CN110837816A - Optical character recognition system, edge node and system - Google Patents
Optical character recognition system, edge node and system Download PDFInfo
- Publication number
- CN110837816A CN110837816A CN201911125924.3A CN201911125924A CN110837816A CN 110837816 A CN110837816 A CN 110837816A CN 201911125924 A CN201911125924 A CN 201911125924A CN 110837816 A CN110837816 A CN 110837816A
- Authority
- CN
- China
- Prior art keywords
- node
- image data
- image
- optical character
- available
- 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
- 238000012015 optical character recognition Methods 0.000 title claims abstract description 68
- 238000012545 processing Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000010801 machine learning Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- 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
Abstract
The invention provides an optical character recognition system, an edge node and a system, wherein the optical character recognition system comprises: the edge node is used for acquiring image data; when the image recognition capability is available, performing optical character recognition on the image data; when the image recognition capability is not available, uploading the image data to the cloud node; and the cloud node is used for carrying out optical character recognition on the image data uploaded by the edge node. The invention can identify the image data and has high efficiency.
Description
Technical Field
The invention relates to the field of internet, in particular to an optical character recognition system, an edge node and a system.
Background
Image data Recognition, namely Optical Character Recognition (OCR), Recognition, in the prior art, OCR Recognition generally photographs image data through a high-speed photographing instrument, transmits the image data to a cloud of a network layer for automatic processing, and returns an automatic processing result.
Disclosure of Invention
The embodiment of the invention provides an optical character recognition system, which is used for recognizing image data and has high efficiency, and the system comprises:
the edge node is used for acquiring image data; when the image recognition capability is available, performing optical character recognition on the image data; when the image recognition capability is not available, uploading the image data to the cloud node;
and the cloud node is used for carrying out optical character recognition on the image data uploaded by the edge node.
The embodiment of the invention provides an edge node which is used for identifying image data and has high efficiency, and the edge node comprises:
the image acquisition module is used for acquiring image data;
the image processing module is used for carrying out optical character recognition on the image data when the edge node has the image recognition capability; and uploading the image data to the cloud node when the edge node does not have the image identification capability.
The embodiment of the invention provides an edge system, which is used for identifying image data and has high efficiency, and the edge system comprises:
the edge node is used for acquiring image data; when the image recognition capability is available, performing optical character recognition on the image data; and uploading the image data to the cloud end node when the image recognition capability is not available.
In the embodiment of the invention, the edge node firstly acquires image data; then, when the image recognition capability is provided, optical character recognition is carried out on the image data; when the image recognition capability is not available, uploading the image data to the cloud node; and the cloud node is used for carrying out optical character recognition on the image data uploaded by the edge node. In the system, when the edge node has the image recognition capability, the optical character recognition is carried out on the image data; when the image recognition capability is not available, uploading the image data to the cloud node; the image data uploaded by the edge nodes are subjected to optical character recognition by the cloud nodes, so that the edge nodes are fully utilized, interaction with the cloud nodes is reduced, and the image data recognition efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a schematic diagram of an optical character recognition system in accordance with an embodiment of the present invention;
FIG. 2 is another schematic diagram of an optical character recognition system in accordance with an embodiment of the present invention;
FIG. 3 illustrates a process for image data recognition according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating an embodiment of image data recognition using a machine learning model;
FIG. 5 is a diagram of an edge node according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an edge node in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
Image data Recognition, namely image data Recognition, at present, OCR (Optical Character Recognition) Recognition generally photographs the listed image data through a high-speed photographing instrument, transmits the photographed image data to a cloud end of a network layer for automatic processing, and then returns an automatic processing result. For example, in banking, identification of documents such as bank cards and identification cards, professional bank notes (such as special invoices, value-added tax invoices, account receipts, and the like) and handwritten signatures are often required to be identified, and as the handling mode of banking is changed from a traditional counter mode, an internet bank mode and a telephone bank mode to mobile equipment such as a mobile phone bank and an intelligent counter, a data acquisition mode is more convenient and efficient, the data volume is exponentially increased, and the real-time performance of system identification notes is also required to be higher, so that the above mode cannot meet the existing requirements.
Fig. 1 is a schematic diagram of an optical character recognition system according to an embodiment of the present invention, as shown in fig. 1, the system includes:
the edge node is used for acquiring image data; when the image recognition capability is available, performing optical character recognition on the image data; when the image recognition capability is not available, uploading the image data to the cloud node;
and the cloud node is used for carrying out optical character recognition on the image data uploaded by the edge node.
