification device, which is characterized in that described device includes:
Image collection module, for obtaining nameplate image；
Type identification module, for identification the nameplate type of the nameplate image；
Text region module for determining corresponding Text region model according to the nameplate type, and is known using the text
Other model identifies nameplate text.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In when the processor executes the computer program the step of method described in any one of realization 1 to 7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910405844.7A CN110110726A (en) | 2019-05-15 | 2019-05-15 | Power equipment nameplate identification method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910405844.7A CN110110726A (en) | 2019-05-15 | 2019-05-15 | Power equipment nameplate identification method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110110726A true CN110110726A (en) | 2019-08-09 |
Family
ID=67490380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910405844.7A Pending CN110110726A (en) | 2019-05-15 | 2019-05-15 | Power equipment nameplate identification method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110110726A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401289A (en) * | 2020-03-24 | 2020-07-10 | 国网上海市电力公司 | Intelligent identification method and device for transformer component |
| CN112364866A (en) * | 2020-11-17 | 2021-02-12 | 广东电网有限责任公司阳江供电局 | Power equipment data plate APP and applet recognition system |
| CN112418214A (en) * | 2020-11-06 | 2021-02-26 | 北京五八信息技术有限公司 | Vehicle identification code identification method and device, electronic equipment and storage medium |
| CN112580632A (en) * | 2020-12-24 | 2021-03-30 | 南方电网深圳数字电网研究院有限公司 | Nameplate identification method, nameplate identification system, electronic equipment and computer-readable storage medium |
| CN112651313A (en) * | 2020-12-17 | 2021-04-13 | 国网上海市电力公司 | Equipment nameplate double-intelligent identification method, storage medium and terminal |
| CN113392730A (en) * | 2021-05-31 | 2021-09-14 | 国网福建省电力有限公司 | Power distribution network equipment image identification method and computer readable storage medium |
| CN113591066A (en) * | 2021-07-23 | 2021-11-02 | 广州绿怡信息科技有限公司 | Equipment identity identification method and device |
| CN114118908A (en) * | 2021-11-15 | 2022-03-01 | 国网辽宁省电力有限公司阜新供电公司 | Electric power material acceptance judging system and method |
| CN114897581A (en) * | 2022-05-26 | 2022-08-12 | 平安国际融资租赁有限公司 | Method and device for surveying rental equipment, computer equipment and storage medium |
| WO2022222777A1 (en) * | 2021-04-23 | 2022-10-27 | 杭州睿胜软件有限公司 | Method and apparatus for identifying document |
| WO2023103894A1 (en) * | 2021-12-07 | 2023-06-15 | 广东电网有限责任公司东莞供电局 | Nameplate recognition model training method, nameplate recognition method, and related apparatuses |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002245404A (en) * | 2001-02-14 | 2002-08-30 | Fujitsu Ltd | Program and device for segmenting area |
| CN106557747A (en) * | 2016-11-15 | 2017-04-05 | 平安科技（深圳）有限公司 | The method and device of identification insurance single numbers |
| CN107577981A (en) * | 2016-07-04 | 2018-01-12 | 高德信息技术有限公司 | A kind of road traffic index identification method and device |
| CN108229463A (en) * | 2018-02-07 | 2018-06-29 | 众安信息技术服务有限公司 | Character recognition method based on image |
| CN108804971A (en) * | 2017-04-26 | 2018-11-13 | 联想新视界（天津）科技有限公司 | A kind of image identification system, augmented reality show equipment and image-recognizing method |
| CN109359647A (en) * | 2018-10-16 | 2019-02-19 | 翟红鹰 | Identify the method, equipment and computer readable storage medium of a variety of certificates |
| CN109446900A (en) * | 2018-09-21 | 2019-03-08 | 平安科技（深圳）有限公司 | Certificate authenticity verification method, apparatus, computer equipment and storage medium |
| CN109657671A (en) * | 2018-12-19 | 2019-04-19 | 深圳供电局有限公司 | Nameplate character recognition method and device, computer equipment and storage medium |
-
2019
- 2019-05-15 CN CN201910405844.7A patent/CN110110726A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002245404A (en) * | 2001-02-14 | 2002-08-30 | Fujitsu Ltd | Program and device for segmenting area |
| CN107577981A (en) * | 2016-07-04 | 2018-01-12 | 高德信息技术有限公司 | A kind of road traffic index identification method and device |
| CN106557747A (en) * | 2016-11-15 | 2017-04-05 | 平安科技（深圳）有限公司 | The method and device of identification insurance single numbers |
| CN108804971A (en) * | 2017-04-26 | 2018-11-13 | 联想新视界（天津）科技有限公司 | A kind of image identification system, augmented reality show equipment and image-recognizing method |
| CN108229463A (en) * | 2018-02-07 | 2018-06-29 | 众安信息技术服务有限公司 | Character recognition method based on image |
| CN109446900A (en) * | 2018-09-21 | 2019-03-08 | 平安科技（深圳）有限公司 | Certificate authenticity verification method, apparatus, computer equipment and storage medium |
| CN109359647A (en) * | 2018-10-16 | 2019-02-19 | 翟红鹰 | Identify the method, equipment and computer readable storage medium of a variety of certificates |
