CN117058693A - Intelligent handwriting recognition method of electromagnetic touch screen - Google Patents
Intelligent handwriting recognition method of electromagnetic touch screen Download PDFInfo
- Publication number
- CN117058693A CN117058693A CN202311321705.9A CN202311321705A CN117058693A CN 117058693 A CN117058693 A CN 117058693A CN 202311321705 A CN202311321705 A CN 202311321705A CN 117058693 A CN117058693 A CN 117058693A
- Authority
- CN
- China
- Prior art keywords
- handwriting
- data
- input
- touch screen
- handwriting data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012805 post-processing Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 230000006698 induction Effects 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 11
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000006872 improvement Effects 0.000 description 6
- 238000012795 verification Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 230000005672 electromagnetic field Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000013518 transcription Methods 0.000 description 1
- 230000035897 transcription Effects 0.000 description 1
Classifications
-
- 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
- G06V30/32—Digital ink
- G06V30/36—Matching; Classification
-
- 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
- G06V30/18—Extraction of features or characteristics of the image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Discrimination (AREA)
Abstract
The invention relates to the technical field of handwriting recognition, in particular to an intelligent handwriting recognition method of an electromagnetic touch screen. Which comprises the following method steps: capturing handwriting data of handwriting input, and continuously learning and adapting to the personalized handwriting style of a user; collecting input handwriting data, and preprocessing the collected handwriting data; extracting features from the handwriting data after the preprocessing operation, identifying the handwriting data after the feature extraction, identifying different cultural backgrounds, and performing post-processing operation on the identified handwriting data; and matching the handwriting data after the post-processing operation with a font library to obtain a matching result. The invention can more accurately identify and understand the handwriting input of the user by continuously learning and adapting to the habit and personalized handwriting style of the user, thereby improving the identification accuracy.
Description
Technical Field
The invention relates to the technical field of handwriting recognition, in particular to an intelligent handwriting recognition method of an electromagnetic touch screen.
Background
In recent years, the intelligent handwriting recognition technology is applied more and more widely, the handwriting recognition technology is applied to our daily life, and is also applied to a plurality of industries, the intelligent handwriting recognition technology mainly converts handwriting of handwriting into a text form, and the intelligent handwriting recognition technology can be applied to scenes such as scanning of handwriting notes, transcription of handwriting letters, automatic processing of handwriting forms and the like, so that the importance of the intelligent handwriting recognition technology is seen, when handwriting is input and recognized, the handwritten characters can be directly used as input for recognition, a keyboard input mode can be replaced, and the working efficiency and the convenience of information management are improved.
Although the intelligent handwriting recognition technology brings great convenience to our life and work, the intelligent handwriting recognition method may have the problem of low recognition accuracy under certain conditions, especially for some complicated fonts, fuzzy or skewed handwriting texts, the error recognition or partial recognition error may be caused, thus affecting the accuracy of recognition results, and the special handwriting style or individuation requirements for individual users may not be fully satisfied, not only may the handwriting habit and character structure of different cultural backgrounds be different, but also the intelligent handwriting recognition method may have difficulty in recognizing some special characters, symbols or writing rules, thus causing insufficient sensitivity to handwriting of specific cultures, affecting the accuracy and adaptability of recognition, so that we provide the intelligent handwriting recognition method of the electromagnetic touch screen.
Disclosure of Invention
The invention aims to provide an intelligent handwriting recognition method of an electromagnetic touch screen, so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides an intelligent handwriting recognition method for an electromagnetic touch screen, comprising the following method steps:
s1, capturing handwriting data of handwriting input by an electromagnetic touch screen through information of an induction pen, continuously learning and adapting to personalized handwriting styles of users, and transmitting the handwriting data of different styles into a training data set for storage;
s2, acquiring input handwriting data, and preprocessing the acquired handwriting data;
s3, extracting characteristics of the handwriting data after the preprocessing operation, identifying the handwriting data after the characteristics are extracted, identifying different cultural backgrounds, and performing post-processing operation on the identified handwriting data;
and S4, matching the handwriting data after post-processing operation with a font library to obtain a matching result.
As a further improvement of the technical scheme, the electromagnetic touch screen in S1 captures input handwriting data by sensing position, pressure and angle information of a pen, a linear regression incremental training algorithm is utilized to continuously learn and adapt to personalized handwriting styles of users, handwriting data of different styles are captured, and handwriting data of different styles are transmitted into a training data set and stored.