In the embodiment of the invention, when the edge node has the image recognition capability, the edge node performs optical character recognition on the image data; when the image recognition capability is not available, uploading the image data to the cloud node; the image data uploaded by the edge nodes are subjected to optical character recognition by the cloud nodes, so that the edge nodes are fully utilized, interaction with the cloud nodes is reduced, and the image data recognition efficiency is improved.
During specific implementation, the cloud node can be a cloud server, the cloud server has strong computing power, the image data identification efficiency is high, but after the edge node is adopted to obtain the image data, the process of uploading the image data to the cloud node is influenced by network bandwidth, the identification result cannot be fed back in real time, and the efficiency is influenced, so that the edge node is firstly considered to be adopted to identify the image data as far as possible. One or more edge nodes can be provided, and can be determined according to actual conditions.
In an embodiment, the edge node is specifically configured to:
shooting image data; and/or, importing the image data in batch.
In one embodiment, an edge node comprises:
and a terminal node.
In a specific implementation, the terminal device may be a high-speed camera, a mobile phone, a counter, or the like, generally has a capability of capturing image data, stores the captured image data, and when the edge node has an image recognition capability, may directly perform optical character recognition on the stored image data. In addition, the edge node may also obtain the image data by importing the image data in batch. The range of the image data is wide, and for example, the image data of certificates which are relatively large in recognition amount and high in real-time requirement in banking business handling, and the like.
In one embodiment, an edge node comprises: an intermediate node between the terminal node and the cloud end node;
the terminal node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; uploading the image data to an intermediate node when the image recognition capability is unavailable;
the intermediate node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; and uploading the image data to the cloud end node when the image recognition capability is not available.
In the above embodiment, the intermediate node may be an intermediate server, for example, in banking, the intermediate server may be a branch server or a head office server, and through the above process, optical character recognition may be performed on the image data to be placed on the terminal device and the intermediate node as much as possible, so as to avoid interaction with the cloud server as much as possible, thereby reducing network transmission, also reducing occupation of network bandwidth, and improving experience of performing OCR recognition by a user.
In one embodiment, there are a plurality of intermediate nodes;
the intermediate node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; and when the image recognition capability is not available, uploading the image data to a previous-level node of the intermediate node, wherein the previous-level node of the intermediate node is the intermediate node or the cloud-end node.
Fig. 2 is another schematic diagram of an optical character recognition system in an embodiment of the present invention, and as shown in fig. 2, the edge system includes a plurality of intermediate nodes and a plurality of terminal devices, where the terminal nodes are specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; uploading the image data to an intermediate node when the image recognition capability is unavailable; the intermediate node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; and when the image recognition capability is not available, uploading the image data to a previous-level node of the intermediate node, wherein the previous-level node of the intermediate node is the intermediate node or the cloud-end node. After each intermediate node receives the image data, if the intermediate node does not have the image recognition capability, the intermediate node uploads the image data to the previous-level node of the intermediate node, and when all the intermediate nodes do not have the image recognition capability, the image data are finally transmitted to the cloud-end node to be recognized.
In specific implementation, no matter the edge node, the middle node or the cloud node, when performing image data identification, the method generally includes a plurality of steps, and fig. 3 is a process of performing image data identification in an embodiment of the present invention, as shown in fig. 3, the process includes:
the received image data is preprocessed, namely the processes from obtaining a binary image which is either black or white, or a gray-scale or color image to independently generating individual character images belong to image preprocessing. The method comprises image processing such as image normalization, noise removal, image correction and the like, and document preprocessing such as image-text analysis and separation of character lines and characters. In the aspect of image preprocessing, the current technology is mature, and generally, the image, the table and the text area must be separated first, and even the layout direction of the article, the synopsis of the article and the main body of the content can be distinguished, and the size of the text and the font of the text can be determined as the original document.
the character feature extraction is the core of the OCR, and the character feature extraction directly affects the recognition quality, and the character feature classification can be divided into two categories: one is statistical characteristics, such as the ratio of black/white point ratio in the text area, when the text area is divided into several areas, the combination of the ratio of black/white point ratio of the areas becomes a numerical vector of the space; the second is the structural characteristic, such as the number and position of the stroke end points and cross points of the character after the character image is thinned, or the stroke segments are taken as the characteristic and matched with a special comparison method for comparison.
there are many methods for comparison and identification, which can be performed by comparison with an existing database or by machine learning model, and include a well-known method such as euclidean space comparison method, Relaxation comparison method (relax comparison), Dynamic Programming (DP), and database establishment and comparison of a neural network, hmm (hidden markov model), and an expert System (expert System) is proposed to make the recognition result more stable, and the confidence level of the recognition result is particularly high by using the different complementarity of various feature comparison methods.
since the recognition rate of OCR cannot reach one hundred percent, the recognition can be corrected in order to improve the recognition accuracy, and the correction method includes word post-processing, manual correction and the like.
Fig. 4 is a flowchart of performing image data recognition by using a machine learning model according to an embodiment of the present invention, and corresponds to step 303, the process includes:
and step 404, in the training process, adjusting parameters of the machine learning model until a loss function of the machine learning model meets a preset convergence condition, and obtaining the trained machine learning model.
Of course, it is understood that other processes may be adopted for image data recognition using the machine learning model, and all the related modifications are within the scope of the present invention.
In the optical character recognition system provided by the embodiment of the invention, when the edge node has the image recognition capability, the optical character recognition is carried out on the image data; when the image recognition capability is not available, uploading the image data to the cloud node; the image data uploaded by the edge nodes are subjected to optical character recognition by the cloud nodes, so that the edge nodes are fully utilized, interaction with the cloud nodes is reduced, and the image data recognition efficiency is improved. In addition, the utilization rate of the edge nodes is improved, the computing pressure of the cloud end nodes is reduced, the processing and maintenance cost of the cloud end nodes is reduced, and the benefit is increased.
Based on the same inventive concept, the embodiment of the present invention further provides an edge node, as described in the following embodiments. Since the principles of these solutions are similar to those of optical character recognition systems, the repetition is not repeated.
Fig. 5 is a schematic diagram of an edge node in the embodiment of the present invention, and as shown in fig. 5, the edge node includes:
the image acquisition module is used for acquiring image data;
the image processing module is used for carrying out optical character recognition on the image data when the edge node has the image recognition capability; and uploading the image data to the cloud node when the edge node does not have the image identification capability.
In one embodiment, the image acquisition module is specifically configured to:
shooting image data; and/or, importing the image data in batch.
In one embodiment, the edge nodes are:
a terminal node;
or, an intermediate node between the end node and the cloud end node.
In one embodiment, the image processing module is specifically configured to:
when the image recognition capability is available, performing optical character recognition on the image data; and when the image recognition capability is not available, uploading the image data to a previous-level node of the intermediate node, wherein the previous-level node of the intermediate node is the intermediate node or the cloud-end node.
In the edge node provided by the embodiment of the invention, when the edge node has the image recognition capability, the edge node performs optical character recognition on image data; when the image recognition capability is not available, uploading the image data to the cloud node; the image data uploaded by the edge nodes are subjected to optical character recognition by the cloud nodes, so that the edge nodes are fully utilized, interaction with the cloud nodes is reduced, and the image data recognition efficiency is improved. In addition, the utilization rate of the edge nodes is improved, the computing pressure of the cloud end nodes is reduced, the processing and maintenance cost of the cloud end nodes is reduced, and the benefit is increased.
Based on the same inventive concept, the embodiment of the present invention further provides an edge system, as described in the following embodiments. Since the principles of these solutions are similar to those of optical character recognition systems, the repetition is not repeated.
Fig. 6 is a schematic diagram of an edge node in the embodiment of the present invention, and as shown in fig. 6, the edge system includes:
the edge node is used for acquiring image data; when the image recognition capability is available, performing optical character recognition on the image data; and uploading the image data to the cloud end node when the image recognition capability is not available.
In one embodiment, an edge node comprises:
and a terminal node.
In an embodiment, the edge node further comprises:
an intermediate node between the terminal node and the cloud end node;
the terminal node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; uploading the image data to an intermediate node when the image recognition capability is unavailable;
the intermediate node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; and uploading the image data to the cloud end node when the image recognition capability is not available.
In one embodiment, there are a plurality of intermediate nodes;
the intermediate node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; and when the image recognition capability is not available, uploading the image data to a previous-level node of the intermediate node, wherein the previous-level node of the intermediate node is the intermediate node or the cloud-end node.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (13)
1. An optical character recognition system, comprising:
the edge node is used for acquiring image data; when the image recognition capability is available, performing optical character recognition on the image data; when the image recognition capability is not available, uploading the image data to the cloud node;
and the cloud node is used for carrying out optical character recognition on the image data uploaded by the edge node.
2. The optical character recognition system of claim 1, wherein the edge node is specifically configured to:
shooting image data; and/or, importing the image data in batch.
3. The optical character recognition system of claim 1 wherein the edge node comprises:
and a terminal node.
4. The optical character recognition system of claim 3 wherein the edge node comprises: an intermediate node between the terminal node and the cloud end node;
the terminal node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; uploading the image data to an intermediate node when the image recognition capability is unavailable;
the intermediate node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; and uploading the image data to the cloud end node when the image recognition capability is not available.
5. The optical character recognition system of claim 4 wherein there are a plurality of intermediate nodes;
the intermediate node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; and when the image recognition capability is not available, uploading the image data to a previous-level node of the intermediate node, wherein the previous-level node of the intermediate node is the intermediate node or the cloud-end node.
6. An edge node, comprising:
the image acquisition module is used for acquiring image data;
the image processing module is used for carrying out optical character recognition on the image data when the edge node has the image recognition capability; and uploading the image data to the cloud node when the edge node does not have the image identification capability.
7. The edge node of claim 6, wherein the image acquisition module is specifically configured to:
shooting image data; and/or, importing the image data in batch.
8. The edge node of claim 6, wherein the edge node is:
a terminal node;
or, an intermediate node between the end node and the cloud end node.
9. The edge node of claim 8, wherein the image processing module is specifically configured to:
when the image recognition capability is available, performing optical character recognition on the image data; and when the image recognition capability is not available, uploading the image data to a previous-level node of the intermediate node, wherein the previous-level node of the intermediate node is the intermediate node or the cloud-end node.
10. An edge system, comprising:
the edge node is used for acquiring image data; when the image recognition capability is available, performing optical character recognition on the image data; and uploading the image data to the cloud end node when the image recognition capability is not available.
11. The edge system of claim 10, wherein an edge node comprises:
and a terminal node.
12. The edge system of claim 11, wherein the edge node further comprises:
an intermediate node between the terminal node and the cloud end node;
the terminal node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; uploading the image data to an intermediate node when the image recognition capability is unavailable;
the intermediate node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; and uploading the image data to the cloud end node when the image recognition capability is not available.
13. The edge system of claim 12, wherein there are a plurality of intermediate nodes;
the intermediate node is specifically configured to: when the image recognition capability is available, performing optical character recognition on the image data; and when the image recognition capability is not available, uploading the image data to a previous-level node of the intermediate node, wherein the previous-level node of the intermediate node is the intermediate node or the cloud-end node.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911125924.3A CN110837816A (en) | 2019-11-18 | 2019-11-18 | Optical character recognition system, edge node and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911125924.3A CN110837816A (en) | 2019-11-18 | 2019-11-18 | Optical character recognition system, edge node and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110837816A true CN110837816A (en) | 2020-02-25 |
Family
ID=69576750
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911125924.3A Pending CN110837816A (en) | 2019-11-18 | 2019-11-18 | Optical character recognition system, edge node and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110837816A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101088108A (en) * | 2005-01-06 | 2007-12-12 | 国际商业机器公司 | On-line correction of check code line recognition in point-of-sale stations |
CN101727594A (en) * | 2009-11-26 | 2010-06-09 | 南京烽火星空通信发展有限公司 | Method and system for identifying bar code of server-assisted mobile terminal |
US20140078559A1 (en) * | 2012-08-27 | 2014-03-20 | Tencent Technology (Shenzhen) Company Limited | Mobile terminals and methods for generating electronic documents for the same |
CN104036271A (en) * | 2014-06-11 | 2014-09-10 | 新达通科技股份有限公司 | Method and device for identifying crown word number of paper money and character, and ATM (Automatic Teller Machine) |
CN106446882A (en) * | 2016-08-31 | 2017-02-22 | 武汉颂大教育科技股份有限公司 | method for intelligently marking paper with trace left based on 8-character code |
CN106997686A (en) * | 2017-05-22 | 2017-08-01 | 苏州工业园区服务外包职业学院 | Parking lot intelligent control system and control method based on programmable map |
CN110132358A (en) * | 2019-05-30 | 2019-08-16 | 北京市众诚恒祥能源投资管理有限公司 | A kind of sewage disposal device fault monitoring system based on cloud computing |
CN110347500A (en) * | 2019-06-18 | 2019-10-18 | 东南大学 | For the task discharging method towards deep learning application in edge calculations environment |
CN110390246A (en) * | 2019-04-16 | 2019-10-29 | 江苏慧中数据科技有限公司 | A kind of video analysis method in side cloud environment |
-
2019
- 2019-11-18 CN CN201911125924.3A patent/CN110837816A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101088108A (en) * | 2005-01-06 | 2007-12-12 | 国际商业机器公司 | On-line correction of check code line recognition in point-of-sale stations |
CN101727594A (en) * | 2009-11-26 | 2010-06-09 | 南京烽火星空通信发展有限公司 | Method and system for identifying bar code of server-assisted mobile terminal |
US20140078559A1 (en) * | 2012-08-27 | 2014-03-20 | Tencent Technology (Shenzhen) Company Limited | Mobile terminals and methods for generating electronic documents for the same |
CN104036271A (en) * | 2014-06-11 | 2014-09-10 | 新达通科技股份有限公司 | Method and device for identifying crown word number of paper money and character, and ATM (Automatic Teller Machine) |
CN106446882A (en) * | 2016-08-31 | 2017-02-22 | 武汉颂大教育科技股份有限公司 | method for intelligently marking paper with trace left based on 8-character code |
CN106997686A (en) * | 2017-05-22 | 2017-08-01 | 苏州工业园区服务外包职业学院 | Parking lot intelligent control system and control method based on programmable map |
CN110390246A (en) * | 2019-04-16 | 2019-10-29 | 江苏慧中数据科技有限公司 | A kind of video analysis method in side cloud environment |
CN110132358A (en) * | 2019-05-30 | 2019-08-16 | 北京市众诚恒祥能源投资管理有限公司 | A kind of sewage disposal device fault monitoring system based on cloud computing |
CN110347500A (en) * | 2019-06-18 | 2019-10-18 | 东南大学 | For the task discharging method towards deep learning application in edge calculations environment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111652093B (en) | Text image processing method and device | |
CN112818951B (en) | Ticket identification method | |
CN110569341B (en) | Method and device for configuring chat robot, computer equipment and storage medium | |
CN110210413A (en) | A kind of multidisciplinary paper content detection based on deep learning and identifying system and method | |
CN111652332B (en) | Deep learning handwritten Chinese character recognition method and system based on two classifications | |
WO2021042505A1 (en) | Note generation method and apparatus based on character recognition technology, and computer device | |
CN101089874A (en) | Identify recognising method for remote human face image | |
US20200134382A1 (en) | Neural network training utilizing specialized loss functions | |
CN111832423A (en) | Bill information identification method, device and system | |
CN112766255A (en) | Optical character recognition method, device, equipment and storage medium | |
CN112257612B (en) | Unmanned aerial vehicle video frame filtering method and device based on edge intelligence | |
CN110969154A (en) | Text recognition method and device, computer equipment and storage medium | |
Wahlberg et al. | Large scale continuous dating of medieval scribes using a combined image and language model | |
US8195626B1 (en) | Compressing token-based files for transfer and reconstruction | |
Guan et al. | Improving handwritten OCR with augmented text line images synthesized from online handwriting samples by style-conditioned GAN | |
CN110942067A (en) | Text recognition method and device, computer equipment and storage medium | |
CN108090728B (en) | Express information input method and system based on intelligent terminal | |
CN106897770B (en) | Method and device for establishing license plate recognition model | |
Rahmat et al. | Android-based text recognition on receipt bill for tax sampling system | |
CN111881880A (en) | Bill text recognition method based on novel network | |
CN110837816A (en) | Optical character recognition system, edge node and system | |
CN116645683A (en) | Signature handwriting identification method, system and storage medium based on prompt learning | |
CN110555462A (en) | non-fixed multi-character verification code identification method based on convolutional neural network | |
CN116229528A (en) | Living body palm vein detection method, device, equipment and storage medium | |
Ajao et al. | Yoruba handwriting word recognition quality evaluation of preprocessing attributes using information theory approach |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200225 |
|
RJ01 | Rejection of invention patent application after publication |