CN108446621A - Bank slip recognition method, server and computer readable storage medium - Google Patents
Bank slip recognition method, server and computer readable storage medium Download PDFInfo
- Publication number
- CN108446621A CN108446621A CN201810208586.9A CN201810208586A CN108446621A CN 108446621 A CN108446621 A CN 108446621A CN 201810208586 A CN201810208586 A CN 201810208586A CN 108446621 A CN108446621 A CN 108446621A
- Authority
- CN
- China
- Prior art keywords
- bill
- picture
- bill picture
- training
- character
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/04—Billing or invoicing
-
- 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
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- 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
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Technology Law (AREA)
- Image Analysis (AREA)
- Character Discrimination (AREA)
Abstract
The invention discloses a kind of bank slip recognition methods, this method includes receiving bill picture to be identified, trained bill picture identification model handles the bill picture in advance, text detection is carried out to the bill picture using text detection model trained in advance, determine that the bill picture includes the target character region of character and the field to be identified that the target character region includes, for the field to be identified, corresponding text identification model is called to carry out character recognition, the character information for including with the multiple field to be identified identified respectively in the target character region, and the result of identification is exported.The present invention also provides a kind of server and computer readable storage mediums.Bank slip recognition method, server and computer readable storage medium provided by the invention can improve the digitlization efficiency of bill, reduce the working strength of business personnel, improve accuracy or the fining of data.
Description
Technical field
The present invention relates to field of image recognition more particularly to a kind of bank slip recognition method, server computer readable storages
Medium.
Background technology
Nowadays with the economic development and improvement of people's living standards, more and more people select purchase medical treatment, commercially,
The insurances such as finance.Some of which insurance company has slowly started self-service Claims Resolution business, for example user is carrying out medical Claims Resolution process
In, it is only necessary to outpatient service or in hospital invoice are taken pictures and upload to insurance company's system, insurance company business personnel can upload user
In data input to Claims Resolution system on invoice picture, to carry out next step operation, this mode greatly facilitates user's progress
The process of Claims Resolution.But on the other hand, the operating pressure in terms of insurance company is also increased.Problem, which is mainly manifested in, to be needed to spend
A large amount of manpower handles the bill images of user's upload, and when many business personnel also can generate sense tired out to single work,
So that data inputting error rate increases.
By introducing bank slip recognition technology, the digitlization efficiency of bill can be improved under certain condition, reduces business people
The working strength of member, improves accuracy or the fining of data.Different from traditional bill scanning recognition technology, on user takes pictures
The identification difficulty of the bill picture of biography greatly increases, and the photo environment for being mainly manifested in user is different, illumination, rotation angle, figure
Image sharpness, is blocked or even the performance level of bill is all different, these factors are all brought greatly to bank slip recognition process
Challenge.
Invention content
In view of this, the present invention proposes a kind of bank slip recognition method and server, with solve how quickly, accurately identify ticket
The problem of according to picture.
First, to achieve the above object, the present invention proposes a kind of bank slip recognition method, and the method comprising the steps of：
Bill picture to be identified is received, trained bill picture identification model handles the bill picture in advance
The bill picture that obtains that treated；
Using text detection model trained in advance, treated that bill picture carries out text detection to described, determine described in
Treated, and bill picture includes the target character region of character and the field to be identified that the target character region includes；
For the field to be identified, corresponding text identification model is called to carry out character recognition, the text identification mould
Type identifies the character information that the field to be identified includes, and generates confidence level for the character information of identification；And
The confidence level is compared with preset confidence threshold value, if the confidence level is higher than the confidence level threshold
Value, then export the character information that the target character region includes according to presetting method, if the confidence level is less than the confidence
Threshold value is spent, then the document picture is tested identification by third party, and the result that the third party inspection is identified is defeated
Go out；
Wherein, the presetting method includes：Retain bill odd numbers top ten；Use the cosine similarity in tf-idf algorithms
Match the best hospital name of hospital's field；The date is extracted as the date in the original character string result of algorithm output；
The big writing of Chinese characters amount of money is carried out to turn Arabic numerals processing；It removes irrelevant character and retains 2 significant digits, it is defeated to algorithm
All amount of money parts gone out carry out uniform format.
Preferably, the bill picture identification model, which to the bill picture handle, includes：To the bill picture
Classification processing, denoising, correction process and interception bill processing are carried out, the classification processing, denoising, correction will be passed through
The bill picture of processing and interception bill processing is as treated bill picture.
Preferably, the classification, which is handled, includes：The bill picture is divided into outpatient service bill, in hospital bill and other
Three kinds of classifications of class bill；The denoising is：Picture smooth treatment and wavelet filtering processing are carried out to the bill picture；Institute
It includes step to state correction process：The bill central point and seal central point in the bill picture for determining the bill picture
Position determines the rotation angle of bill according to the relative position relation of the bill central point and seal central point, according to the angle
Bill is rotated to horizontal direction by degree；The interception bill is：Bill is intercepted from original document picture and is come out, removal is original
The background picture of bill picture.
Preferably, the bill picture identification model be depth convolutional neural networks, the depth convolutional neural networks be
Chosen in the environment of CaffeNet based on depth convolutional neural networks SSD (Single Shot MultiBox Detector)
Algorithm model, the training process of the bill picture identification model includes step：
Bill picture classification is preset for each prepare preset quantity be labeled with the corresponding other bill picture of picture category
Sample；
The corresponding picture sample of each described default picture classification is divided into the training subset and the second ratio of the first ratio
The verification subset of example mixes the picture sample in each training subset to obtain training set, and by each verification
Picture sample in subset is mixed to be verified collection；
The bill picture identification model is trained using the training set；And
Using it is described verification collection verification training the bill picture identification model accuracy rate, if accuracy rate be more than or
Equal to default accuracy rate, then training terminates；If accuracy rate is less than the default accuracy rate, increase each described default picture
The quantity of the corresponding picture sample of classification, and re-execute above step；
Wherein, the default picture classification includes outpatient service bill and bill in hospital, and the preset quantity is 1000, described
First ratio and the second ratio are 80%, 20%.
Preferably, the text detection model is CTPN (the Connectionist Text based on CaffeNet
Proposal Network) model, the text detection model carries out area to the character zone of treated the bill picture
Domain identifies, treated that bill on piece identifies comprising character information and small frame that fixed width is preset value from described, will
Include that the small frame of character information is stitched together the target line word to be formed comprising character information according to sequencing in same a line
Accord with region, wherein the preset value is 16 pixel wides.
Preferably, the training process of the text detection model includes step：
S1 obtains the bill picture sample of preset quantity for field to be identified；
The difference of the second preset quantity is arranged every the pixel of the first preset quantity in each bill picture sample in S2
Depth-width ratio and fixed width be preset value small frame, to including the field to be identified in each bill picture sample
The small frame of some or all of character information is marked, by the bill picture sample of the character information comprising the field to be identified
It is included into the first training set, and the bill picture sample of the character information not comprising the field to be identified is included into the second training set；
S3 extracts the bill picture sample of the first preset ratio from the first training set and the second training set respectively
As samples pictures to be trained, and using remaining bill picture sample in the first training set and the second training set as to be verified
Samples pictures；
S4 carries out model training using each samples pictures to be trained of extraction, to generate the text identification model,
And the text identification model of generation is verified using each samples pictures to be verified；And
S5, if being verified rate is more than or equal to predetermined threshold value, training is completed, if being verified rate is less than predetermined threshold value,
Then increase the quantity of document picture sample, and repeats step S2, S3, S4；
Wherein, the preset quantity is 100,000, and first preset quantity is 16, and second preset quantity is 10, institute
It is 16 pixel wides to state preset value, and first preset ratio is 80%, and the predetermined threshold value is 98%.
Preferably, the text identification model includes convolutional layer, circulating net network layers and translation layer, the text identification model
Include to the step of target character region progress character recognition：
The convolutional layer carries out feature extraction to treated the bill picture stripping and slicing；
On all channels of convolutional layer output, from left to right splices by column, obtain characteristic sequence；
The obtained characteristic sequence is put into the identification in the circulating net network layers into line character；
The translation layer handles the result of identification, according to the recognition result that character dictionary creation is last.
8. bank slip recognition method as claimed in claim 7, which is characterized in that the training process of the text identification model
Including step：
The bill picture sample for obtaining preset quantity, is divided into the first data by the bill picture sample according to preset ratio
Collection and the second data set, the picture sample quantity in first data set are more than the picture sample number in second data set
Amount, first data set is as training set, and second data set is as test set；And
Picture sample in first data set is sent into the text identification model and carries out model training, is often carried out pre-
If number of iterations, the text identification model is tested using second data set, if text when test is known
Other model dissipates the error of bill picture recognition, then adjusting training parameter and re -training, text when making to train
Error convergence of the identification model to the identification of bill picture.
In addition, to achieve the above object, the present invention also provides a kind of server, including memory, processor and it is stored in
On the memory and the bank slip recognition system that can run on the processor, the bank slip recognition system is by the processor
It is realized such as the step of above-mentioned bank slip recognition method when execution.
Further, to achieve the above object, the present invention also provides a kind of computer readable storage medium, the computers
Readable storage medium storing program for executing is stored with bank slip recognition system, and the bank slip recognition system can be executed by least one processor, so that institute
At least one processor is stated to execute such as the step of above-mentioned bank slip recognition method.
Compared to the prior art, bank slip recognition method, server and computer readable storage medium proposed by the invention,
Bill picture to be identified is received first, and the bill picture identification model trained in advance is according to preset rules to the bill picture
It is pre-processed；Secondly, text detection carried out to the bill picture using text detection model trained in advance, described in acquisition
Bill picture includes the target character region of character, and the target character region includes multiple fields to be identified；Again, for
The target character region calls corresponding text identification model to carry out character recognition, to identify the target character respectively
The character information that the multiple field to be identified in region includes；Finally, mesh described in the text identification Model Identification is obtained
The confidence level that the generates when character information that mark character zone includes, by the confidence level of acquisition and preset confidence threshold value into
Row compares, if the confidence level is higher than the confidence threshold value, exporting the target character region according to presetting method includes
Character information, if the confidence level be less than the confidence threshold value, the document picture is tested by third party
Identification, and the result that the third party inspection is identified exports.Using bank slip recognition method proposed by the invention, server and
Computer readable storage medium can improve the digitlization efficiency of bill, reduce the working strength of business personnel, improve data
Accuracy or fining, also, combine deep learning algorithm and third party's auxiliary that can more accurately identify bill, compared to
The prior art, the present invention is more convenient, quick, accurate, and significantly reduces cost.
Description of the drawings
Fig. 1 is the schematic diagram of one optional hardware structure of server of the present invention；
Fig. 2 is the program module schematic diagram of bank slip recognition system first embodiment of the present invention；
Fig. 3 is the program module schematic diagram of bank slip recognition system second embodiment of the present invention；
Fig. 4 is the flow diagram of bank slip recognition method first embodiment of the present invention；
Fig. 5 is the flow diagram of bank slip recognition method second embodiment of the present invention；
Fig. 6 is the flow diagram of bank slip recognition method 3rd embodiment of the present invention；
Fig. 7 is the flow diagram of bank slip recognition method fourth embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
The every other embodiment obtained is put, shall fall within the protection scope of the present invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is used for description purposes only, and cannot
It is interpreted as indicating or implying its relative importance or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include at least one of the features.In addition, the skill between each embodiment
Art scheme can be combined with each other, but must can be implemented as basis with those of ordinary skill in the art, when technical solution
Will be understood that the combination of this technical solution is not present in conjunction with there is conflicting or cannot achieve when, also not the present invention claims
Protection domain within.
As shown in fig.1, being the schematic diagram of 1 one optional hardware structure of server of the present invention.
In the present embodiment, the server 1 may include, but be not limited only to, and can be in communication with each other connection by system bus and deposit
Reservoir 11, processor 12, network interface 13.It should be pointed out that Fig. 1 illustrates only the server 1 with component 11-13, but
Be it should be understood that, it is not required that implement all components shown, the implementation that can be substituted is more or less component.
Wherein, the server 1 can be rack-mount server, blade server, tower server or cabinet-type clothes
The computing devices such as business device, which can be independent server, can also be the server set that multiple servers are formed
Group.
The memory 11 include at least a type of readable storage medium storing program for executing, the readable storage medium storing program for executing include flash memory,
Hard disk, multimedia card, card-type memory (for example, SD or DX memories etc.), random access storage device (RAM), static random are visited
It asks memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), may be programmed read-only deposit
Reservoir (PROM), magnetic storage, disk, CD etc..In some embodiments, the memory 11 can be the server
1 internal storage unit, for example, the server 1 hard disk or memory.In further embodiments, the memory 11 can also
It is the External memory equipment of the server 1, such as the plug-in type hard disk being equipped on the server 1, intelligent memory card (Smart
Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card) etc..Certainly, described
Memory 11 can also both include the server 1 internal storage unit and also including its External memory equipment.In the present embodiment,
The memory 11 is installed on the operating system and types of applications software of the server 1 commonly used in storage, such as bill is known
The program code etc. of other system 2.It has exported or will export in addition, the memory 11 can be also used for temporarily storing
Various types of data.
The processor 12 can be in some embodiments central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips.The processor 12 is commonly used in the control clothes
The overall operation of business device 1.In the present embodiment, the processor 12 for run the program code stored in the memory 11 or
Person handles data, such as runs the bank slip recognition system 2 etc..