As a further improvement of the technical scheme, the linear regression incremental training algorithm formula:
;
representing capturing handwriting data of different styles;
representing the number of fonts of the input handwriting; />Is the number of samples used to control the stride of the update;
representing the position of the input handwriting; />Representative pressure of the input handwriting;
representing an angle of input handwriting;
representing a modified vector of the input handwriting, comprising a position +.>Corresponding actual output values;
representing the predicted value obtained by multiplying the font number of the input handwriting, the position of the input handwriting and the angle of the input handwriting;
representing the difference between the actual output value and the model predicted value.
As a further improvement of the technical scheme, the S2 collects input handwriting data, performs preprocessing operation on the collected handwriting data, and performs feature extraction on the handwriting data after the preprocessing operation.
As a further improvement of the technical scheme, in the step S3, feature extraction is performed on the handwriting data after the preprocessing operation, the feature extraction is performed to describe the shape, the outline and the curve of handwriting, and meanwhile, the handwriting data after the feature extraction is identified.
As a further improvement of the technical scheme, in the step S4, the handwriting data after the feature extraction is identified, handwriting under different cultural backgrounds is identified, the identified handwriting data is converted into identifiable text data, then the converted text data is predicted, and meanwhile, the converted text data is subjected to post-processing operation.
As a further improvement of the technical scheme, in S4, the text data after the post-processing operation and the predicted text data are matched, and the matching result is obtained by matching the text data after the post-processing operation and the predicted text data with the text data in the font library.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the intelligent handwriting recognition method of the electromagnetic touch screen, handwriting data of different styles are captured, the custom and the personalized handwriting style of a user are continuously learned and adapted, handwriting input of the user can be more accurately recognized and understood, and therefore recognition accuracy is improved.
2. In the intelligent handwriting recognition method of the electromagnetic touch screen, handwriting data after feature extraction are recognized, handwriting under different cultural backgrounds is recognized, handwriting recognition is performed according to writing standards and habits of the handwriting data after feature extraction on specific languages, and therefore writing modes of users are adapted, and recognition accuracy and perception are improved.
Drawings
FIG. 1 is a block diagram of the overall steps of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The invention provides an intelligent handwriting recognition method of an electromagnetic touch screen, referring to FIG. 1, comprising the following steps:
s1, capturing handwriting data of handwriting input by an electromagnetic touch screen through information of an induction pen, continuously learning and adapting to personalized handwriting styles of users, and transmitting the handwriting data of different styles into a training data set for storage;
s2, acquiring input handwriting data, and preprocessing the acquired handwriting data;
s3, extracting characteristics of the handwriting data after the preprocessing operation, identifying the handwriting data after the characteristics are extracted, identifying different cultural backgrounds, and performing post-processing operation on the identified handwriting data;
and S4, matching the handwriting data after post-processing operation with a font library to obtain a matching result.
Firstly, the electromagnetic touch screen in S1 captures input handwriting data through sensing position, pressure and angle information of a pen, the electromagnetic touch screen is mainly realized based on an electromagnetic induction principle, the motion of the pen is tracked through an electromagnetic field on a sensing plate, a linear regression incremental training algorithm is utilized, the system continuously learns and adapts to the personalized handwriting style of a user, the handwriting style is different from person to person through learning the personalized handwriting style of the user, the handwriting characteristics of each person are unique, handwriting data of different styles are captured, the system can better adapt to the habit of the user, personalized handwriting recognition experience is provided, the user can write more naturally, excessive correction and adjustment are not needed, so that the use comfort and satisfaction of the user can be increased, meanwhile, handwriting data of different styles are transmitted into a training data set and stored, more samples can be improved and researched through storing handwriting data of different styles, researchers can discover and understand handwriting data of different styles through analyzing the handwriting data of different styles, and provide more reference and guidance for optimizing recognition algorithm and improving handwriting style performance;
the method comprises the following steps of:
1. construction of the induction plate: the induction plate is a key component of the electromagnetic touch screen and is generally composed of two layers of electromagnetic plates (also called induction layers), wherein one layer is a transverse direction induction plate and the other layer is a longitudinal direction induction plate;
2. transmitting electromagnetic signals: the induction plate emits a low frequency electromagnetic signal forming an electromagnetic field, typically at a frequency of several tens of khz, which is able to penetrate the upper induction layer.
3. Antenna and chip of induction pen: a small antenna is arranged in the induction pen and is provided with a small chip, the antenna is used as a connector between the induction pen and the induction plate, electromagnetic signals emitted by the induction plate are induced, and the induced signals are transmitted to the chip;
4. electromagnetic signal induction: a series of induction coils are arranged on the induction layer, the induction coils sense the information such as the position, the pressure, the angle and the like of the induction pen through electromagnetic signals emitted by the induction plate, and when the induction pen approaches the induction plate and contacts or floats with the induction plate, the induction coils sense the passing position and other parameters of the induction pen;
5. signal processing and output: the induction coil transmits the sensed signal to the signal processing module, samples, filters, amplifies and the like the signal to obtain more stable and accurate data, and outputs the processed data to a computer or other equipment for further processing and identification;
linear regression incremental training algorithm formula:
;
representing capturing handwriting data of different styles;
representing the number of fonts of the input handwriting; />Is the number of samples used to control the stride of the update;
representing the position of the input handwriting; />Representative pressure of the input handwriting;
representing an angle of input handwriting;
representing a modified vector of the input handwriting, comprising a position +.>Corresponding actual output values;
representing the predicted value obtained by multiplying the font number of the input handwriting, the position of the input handwriting and the angle of the input handwriting;
representing a difference value between the actual output value and the model predicted value;
the formula mainly enables the system to continuously learn and adapt to the personalized handwriting style of the user, the handwriting styles of different users can change along with the change of time and use habit, the system is allowed to learn and adapt to the personalized handwriting style of the user, the system has self-adapting capability, the system can adapt to the change of the user, the error rate is reduced, and high-quality handwriting recognition service is continuously provided.
Secondly, the handwriting data input through the induction pen is collected, the collected handwriting data is preprocessed, the preprocessing operation comprises denoising (the input handwriting data may contain some noise, such as random discontinuous points or suddenly-hopped values), smoothing (the input handwriting data usually has some burrs or oscillations, which affect the subsequent recognition algorithm, the smoothing method is usually adopted to enable the data to be smoother), normalization (the input handwriting data usually has different scales and ranges, the normalization processing needs to be carried out for facilitating the subsequent processing and recognition), data resampling (the sampling frequency of the original data set is adjusted to be new frequency so as to adapt to specific analysis or application requirements), and data correction (the input handwriting data has some errors, such as writing inclination or moving unevenness and the like, the data can be aligned through some correction methods), the quality of the input handwriting data can be improved through the preprocessing operation, the interference and noise can be reduced, the subsequent recognition algorithm is more accurate and reliable, and the handwriting characteristics of the preprocessed handwriting data are extracted.
The handwriting data after preprocessing operation is subjected to feature extraction, and the feature extraction method is utilized to describe the shape, the outline and the curve of handwriting, wherein the feature extraction method comprises a stroke length (the length of the stroke can be obtained by calculating Euclidean distance between points on a stroke path), an angle (the direction in which the stroke is positioned can be described by calculating the angle between adjacent strokes), a curvature (the curvature is a quantization index for describing the bending degree of the curve of the stroke), a slope (the slope is a quantization index for describing the inclination degree of a stroke line segment), a line width (the width feature of the line can be described by calculating the distance from the point to the axis on the stroke path), a contour feature (the outline feature can be extracted by calculating convex hulls, boundary rectangles, minimum circumscribed rectangles and the like of the stroke), a shape descriptor (the shape descriptor can be extracted by calculating the appearance feature of the stroke), and a gray histogram (the brightness distribution condition of the handwriting image can be described by calculating the gray histogram of the handwriting image).
The handwriting data after feature extraction is identified, handwriting under different cultural backgrounds is identified, the writing of the different cultural backgrounds possibly comprises special characters, symbols or writing rules, such as Chinese characters and Japanese kana, through identifying the cultural backgrounds, the system can better process and identify the special characters and symbols, errors and confusion are avoided, the identified handwriting data are converted into identifiable text data, after the handwriting is converted into a text form, editing, modifying and processing can be conveniently carried out, the text has a structured form, various operations such as copying, cutting, pasting and searching can be carried out, the information processing efficiency and convenience are improved, the converted text data are predicted, the next handwritten character or word of a user can be predicted in advance according to the input context and habit of the user through predicting the input handwriting data, in this way, the system can automatically complete partial input in the user input process, reduce the input burden of the user, improve the input speed and smoothness, and carry out post-processing operation on the converted text data.
Post-processing operations include error correction (errors may occur during recognition, such as wrongly recognized characters or words, by applying error correction algorithms, some obvious errors, such as spelling errors or word order errors, may be automatically corrected according to context and language model information, etc.), verification (verification of recognition results to exclude recognition errors or low confidence results, verification may be performed by setting a threshold, only accepting results with confidence higher than the threshold, or by other verification methods, such as character-level or language-level verification rules), correction (correction of uncertain recognition results according to specific rules or models, which may include correction based on language models, replacement of unlawful or low probability results with more reasonable words or phrases), consistency processing (recognition results may be connected and repaired to ensure consistency and consistency of results, for example, in text recognition tasks, language model-based methods may be applied, by supplementing missing words or repairing errors, results may be more orderly and naturally), the system may produce some errors or recognition errors in use, in particular by correcting errors or mistakes in text recognition, by skew or skew correction algorithms, and other corrective operations may be performed by fuzzy rules or by fuzzy rules.
Meanwhile, the text data after post-processing operation and the predicted text data are matched, so that fonts can be conveniently and accurately identified later, and the best matching result is obtained by matching the text data after post-processing operation and the predicted text data with the text data in the font library.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. The intelligent handwriting recognition method of the electromagnetic touch screen is characterized by comprising the following steps of: the method comprises the following steps:
s1, capturing handwriting data of handwriting input by an electromagnetic touch screen through information of an induction pen, continuously learning and adapting to personalized handwriting styles of users, and transmitting the handwriting data of different styles into a training data set for storage;
s2, acquiring input handwriting data, and preprocessing the acquired handwriting data;
s3, extracting characteristics of the handwriting data after the preprocessing operation, identifying the handwriting data after the characteristics are extracted, identifying different cultural backgrounds, and performing post-processing operation on the identified handwriting data;
and S4, matching the handwriting data after post-processing operation with a font library to obtain a matching result.
2. The intelligent handwriting recognition method of the electromagnetic touch screen according to claim 1, wherein the method comprises the following steps of: and S1, capturing input handwriting data by the electromagnetic touch screen through sensing position, pressure and angle information of a pen, and capturing handwriting data of different styles by adopting a linear regression incremental training algorithm to learn and adapt to personalized handwriting styles of users.
3. The intelligent handwriting recognition method of the electromagnetic touch screen according to claim 2, wherein the method comprises the following steps of: the formula of the linear regression incremental training algorithm is as follows:
;
representing capturing handwriting data of different styles;
representing the number of fonts of the input handwriting; />Is the number of samples used to control the stride of the update;
representing the position of the input handwriting; />Representative pressure of the input handwriting;
representing an angle of input handwriting;
representing a modified vector of the input handwriting, comprising a position +.>Corresponding actual output values;
representing the predicted value obtained by multiplying the font number of the input handwriting, the position of the input handwriting and the angle of the input handwriting;
representing the difference between the actual output value and the model predicted value.
4. The intelligent handwriting recognition method of the electromagnetic touch screen according to claim 1, wherein the method comprises the following steps of: and S2, acquiring input handwriting data, preprocessing the acquired handwriting data, and extracting features of the preprocessed handwriting data.
5. The intelligent handwriting recognition method of the electromagnetic touch screen according to claim 1, wherein the method comprises the following steps of: and in the step S3, the handwriting data after the preprocessing operation is subjected to feature extraction, the feature extraction is performed to describe the shape, the outline and the curve of handwriting, and meanwhile, the handwriting data after the feature extraction is identified.
6. The intelligent handwriting recognition method of the electromagnetic touch screen according to claim 1, wherein the method comprises the following steps of: and S3, recognizing the handwriting data after the feature extraction, recognizing handwriting under different cultural backgrounds, converting the recognized handwriting data into identifiable text data, predicting the converted text data, and performing post-processing operation on the converted text data.
7. The intelligent handwriting recognition method of the electromagnetic touch screen according to claim 1, wherein the method comprises the following steps of: and in the step S4, matching the text data after the post-processing operation and the predicted text data, and obtaining a matching result by matching the text data after the post-processing operation and the predicted text data with the text data in the font library.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311321705.9A CN117058693B (en) | 2023-10-13 | 2023-10-13 | Intelligent handwriting recognition method of electromagnetic touch screen |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311321705.9A CN117058693B (en) | 2023-10-13 | 2023-10-13 | Intelligent handwriting recognition method of electromagnetic touch screen |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117058693A true CN117058693A (en) | 2023-11-14 |
CN117058693B CN117058693B (en) | 2024-01-26 |
Family
ID=88655817
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311321705.9A Active CN117058693B (en) | 2023-10-13 | 2023-10-13 | Intelligent handwriting recognition method of electromagnetic touch screen |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117058693B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080086437A1 (en) * | 2006-10-05 | 2008-04-10 | Siemens Corporate Research, Inc. | Incremental Learning of Nonlinear Regression Networks For Machine Condition Monitoring |
JP2008102782A (en) * | 2006-10-19 | 2008-05-01 | Ricoh Co Ltd | Handwriting input device and handwriting input method |
EP1920386A1 (en) * | 2005-08-29 | 2008-05-14 | Microsoft Corporation | Style aware use of writing input |
CN101930545A (en) * | 2009-06-24 | 2010-12-29 | 夏普株式会社 | Handwriting recognition method and device |
CN106384094A (en) * | 2016-09-18 | 2017-02-08 | 北京大学 | Chinese word stock automatic generation method based on writing style modeling |
CN115331236A (en) * | 2022-06-17 | 2022-11-11 | 北京易道博识科技有限公司 | Method and device for generating handwriting whole-line sample |
-
2023
- 2023-10-13 CN CN202311321705.9A patent/CN117058693B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1920386A1 (en) * | 2005-08-29 | 2008-05-14 | Microsoft Corporation | Style aware use of writing input |
CN101253513A (en) * | 2005-08-29 | 2008-08-27 | 微软公司 | Style aware use of writing input |
US20080086437A1 (en) * | 2006-10-05 | 2008-04-10 | Siemens Corporate Research, Inc. | Incremental Learning of Nonlinear Regression Networks For Machine Condition Monitoring |
JP2008102782A (en) * | 2006-10-19 | 2008-05-01 | Ricoh Co Ltd | Handwriting input device and handwriting input method |
CN101930545A (en) * | 2009-06-24 | 2010-12-29 | 夏普株式会社 | Handwriting recognition method and device |
CN106384094A (en) * | 2016-09-18 | 2017-02-08 | 北京大学 | Chinese word stock automatic generation method based on writing style modeling |
CN115331236A (en) * | 2022-06-17 | 2022-11-11 | 北京易道博识科技有限公司 | Method and device for generating handwriting whole-line sample |
Also Published As
Publication number | Publication date |
---|---|
CN117058693B (en) | 2024-01-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR100248917B1 (en) | Pattern recognizing apparatus and method | |
US9711117B2 (en) | Method and apparatus for recognising music symbols | |
AU737039B2 (en) | Methods and apparatuses for handwriting recognition | |
Balci et al. | Handwritten text recognition using deep learning | |
CN112052852B (en) | Character recognition method of handwriting meteorological archive data based on deep learning | |
US20060050962A1 (en) | System, process and software arrangement for recognizing handwritten characters | |
US20060062467A1 (en) | Symbol grouping and recognition in expression recognition | |
CN112818951B (en) | Ticket identification method | |
Malik et al. | An efficient segmentation technique for Urdu optical character recognizer (OCR) | |
EP3828685B1 (en) | Gesture stroke recognition in touch-based user interface input | |
CN101354749B (en) | Method for making dictionary, hand-written input method and apparatus | |
Kasem et al. | Advancements and Challenges in Arabic Optical Character Recognition: A Comprehensive Survey | |
Singh et al. | Online handwritten Gurmukhi words recognition: An inclusive study | |
CN117058693B (en) | Intelligent handwriting recognition method of electromagnetic touch screen | |
CN117152768A (en) | Off-line identification method and system for scanning pen | |
CN112528980B (en) | OCR recognition result correction method and terminal and system thereof | |
CN113569577B (en) | Text recognition method based on natural language semantic analysis | |
Bennour et al. | A deep learning framework for historical manuscripts writer identification using data-driven features | |
Rani et al. | A performance efficient technique for recognition of Telugu script using template matching | |
JP3180792B2 (en) | Character recognition device, character learning device, and computer-readable recording medium | |
Pavlidis et al. | On-line handwriting recognition using physics-based shape metamorphosis | |
Sweidan et al. | Handwritten Arabic Bills Reader and Recognizer | |
CN117111826B (en) | Capacitive pen screen interaction control method and system based on handwriting characteristics | |
EP4086744B1 (en) | Gesture stroke recognition in touch-based user interface input | |
CN117975466B (en) | Universal scene card identification system based on layout analysis |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |