CN111428710A - File classification collaboration robot and image character recognition method based on same - Google Patents
File classification collaboration robot and image character recognition method based on same Download PDFInfo
- Publication number
- CN111428710A CN111428710A CN202010182139.8A CN202010182139A CN111428710A CN 111428710 A CN111428710 A CN 111428710A CN 202010182139 A CN202010182139 A CN 202010182139A CN 111428710 A CN111428710 A CN 111428710A
- Authority
- CN
- China
- Prior art keywords
- picture
- text
- character recognition
- text line
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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 discloses a file classification cooperation robot and an image character recognition method based on the same, wherein the file classification cooperation robot comprises: the camera shooting device is used for shooting images of the file; the robot main body is used for placing the file to a position designated by a user; and the upper computer is used for identifying and outputting characters in the text pictures and correspondingly overall controlling the robot main body to move and is respectively connected with the camera device and the robot main body. The image character recognition method of the robot comprises the following steps: converting the acquired text line picture into a standard text line picture; constructing a picture character recognition model according to the standard text line picture; and outputting the characters in the text picture to be recognized based on the picture character recognition model. Compared with the prior art, the method has the advantages of ingenious design, intelligent and efficient classification and identification, can manually classify and arrange the files, and is favorable for reducing the workload of office people.
Description
Technical Field
The invention relates to the field of file management, in particular to a file classification cooperation robot and an image character recognition method based on the same.
Background
The existing urban population has high working pressure, a large amount of paper documents need to be processed, the arrangement of the paper documents is extremely precious in efficiency, and in view of the fact that most of the existing document classification methods adopt manual classification, the classification efficiency is low, and classification errors are easy to occur, a series of devices are correspondingly put out on the market to carry out machine classification so as to reduce the manual burden, but complete manual removal cannot be realized, for example, in Chinese patent CN110369296A, an office document arrangement system and a prompt method thereof are provided, the office document arrangement system adopts an RFID electronic tag mode to store and classify the paper documents, but still needs to manually carry out preliminary identification on the documents to be classified and install electronic tags on the documents to be classified, when the number of the documents to be classified is large, or the documents to be classified need to be numerous, still needs to manually install a large amount of electronic tags, the efficiency is still low and there is a certain error rate.
Disclosure of Invention
In order to solve the above problems, an object of the present invention is to provide a document classification collaboration robot and an image character recognition method based on the same, which can artificially classify and arrange documents and are beneficial to reducing the workload of office people.
In order to make up for the defects of the prior art, the embodiment of the invention adopts the following technical scheme:
a document classification collaboration robot, comprising:
the camera shooting device is used for shooting images of the file;
the robot main body is used for placing the file to a position designated by a user;
and the upper computer is used for identifying and outputting characters in the text pictures and correspondingly overall controlling the robot main body to move and is respectively connected with the camera device and the robot main body.
An image character recognition method of a file classification collaboration robot comprises the following steps:
converting the acquired text line picture into a standard text line picture;
constructing a picture character recognition model according to the standard text line picture;
and outputting the characters in the text picture to be recognized based on the picture character recognition model.
One or more technical schemes provided in the embodiment of the invention have at least the following beneficial effects: based on the cooperation of camera device, robot main part and host computer, can shoot the file picture and discern to characters wherein, and then realize the classification management to the file according to the characters of discernment, need not whole flow of artifical assistance, intelligent control degree is high, especially, construct relevant identification model to the picture of shooing, can systematically discern the characters in the file, the recognition effect is comparatively outstanding, the condition of misidentification is difficult to appear, greatly reduced the discernment error rate. Therefore, the invention has the advantages of ingenious design, intelligent and efficient classification and identification, can manually classify and arrange the files, and is favorable for reducing the workload of office people.
Further, the converting the acquired text line picture into a standard text line picture includes:
forming a preset text line binary image according to the acquired text line image;
determining a preset background picture according to the text picture to be recognized;
and synthesizing the text line binarization picture and the background picture to obtain a standard text line picture.
Further, the forming of the preset text line binarization picture according to the acquired text line picture includes:
extracting a plurality of related text contents from the acquired text line pictures;
processing the text content to generate a corresponding text image;
and forming a preset text line binarization picture according to the text image.
Further, the determining a preset background picture according to the text picture to be recognized includes:
determining a related standard template picture according to the text picture to be recognized;
acquiring a background area without characters from the standard template picture;
and forming a preset background picture according to the background area without the characters.
Further, the constructing a picture character recognition model according to the standard text line picture includes:
obtaining a corresponding sample picture according to the standard text line picture;
integrating the sample picture and the text content in the sample picture to form a training sample set;
and constructing a picture character recognition model through a deep neural network based on the training sample set, wherein the deep neural network is designed to take the sample picture as training data and take the text content of the sample picture as a label.
Further, the obtaining of the corresponding sample picture according to the standard text line picture includes:
and carrying out expansion change processing on the standard text line picture to obtain a corresponding sample picture, wherein the expansion change processing comprises one or more of perspective transformation, tone transformation, shadow effect addition, highlight effect addition, noise addition, clipping, scaling and compression.
Further, the outputting the words in the text picture to be recognized based on the picture word recognition model includes:
acquiring a plurality of related entries from characters in the text picture to be recognized;
splitting and combining a plurality of entries to generate new entries;
and converting the new entry into corresponding text content according to a preset font type.
Further, after the outputting the words in the text picture to be recognized based on the picture word recognition model, the method further includes:
and comparing the output characters in the text picture to be recognized with the determined user classification rule in the upper computer, if the output characters are consistent with the user classification rule in the upper computer, sending an instruction through the upper computer to enable the robot main body to place the file at a position appointed by a user, and otherwise, returning to obtain a text line picture and executing the image character recognition method.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The following description of the preferred embodiments of the present invention will be made in conjunction with the accompanying drawings.
FIG. 1 is a block diagram schematically illustrating a structure of a document classification collaboration robot according to an embodiment of the present invention;
FIG. 2 is a block diagram illustrating the overall steps of the image character recognition method according to the embodiment of the present invention;
fig. 3 is a schematic flow chart of a step "convert an acquired text line picture into a standard text line picture" in the image character recognition method according to the embodiment of the present invention;
FIG. 4 is a schematic flow chart of "building a text recognition model according to the standard text line picture" in the image text recognition method according to the embodiment of the present invention;
FIG. 5 is a schematic flow chart of "outputting characters in a text picture to be recognized based on the picture character recognition model" in the image character recognition method according to the embodiment of the present invention;
fig. 6 is a flowchart illustrating steps of an image character recognition method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It should be noted that, if not conflicted, the various features of the embodiments of the invention may be combined with each other within the scope of protection of the invention. Additionally, while functional block divisions are performed in system schematics, with logical sequences shown in flowcharts, in some cases the steps shown or described may be performed in a different order than the block divisions in the systems, or in the flowcharts.
The embodiments of the present invention will be further explained with reference to the drawings.
Referring to fig. 1, a document classification collaboration robot according to an embodiment of the present invention includes:
the camera shooting device is used for shooting images of the file;
the robot main body is used for placing the file to a position designated by a user;
and the upper computer is used for identifying and outputting characters in the text pictures and correspondingly overall controlling the robot main body to move and is respectively connected with the camera device and the robot main body.
Referring to fig. 2 and 6, an image character recognition method of a document classification collaboration robot according to an embodiment of the present invention includes:
converting the acquired text line picture into a standard text line picture;
constructing a picture character recognition model according to the standard text line picture;
and outputting the characters in the text picture to be recognized based on the picture character recognition model.
Specifically, based on the cooperation of camera device, robot main part and host computer, can shoot the file picture and discern to characters wherein, and then realize the classification management to the file according to the characters of discernment, need not artifical whole flow of assistance, intelligent control degree is high, especially, construct relevant identification model to the picture of shooing, can discern the characters in the file systematically, the recognition effect is comparatively outstanding, the condition of misrecognition is difficult to appear, greatly reduced discernment error rate. Therefore, the invention has the advantages of ingenious design, intelligent and efficient classification and identification, can manually classify and arrange the files, and is favorable for reducing the workload of office people.