The network interface 13 may include radio network interface or wired network interface, which is commonly used in
Communication connection is established between the server 1 and other electronic equipments.
So far, oneself is through describing the hardware configuration and function of relevant device of the present invention in detail.In the following, above-mentioned introduction will be based on
It is proposed each embodiment of the present invention.
First, the present invention proposes a kind of bank slip recognition system 2.
As shown in fig.2, being the Program modual graph of 2 first embodiment of bank slip recognition system of the present invention.
In the present embodiment, the bank slip recognition system 2 includes a series of computer program being stored on memory 11
The bank slip recognition operation of various embodiments of the present invention may be implemented when the computer program instructions are executed by processor 12 in instruction.
In some embodiments, the specific operation realized based on the computer program instructions each section, bank slip recognition system 2 can be with
It is divided into one or more modules.For example, in fig. 2, the bank slip recognition system 2 can be divided into preprocessing module
21,24 grades of text detection module 22, text identification module 23, comparison module output modules 25.Wherein：
The preprocessing module 21 receives bill picture to be identified, instructs in advance for receiving bill picture to be identified
Experienced bill picture identification model is handled to obtain treated bill picture to the bill picture.
Specifically, the preprocessing module 21 receives bill picture to be identified, according to default step to the bill
Piece is pre-processed, and the default step can be classified to the bill picture, denoising, correction, intercept bill, according to
The default step, the bill picture identification model trained in advance carry out classification processing to the bill picture, denoising, rectify
Positive processing and interception bill processing.
Specifically, the classification processing is described convenient for subsequent processing for the bill picture received to be classified
Denoising can eliminate the noise spot of bill picture, and image can be made to generate less fuzzy, the bill possibility that user uploads
Can be there are many rotation angle, bill must be rotated to and is correctly oriented by we, next step operation could be carried out, to bill picture
Carry out correction process can make bill rotates to be correctly oriented, the interception bill for by bill from original document picture
Interception comes out, and original document picture includes bill and background picture, and the interference of background picture can be removed by intercepting bill.
Specifically, the bill picture identification model is depth convolutional neural networks (for example, the depth convolutional neural networks
Can be to be chosen in the environment of CaffeNet based on depth convolutional neural networks SSD (Single Shot MultiBox
Detector) algorithm model), basic network topology has used the network structure of VGG16, then eliminates rearmost full connection
Layer, adds the characteristic layer of six additional different scales.
The depth convolutional neural networks model that the present invention uses is by 1 input layer, 13 convolutional layers, 5 pond layers, 2
Full articulamentum, 1 classification layer are constituted.The detailed construction of the depth convolutional neural networks model is as shown in table 1.
Table 1
Wherein：Layer Name row indicate that each layer of title, Input table show that input layer, Conv indicate the convolution of model
Layer, Conv1 indicate that the 1st convolutional layer of model, MaxPool indicate that the maximum value pond layer of model, MaxPool1 indicate model
The 1st maximum value pond layer, Fc indicate model in full articulamentum, Fc1 indicate model in the 1st full articulamentum, Softmax
Indicate Softmax graders；Batch Size indicate the input picture number of current layer；Kernel Size indicate current layer volume
The scale (for example, Kernel Size can be equal to 3, indicating that the scale of convolution kernel is 3x 3) of product core；Stride Size are indicated
The moving step length of convolution kernel finishes the distance that a convolution is moved to next convolution position later；Pad Size expressions pair
The size of image completion among current network layer.
The text detection module 22, after using text detection model trained in advance to the processing of preprocessing module 21
Bill picture carry out text detection, determine that the bill picture includes the target character region of character and the target character
The field to be identified that region includes.
Specifically, the text detection model uses CTPN (the Connectionist Text based on CaffeNet
Proposal Network) model, CTPN model structures include VGG16 (convolutional neural networks), LSTM, full articulamentum etc.,
In, VGG is in the network developed from Alex-net, and LSTM (Long Short-Term Memory) is shot and long term memory net
Network is a kind of time recurrent neural network.
Include to the step of bill picture progress text detection using the text detection model：
Depth characteristic is obtained using VGG16；
Text proposal (part for line of text) are detected with the frame of fixed width (for example, 16 pixel wides),
And with a line frame, corresponding feature conspires to create sequence to handle, is input in LSTM；
It is returned and is classified using full articulamentum, and qualified text proposal are merged into final text
This line, the line of text, that is, character zone.
CTPN makes full use of text line to have the characteristics that context connection, in conjunction with RNN and CNN, improves text detection
Precision.
The text identification module 23 calls corresponding text identification model to carry out for being directed to the field to be identified
Character recognition, the text identification Model Identification go out the character information that the field to be identified includes, and for the described of identification
Character information generates confidence level.
Specifically, the model structure of the CNN+LSTM+CTC of the text identification model based on MXNet, wherein CNN
(Convolutional Neural Networks) is convolutional neural networks, CTC (Connectionist temporal
Classification last layer for) being connected on CNN networks is used for used in Sequence Learning, the structure packet of the text identification model
Include convolutional layer (Convolutional Layers), circulating net network layers (Recurrent Layers) and translation layer
(Transcription Layer), the model include to the step of target character region progress character recognition：
Convolutional layer (Convolutional Layers) carries out feature extraction to input picture stripping and slicing；
On all channels of the last one convolutional layer output, from left to right splices by column, obtain characteristic sequence；
Obtained characteristic sequence is put into the identification in circulating net network layers (Recurrent Layers) into line character；
The result of identification is handled by translation layer (Transcription Layer), according to character dictionary creation
Last recognition result.
The training step of the model includes：
The bill picture sample for obtaining preset quantity (for example, 100,000), by the bill picture sample according to X：Y (for example,
8:2) ratio is divided into the first data set and the second data set, and the picture sample quantity in the first data set is more than the second data set
In picture sample quantity, the first data set is as training set, and the second data set is as test set；
Picture sample in first data set is sent into text identification model and carries out model training, at regular intervals (example
As often carried out 1000 iteration), model is tested using the second data set, to assess currently trained modelling effect.It surveys
When examination, character information identification is carried out using the picture in obtained the second data set of model pair of training, and and test picture
Name, which is referred to as, to be compared, to calculate the error of the result and annotation results of identification.If model when test is to the mistake of bill picture recognition
Difference dissipates, then adjusting training parameter and re -training, and model receives the error of the identification of bill picture when enabling to train
It holds back.After error convergence, terminate model training, the model of generation is as final text identification model.
Specifically, the text identification model is when carrying out character recognition, can be generated pair to the character information identified
The confidence level answered.Obtain confidence level the step of can be：For different fields to be identified, set using corresponding formula estimation broad sense
Reliability；The confidence level is obtained according to generalized confidence.It is obtained for example, can be calculated at a distance from representative sample according to unknown sample
The generalized confidence is taken, multilayer feedforward neural network can also be used to obtain generalized confidence, the method that statistics can be used
Deduce the confidence level from the generalized confidence.It should be noted that technical staff can select suitable public affairs as needed
Formula and tool needle generate corresponding confidence level to the character information of identification, and which is not described herein again.
The comparison module 24, for the confidence level obtained to be compared with preset confidence threshold value.
Specifically, if the confidence level is higher than the confidence threshold value, retain the word that the target character region includes
Information is accorded with, if the confidence level is less than the confidence threshold value, the document picture is tested identification by third party.
The output module 25, the output for carrying out character identification result according to the output valve of comparison module 24, if than
The confidence level is inputted compared with device and is higher than the confidence threshold value, then exporting the target character region according to preset rules includes
Character information is tested the document picture knowledge by third party if the confidence level is less than the confidence threshold value
Not, and by the third party inspection result identified exports.
Specifically, the preset rules include：The retainable top ten of bill odd numbers；Hospital's field uses tf-idf algorithms
In cosine similarity go to match best hospital name；Day part extracts in the original character string result that algorithm exports
Date；The big writing of Chinese characters amount of money carries out turning Arabic numerals processing；All amount of money parts have carried out format to algorithm output result
It is unified, it removes irrelevant character and retains 2 significant digits.
Specifically, the third party can be crowdsourcing platform, and crowdsourcing refers to a company or mechanism by employee in the past
The task of execution is contracted out to unspecific (and being typically large-scale) public network in the form of freedom is voluntary and does
Method.Specifically, the crowdsourcing platform mainly completes following work：
1, the exploitation of algorithm is assisted, is specifically included：Data mark, and desk checking result is returned to identification by data cleansing
Learning system continues to train, the accuracy rate of identification model is continuously improved；
2, algorithm is manually combined, and for complex fields, algorithm realizes detection text block, then is difficult to by manually solving annual reporting law
The part of completion, such as by manually going to realize complicated text dividing and uncommon Text region；
3, artificial correction algorithm output as a result, by confidence level it is low algorithm output result be transferred to crowdsourcing, manually carry out again
Verification, to improve final recognition accuracy.
Specifically, the third party is in human assistance algorithm exports outcome procedure, and in order to ensure accuracy rate, we take
The mechanism that task is provided at random, and each task is issued to a certain number of users, then take wherein most people is identical to answer
Case, that is, recycle result finally by the mechanism of cross validation.
As shown in fig.3, being the Program modual graph of 2 second embodiment of bank slip recognition system of the present invention.In the present embodiment, institute
Preprocessing module 21 includes sort module 210, denoising module 220, rectification module 230 and interception in the bank slip recognition system 2 stated
Module 240.
Specifically, the sort module 210 is used for after receiving pending bill picture, utilizes bill trained in advance
The bill classification in the picture that receives is identified in picture recognition model, and exports the classification recognition result of bill (for example, doctor
The classification for treating bill includes outpatient service bill, in hospital bill and other class bills).
Specifically, the denoising module 220 carries out picture smooth treatment to the bill picture and wavelet filtering is handled,
In, neighborhood averaging and median filtering method can be used in described image smoothing processing, and neighborhood averaging is by a pixel and its neighbour
The average value of all pixels is assigned to corresponding pixel in output image in domain, and smooth to achieve the purpose that, process is to make one
A window slides on the image, and the average value of each point value replaces in the value window of window center position, i.e., with several pixels
Average gray replaces the gray scale of a pixel.The medium filtering is a kind of can effectively to inhibit based on sequencing statistical is theoretical
The nonlinear smoothing of noise filters.Its filtering principle is:A neighborhood of a point centered on some pixel is determined first, generally
Then the gray value of each pixel in neighborhood is ranked up by Square Neighborhood, take the new value of pixel grey scale centered on median, this
In neighborhood be commonly known as window；It, can be with using median filtering algorithm after window carries out mobile up and down in the picture
Image is smoothed well.The output pixel of medium filtering be determined by the median of neighborhood image, thus in
It is so sensitive that value filtering can not show a candle to average value to limit pixel value (the larger pixel with surrounding pixel gray value difference), so as to
To eliminate isolated noise spot, image can be made to generate less obscure.
Specifically, the rectification module 230 makes bill rotates to be correctly oriented bill picture progress correction process.
Specifically, bill is intercepted from original document picture and is come out by the interception module 240.
In addition, the present invention also proposes a kind of bank slip recognition method.
As shown in fig.4, being the flow diagram of bank slip recognition method first embodiment of the present invention.In the present embodiment,
The execution sequence of the step in flow chart shown in fig. 5 can change according to different requirements, and certain steps can be omitted.
Step S110 receives bill picture to be identified, and trained bill picture identification model is to the bill in advance
Piece is handled.
Specifically, processing mode includes being classified to the bill picture, denoising, correction, intercepting bill.
Step S120 carries out text detection to the bill picture using text detection model trained in advance, determines institute
State the target character region that bill picture includes character and the field to be identified that the target character region includes.
Specifically, region recognition is carried out to the character zone of the bill picture, packet is identified from the bill on piece
Containing the small frame that character information and fixed width are preset value (for example, 16 pixel wides), and will be at the character information that be included
It is stitched together according to sequencing the target line character zone to be formed comprising character information in the small frame of same a line.
Specifically, concretely following steps are identified to the bill picture of input：
First, obtain characteristics map (W*H*C) with preceding 5 convolutional layers of VGG16
Second, the feature of the window of 3*3*C is taken on each position of the characteristics map of the 5th each convolutional layer, these features
It will be used to predict the corresponding classification informations of the anchor of position k, location information.
The feature (W*3*3*C) of the corresponding 3*3*C of all windows of every a line is input in LSTM, obtains W* by third
256 output
4th, the W*256 of LSTM is input to the full articulamentum of 512 dimensions
5th, full articulamentum feature is input to three classification or returns in layer, because having given tacit consent to each anchor here
Width be 16, and no longer change.It is certain to return the width of rectangle frames out.
6th, with simple line of text construction algorithm, the elongated rectangle in the proposal for the word that classification is obtained
Frame is merged into line of text.
Step S130 calls corresponding text identification model to carry out character recognition for the field to be identified, with respectively
Identify the character information and obtain the text identification that the multiple field to be identified in the target character region includes
The confidence level generated when the character information that target character region described in Model Identification includes.
The confidence level of acquisition is compared by step S140 with preset confidence threshold value, if the confidence level is high
In the confidence threshold value, then the character information that the target character region includes is exported according to presetting method, if the confidence
Degree is less than the confidence threshold value, then the document picture is tested identification by third party, and the third party is examined
Test the result output of identification.
As shown in figure 5, being the flow diagram of the second embodiment of bank slip recognition method of the present invention.In the present embodiment, institute
It includes step to state pretreatment in the step S110 of bank slip recognition method：
Step S210 classifies to the bill picture.
Step S220 carries out denoising to the bill picture.
Step S230 corrects the bill picture.
Specifically, the correction process includes step：
Determine that the position of the seal central point in bill is clicked at bill center；
According to the relative position relation of bill central point and seal central point, the rotation angle of bill is determined；
Bill is rotated to horizontal direction come (being rotated clockwise or counter-clockwise) according to the angle.
Step S240 carries out interception bill to the bill picture.
As shown in fig. 6, being the flow diagram of the 3rd embodiment of bank slip recognition method of the present invention.In the present embodiment, institute
The training step for stating the text detection model in the step S120 of bank slip recognition method includes：
Step S310, for each default bill picture classification prepare preset quantity to be labeled with corresponding picture category other
Bill picture sample.
Specifically, the default picture classification includes outpatient service bill and bill, the preset quantity are 1000 in hospital.
The corresponding picture sample of each described default picture classification is divided into the training subset of the first ratio by step S320
With the verification subset of the second ratio, the picture sample in each training subset is mixed to obtain training set, and will be described
Picture sample in each verification subset is mixed to be verified collection.
Specifically, first ratio and the second ratio are 80%, 20%.
Step S330 trains the bill picture identification model using the training set.
Step S340, using the accuracy rate of the bill picture identification model of the verification collection verification training, if accurately
Rate is more than or equal to default accuracy rate, then training terminates；If accuracy rate is less than the default accuracy rate, increase described each
The quantity of the corresponding picture sample of a default picture classification, and re-execute above step.
Specifically, the default accuracy rate can be 90%.
As shown in fig. 7, being the flow diagram of the 3rd embodiment of bank slip recognition method of the present invention.In the present embodiment, institute
It includes that character in character zone is known to bill picture to state text identification model in the step S130 of bank slip recognition method
Other step includes：
Step S410, the convolutional layer carry out feature extraction to the bill picture stripping and slicing.
Step S420 from left to right splices on all channels of convolutional layer output, obtains characteristic sequence by column.
The obtained characteristic sequence is put into the identification in the circulating net network layers into line character by step S430.
Step S440, the translation layer handle the result of identification, according to the identification knot that character dictionary creation is last
Fruit.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be expressed in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal equipment (can be mobile phone, computer, clothes
Be engaged in device, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of bank slip recognition method is applied to server, which is characterized in that the method includes the steps：
Bill picture to be identified is received, the bill picture is handled using bill picture identification model trained in advance
The bill picture that obtains that treated；
Using text detection model trained in advance, treated that bill picture carries out text detection to described, determines the processing
Bill picture afterwards includes the target character region of character and the field to be identified that the target character region includes；
For the field to be identified, corresponding text identification model is called to carry out character recognition, the text identification model is known
Do not go out the character information that the field to be identified includes, and confidence level is generated for the character information of identification；And
The confidence level is compared with preset confidence threshold value, if the confidence level is higher than the confidence threshold value,
The character information that the target character region includes is exported according to presetting method, if the confidence level is less than the confidence level threshold
Value is then tested the document picture identification by third party, and the result output that the third party inspection is identified；
Wherein, the presetting method includes：Retain bill odd numbers top ten；It is matched using the cosine similarity in tf-idf algorithms
The best hospital name of hospital's field；The date is extracted as the date in the original character string result of algorithm output；It will be big
The writing of Chinese characters amount of money carries out turning Arabic numerals processing；It removes irrelevant character and retains 2 significant digits, to algorithm output
All amount of money parts carry out uniform format.
2. bank slip recognition method as described in claim 1, which is characterized in that the bill picture identification model is to the bill
Picture carries out processing：Classification processing, denoising, correction process and interception bill processing are carried out to the bill picture,
It will be used as that treated by the bill picture of the classification processing, denoising, correction process and interception bill processing
Bill picture.
3. the bank slip recognition method stated such as claim 2, which is characterized in that the classification, which is handled, includes：By the bill picture
It is divided into outpatient service bill, in hospital three kinds of classifications of bill and other class bills；The denoising is：To the bill picture into
Row picture smooth treatment and wavelet filtering processing；The correction process includes step：Determine the bill center of the bill picture
The position of point and the seal central point in the bill picture, according to the relative position of the bill central point and seal central point
Relationship determines the rotation angle of bill, and bill is rotated to horizontal direction according to the angle；The interception bill is：By bill
It intercepts and comes out from original document picture, remove the background picture of original document picture.
4. the bank slip recognition method as described in claim 1-3, which is characterized in that the bill picture identification model is rolled up for depth
Product neural network, which is to be chosen in the environment of CaffeNet based on depth convolutional neural networks
The algorithm model of SSD (Single Shot MultiBox Detector), the training process packet of the bill picture identification model
Include step：
Bill picture classification is preset for each prepare preset quantity be labeled with the corresponding other bill picture sample of picture category；
Each described default picture classification corresponding picture sample is divided into the training subset and the second ratio of the first ratio
Subset is verified, the picture sample in each training subset is mixed to obtain training set, and by each verification subset
In picture sample mixed be verified collection；
The bill picture identification model is trained using the training set；And
Using the accuracy rate of the bill picture identification model of the verification collection verification training, if accuracy rate is more than or equal to
Default accuracy rate, then training terminate；If accuracy rate is less than the default accuracy rate, increase each described default picture classification
The quantity of corresponding picture sample, and re-execute above step；
Wherein, the default picture classification includes outpatient service bill and bill in hospital, and the preset quantity is 1000, and described first
Ratio and the second ratio are 80%, 20%.
5. bank slip recognition method as described in claim 1, which is characterized in that the text detection model is based on CaffeNet
CTPN (Connectionist Text Proposal Network) model, after the text detection model is to the processing
The character zone of bill picture carry out region recognition, from it is described treated bill on piece identifies comprising character information and
Fixed width is the small frame of preset value, will be stitched together according to sequencing in small frame of the same a line comprising character information,
Form the target line character zone for including character information, wherein the preset value is 16 pixel wides.
6. bank slip recognition method as claimed in claim 5, which is characterized in that the training process of the text detection model includes
Step：
S1 obtains the bill picture sample of preset quantity for field to be identified；
S2, every the pixel of the first preset quantity in each bill picture sample, the difference of the second preset quantity of setting is high wide
Ratio and small frame that fixed width is preset value, to including the part of the field to be identified in each bill picture sample
Or the small frame of alphabet information is marked, and the bill picture sample of the character information comprising the field to be identified is included into
First training set, and the bill picture sample of the character information not comprising the field to be identified is included into the second training set；
S3 extracts the bill picture sample conduct of the first preset ratio from the first training set and the second training set respectively
Samples pictures to be trained, and using remaining bill picture sample in the first training set and the second training set as sample to be verified
This picture；
S4 carries out model training, to generate the text identification model, and profit using each samples pictures to be trained of extraction
The text identification model of generation is verified with each samples pictures to be verified；And
S5, if being verified rate is more than or equal to predetermined threshold value, training is completed, if being verified rate is less than predetermined threshold value, is increased
Add the quantity of document picture sample, and repeats step S2, S3, S4；
Wherein, the preset quantity is 100,000, and first preset quantity is 16, and second preset quantity is 10, described pre-
If value is 16 pixel wides, first preset ratio is 80%, and the predetermined threshold value is 98%.
7. bank slip recognition method as described in claim 1, which is characterized in that the text identification model includes convolutional layer, follows
Looped network network layers and translation layer, the text identification model include to the step of target character region progress character recognition：
The convolutional layer carries out feature extraction to treated the bill picture stripping and slicing；
On all channels of convolutional layer output, from left to right splices by column, obtain characteristic sequence；
The obtained characteristic sequence is put into the identification in the circulating net network layers into line character；
The translation layer handles the result of identification, according to the recognition result that character dictionary creation is last.
8. bank slip recognition method as claimed in claim 7, which is characterized in that the training process of the text identification model includes
Step：
Obtain preset quantity bill picture sample, by the bill picture sample according to preset ratio be divided into the first data set and
Second data set, the picture sample quantity in first data set are more than the picture sample quantity in second data set,
First data set is as training set, and second data set is as test set；And
Picture sample in first data set is sent into the text identification model and carries out model training, is often carried out default time
Number iteration, the text identification model is tested using second data set, if text identification mould when test
Type dissipates the error of bill picture recognition, then adjusting training parameter and re -training, text identification when making to train
Error convergence of the model to the identification of bill picture.
9. a kind of server, which is characterized in that the server includes memory, processor and is stored on the memory simultaneously
The bank slip recognition system that can be run on the processor is realized when the bank slip recognition system is executed by the processor as weighed
Profit requires the step of bank slip recognition method described in any one of 1-8.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has bank slip recognition system, the ticket
It can be executed by least one processor according to identifying system, so that at least one processor is executed as appointed in claim 1-8
The step of bank slip recognition method described in one.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810208586.9A CN108446621A (en) | 2018-03-14 | 2018-03-14 | Bank slip recognition method, server and computer readable storage medium |
| PCT/CN2018/089202 WO2019174130A1 (en) | 2018-03-14 | 2018-05-31 | Bill recognition method, server, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810208586.9A CN108446621A (en) | 2018-03-14 | 2018-03-14 | Bank slip recognition method, server and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108446621A true CN108446621A (en) | 2018-08-24 |
Family
ID=63194307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810208586.9A Pending CN108446621A (en) | 2018-03-14 | 2018-03-14 | Bank slip recognition method, server and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108446621A (en) |
| WO (1) | WO2019174130A1 (en) |
Cited By (125)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117848A (en) * | 2018-09-07 | 2019-01-01 | 泰康保险集团股份有限公司 | A kind of line of text character identifying method, device, medium and electronic equipment |
| CN109241271A (en) * | 2018-08-30 | 2019-01-18 | 天津做票君机器人科技有限公司 | A kind of method that negotiation by draft robot identifies due date of bill in natural language |
| CN109461247A (en) * | 2018-10-29 | 2019-03-12 | 北京慧流科技有限公司 | Note validating method and device, electronic equipment and storage medium |
| CN109542649A (en) * | 2018-11-23 | 2019-03-29 | 于兴虎 | A method of image memory is quickly shared across language under vision servo system |
| CN109583443A (en) * | 2018-11-15 | 2019-04-05 | 四川长虹电器股份有限公司 | A kind of video content judgment method based on Text region |
| CN109637000A (en) * | 2018-10-23 | 2019-04-16 | 深圳壹账通智能科技有限公司 | The invoice method of inspection and device, storage medium, electric terminal |
| CN109635796A (en) * | 2018-11-20 | 2019-04-16 | 泰康保险集团股份有限公司 | Recognition methods, device and the equipment of questionnaire |
| CN109635627A (en) * | 2018-10-23 | 2019-04-16 | 中国平安财产保险股份有限公司 | Pictorial information extracting method, device, computer equipment and storage medium |
| CN109670494A (en) * | 2018-12-13 | 2019-04-23 | 深源恒际科技有限公司 | A kind of Method for text detection and system of subsidiary recognition confidence |
| CN109685100A (en) * | 2018-11-12 | 2019-04-26 | 平安科技（深圳）有限公司 | Character identifying method, server and computer readable storage medium |
| CN109784235A (en) * | 2018-12-29 | 2019-05-21 | 广东益萃网络科技有限公司 | Method for automatically inputting, device, computer equipment and the storage medium of paper form |
| CN109784339A (en) * | 2018-12-13 | 2019-05-21 | 平安普惠企业管理有限公司 | Picture recognition test method, device, computer equipment and storage medium |
| CN109829437A (en) * | 2019-02-01 | 2019-05-31 | 北京旷视科技有限公司 | Image processing method, text recognition method, device and electronic system |
| CN109858420A (en) * | 2019-01-24 | 2019-06-07 | 国信电子票据平台信息服务有限公司 | A kind of bill processing system and processing method |
| CN109872444A (en) * | 2019-02-27 | 2019-06-11 | 杭州睿琪软件有限公司 | A kind of bank slip recognition method and device |
| CN109886077A (en) * | 2018-12-28 | 2019-06-14 | 北京旷视科技有限公司 | Image-recognizing method, device, computer equipment and storage medium |
| CN109886257A (en) * | 2019-01-30 | 2019-06-14 | 四川长虹电器股份有限公司 | Using the method for deep learning correction invoice picture segmentation result in a kind of OCR system |
| CN109948549A (en) * | 2019-03-20 | 2019-06-28 | 深圳市华付信息技术有限公司 | OCR data creation method, device, computer equipment and storage medium |
| CN109978890A (en) * | 2019-02-25 | 2019-07-05 | 平安科技（深圳）有限公司 | Target extraction method, device and terminal device based on image procossing |
| CN110070042A (en) * | 2019-04-23 | 2019-07-30 | 北京字节跳动网络技术有限公司 | Character recognition method, device and electronic equipment |
| CN110109922A (en) * | 2019-04-04 | 2019-08-09 | 平安普惠企业管理有限公司 | Performance data acquisition methods, device, computer equipment and storage medium |
| CN110110123A (en) * | 2019-04-04 | 2019-08-09 | 平安科技（深圳）有限公司 | The training set update method and device of detection model |
| CN110135409A (en) * | 2019-04-04 | 2019-08-16 | 平安科技（深圳）有限公司 | The optimization method and device of identification model |
| CN110175610A (en) * | 2019-05-23 | 2019-08-27 | 上海交通大学 | A kind of bill images text recognition method for supporting secret protection |
| CN110189141A (en) * | 2019-04-17 | 2019-08-30 | 深圳壹账通智能科技有限公司 | Verification method, device and the computer equipment of invoice |
| CN110210400A (en) * | 2019-06-03 | 2019-09-06 | 上海眼控科技股份有限公司 | A kind of form document detection method and equipment |
| CN110210503A (en) * | 2019-06-14 | 2019-09-06 | 厦门历思科技服务有限公司 | A kind of seal recognition methods and device and equipment |
| CN110245658A (en) * | 2019-05-21 | 2019-09-17 | 深圳壹账通智能科技有限公司 | A kind of bank slip recognition method, apparatus, storage medium and server |
| CN110276253A (en) * | 2019-05-15 | 2019-09-24 | 中国科学院信息工程研究所 | A kind of fuzzy literal detection recognition method based on deep learning |
| CN110287952A (en) * | 2019-07-01 | 2019-09-27 | 中科软科技股份有限公司 | A kind of recognition methods and system for tieing up sonagram piece character |
| CN110399875A (en) * | 2019-07-31 | 2019-11-01 | 山东浪潮人工智能研究院有限公司 | A kind of form of general use information extracting method based on deep learning and pixel projection |
| CN110414927A (en) * | 2019-07-05 | 2019-11-05 | 西安网算数据科技有限公司 | A kind of bill processing automatically generates the method and device of voucher |
| CN110490193A (en) * | 2019-07-24 | 2019-11-22 | 西安网算数据科技有限公司 | Single Text RegionDetection method and ticket contents recognition methods |
| CN110490267A (en) * | 2019-08-23 | 2019-11-22 | 四川长虹电器股份有限公司 | A kind of bill method for sorting based on deep learning |
| CN110525069A (en) * | 2019-08-21 | 2019-12-03 | 珠海思格特智能系统有限公司 | A kind of OCR comparison system and its method for intelligent stamper machine |
| CN110647829A (en) * | 2019-09-12 | 2020-01-03 | 全球能源互联网研究院有限公司 | Bill text recognition method and system |
| CN110647956A (en) * | 2019-08-12 | 2020-01-03 | 深圳市华付信息技术有限公司 | Invoice information extraction method combined with two-dimensional code recognition |
| CN110717516A (en) * | 2019-09-06 | 2020-01-21 | 中国平安财产保险股份有限公司 | Bill image classification method and device and computer readable storage medium |
| CN110738203A (en) * | 2019-09-06 | 2020-01-31 | 中国平安财产保险股份有限公司 | Method and device for outputting field structuralization and computer readable storage medium |
| CN110765910A (en) * | 2019-10-14 | 2020-02-07 | 西安网算数据科技有限公司 | Bill region identification method and device in dense scene |
| CN110807455A (en) * | 2019-09-19 | 2020-02-18 | 平安科技（深圳）有限公司 | Bill detection method, device and equipment based on deep learning and storage medium |
| CN110895691A (en) * | 2018-09-12 | 2020-03-20 | 阿里巴巴集团控股有限公司 | Image processing method and device and electronic equipment |
| WO2020062804A1 (en) * | 2018-09-25 | 2020-04-02 | 平安科技（深圳）有限公司 | Method and apparatus for recognizing photographed image of driving license in natural scene and electronic device |
| CN110956133A (en) * | 2019-11-29 | 2020-04-03 | 上海眼控科技股份有限公司 | Training method of single character text normalization model, text recognition method and device |
| CN110991270A (en) * | 2019-11-15 | 2020-04-10 | 泰康保险集团股份有限公司 | Text recognition method and device, electronic equipment and storage medium |
| CN111027532A (en) * | 2019-12-11 | 2020-04-17 | 上海眼控科技股份有限公司 | System and method for identifying tax amount of insurance policy vehicle and ship for forced insurance |
| CN111027443A (en) * | 2019-12-04 | 2020-04-17 | 华南理工大学 | Bill text detection method based on multitask deep learning |
| CN111079562A (en) * | 2019-11-27 | 2020-04-28 | 浙江大学 | Multi-stage data generation self-circulation financial invoice text intelligent identification system and method |
| CN111091499A (en) * | 2018-10-24 | 2020-05-01 | 方正国际软件(北京)有限公司 | Method and device for correcting image of mobile terminal |
| CN111160188A (en) * | 2019-12-20 | 2020-05-15 | 中国建设银行股份有限公司 | Financial bill identification method, device, equipment and storage medium |
| CN111192660A (en) * | 2019-12-24 | 2020-05-22 | 上海联影智能医疗科技有限公司 | Image report analysis method, equipment and computer storage medium |
| CN111209856A (en) * | 2020-01-06 | 2020-05-29 | 泰康保险集团股份有限公司 | Invoice information identification method and device, electronic equipment and storage medium |
| CN111242034A (en) * | 2020-01-14 | 2020-06-05 | 支付宝(杭州)信息技术有限公司 | Document image processing method and device, processing equipment and client |
| CN111259882A (en) * | 2020-01-14 | 2020-06-09 | 平安科技（深圳）有限公司 | Bill identification method and device and computer equipment |
| CN111291726A (en) * | 2020-03-12 | 2020-06-16 | 泰康保险集团股份有限公司 | Medical bill sorting method, device, equipment and medium |
| CN111291619A (en) * | 2020-01-14 | 2020-06-16 | 支付宝(杭州)信息技术有限公司 | Method, device and client for on-line recognition of characters in claim settlement document |
| CN111310762A (en) * | 2020-03-16 | 2020-06-19 | 天津得迈科技有限公司 | Intelligent medical bill identification method based on Internet of things |
| CN111325104A (en) * | 2020-01-22 | 2020-06-23 | 平安科技（深圳）有限公司 | Text recognition method, device and storage medium |
| CN111325207A (en) * | 2020-03-05 | 2020-06-23 | 中国银行股份有限公司 | Bill identification method and device based on preprocessing |
| CN111340032A (en) * | 2020-03-16 | 2020-06-26 | 天津得迈科技有限公司 | Character recognition method based on application scene in financial field |
| CN111368902A (en) * | 2020-02-28 | 2020-07-03 | 北京三快在线科技有限公司 | Data labeling method and device |
| CN111401221A (en) * | 2020-03-12 | 2020-07-10 | 重庆农村商业银行股份有限公司 | Card ticket identification method, device, equipment and storage medium |
| CN111414905A (en) * | 2020-02-25 | 2020-07-14 | 泰康保险集团股份有限公司 | Text detection method, text detection device, electronic equipment and storage medium |
| CN111414917A (en) * | 2020-03-18 | 2020-07-14 | 民生科技有限责任公司 | Identification method of low-pixel-density text |
| CN111428599A (en) * | 2020-03-17 | 2020-07-17 | 北京公瑾科技有限公司 | Bill identification method, device and equipment |
| CN111428725A (en) * | 2020-04-13 | 2020-07-17 | 北京令才科技有限公司 | Data structuring processing method and device and electronic equipment |
| CN111444792A (en) * | 2020-03-13 | 2020-07-24 | 安诚迈科(北京)信息技术有限公司 | Bill recognition method, electronic device, storage medium and device |
| CN111444912A (en) * | 2020-01-14 | 2020-07-24 | 国网电子商务有限公司 | Bill image character recognition method and device |
| CN111461100A (en) * | 2020-03-31 | 2020-07-28 | 重庆农村商业银行股份有限公司 | Bill identification method and device, electronic equipment and storage medium |
| CN111462388A (en) * | 2020-03-19 | 2020-07-28 | 广州市玄武无线科技股份有限公司 | Bill inspection method and device, terminal equipment and storage medium |
| CN111461105A (en) * | 2019-01-18 | 2020-07-28 | 顺丰科技有限公司 | Text recognition method and device |
| CN111476227A (en) * | 2020-03-17 | 2020-07-31 | 平安科技（深圳）有限公司 | Target field recognition method and device based on OCR (optical character recognition) and storage medium |
| CN111553334A (en) * | 2020-04-21 | 2020-08-18 | 招商局金融科技有限公司 | Questionnaire image recognition method, electronic device, and storage medium |
| CN111626076A (en) * | 2019-02-27 | 2020-09-04 | 富士通株式会社 | Information processing method, information processing apparatus, and scanner |
| CN111652232A (en) * | 2020-05-29 | 2020-09-11 | 泰康保险集团股份有限公司 | Bill identification method and device, electronic equipment and computer readable storage medium |
| CN111652259A (en) * | 2019-04-16 | 2020-09-11 | 上海铼锶信息技术有限公司 | Method and system for cleaning data |
| CN111666868A (en) * | 2020-06-03 | 2020-09-15 | 阳光保险集团股份有限公司 | Insurance policy identification method and device and computer equipment |
| CN111666886A (en) * | 2020-06-08 | 2020-09-15 | 成都知识视觉科技有限公司 | Image preprocessing method for medical document structured knowledge extraction |
| CN111695439A (en) * | 2020-05-20 | 2020-09-22 | 平安科技（深圳）有限公司 | Image structured data extraction method, electronic device and storage medium |
| CN111814785A (en) * | 2020-06-11 | 2020-10-23 | 浙江大华技术股份有限公司 | Invoice recognition method, training method of related model, related equipment and device |
| CN111814906A (en) * | 2020-07-23 | 2020-10-23 | 上海东普信息科技有限公司 | Method, device and equipment for transplanting express waybill recognition model and storage medium |
| CN111832423A (en) * | 2020-06-19 | 2020-10-27 | 北京邮电大学 | Bill information identification method, device and system |
| CN111881882A (en) * | 2020-08-10 | 2020-11-03 | 晶璞(上海)人工智能科技有限公司 | Medical bill rotation correction method and system based on deep learning |
| CN111931664A (en) * | 2020-08-12 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Mixed note image processing method and device, computer equipment and storage medium |
| CN111968056A (en) * | 2020-08-18 | 2020-11-20 | 中国银行股份有限公司 | Online check deposit business processing method, client, cloud server and system |
| CN112037077A (en) * | 2020-09-03 | 2020-12-04 | 平安健康保险股份有限公司 | Seal identification method, device, equipment and storage medium based on artificial intelligence |
| CN112036396A (en) * | 2020-09-14 | 2020-12-04 | 上海高德威智能交通系统有限公司 | Ship name recognition method and device, electronic equipment and computer readable storage medium |
| CN112052858A (en) * | 2020-09-02 | 2020-12-08 | 中国银行股份有限公司 | Method for extracting target field in bill image and related device |
| CN112241727A (en) * | 2020-10-30 | 2021-01-19 | 深圳供电局有限公司 | Multi-ticket identification method and system and readable storage medium |
| CN112258259A (en) * | 2019-08-14 | 2021-01-22 | 北京京东尚科信息技术有限公司 | Data processing method, device and computer readable storage medium |
| CN112396047A (en) * | 2020-10-30 | 2021-02-23 | 北京文思海辉金信软件有限公司 | Training sample generation method and device, computer equipment and storage medium |
| CN112434689A (en) * | 2020-12-01 | 2021-03-02 | 天冕信息技术(深圳)有限公司 | Method, device and equipment for identifying information in picture and storage medium |
| CN112464845A (en) * | 2020-12-04 | 2021-03-09 | 山东产研鲲云人工智能研究院有限公司 | Bill recognition method, equipment and computer storage medium |
| CN112508017A (en) * | 2020-12-15 | 2021-03-16 | 通号智慧城市研究设计院有限公司 | Intelligent digital display instrument reading identification method, system, processing equipment and storage medium |
| CN112507914A (en) * | 2020-12-15 | 2021-03-16 | 江苏国光信息产业股份有限公司 | OCR (optical character recognition) method and recognition system based on bankbook and bill characters |
| CN112541505A (en) * | 2020-12-11 | 2021-03-23 | 上海云从企业发展有限公司 | Text recognition method, text recognition device and computer-readable storage medium |
| CN112560861A (en) * | 2020-12-10 | 2021-03-26 | 上海亿保健康管理有限公司 | Bill processing method, device, equipment and storage medium |
| CN112580657A (en) * | 2020-12-23 | 2021-03-30 | 陕西天诚软件有限公司 | Self-learning character recognition method |
| CN112613510A (en) * | 2020-12-25 | 2021-04-06 | 创新奇智(青岛)科技有限公司 | Picture preprocessing method, character recognition model training method and character recognition method |
| CN112613553A (en) * | 2020-12-18 | 2021-04-06 | 中电金信软件有限公司 | Picture sample set generation method and device, computer equipment and storage medium |
| CN112632926A (en) * | 2020-12-29 | 2021-04-09 | 平安科技（深圳）有限公司 | Data processing method and device for bill, electronic equipment and storage medium |
| CN112699860A (en) * | 2021-03-24 | 2021-04-23 | 成都新希望金融信息有限公司 | Method for automatically extracting and sorting effective information in personal tax APP operation video |
| CN112784932A (en) * | 2021-03-01 | 2021-05-11 | 北京百炼智能科技有限公司 | Font identification method and device and storage medium |
| CN112818951A (en) * | 2021-03-11 | 2021-05-18 | 南京大学 | Ticket identification method |
| CN112837466A (en) * | 2020-12-18 | 2021-05-25 | 北京百度网讯科技有限公司 | Bill recognition method, device, equipment and storage medium |
| CN112989990A (en) * | 2021-03-09 | 2021-06-18 | 平安科技（深圳）有限公司 | Medical bill identification method, device, equipment and storage medium |
| CN113077018A (en) * | 2021-06-07 | 2021-07-06 | 浙江大华技术股份有限公司 | Target object identification method and device, storage medium and electronic device |
| CN113095307A (en) * | 2021-06-09 | 2021-07-09 | 国网浙江省电力有限公司 | Automatic identification method for financial voucher information |
| CN113283421A (en) * | 2021-06-24 | 2021-08-20 | 中国平安人寿保险股份有限公司 | Information identification method, device, equipment and storage medium |
| CN113326895A (en) * | 2021-06-25 | 2021-08-31 | 湖南星汉数智科技有限公司 | Passenger ticket travel itinerary identification method and device, computer equipment and storage medium |
| CN113344690A (en) * | 2021-06-30 | 2021-09-03 | 中国工商银行股份有限公司 | Invoice reimbursement processing method and device |
| CN113469161A (en) * | 2020-03-31 | 2021-10-01 | 顺丰科技有限公司 | Method, device and storage medium for processing logistics list |
| CN113496115A (en) * | 2020-04-08 | 2021-10-12 | 中国移动通信集团广东有限公司 | File content comparison method and device |
| CN113642556A (en) * | 2021-08-04 | 2021-11-12 | 五八有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN113705559A (en) * | 2021-08-31 | 2021-11-26 | 平安银行股份有限公司 | Character recognition method and device based on artificial intelligence and electronic equipment |
| CN113723508A (en) * | 2021-08-30 | 2021-11-30 | 杭州米数科技有限公司 | Bill image classification method and device, computing equipment and storage medium |
| CN113780116A (en) * | 2021-08-26 | 2021-12-10 | 众安在线财产保险股份有限公司 | Invoice classification method and device, computer equipment and storage medium |
| CN113920294A (en) * | 2021-10-20 | 2022-01-11 | 广东亿迅科技有限公司 | Mass invoice identification method and system and storage medium |
| WO2022006829A1 (en) * | 2020-07-09 | 2022-01-13 | 国网电子商务有限公司 | Bill image recognition method and system, electronic device, and storage medium |
| CN113963149A (en) * | 2021-10-29 | 2022-01-21 | 平安科技（深圳）有限公司 | Medical bill picture fuzzy judgment method, system, equipment and medium |
| CN114743198A (en) * | 2022-03-14 | 2022-07-12 | 中国银行股份有限公司 | Method and device for identifying bill with form |
| CN114926831A (en) * | 2022-05-31 | 2022-08-19 | 平安普惠企业管理有限公司 | Text-based recognition method and device, electronic equipment and readable storage medium |
| WO2023284608A1 (en) * | 2021-07-13 | 2023-01-19 | 深圳思谋信息科技有限公司 | Character recognition model generating method and apparatus, computer device, and storage medium |
| CN111626279B (en) * | 2019-10-15 | 2023-06-02 | 西安网算数据科技有限公司 | Negative sample labeling training method and highly-automatic bill identification method |
| CN112651353B (en) * | 2020-12-30 | 2024-04-16 | 南京红松信息技术有限公司 | Target calculation positioning and identifying method based on custom label |
Families Citing this family (103)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110728277B (en) * | 2019-09-27 | 2024-04-05 | 达观数据有限公司 | Intelligent seal detection and identification method and system |
| CN110826330B (en) * | 2019-10-12 | 2023-11-07 | 上海数禾信息科技有限公司 | Name recognition method and device, computer equipment and readable storage medium |
| CN111126125B (en) * | 2019-10-15 | 2023-08-01 | 平安科技（深圳）有限公司 | Method, device, equipment and readable storage medium for extracting target text in certificate |
| CN110766017B (en) * | 2019-10-22 | 2023-08-04 | 国网新疆电力有限公司信息通信公司 | Mobile terminal text recognition method and system based on deep learning |
| CN111860489A (en) * | 2019-12-09 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Certificate image correction method, device, equipment and storage medium |
| CN110827333B (en) * | 2019-10-31 | 2022-05-03 | 国网河北省电力有限公司电力科学研究院 | Relay protection pressing plate splicing identification method, system and medium |
| CN110866495B (en) * | 2019-11-14 | 2022-06-28 | 杭州睿琪软件有限公司 | Bill image recognition method, bill image recognition device, bill image recognition equipment, training method and storage medium |
| CN110941717B (en) * | 2019-11-22 | 2023-08-11 | 深圳马可孛罗科技有限公司 | Passenger ticket rule analysis method and device, electronic equipment and computer readable medium |
| CN111079117B (en) * | 2019-11-28 | 2024-02-13 | 上海三零卫士信息安全有限公司 | Automatic point-contact verification code identification method based on LeNet and SSD |
| CN110991520B (en) * | 2019-11-29 | 2023-05-02 | 汉海信息技术(上海)有限公司 | Method and device for generating training samples |
| CN112990172B (en) * | 2019-12-02 | 2023-12-22 | 阿里巴巴集团控股有限公司 | Text recognition method, character recognition method and device |
| CN111209792B (en) * | 2019-12-02 | 2023-08-01 | 河南科技学院 | Image recognition method and device for value-added tax common invoice |
| CN113033240B (en) * | 2019-12-09 | 2023-05-02 | 上海高德威智能交通系统有限公司 | Multi-line text recognition method, model training method, device, equipment and medium |
| CN112947944B (en) * | 2019-12-11 | 2023-12-05 | 中盈优创资讯科技有限公司 | Business work order processing method and device |
| CN111046886B (en) * | 2019-12-12 | 2023-05-12 | 吉林大学 | Automatic identification method, device and equipment for number plate and computer readable storage medium |
| CN112990208B (en) * | 2019-12-12 | 2024-04-30 | 北京搜狗科技发展有限公司 | Text recognition method and device |
| CN111079641B (en) * | 2019-12-13 | 2024-04-16 | 科大讯飞股份有限公司 | Answer content identification method, related device and readable storage medium |
| CN111191695B (en) * | 2019-12-19 | 2023-05-23 | 杭州安恒信息技术股份有限公司 | Website picture tampering detection method based on deep learning |
| CN111126396B (en) * | 2019-12-25 | 2023-08-22 | 北京科技大学 | Image recognition method, device, computer equipment and storage medium |
| CN111178355B (en) * | 2019-12-27 | 2024-05-10 | 中化资本有限公司 | Seal identification method, device and storage medium |
| CN111160265B (en) * | 2019-12-30 | 2023-01-10 | Oppo（重庆）智能科技有限公司 | File conversion method and device, storage medium and electronic equipment |
| CN111144358A (en) * | 2019-12-30 | 2020-05-12 | 上海眼控科技股份有限公司 | Vehicle quality certificate verification method and device, computer equipment and storage medium |
| CN111340022A (en) * | 2020-02-24 | 2020-06-26 | 深圳市华云中盛科技股份有限公司 | Identity card information identification method and device, computer equipment and storage medium |
| CN111353484A (en) * | 2020-02-28 | 2020-06-30 | 深圳前海微众银行股份有限公司 | Image character recognition method, device, equipment and readable storage medium |
| CN111445058B (en) * | 2020-03-04 | 2024-05-28 | 中国平安人寿保险股份有限公司 | Data analysis method, device, equipment and computer readable storage medium |
| CN111414906B (en) * | 2020-03-05 | 2024-05-24 | 北京交通大学 | Data synthesis and text recognition method for paper bill pictures |
| CN111507324B (en) * | 2020-03-16 | 2024-05-31 | 平安科技（深圳）有限公司 | Card frame recognition method, device, equipment and computer storage medium |
| CN111414911A (en) * | 2020-03-23 | 2020-07-14 | 湖南信息学院 | Card number identification method and system based on deep learning |
| CN111598122B (en) * | 2020-04-01 | 2022-02-08 | 深圳壹账通智能科技有限公司 | Data verification method and device, electronic equipment and storage medium |
| CN111582259B (en) * | 2020-04-10 | 2024-04-16 | 支付宝实验室(新加坡)有限公司 | Machine-readable code identification method, device, electronic equipment and storage medium |
| CN111476243A (en) * | 2020-04-13 | 2020-07-31 | 中国工商银行股份有限公司 | Image character recognition method and device |
| CN111489347B (en) * | 2020-04-15 | 2023-10-31 | 深圳前海环融联易信息科技服务有限公司 | Business license picture quality detection method and device, computer equipment and storage medium |
| CN111507356A (en) * | 2020-04-20 | 2020-08-07 | 恒银金融科技股份有限公司 | Segmentation method of handwritten characters of lower case money of financial bills |
| CN111582786A (en) * | 2020-04-29 | 2020-08-25 | 上海中通吉网络技术有限公司 | Express bill number identification method, device and equipment based on machine learning |
| CN111581242A (en) * | 2020-04-30 | 2020-08-25 | 北京贝禾无忧科技有限公司 | Method and system for identifying enterprise bill use |
| CN111680691B (en) * | 2020-04-30 | 2023-06-02 | 北京三快在线科技有限公司 | Text detection method, text detection device, electronic equipment and computer readable storage medium |
| CN111639566A (en) * | 2020-05-19 | 2020-09-08 | 浙江大华技术股份有限公司 | Method and device for extracting form information |
| CN111639648B (en) * | 2020-05-26 | 2023-09-19 | 浙江大华技术股份有限公司 | Certificate identification method, device, computing equipment and storage medium |
| CN111666932B (en) * | 2020-05-27 | 2023-07-14 | 平安科技（深圳）有限公司 | Document auditing method, device, computer equipment and storage medium |
| CN111814539B (en) * | 2020-05-28 | 2023-07-21 | 平安科技（深圳）有限公司 | Character recognition method and device based on infrared light and ultraviolet light and computer equipment |
| CN111753744B (en) * | 2020-06-28 | 2024-04-16 | 北京百度网讯科技有限公司 | Method, apparatus, device and readable storage medium for bill image classification |
| CN111950356B (en) * | 2020-06-30 | 2024-04-19 | 深圳市雄帝科技股份有限公司 | Seal text positioning method and device and electronic equipment |
| CN111783785B (en) * | 2020-07-02 | 2024-04-09 | 上海海事大学 | Water meter identification system and identification method |
| CN111931229B (en) * | 2020-07-10 | 2023-07-11 | 深信服科技股份有限公司 | Data identification method, device and storage medium |
| CN111950380A (en) * | 2020-07-19 | 2020-11-17 | 中国建设银行股份有限公司 | Bill auditing method and device, electronic equipment and computer-readable storage medium |
| CN111832657A (en) * | 2020-07-20 | 2020-10-27 | 上海眼控科技股份有限公司 | Text recognition method and device, computer equipment and storage medium |
| CN111932593B (en) * | 2020-07-21 | 2024-04-09 | 湖南中联重科智能技术有限公司 | Image registration method, system and equipment based on touch screen gesture correction |
| CN111914706B (en) * | 2020-07-22 | 2023-11-17 | 厦门商集网络科技有限责任公司 | Method and device for detecting and controlling quality of text detection output result |
| CN111914729A (en) * | 2020-07-28 | 2020-11-10 | 中国建设银行股份有限公司 | Voucher association method and device, computer equipment and storage medium |
| CN112069894A (en) * | 2020-08-03 | 2020-12-11 | 许继集团有限公司 | Wire strand scattering identification method based on fast-RCNN model |
| CN112070086B (en) * | 2020-09-09 | 2024-05-07 | 平安科技（深圳）有限公司 | Optimization method of text recognition system, computer equipment and storage medium |
| CN112052853B (en) * | 2020-09-09 | 2024-02-02 | 国家气象信息中心 | Text positioning method of handwriting meteorological archive data based on deep learning |
| CN112100366B (en) * | 2020-09-17 | 2023-10-27 | 广联达科技股份有限公司 | Pavement structure layer display method and device, computer equipment and storage medium |
| CN112270323B (en) * | 2020-09-29 | 2024-02-02 | 西安电子科技大学 | Intelligent medical review control method, system, medium, computer equipment and application |
| CN112115921A (en) * | 2020-09-30 | 2020-12-22 | 北京百度网讯科技有限公司 | True and false identification method and device and electronic equipment |
| CN112232338B (en) * | 2020-10-13 | 2023-09-08 | 中国平安人寿保险股份有限公司 | Data entry method, device, equipment and storage medium for warranty claim checking process |
| CN112232340A (en) * | 2020-10-15 | 2021-01-15 | 马婧 | Method and device for identifying printed information on surface of object |
| CN112257768B (en) * | 2020-10-19 | 2023-01-31 | 广州金融科技股份有限公司 | Method and device for identifying illegal financial pictures and computer storage medium |
| CN112464941B (en) * | 2020-10-23 | 2024-05-24 | 北京思特奇信息技术股份有限公司 | Invoice identification method and system based on neural network |
| CN112257613B (en) * | 2020-10-23 | 2023-08-08 | 中国平安人寿保险股份有限公司 | Physical examination report information structured extraction method and device and computer equipment |
| CN112232296A (en) * | 2020-11-09 | 2021-01-15 | 北京爱笔科技有限公司 | Hyper-parameter exploration method and device |
| CN112396048B (en) * | 2020-11-17 | 2023-09-29 | 中国平安人寿保险股份有限公司 | Picture information extraction method and device, computer equipment and storage medium |
| CN112418206B (en) * | 2020-11-20 | 2024-02-27 | 上海昇晔网络科技有限公司 | Picture classification method based on position detection model and related equipment thereof |
| CN112329708A (en) * | 2020-11-24 | 2021-02-05 | 北京百度网讯科技有限公司 | Bill identification method and device |
| CN112287898A (en) * | 2020-11-26 | 2021-01-29 | 深源恒际科技有限公司 | Method and system for evaluating text detection quality of image |
| CN112288039B (en) * | 2020-11-26 | 2024-01-23 | 深源恒际科技有限公司 | Sample labeling method and system for OCR model training |
| CN112381702B (en) * | 2020-12-02 | 2024-03-15 | 北京皮尔布莱尼软件有限公司 | Image privacy processing method, computing device and storage medium |
| CN112488108A (en) * | 2020-12-11 | 2021-03-12 | 广州小鹏自动驾驶科技有限公司 | Parking space number identification method and device, electronic equipment and storage medium |
| CN112651913B (en) * | 2020-12-17 | 2024-03-29 | 广州市申迪计算机系统有限公司 | Invoice seal desalination method, system, device and computer storage medium |
| CN112507946A (en) * | 2020-12-18 | 2021-03-16 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for processing image |
| CN112507973B (en) * | 2020-12-29 | 2022-09-06 | 中国电子科技集团公司第二十八研究所 | Text and picture recognition system based on OCR technology |
| CN113111882B (en) * | 2021-02-24 | 2022-12-20 | 北京邮电大学 | Card identification method and device, electronic equipment and storage medium |
| CN112949450B (en) * | 2021-02-25 | 2024-01-23 | 北京百度网讯科技有限公司 | Bill processing method, device, electronic equipment and storage medium |
| CN112926565B (en) * | 2021-02-25 | 2024-02-06 | 中国平安人寿保险股份有限公司 | Picture text recognition method, system, equipment and storage medium |
| CN112966583A (en) * | 2021-02-26 | 2021-06-15 | 深圳壹账通智能科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN112818961A (en) * | 2021-03-26 | 2021-05-18 | 北京东方金朔信息技术有限公司 | Image feature identification method and device |
| CN113128490B (en) * | 2021-04-28 | 2023-12-05 | 湖南荣冠智能科技有限公司 | Prescription information scanning and automatic identification method |
| CN113239807B (en) * | 2021-05-14 | 2024-04-02 | 北京百度网讯科技有限公司 | Method and device for training bill identification model and bill identification |
| CN113221869B (en) * | 2021-05-25 | 2023-09-05 | 中国平安人寿保险股份有限公司 | Medical invoice structured information extraction method, device equipment and storage medium |
| CN113255767B (en) * | 2021-05-25 | 2023-11-24 | 深圳壹账通智能科技有限公司 | Bill classification method, device, equipment and storage medium |
| CN113269102A (en) * | 2021-05-28 | 2021-08-17 | 中邮信息科技(北京)有限公司 | Seal information identification method and device, computer equipment and storage medium |
| CN113313114B (en) * | 2021-06-11 | 2023-06-30 | 北京百度网讯科技有限公司 | Certificate information acquisition method, device, equipment and storage medium |
| CN113435439B (en) * | 2021-06-30 | 2023-11-28 | 青岛海尔科技有限公司 | Document auditing method and device, storage medium and electronic device |
| CN113657377B (en) * | 2021-07-22 | 2023-11-14 | 西南财经大学 | Structured recognition method for mechanical bill image |
| CN113591705B (en) * | 2021-07-30 | 2024-03-19 | 华东理工大学 | Inspection robot instrument identification system and method and storage medium |
| CN113627430B (en) * | 2021-08-12 | 2023-06-20 | 石家庄铁道大学 | Cable number detection method and device and electronic equipment |
| CN113537229A (en) * | 2021-08-27 | 2021-10-22 | 广州广电运通金融电子股份有限公司 | Bill image generation method and device, computer equipment and storage medium |
| CN113869131B (en) * | 2021-09-01 | 2024-03-29 | 南京烽火天地通信科技有限公司 | Method for structuring text business license picture |
| CN113627395B (en) * | 2021-09-17 | 2023-11-17 | 平安银行股份有限公司 | Text recognition method, device, medium and electronic equipment |
| CN113963147B (en) * | 2021-09-26 | 2023-09-15 | 西安交通大学 | Key information extraction method and system based on semantic segmentation |
| CN116090463A (en) * | 2021-11-03 | 2023-05-09 | 中移(苏州)软件技术有限公司 | Business card information extraction system training method and device and storage medium |
| CN114240407A (en) * | 2021-11-17 | 2022-03-25 | 广东电网有限责任公司 | Bill risk conduction quantitative evaluation system and method based on block chain |
| CN114299528B (en) * | 2021-12-27 | 2024-03-22 | 万达信息股份有限公司 | Information extraction and structuring method for scanned document |
| CN114267115B (en) * | 2021-12-27 | 2024-03-08 | 江苏银承网络科技股份有限公司 | Bill identification method and system |
| CN114358943A (en) * | 2022-01-12 | 2022-04-15 | 平安普惠企业管理有限公司 | Online bill processing method and device, electronic equipment and storage medium |
| CN114708603A (en) * | 2022-05-25 | 2022-07-05 | 杭州咏柳科技有限公司 | Method, system, device and medium for identifying key information in medical bill |
| CN115170261A (en) * | 2022-06-08 | 2022-10-11 | 姚远 | Systematic method for hospital financial audit |
| CN114818995B (en) * | 2022-06-27 | 2022-10-04 | 广东电网有限责任公司佛山供电局 | Method, device and equipment for identifying and early warning non-work ticket violation operation |
| CN115062722B (en) * | 2022-07-06 | 2023-03-28 | 阿锐巴数据科技(上海)有限公司 | AI training method based on cloud service big data cleaning and artificial intelligence cloud system |
| CN115690803A (en) * | 2022-10-31 | 2023-02-03 | 中电金信软件(上海)有限公司 | Digital image recognition method and device, electronic equipment and readable storage medium |
| CN117197816A (en) * | 2023-06-19 | 2023-12-08 | 珠海盈米基金销售有限公司 | User material identification method and system |
| CN117408764B (en) * | 2023-12-13 | 2024-05-03 | 江西曼荼罗软件有限公司 | Medical fee change method, system, storage medium and electronic equipment |
| CN117649672B (en) * | 2024-01-30 | 2024-04-26 | 湖南大学 | Font type visual detection method and system based on active learning and transfer learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488999A (en) * | 2013-09-11 | 2014-01-01 | 东华大学 | Invoice data recording method |
| CN105095842A (en) * | 2014-05-22 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying information of bill |
| CN105574513A (en) * | 2015-12-22 | 2016-05-11 | 北京旷视科技有限公司 | Character detection method and device |
| CN107346580A (en) * | 2016-05-05 | 2017-11-14 | 腾讯科技（深圳）有限公司 | Billing information recognition methods and device |
| CN107798299A (en) * | 2017-10-09 | 2018-03-13 | 平安科技（深圳）有限公司 | Billing information recognition methods, electronic installation and readable storage medium storing program for executing |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9460358B2 (en) * | 2014-07-15 | 2016-10-04 | Google Inc. | Extracting card identification data |
| CN107403130A (en) * | 2017-04-19 | 2017-11-28 | 北京粉笔未来科技有限公司 | A kind of character identifying method and character recognition device |
| CN107481238A (en) * | 2017-09-20 | 2017-12-15 | 众安信息技术服务有限公司 | Image quality measure method and device |
| CN107766809B (en) * | 2017-10-09 | 2020-05-19 | 平安科技（深圳）有限公司 | Electronic device, bill information identification method, and computer-readable storage medium |
-
2018
- 2018-03-14 CN CN201810208586.9A patent/CN108446621A/en active Pending
- 2018-05-31 WO PCT/CN2018/089202 patent/WO2019174130A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488999A (en) * | 2013-09-11 | 2014-01-01 | 东华大学 | Invoice data recording method |
| CN105095842A (en) * | 2014-05-22 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying information of bill |
| CN105574513A (en) * | 2015-12-22 | 2016-05-11 | 北京旷视科技有限公司 | Character detection method and device |
| CN107346580A (en) * | 2016-05-05 | 2017-11-14 | 腾讯科技（深圳）有限公司 | Billing information recognition methods and device |
| CN107798299A (en) * | 2017-10-09 | 2018-03-13 | 平安科技（深圳）有限公司 | Billing information recognition methods, electronic installation and readable storage medium storing program for executing |
Non-Patent Citations (2)
| Title |
|---|
| SHI BAOGUANG 等: "An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition", 《 ARXIV:1507.05717 [CS.CV]》 * |
| TIAN ZHI等: "Detecting Text in Natural Image with Connectionist Text Proposal Network", 《COMPUTER VISION – ECCV 2016》 * |
Cited By (181)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241271B (en) * | 2018-08-30 | 2021-09-17 | 天津做票君机器人科技有限公司 | Method for identifying draft due date in natural language by draft transaction robot |
| CN109241271A (en) * | 2018-08-30 | 2019-01-18 | 天津做票君机器人科技有限公司 | A kind of method that negotiation by draft robot identifies due date of bill in natural language |
| CN109117848B (en) * | 2018-09-07 | 2022-11-18 | 泰康保险集团股份有限公司 | Text line character recognition method, device, medium and electronic equipment |
| CN109117848A (en) * | 2018-09-07 | 2019-01-01 | 泰康保险集团股份有限公司 | A kind of line of text character identifying method, device, medium and electronic equipment |
| CN110895691B (en) * | 2018-09-12 | 2023-06-23 | 阿里巴巴集团控股有限公司 | Image processing method and device and electronic equipment |
| CN110895691A (en) * | 2018-09-12 | 2020-03-20 | 阿里巴巴集团控股有限公司 | Image processing method and device and electronic equipment |
| WO2020062804A1 (en) * | 2018-09-25 | 2020-04-02 | 平安科技（深圳）有限公司 | Method and apparatus for recognizing photographed image of driving license in natural scene and electronic device |
| CN109637000B (en) * | 2018-10-23 | 2021-12-28 | 深圳壹账通智能科技有限公司 | Invoice detection method and device, storage medium and electronic terminal |
| CN109637000A (en) * | 2018-10-23 | 2019-04-16 | 深圳壹账通智能科技有限公司 | The invoice method of inspection and device, storage medium, electric terminal |
| CN109635627A (en) * | 2018-10-23 | 2019-04-16 | 中国平安财产保险股份有限公司 | Pictorial information extracting method, device, computer equipment and storage medium |
| CN111091499A (en) * | 2018-10-24 | 2020-05-01 | 方正国际软件(北京)有限公司 | Method and device for correcting image of mobile terminal |
| CN111091499B (en) * | 2018-10-24 | 2023-05-23 | 方正国际软件(北京)有限公司 | Mobile terminal image correction method and device |
| CN109461247A (en) * | 2018-10-29 | 2019-03-12 | 北京慧流科技有限公司 | Note validating method and device, electronic equipment and storage medium |
| CN109685100B (en) * | 2018-11-12 | 2024-05-10 | 平安科技（深圳）有限公司 | Character recognition method, server and computer readable storage medium |
| CN109685100A (en) * | 2018-11-12 | 2019-04-26 | 平安科技（深圳）有限公司 | Character identifying method, server and computer readable storage medium |
| CN109583443A (en) * | 2018-11-15 | 2019-04-05 | 四川长虹电器股份有限公司 | A kind of video content judgment method based on Text region |
| CN109635796A (en) * | 2018-11-20 | 2019-04-16 | 泰康保险集团股份有限公司 | Recognition methods, device and the equipment of questionnaire |
| CN109635796B (en) * | 2018-11-20 | 2021-09-28 | 泰康保险集团股份有限公司 | Questionnaire recognition method, device and equipment |
| CN109542649A (en) * | 2018-11-23 | 2019-03-29 | 于兴虎 | A method of image memory is quickly shared across language under vision servo system |
| CN109670494A (en) * | 2018-12-13 | 2019-04-23 | 深源恒际科技有限公司 | A kind of Method for text detection and system of subsidiary recognition confidence |
| CN109784339A (en) * | 2018-12-13 | 2019-05-21 | 平安普惠企业管理有限公司 | Picture recognition test method, device, computer equipment and storage medium |
| CN109670494B (en) * | 2018-12-13 | 2023-09-01 | 北京深智恒际科技有限公司 | Text detection method and system with recognition confidence |
| CN109886077A (en) * | 2018-12-28 | 2019-06-14 | 北京旷视科技有限公司 | Image-recognizing method, device, computer equipment and storage medium |
| CN109784235A (en) * | 2018-12-29 | 2019-05-21 | 广东益萃网络科技有限公司 | Method for automatically inputting, device, computer equipment and the storage medium of paper form |
| CN111461105B (en) * | 2019-01-18 | 2023-11-28 | 顺丰科技有限公司 | Text recognition method and device |
| CN111461105A (en) * | 2019-01-18 | 2020-07-28 | 顺丰科技有限公司 | Text recognition method and device |
| CN109858420A (en) * | 2019-01-24 | 2019-06-07 | 国信电子票据平台信息服务有限公司 | A kind of bill processing system and processing method |
| CN109886257A (en) * | 2019-01-30 | 2019-06-14 | 四川长虹电器股份有限公司 | Using the method for deep learning correction invoice picture segmentation result in a kind of OCR system |
| CN109886257B (en) * | 2019-01-30 | 2022-10-18 | 四川长虹电器股份有限公司 | Method for correcting invoice image segmentation result by adopting deep learning in OCR system |
| CN109829437A (en) * | 2019-02-01 | 2019-05-31 | 北京旷视科技有限公司 | Image processing method, text recognition method, device and electronic system |
| CN109978890B (en) * | 2019-02-25 | 2023-07-07 | 平安科技（深圳）有限公司 | Target extraction method and device based on image processing and terminal equipment |
| CN109978890A (en) * | 2019-02-25 | 2019-07-05 | 平安科技（深圳）有限公司 | Target extraction method, device and terminal device based on image procossing |
| CN109872444A (en) * | 2019-02-27 | 2019-06-11 | 杭州睿琪软件有限公司 | A kind of bank slip recognition method and device |
| CN111626076A (en) * | 2019-02-27 | 2020-09-04 | 富士通株式会社 | Information processing method, information processing apparatus, and scanner |
| CN109872444B (en) * | 2019-02-27 | 2021-03-09 | 杭州睿琪软件有限公司 | Bill identification method and device |
| CN109948549B (en) * | 2019-03-20 | 2022-11-29 | 深圳市华付信息技术有限公司 | OCR data generation method and device, computer equipment and storage medium |
| CN109948549A (en) * | 2019-03-20 | 2019-06-28 | 深圳市华付信息技术有限公司 | OCR data creation method, device, computer equipment and storage medium |
| CN110110123B (en) * | 2019-04-04 | 2023-07-25 | 平安科技（深圳）有限公司 | Training set updating method and device for detection model |
| CN110135409A (en) * | 2019-04-04 | 2019-08-16 | 平安科技（深圳）有限公司 | The optimization method and device of identification model |
| CN110109922B (en) * | 2019-04-04 | 2024-05-24 | 广州易策医管科技有限公司 | Performance data acquisition method, device, computer equipment and storage medium |
| CN110110123A (en) * | 2019-04-04 | 2019-08-09 | 平安科技（深圳）有限公司 | The training set update method and device of detection model |
| CN110109922A (en) * | 2019-04-04 | 2019-08-09 | 平安普惠企业管理有限公司 | Performance data acquisition methods, device, computer equipment and storage medium |
| CN110135409B (en) * | 2019-04-04 | 2023-11-03 | 平安科技（深圳）有限公司 | Optimization method and device for recognition model |
| CN111652259A (en) * | 2019-04-16 | 2020-09-11 | 上海铼锶信息技术有限公司 | Method and system for cleaning data |
| CN111652259B (en) * | 2019-04-16 | 2024-03-08 | 上海铼锶信息技术有限公司 | Method and system for cleaning data |
| CN110189141A (en) * | 2019-04-17 | 2019-08-30 | 深圳壹账通智能科技有限公司 | Verification method, device and the computer equipment of invoice |
| CN110070042A (en) * | 2019-04-23 | 2019-07-30 | 北京字节跳动网络技术有限公司 | Character recognition method, device and electronic equipment |
| CN110276253A (en) * | 2019-05-15 | 2019-09-24 | 中国科学院信息工程研究所 | A kind of fuzzy literal detection recognition method based on deep learning |
| CN110245658A (en) * | 2019-05-21 | 2019-09-17 | 深圳壹账通智能科技有限公司 | A kind of bank slip recognition method, apparatus, storage medium and server |
| CN110175610B (en) * | 2019-05-23 | 2023-09-05 | 上海交通大学 | Bill image text recognition method supporting privacy protection |
| CN110175610A (en) * | 2019-05-23 | 2019-08-27 | 上海交通大学 | A kind of bill images text recognition method for supporting secret protection |
| CN110210400A (en) * | 2019-06-03 | 2019-09-06 | 上海眼控科技股份有限公司 | A kind of form document detection method and equipment |
| CN110210503A (en) * | 2019-06-14 | 2019-09-06 | 厦门历思科技服务有限公司 | A kind of seal recognition methods and device and equipment |
| CN110210503B (en) * | 2019-06-14 | 2021-01-01 | 厦门历思科技服务有限公司 | Seal identification method, device and equipment |
| CN110287952B (en) * | 2019-07-01 | 2021-07-20 | 中科软科技股份有限公司 | Method and system for recognizing characters of dimension picture |
| CN110287952A (en) * | 2019-07-01 | 2019-09-27 | 中科软科技股份有限公司 | A kind of recognition methods and system for tieing up sonagram piece character |
| CN110414927B (en) * | 2019-07-05 | 2023-04-07 | 西安网算数据科技有限公司 | Method and device for automatically generating voucher during bill processing |
| CN110414927A (en) * | 2019-07-05 | 2019-11-05 | 西安网算数据科技有限公司 | A kind of bill processing automatically generates the method and device of voucher |
| CN110490193A (en) * | 2019-07-24 | 2019-11-22 | 西安网算数据科技有限公司 | Single Text RegionDetection method and ticket contents recognition methods |
| CN110399875A (en) * | 2019-07-31 | 2019-11-01 | 山东浪潮人工智能研究院有限公司 | A kind of form of general use information extracting method based on deep learning and pixel projection |
| CN110647956B (en) * | 2019-08-12 | 2024-03-29 | 深圳市华付信息技术有限公司 | Invoice information extraction method combining two-dimension code recognition |
| CN110647956A (en) * | 2019-08-12 | 2020-01-03 | 深圳市华付信息技术有限公司 | Invoice information extraction method combined with two-dimensional code recognition |
| CN112258259A (en) * | 2019-08-14 | 2021-01-22 | 北京京东尚科信息技术有限公司 | Data processing method, device and computer readable storage medium |
| CN110525069A (en) * | 2019-08-21 | 2019-12-03 | 珠海思格特智能系统有限公司 | A kind of OCR comparison system and its method for intelligent stamper machine |
| CN110490267A (en) * | 2019-08-23 | 2019-11-22 | 四川长虹电器股份有限公司 | A kind of bill method for sorting based on deep learning |
| CN110717516B (en) * | 2019-09-06 | 2023-08-25 | 中国平安财产保险股份有限公司 | Bill image classification method, device and computer readable storage medium |
| CN110738203B (en) * | 2019-09-06 | 2024-04-05 | 中国平安财产保险股份有限公司 | Field structured output method, device and computer readable storage medium |
| CN110717516A (en) * | 2019-09-06 | 2020-01-21 | 中国平安财产保险股份有限公司 | Bill image classification method and device and computer readable storage medium |
| CN110738203A (en) * | 2019-09-06 | 2020-01-31 | 中国平安财产保险股份有限公司 | Method and device for outputting field structuralization and computer readable storage medium |
| CN110647829A (en) * | 2019-09-12 | 2020-01-03 | 全球能源互联网研究院有限公司 | Bill text recognition method and system |
| CN110807455A (en) * | 2019-09-19 | 2020-02-18 | 平安科技（深圳）有限公司 | Bill detection method, device and equipment based on deep learning and storage medium |
| CN110765910A (en) * | 2019-10-14 | 2020-02-07 | 西安网算数据科技有限公司 | Bill region identification method and device in dense scene |
| CN111626279B (en) * | 2019-10-15 | 2023-06-02 | 西安网算数据科技有限公司 | Negative sample labeling training method and highly-automatic bill identification method |
| CN110991270B (en) * | 2019-11-15 | 2023-10-20 | 泰康保险集团股份有限公司 | Text recognition method, device, electronic equipment and storage medium |
| CN110991270A (en) * | 2019-11-15 | 2020-04-10 | 泰康保险集团股份有限公司 | Text recognition method and device, electronic equipment and storage medium |
| CN111079562A (en) * | 2019-11-27 | 2020-04-28 | 浙江大学 | Multi-stage data generation self-circulation financial invoice text intelligent identification system and method |
| CN110956133A (en) * | 2019-11-29 | 2020-04-03 | 上海眼控科技股份有限公司 | Training method of single character text normalization model, text recognition method and device |
| CN111027443A (en) * | 2019-12-04 | 2020-04-17 | 华南理工大学 | Bill text detection method based on multitask deep learning |
| CN111027443B (en) * | 2019-12-04 | 2023-04-07 | 华南理工大学 | Bill text detection method based on multitask deep learning |
| CN111027532A (en) * | 2019-12-11 | 2020-04-17 | 上海眼控科技股份有限公司 | System and method for identifying tax amount of insurance policy vehicle and ship for forced insurance |
| CN111160188A (en) * | 2019-12-20 | 2020-05-15 | 中国建设银行股份有限公司 | Financial bill identification method, device, equipment and storage medium |
| CN111192660A (en) * | 2019-12-24 | 2020-05-22 | 上海联影智能医疗科技有限公司 | Image report analysis method, equipment and computer storage medium |
| CN111192660B (en) * | 2019-12-24 | 2023-10-13 | 上海联影智能医疗科技有限公司 | Image report analysis method, device and computer storage medium |
| CN111209856A (en) * | 2020-01-06 | 2020-05-29 | 泰康保险集团股份有限公司 | Invoice information identification method and device, electronic equipment and storage medium |
| CN111209856B (en) * | 2020-01-06 | 2023-10-17 | 泰康保险集团股份有限公司 | Invoice information identification method and device, electronic equipment and storage medium |
| CN111259882A (en) * | 2020-01-14 | 2020-06-09 | 平安科技（深圳）有限公司 | Bill identification method and device and computer equipment |
| CN111291619A (en) * | 2020-01-14 | 2020-06-16 | 支付宝(杭州)信息技术有限公司 | Method, device and client for on-line recognition of characters in claim settlement document |
| CN111259882B (en) * | 2020-01-14 | 2023-12-26 | 平安科技（深圳）有限公司 | Bill identification method and device and computer equipment |
| CN111242034A (en) * | 2020-01-14 | 2020-06-05 | 支付宝(杭州)信息技术有限公司 | Document image processing method and device, processing equipment and client |
| CN111444912A (en) * | 2020-01-14 | 2020-07-24 | 国网电子商务有限公司 | Bill image character recognition method and device |
| CN111325104A (en) * | 2020-01-22 | 2020-06-23 | 平安科技（深圳）有限公司 | Text recognition method, device and storage medium |
| CN111414905A (en) * | 2020-02-25 | 2020-07-14 | 泰康保险集团股份有限公司 | Text detection method, text detection device, electronic equipment and storage medium |
| CN111414905B (en) * | 2020-02-25 | 2023-08-18 | 泰康保险集团股份有限公司 | Text detection method, text detection device, electronic equipment and storage medium |
| CN111368902A (en) * | 2020-02-28 | 2020-07-03 | 北京三快在线科技有限公司 | Data labeling method and device |
| CN111325207A (en) * | 2020-03-05 | 2020-06-23 | 中国银行股份有限公司 | Bill identification method and device based on preprocessing |
| CN111291726A (en) * | 2020-03-12 | 2020-06-16 | 泰康保险集团股份有限公司 | Medical bill sorting method, device, equipment and medium |
| CN111291726B (en) * | 2020-03-12 | 2023-08-08 | 泰康保险集团股份有限公司 | Medical bill sorting method, device, equipment and medium |
| CN111401221A (en) * | 2020-03-12 | 2020-07-10 | 重庆农村商业银行股份有限公司 | Card ticket identification method, device, equipment and storage medium |
| CN111444792A (en) * | 2020-03-13 | 2020-07-24 | 安诚迈科(北京)信息技术有限公司 | Bill recognition method, electronic device, storage medium and device |
| CN111444792B (en) * | 2020-03-13 | 2023-05-09 | 安诚迈科(北京)信息技术有限公司 | Bill identification method, electronic equipment, storage medium and device |
| CN111340032A (en) * | 2020-03-16 | 2020-06-26 | 天津得迈科技有限公司 | Character recognition method based on application scene in financial field |
| CN111310762A (en) * | 2020-03-16 | 2020-06-19 | 天津得迈科技有限公司 | Intelligent medical bill identification method based on Internet of things |
| CN111476227A (en) * | 2020-03-17 | 2020-07-31 | 平安科技（深圳）有限公司 | Target field recognition method and device based on OCR (optical character recognition) and storage medium |
| CN111428599B (en) * | 2020-03-17 | 2023-10-20 | 北京子敬科技有限公司 | Bill identification method, device and equipment |
| CN111476227B (en) * | 2020-03-17 | 2024-04-05 | 平安科技（深圳）有限公司 | Target field identification method and device based on OCR and storage medium |
| CN111428599A (en) * | 2020-03-17 | 2020-07-17 | 北京公瑾科技有限公司 | Bill identification method, device and equipment |
| CN111414917A (en) * | 2020-03-18 | 2020-07-14 | 民生科技有限责任公司 | Identification method of low-pixel-density text |
| CN111462388A (en) * | 2020-03-19 | 2020-07-28 | 广州市玄武无线科技股份有限公司 | Bill inspection method and device, terminal equipment and storage medium |
| CN113469161A (en) * | 2020-03-31 | 2021-10-01 | 顺丰科技有限公司 | Method, device and storage medium for processing logistics list |
| CN111461100A (en) * | 2020-03-31 | 2020-07-28 | 重庆农村商业银行股份有限公司 | Bill identification method and device, electronic equipment and storage medium |
| CN113496115A (en) * | 2020-04-08 | 2021-10-12 | 中国移动通信集团广东有限公司 | File content comparison method and device |
| CN113496115B (en) * | 2020-04-08 | 2023-07-28 | 中国移动通信集团广东有限公司 | File content comparison method and device |
| CN111428725A (en) * | 2020-04-13 | 2020-07-17 | 北京令才科技有限公司 | Data structuring processing method and device and electronic equipment |
| CN111553334A (en) * | 2020-04-21 | 2020-08-18 | 招商局金融科技有限公司 | Questionnaire image recognition method, electronic device, and storage medium |
| CN111695439A (en) * | 2020-05-20 | 2020-09-22 | 平安科技（深圳）有限公司 | Image structured data extraction method, electronic device and storage medium |
| CN111695439B (en) * | 2020-05-20 | 2024-05-10 | 平安科技（深圳）有限公司 | Image structured data extraction method, electronic device and storage medium |
| CN111652232B (en) * | 2020-05-29 | 2023-08-22 | 泰康保险集团股份有限公司 | Bill identification method and device, electronic equipment and computer readable storage medium |
| CN111652232A (en) * | 2020-05-29 | 2020-09-11 | 泰康保险集团股份有限公司 | Bill identification method and device, electronic equipment and computer readable storage medium |
| CN111666868A (en) * | 2020-06-03 | 2020-09-15 | 阳光保险集团股份有限公司 | Insurance policy identification method and device and computer equipment |
| CN111666886A (en) * | 2020-06-08 | 2020-09-15 | 成都知识视觉科技有限公司 | Image preprocessing method for medical document structured knowledge extraction |
| CN111814785B (en) * | 2020-06-11 | 2024-03-29 | 浙江大华技术股份有限公司 | Invoice recognition method, training method of relevant model, relevant equipment and device |
| CN111814785A (en) * | 2020-06-11 | 2020-10-23 | 浙江大华技术股份有限公司 | Invoice recognition method, training method of related model, related equipment and device |
| CN111832423A (en) * | 2020-06-19 | 2020-10-27 | 北京邮电大学 | Bill information identification method, device and system |
| WO2022006829A1 (en) * | 2020-07-09 | 2022-01-13 | 国网电子商务有限公司 | Bill image recognition method and system, electronic device, and storage medium |
| CN111814906B (en) * | 2020-07-23 | 2023-07-11 | 上海东普信息科技有限公司 | Express delivery face list recognition model transplanting method, device, equipment and storage medium |
| CN111814906A (en) * | 2020-07-23 | 2020-10-23 | 上海东普信息科技有限公司 | Method, device and equipment for transplanting express waybill recognition model and storage medium |
| CN111881882A (en) * | 2020-08-10 | 2020-11-03 | 晶璞(上海)人工智能科技有限公司 | Medical bill rotation correction method and system based on deep learning |
| CN111931664A (en) * | 2020-08-12 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Mixed note image processing method and device, computer equipment and storage medium |
| CN111931664B (en) * | 2020-08-12 | 2024-01-12 | 腾讯科技（深圳）有限公司 | Mixed-pasting bill image processing method and device, computer equipment and storage medium |
| CN111968056A (en) * | 2020-08-18 | 2020-11-20 | 中国银行股份有限公司 | Online check deposit business processing method, client, cloud server and system |
| CN112052858A (en) * | 2020-09-02 | 2020-12-08 | 中国银行股份有限公司 | Method for extracting target field in bill image and related device |
| CN112052858B (en) * | 2020-09-02 | 2023-09-12 | 中国银行股份有限公司 | Method and related device for extracting target field in bill image |
| CN112037077A (en) * | 2020-09-03 | 2020-12-04 | 平安健康保险股份有限公司 | Seal identification method, device, equipment and storage medium based on artificial intelligence |
| CN112036396A (en) * | 2020-09-14 | 2020-12-04 | 上海高德威智能交通系统有限公司 | Ship name recognition method and device, electronic equipment and computer readable storage medium |
| CN112396047B (en) * | 2020-10-30 | 2022-03-08 | 中电金信软件有限公司 | Training sample generation method and device, computer equipment and storage medium |
| CN112241727A (en) * | 2020-10-30 | 2021-01-19 | 深圳供电局有限公司 | Multi-ticket identification method and system and readable storage medium |
| CN112396047A (en) * | 2020-10-30 | 2021-02-23 | 北京文思海辉金信软件有限公司 | Training sample generation method and device, computer equipment and storage medium |
| CN112434689A (en) * | 2020-12-01 | 2021-03-02 | 天冕信息技术(深圳)有限公司 | Method, device and equipment for identifying information in picture and storage medium |
| CN112464845A (en) * | 2020-12-04 | 2021-03-09 | 山东产研鲲云人工智能研究院有限公司 | Bill recognition method, equipment and computer storage medium |
| CN112560861B (en) * | 2020-12-10 | 2022-11-18 | 上海亿保健康管理有限公司 | Bill processing method, device, equipment and storage medium |
| CN112560861A (en) * | 2020-12-10 | 2021-03-26 | 上海亿保健康管理有限公司 | Bill processing method, device, equipment and storage medium |
| CN112541505A (en) * | 2020-12-11 | 2021-03-23 | 上海云从企业发展有限公司 | Text recognition method, text recognition device and computer-readable storage medium |
| CN112541505B (en) * | 2020-12-11 | 2021-07-23 | 上海云从企业发展有限公司 | Text recognition method, text recognition device and computer-readable storage medium |
| CN112508017A (en) * | 2020-12-15 | 2021-03-16 | 通号智慧城市研究设计院有限公司 | Intelligent digital display instrument reading identification method, system, processing equipment and storage medium |
| CN112507914A (en) * | 2020-12-15 | 2021-03-16 | 江苏国光信息产业股份有限公司 | OCR (optical character recognition) method and recognition system based on bankbook and bill characters |
| US20210312173A1 (en) * | 2020-12-18 | 2021-10-07 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus and device for recognizing bill and storage medium |
| CN112837466A (en) * | 2020-12-18 | 2021-05-25 | 北京百度网讯科技有限公司 | Bill recognition method, device, equipment and storage medium |
| CN112613553A (en) * | 2020-12-18 | 2021-04-06 | 中电金信软件有限公司 | Picture sample set generation method and device, computer equipment and storage medium |
| CN112580657A (en) * | 2020-12-23 | 2021-03-30 | 陕西天诚软件有限公司 | Self-learning character recognition method |
| CN112580657B (en) * | 2020-12-23 | 2022-11-01 | 陕西天诚软件有限公司 | Self-learning character recognition method |
| CN112613510A (en) * | 2020-12-25 | 2021-04-06 | 创新奇智(青岛)科技有限公司 | Picture preprocessing method, character recognition model training method and character recognition method |
| CN112613510B (en) * | 2020-12-25 | 2023-10-31 | 创新奇智(青岛)科技有限公司 | Picture preprocessing method, character recognition model training method and character recognition method |
| CN112632926A (en) * | 2020-12-29 | 2021-04-09 | 平安科技（深圳）有限公司 | Data processing method and device for bill, electronic equipment and storage medium |
| CN112632926B (en) * | 2020-12-29 | 2023-10-31 | 平安科技（深圳）有限公司 | Bill data processing method and device, electronic equipment and storage medium |
| CN112651353B (en) * | 2020-12-30 | 2024-04-16 | 南京红松信息技术有限公司 | Target calculation positioning and identifying method based on custom label |
| CN112784932B (en) * | 2021-03-01 | 2024-06-07 | 北京百炼智能科技有限公司 | Font identification method, device and storage medium |
| CN112784932A (en) * | 2021-03-01 | 2021-05-11 | 北京百炼智能科技有限公司 | Font identification method and device and storage medium |
| CN112989990B (en) * | 2021-03-09 | 2023-08-04 | 平安科技（深圳）有限公司 | Medical bill identification method, device, equipment and storage medium |
| CN112989990A (en) * | 2021-03-09 | 2021-06-18 | 平安科技（深圳）有限公司 | Medical bill identification method, device, equipment and storage medium |
| CN112818951B (en) * | 2021-03-11 | 2023-11-21 | 南京大学 | Ticket identification method |
| CN112818951A (en) * | 2021-03-11 | 2021-05-18 | 南京大学 | Ticket identification method |
| CN112699860B (en) * | 2021-03-24 | 2021-06-22 | 成都新希望金融信息有限公司 | Method for automatically extracting and sorting effective information in personal tax APP operation video |
| CN112699860A (en) * | 2021-03-24 | 2021-04-23 | 成都新希望金融信息有限公司 | Method for automatically extracting and sorting effective information in personal tax APP operation video |
| CN113077018A (en) * | 2021-06-07 | 2021-07-06 | 浙江大华技术股份有限公司 | Target object identification method and device, storage medium and electronic device |
| CN113095307A (en) * | 2021-06-09 | 2021-07-09 | 国网浙江省电力有限公司 | Automatic identification method for financial voucher information |
| CN113283421B (en) * | 2021-06-24 | 2024-03-01 | 中国平安人寿保险股份有限公司 | Information identification method, device, equipment and storage medium |
| CN113283421A (en) * | 2021-06-24 | 2021-08-20 | 中国平安人寿保险股份有限公司 | Information identification method, device, equipment and storage medium |
| CN113326895A (en) * | 2021-06-25 | 2021-08-31 | 湖南星汉数智科技有限公司 | Passenger ticket travel itinerary identification method and device, computer equipment and storage medium |
| CN113344690A (en) * | 2021-06-30 | 2021-09-03 | 中国工商银行股份有限公司 | Invoice reimbursement processing method and device |
| WO2023284608A1 (en) * | 2021-07-13 | 2023-01-19 | 深圳思谋信息科技有限公司 | Character recognition model generating method and apparatus, computer device, and storage medium |
| CN113642556A (en) * | 2021-08-04 | 2021-11-12 | 五八有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN113780116A (en) * | 2021-08-26 | 2021-12-10 | 众安在线财产保险股份有限公司 | Invoice classification method and device, computer equipment and storage medium |
| CN113723508B (en) * | 2021-08-30 | 2024-04-19 | 杭州米数科技有限公司 | Bill image classification method, device, computing equipment and storage medium |
| CN113723508A (en) * | 2021-08-30 | 2021-11-30 | 杭州米数科技有限公司 | Bill image classification method and device, computing equipment and storage medium |
| CN113705559A (en) * | 2021-08-31 | 2021-11-26 | 平安银行股份有限公司 | Character recognition method and device based on artificial intelligence and electronic equipment |
| CN113705559B (en) * | 2021-08-31 | 2024-05-10 | 平安银行股份有限公司 | Character recognition method and device based on artificial intelligence and electronic equipment |
| CN113920294A (en) * | 2021-10-20 | 2022-01-11 | 广东亿迅科技有限公司 | Mass invoice identification method and system and storage medium |
| CN113920294B (en) * | 2021-10-20 | 2024-06-11 | 广东亿迅科技有限公司 | Method, system and storage medium for identifying massive invoices |
| CN113963149A (en) * | 2021-10-29 | 2022-01-21 | 平安科技（深圳）有限公司 | Medical bill picture fuzzy judgment method, system, equipment and medium |
| CN114743198A (en) * | 2022-03-14 | 2022-07-12 | 中国银行股份有限公司 | Method and device for identifying bill with form |
| CN114926831A (en) * | 2022-05-31 | 2022-08-19 | 平安普惠企业管理有限公司 | Text-based recognition method and device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019174130A1 (en) | 2019-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108446621A (en) | Bank slip recognition method, server and computer readable storage medium | |
| CN110826519B (en) | Face shielding detection method and device, computer equipment and storage medium | |
| CN107798299B (en) | Bill information identification method, electronic device and readable storage medium | |
| RU2695489C1 (en) | Identification of fields on an image using artificial intelligence | |
| CN110210286B (en) | Fundus image-based abnormality identification method, fundus image-based abnormality identification device, fundus image-based abnormality identification equipment and fundus image-based abnormality identification storage medium | |
| CN107679997A (en) | Method, apparatus, terminal device and storage medium are refused to pay in medical treatment Claims Resolution | |
| CN107798321A (en) | A kind of examination paper analysis method and computing device | |
| WO2018090641A1 (en) | Method, apparatus and device for identifying insurance policy number, and computer-readable storage medium | |
| CN105989330A (en) | Picture detection method and apparatus | |
| Gao et al. | A Novel Deep Convolutional Neural Network Based on ResNet‐18 and Transfer Learning for Detection of Wood Knot Defects | |
| CN110210625A (en) | Modeling method, device, computer equipment and storage medium based on transfer learning | |
| CN113111880B (en) | Certificate image correction method, device, electronic equipment and storage medium | |
| WO2021232670A1 (en) | Pcb component identification method and device | |
| US11809519B2 (en) | Semantic input sampling for explanation (SISE) of convolutional neural networks | |
| CN110502694A (en) | Lawyer's recommended method and relevant device based on big data analysis | |
| CN112686258A (en) | Physical examination report information structuring method and device, readable storage medium and terminal | |
| CN110458644A (en) | A kind of information processing method and relevant device | |
| CN109086765B (en) | Licence plate recognition method, device, medium, server and automobile data recorder | |
| CN116311214B (en) | License plate recognition method and device | |
| CN111862040B (en) | Portrait picture quality evaluation method, device, equipment and storage medium | |
| CN113837151A (en) | Table image processing method and device, computer equipment and readable storage medium | |
| CN111507288A (en) | Image detection method, image detection device, computer equipment and storage medium | |
| Qin et al. | Finger-vein quality assessment based on deep features from grayscale and binary images | |
| Phoka et al. | Image based phishing detection using transfer learning | |
| CN111368602A (en) | Face image blurring degree evaluation method and device, readable storage medium and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180824 |