| CN109657671A (en) * | 2018-12-19 | 2019-04-19 | 深圳供电局有限公司 | Nameplate character recognition method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 齐力: "《公共安全大数据分析挖掘》", 31 December 2017, 上海科技技术出版社 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401289A (en) * | 2020-03-24 | 2020-07-10 | 国网上海市电力公司 | Intelligent identification method and device for transformer component |
| CN111401289B (en) * | 2020-03-24 | 2024-01-23 | 国网上海市电力公司 | Intelligent identification method and device for transformer component |
| CN112418214A (en) * | 2020-11-06 | 2021-02-26 | 北京五八信息技术有限公司 | Vehicle identification code identification method and device, electronic equipment and storage medium |
| CN112364866A (en) * | 2020-11-17 | 2021-02-12 | 广东电网有限责任公司阳江供电局 | Power equipment data plate APP and applet recognition system |
| CN112651313A (en) * | 2020-12-17 | 2021-04-13 | 国网上海市电力公司 | Equipment nameplate double-intelligent identification method, storage medium and terminal |
| CN112580632A (en) * | 2020-12-24 | 2021-03-30 | 南方电网深圳数字电网研究院有限公司 | Nameplate identification method, nameplate identification system, electronic equipment and computer-readable storage medium |
| WO2022222777A1 (en) * | 2021-04-23 | 2022-10-27 | 杭州睿胜软件有限公司 | Method and apparatus for identifying document |
| CN113392730A (en) * | 2021-05-31 | 2021-09-14 | 国网福建省电力有限公司 | Power distribution network equipment image identification method and computer readable storage medium |
| CN113591066A (en) * | 2021-07-23 | 2021-11-02 | 广州绿怡信息科技有限公司 | Equipment identity identification method and device |
| CN114118908A (en) * | 2021-11-15 | 2022-03-01 | 国网辽宁省电力有限公司阜新供电公司 | Electric power material acceptance judging system and method |
| WO2023103894A1 (en) * | 2021-12-07 | 2023-06-15 | 广东电网有限责任公司东莞供电局 | Nameplate recognition model training method, nameplate recognition method, and related apparatuses |
| CN114897581A (en) * | 2022-05-26 | 2022-08-12 | 平安国际融资租赁有限公司 | Method and device for surveying rental equipment, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110726A (en) | Power equipment nameplate identification method and device, computer equipment and storage medium | |
| CN109783785B (en) | Method and device for generating experiment detection report and computer equipment | |
| CN110334357A (en) | A kind of method, apparatus, storage medium and electronic equipment for naming Entity recognition | |
| CN110399800B (en) | License plate detection method and system based on deep learning VGG16 framework and storage medium | |
| CN109858414A (en) | A kind of invoice piecemeal detection method | |
| CN112926654A (en) | Pre-labeling model training and certificate pre-labeling method, device, equipment and medium | |
| CN107797989A (en) | Enterprise name recognition methods, electronic equipment and computer-readable recording medium | |
| CN110705489B (en) | Training method and device for target recognition network, computer equipment and storage medium | |
| CN110633751A (en) | Training method of car logo classification model, car logo identification method, device and equipment | |
| CN110222336A (en) | Analysis of financial statement method, apparatus, computer equipment and storage medium | |
| CN113344079B (en) | Image tag semi-automatic labeling method, system, terminal and medium | |
| CN111310829A (en) | Confusion matrix-based classification result detection method and device and storage medium | |
| CN115935344A (en) | Abnormal equipment identification method and device and electronic equipment | |
| CN117036843A (en) | Target detection model training method, target detection method and device | |
| CN115690514A (en) | Image recognition method and related equipment | |
| CN114240928A (en) | Board quality partition detection method, device and equipment and readable storage medium | |
| CN113283388B (en) | Training method, device, equipment and storage medium of living body face detection model | |
| WO2024159819A1 (en) | Training method, layout analysis method, quality assessment method, and apparatuses, device, and medium | |
| CN113591884B (en) | Method, device, equipment and storage medium for determining character recognition model | |
| CN111290953B (en) | Method and device for analyzing test logs | |
| CN112163400A (en) | Information processing method and device | |
| CN116824572A (en) | Small sample point cloud object identification method, system and medium based on global and part matching | |
| CN113128496B (en) | Method, device and equipment for extracting structured data from image | |
| CN115237859A (en) | Method, device and equipment for detecting quality of required document and storage medium | |
| CN111078984B (en) | Network model issuing method, device, computer equipment and storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 518001 power dispatching communication building, No. 4020 Shennan East Road, Shenzhen, Guangdong, Luohu District Applicant after: Shenzhen Power Supply Co.,Ltd. Applicant after: DINGXIN INFORMATION TECHNOLOGY Co.,Ltd. Address before: 518000 Xinzhou Power Dispatching Building, No. 39, Central Road, Futian District, Shenzhen City, Guangdong Province Applicant before: Shenzhen Power Supply Co.,Ltd. Applicant before: DINGXIN INFORMATION TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190809 |