The functions of the robot main body are not limited to the above contents, and actually, when the recognition shooting of the camera device is blocked, the camera device can feed back the recognition shooting to the upper computer, so that the robot main body is controlled to move the obstacle, and a good auxiliary shooting effect is achieved; in addition, the upper computer stores a database of standard text line pictures, so that a corresponding picture character recognition model can be easily constructed according to any standard text line picture; in addition, when the image capturing device identifies the document, based on the paper document classification rule input by the user, the document is generally shot and identified from near to far, that is, the document is shot one by one and identified respectively, so as to avoid mistakes and omissions. Referring to fig. 5, this step: and outputting the characters in the text picture to be recognized based on the picture character recognition model, wherein the characters in the text picture to be recognized can be output only by acquiring the text picture to be recognized and then inputting the acquired characters into the picture character recognition model, so that the method is very convenient and reliable.
Further, referring to fig. 3, the converting the acquired text line picture into a standard text line picture includes:
forming a preset text line binary image according to the acquired text line image;
determining a preset background picture according to the text picture to be recognized;
and synthesizing the text line binarization picture and the background picture to obtain a standard text line picture.
Specifically, the acquired text line picture is converted into a standard text line picture, and can be matched with a database of the standard text line picture in an upper computer, so that a related picture character recognition model can be conveniently constructed, wherein the acquired text line picture is binarized, the brightness of the text line picture can be more clearly visible, and the recognition degree of the text line picture is improved.
Further, the forming of the preset text line binarization picture according to the acquired text line picture includes:
extracting a plurality of related text contents from the acquired text line pictures;
processing the text content to generate a corresponding text image;
and forming a preset text line binarization picture according to the text image.
In this embodiment, the text features of the text line picture can be embodied by extracting the text content in the acquired text line picture, and then the text features are output in the form of a text image and finally converted into the text line binarization picture.
Furthermore, the determining a preset background picture according to the text picture to be recognized includes:
determining a related standard template picture according to the text picture to be recognized;
acquiring a background area without characters from the standard template picture;
and forming a preset background picture according to the background area without the characters.
Specifically, the text picture to be recognized is compared with the standard template picture, and the text picture to be recognized can be mapped on the standard template picture, so that only a background area without characters is acquired in the standard template picture, namely, the corresponding background area is extracted from the text picture to be recognized, and therefore, the background picture can be conveniently and effectively generated for the text picture to be recognized through the conversion.
Further, referring to fig. 4, the constructing a picture text recognition model according to the standard text line picture includes:
obtaining a corresponding sample picture according to the standard text line picture;
integrating the sample picture and the text content in the sample picture to form a training sample set;
and constructing a picture character recognition model through a deep neural network based on the training sample set, wherein the deep neural network is designed to take the sample picture as training data and take the text content of the sample picture as a label.
In the embodiment, training is performed based on the sample picture and the text content thereof, the features of the standard text line picture can be reflected in the training set, so that the recognition degree of the constructed and formed picture character recognition model is more accurate, and the picture data can be integrated and processed more stably by adopting the deep neural network for construction, so that the construction of the recognition model is more convenient and effective. Specifically, a CRNN model is set as a network model of a deep neural network, the CRNN model including a volume using CNNsA packed layer, a circulating layer using Bi L STM and a transcription layer using CTC, expressed as
Wherein χ ═ { I ═ Ii,,LII denotes a training sample set, Ii,L for the ith sample pictureIFor the text content in the ith sample picture, YIThe index i is the sequence number of the training data in the training sample set.
Further, the obtaining of the corresponding sample picture according to the standard text line picture includes:
and performing one or more of extended variable-view transformation, tone transformation, shadow effect addition, highlight effect addition, noise addition, clipping, scaling and compression on the standard text line picture. Specifically, the standard text line picture is subjected to the extended change processing, so that the picture defects existing in the standard text line picture can be eliminated, and a sample picture with more stable and rich properties can be obtained, wherein the extended change processing is obtained by the inventor according to experiments and experiences.
Further, the outputting the words in the text picture to be recognized based on the picture word recognition model includes:
acquiring a plurality of related entries from characters in the text picture to be recognized;
splitting and combining a plurality of entries to generate new entries;
and converting the new entry into corresponding text content according to a preset font type.
In the embodiment, by performing combined expansion on the characters in the text image, more new terms can be generated and the matching between the new terms and the text content can be realized, so that the application range of the method is expanded on the original basis, and the method can be adapted to the image character recognition model to output the characters in the text image to be recognized.
Further, after the outputting the words in the text picture to be recognized based on the picture word recognition model, the method further includes:
and comparing the output characters in the text picture to be recognized with the determined user classification rule in the upper computer, if the output characters are consistent with the user classification rule in the upper computer, sending an instruction through the upper computer to enable the robot main body to place the file at a position appointed by a user, and otherwise, returning to obtain a text line picture and executing the image character recognition method.
Specifically, the user classification rule determined in the upper computer is a classification method determined by the user, for example, according to mathematical characters, subject differences and the like, the user can conveniently participate in making the classification; because there is more than one file processed in practice, the steps can be repeatedly executed until judging whether the file is the last file, if so, the classification is ended, otherwise, the classification is continuously carried out according to the steps, and therefore, whether the characters in the text picture to be recognized meet the classification requirements of the user can be verified through comparison, so that errors can be found out conveniently, and the error rate is reduced.
While the preferred embodiments and basic principles of the present invention have been described in detail, it will be understood by those skilled in the art that the invention is not limited to the embodiments, but is intended to cover various modifications, equivalents and alternatives falling within the scope of the invention as claimed.
Claims (9)
1. A document classification collaboration robot, comprising:
the camera shooting device is used for shooting images of the file;
the robot main body is used for placing the file to a position designated by a user;
and the upper computer is used for identifying and outputting characters in the text pictures and correspondingly overall controlling the robot main body to move and is respectively connected with the camera device and the robot main body.
2. The image character recognition method of the file classification collaboration robot based on claim 1 is characterized by comprising the following steps:
converting the acquired text line picture into a standard text line picture;
constructing a picture character recognition model according to the standard text line picture;
and outputting the characters in the text picture to be recognized based on the picture character recognition model.
3. The image character recognition method based on the file classification collaboration robot as claimed in claim 2, wherein the converting the acquired text line picture into a standard text line picture comprises:
forming a preset text line binary image according to the acquired text line image;
determining a preset background picture according to the text picture to be recognized;
and synthesizing the text line binarization picture and the background picture to obtain a standard text line picture.
4. The image character recognition method based on the file classification collaboration robot as claimed in claim 3, wherein the step of forming the preset text line binarization picture according to the obtained text line picture comprises:
extracting a plurality of related text contents from the acquired text line pictures;
processing the text content to generate a corresponding text image;
and forming a preset text line binarization picture according to the text image.
5. The image character recognition method based on the file classification collaboration robot as claimed in claim 3, wherein the determining of the preset background picture according to the text picture to be recognized comprises:
determining a related standard template picture according to the text picture to be recognized;
acquiring a background area without characters from the standard template picture;
and forming a preset background picture according to the background area without the characters.
6. The image character recognition method based on the file classification collaboration robot as claimed in claim 2, wherein the constructing of the image character recognition model according to the standard text line image comprises:
obtaining a corresponding sample picture according to the standard text line picture;
integrating the sample picture and the text content in the sample picture to form a training sample set;
and constructing a picture character recognition model through a deep neural network based on the training sample set, wherein the deep neural network is designed to take the sample picture as training data and take the text content of the sample picture as a label.
7. The image character recognition method based on a document classification collaboration robot as claimed in claim 6, wherein the obtaining of the corresponding sample picture according to the standard text line picture comprises:
and carrying out expansion change processing on the standard text line picture to obtain a corresponding sample picture, wherein the expansion change processing comprises one or more of perspective transformation, tone transformation, shadow effect addition, highlight effect addition, noise addition, clipping, scaling and compression.
8. The image character recognition method based on a document classification collaboration robot as claimed in claim 2, wherein the outputting characters in the text image to be recognized based on the image character recognition model comprises:
acquiring a plurality of related entries from characters in the text picture to be recognized;
splitting and combining a plurality of entries to generate new entries;
and converting the new entry into corresponding text content according to a preset font type.
9. The image character recognition method based on a document classification collaboration robot as claimed in claim 2 or 8, wherein after outputting the characters in the text image to be recognized based on the image character recognition model, the method further comprises:
and comparing the output characters in the text picture to be recognized with the determined user classification rule in the upper computer, if the output characters are consistent with the user classification rule in the upper computer, sending an instruction through the upper computer to enable the robot main body to place the file at a position appointed by a user, and otherwise, returning to obtain a text line picture and executing the image character recognition method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010182139.8A CN111428710A (en) | 2020-03-16 | 2020-03-16 | File classification collaboration robot and image character recognition method based on same |
| PCT/CN2020/112598 WO2021184692A1 (en) | 2020-03-16 | 2020-08-31 | Document classification collaborative robot and image character recognition method based thereon |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010182139.8A CN111428710A (en) | 2020-03-16 | 2020-03-16 | File classification collaboration robot and image character recognition method based on same |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111428710A true CN111428710A (en) | 2020-07-17 |
Family
ID=71547960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010182139.8A Pending CN111428710A (en) | 2020-03-16 | 2020-03-16 | File classification collaboration robot and image character recognition method based on same |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111428710A (en) |
| WO (1) | WO2021184692A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112686243A (en) * | 2020-12-29 | 2021-04-20 | 平安普惠企业管理有限公司 | Method and device for intelligently identifying picture characters, computer equipment and storage medium |
| CN112906693A (en) * | 2021-03-05 | 2021-06-04 | 杭州费尔斯通科技有限公司 | Method for identifying subscript character and subscript character |
| WO2021184692A1 (en) * | 2020-03-16 | 2021-09-23 | 五邑大学 | Document classification collaborative robot and image character recognition method based thereon |
| CN113807416A (en) * | 2021-08-30 | 2021-12-17 | 国泰新点软件股份有限公司 | Model training method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104827459A (en) * | 2015-04-07 | 2015-08-12 | 济南大学 | Intelligent book arrangement robot and arrangement method thereof |
| CN206318532U (en) * | 2016-11-02 | 2017-07-11 | 孔庆周 | A kind of file ordering collating unit in bulk |
| CN107609549A (en) * | 2017-09-20 | 2018-01-19 | 北京工业大学 | The Method for text detection of certificate image under a kind of natural scene |
| CN108000525A (en) * | 2017-10-23 | 2018-05-08 | 广东数相智能科技有限公司 | A kind of taking care of books robot and the misplaced recognition methods of books based on robot |
| CN109650021A (en) * | 2018-12-27 | 2019-04-19 | 安徽清芝商用机器有限公司 | A kind of slim file accessing transportation robot device and its application method |
| CN110378350A (en) * | 2019-07-23 | 2019-10-25 | 中国工商银行股份有限公司 | A kind of method, apparatus and system of Text region |
| CN110414519A (en) * | 2019-06-27 | 2019-11-05 | 众安信息技术服务有限公司 | A kind of recognition methods of picture character and its identification device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI506461B (en) * | 2013-07-16 | 2015-11-01 | Univ Nat Taiwan Science Tech | Method and system for human action recognition |
| CN109325493A (en) * | 2018-08-23 | 2019-02-12 | 厦门理工学院 | A kind of character recognition method and anthropomorphic robot based on anthropomorphic robot |
| CN109807883A (en) * | 2018-12-17 | 2019-05-28 | 广州正瀚材料科技有限公司 | A kind of archiving method of file |
| CN110369296A (en) * | 2019-06-25 | 2019-10-25 | 安徽永顺信息科技有限公司 | A kind of office document clearing system and its reminding method |
| CN111428710A (en) * | 2020-03-16 | 2020-07-17 | 五邑大学 | File classification collaboration robot and image character recognition method based on same |
-
2020
- 2020-03-16 CN CN202010182139.8A patent/CN111428710A/en active Pending
- 2020-08-31 WO PCT/CN2020/112598 patent/WO2021184692A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104827459A (en) * | 2015-04-07 | 2015-08-12 | 济南大学 | Intelligent book arrangement robot and arrangement method thereof |
| CN206318532U (en) * | 2016-11-02 | 2017-07-11 | 孔庆周 | A kind of file ordering collating unit in bulk |
| CN107609549A (en) * | 2017-09-20 | 2018-01-19 | 北京工业大学 | The Method for text detection of certificate image under a kind of natural scene |
| CN108000525A (en) * | 2017-10-23 | 2018-05-08 | 广东数相智能科技有限公司 | A kind of taking care of books robot and the misplaced recognition methods of books based on robot |
| CN109650021A (en) * | 2018-12-27 | 2019-04-19 | 安徽清芝商用机器有限公司 | A kind of slim file accessing transportation robot device and its application method |
| CN110414519A (en) * | 2019-06-27 | 2019-11-05 | 众安信息技术服务有限公司 | A kind of recognition methods of picture character and its identification device |
| CN110378350A (en) * | 2019-07-23 | 2019-10-25 | 中国工商银行股份有限公司 | A kind of method, apparatus and system of Text region |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021184692A1 (en) * | 2020-03-16 | 2021-09-23 | 五邑大学 | Document classification collaborative robot and image character recognition method based thereon |
| CN112686243A (en) * | 2020-12-29 | 2021-04-20 | 平安普惠企业管理有限公司 | Method and device for intelligently identifying picture characters, computer equipment and storage medium |
| CN112906693A (en) * | 2021-03-05 | 2021-06-04 | 杭州费尔斯通科技有限公司 | Method for identifying subscript character and subscript character |
| CN112906693B (en) * | 2021-03-05 | 2022-06-24 | 杭州费尔斯通科技有限公司 | Method for identifying subscript character and subscript character |
| CN113807416A (en) * | 2021-08-30 | 2021-12-17 | 国泰新点软件股份有限公司 | Model training method and device, electronic equipment and storage medium |
| CN113807416B (en) * | 2021-08-30 | 2024-04-05 | 国泰新点软件股份有限公司 | Model training method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021184692A1 (en) | 2021-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428710A (en) | File classification collaboration robot and image character recognition method based on same | |
| CN108664996B (en) | Ancient character recognition method and system based on deep learning | |
| CN111782772A (en) | Text automatic generation method, device, equipment and medium based on OCR technology | |
| CN112818951B (en) | Ticket identification method | |
| CN103488983A (en) | Business card OCR data correction method and system based on knowledge base | |
| CN111860525B (en) | Bottom-up optical character recognition method suitable for terminal block | |
| CN109583438B (en) | The recognition methods of the text of electronic image and image processing apparatus | |
| CN102663138A (en) | Method and device for inputting formula query terms | |
| CN112862024B (en) | Text recognition method and system | |
| CN112883980B (en) | Data processing method and system | |
| CN112507800A (en) | Pedestrian multi-attribute cooperative identification method based on channel attention mechanism and light convolutional neural network | |
| CN115862045B (en) | Case automatic identification method, system, equipment and storage medium based on image-text identification technology | |
| CN114092938B (en) | Image recognition processing method and device, electronic equipment and storage medium | |
| CN113626444A (en) | Table query method, device, equipment and medium based on bitmap algorithm | |
| Obaidullah et al. | Structural feature based approach for script identification from printed Indian document | |
| CN113780276A (en) | Text detection and identification method and system combined with text classification | |
| CN115830620B (en) | Archive text data processing method and system based on OCR | |
| CN111444876A (en) | Image-text processing method and system and computer readable storage medium | |
| CN112446297B (en) | Electronic vision aid and intelligent mobile phone text auxiliary reading method applicable to same | |
| Ajao et al. | Yoruba handwriting word recognition quality evaluation of preprocessing attributes using information theory approach | |
| CN111178409B (en) | Image matching and recognition system based on big data matrix stability analysis | |
| Satav et al. | Data extraction from invoices using computer vision | |
| CN109460701B (en) | Font identification method based on longitudinal and transverse histograms | |
| CN112329695A (en) | Dynamic handwriting recognition method based on intelligent blackboard | |
| CN112395834A (en) | Brain graph generation method, device and equipment based on picture input and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |