CN112329695A - Dynamic handwriting recognition method based on intelligent blackboard - Google Patents

Dynamic handwriting recognition method based on intelligent blackboard Download PDF

Info

Publication number
CN112329695A
CN112329695A CN202011291885.7A CN202011291885A CN112329695A CN 112329695 A CN112329695 A CN 112329695A CN 202011291885 A CN202011291885 A CN 202011291885A CN 112329695 A CN112329695 A CN 112329695A
Authority
CN
China
Prior art keywords
handwriting
database
intelligent blackboard
point
dynamic
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.)
Withdrawn
Application number
CN202011291885.7A
Other languages
Chinese (zh)
Inventor
朱玉荣
汤鹏飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Wenxiang Information Technology Co Ltd
Original Assignee
Anhui Wenxiang Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Anhui Wenxiang Information Technology Co Ltd filed Critical Anhui Wenxiang Information Technology Co Ltd
Priority to CN202011291885.7A priority Critical patent/CN112329695A/en
Publication of CN112329695A publication Critical patent/CN112329695A/en
Withdrawn legal-status Critical Current

Links

Images

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
    • G06V30/333—Preprocessing; Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/30—Noise filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Character Discrimination (AREA)

Abstract

The invention discloses a dynamic handwriting recognition method based on an intelligent blackboard, and relates to the technical field of handwriting recognition. The invention comprises the following steps: collecting sample handwriting and establishing a template characteristic database; the intelligent blackboard updates a local template characteristic database; a sensor arranged in the intelligent blackboard acquires handwriting data and establishes a dynamic handwriting database; preprocessing the acquired handwriting data and extracting characteristics; performing feature matching according to the features and the template feature database, and calculating the accumulated distortion degree; comparing the calculated total distortion degree with a threshold value to judge the authenticity of the handwriting; and outputting matching result feedback. According to the method, a large amount of sample handwriting is collected to establish template characteristic data, the intelligent blackboard performs characteristic extraction on the teacher handwriting, handwriting characteristic matching is performed on the teacher handwriting and the template characteristic database, accumulated distortion is calculated, the matching result is fed back and stored, and therefore the recognition efficiency and accuracy of the intelligent blackboard handwriting are improved.

Description

Dynamic handwriting recognition method based on intelligent blackboard
Technical Field
The invention belongs to the technical field of handwriting recognition, and particularly relates to a dynamic handwriting recognition method based on an intelligent blackboard.
Background
With the rapid advance of computer technology, man-machine interaction technology is more and more popular in people's life. Human-computer interaction (HCI) technology refers to an interactive process between a Human and a computer that is performed by a user and the computer using some operation method. The development of the system is approximately in a pure manual operation stage, a language command control stage, a user interface stage and the like, however, with the continuous development of the artificial intelligence and other technologies in recent years, the development of the human-computer interaction technology is gradually emphasized.
With the continuous expansion of computers in the application field, the existing teacher blackboard cannot meet the higher-level requirements of students and teachers on daily requirements. In the teaching process of using the intelligent blackboard by a teacher, the teacher needs to use the electronic pen to write on the display screen of the intelligent blackboard in a way, so that students can conveniently observe and study in a classroom; however, the existing intelligent blackboard has certain defects in handwriting recognition of teachers, such as: in the course of lessons, because of the difference of disciplines, the teacher often clamps Chinese, English and letters on the writing board, and the conversion recognition rate of the intelligent blackboard is not high; the handwriting, writing habit and writing strokes of the teacher are different, so that the intelligent blackboard is also the reason of difficult recognition and low accuracy; the writing habits of different teachers are different, for example, after a terminal call is written, a point is printed at the tail habitually, the intelligent blackboard is often analyzed into data or a symbol, and the point has no practical significance and can not be displayed.
Therefore, the application document provides a dynamic handwriting recognition method based on an intelligent blackboard, and the problems can be effectively solved.
Disclosure of Invention
The invention aims to provide a dynamic handwriting recognition method based on a smart blackboard, which is characterized in that template characteristic data are established by collecting a large number of sample handwriting, the smart blackboard performs characteristic extraction on the teacher handwriting, performs handwriting characteristic matching with a template characteristic database, calculates accumulated distortion, and feeds back and stores matching results, thereby solving the problems of high handwriting recognition difficulty and low accuracy of the existing smart blackboard.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a dynamic handwriting recognition method based on an intelligent blackboard, which comprises the following steps:
step S1: the server processes a large number of collected sample chirographis and establishes a template characteristic database;
step S2: the intelligent blackboard remotely accesses a server and updates a local template characteristic database in real time;
step S3: a sensor arranged in the intelligent blackboard acquires handwriting data and establishes a dynamic handwriting database;
step S4: preprocessing the acquired handwriting data;
step S5: preprocessing the handwriting, and then extracting the characteristics of the handwriting;
step S6: matching the handwriting characteristics aiming at the extracted characteristics and the template characteristic database, and calculating the accumulated distortion degree through a text algorithm;
step S7: comparing the calculated total distortion degree with a threshold value to judge the authenticity of the handwriting;
step S8: and feeding back the result of correct matching to the dynamic handwriting database to find out and store the corresponding handwriting data.
Preferably, in the step S1, the server processes the collected large number of sample scripts as follows:
step S11: distinguishing and detecting noise points and edge points by adopting a pulse coupling neural network;
step S12: processing the noise points by utilizing a composite denoising algorithm;
step S13: extracting edge points in the handwriting image by adopting a cellular neural network;
step S14: obtaining connected line segments according to the extracted edge points, and extracting the characteristics of each connected line segment by using the curvature;
step S15: inputting the extracted features into a template feature database, and matching the extracted features with corresponding characters;
step S16: and training the cellular neural network according to the handwriting characteristics of the handwriting image training sample.
Preferably, in step S13, the de-noised handwriting grayscale image in step S12 is histogram equalized, and a cellular neural network model of the handwriting grayscale image is established for processing: taking the gray value of each pixel point in the equalized handwriting gray image as the corresponding input in the cellular neural network model; traversing the output value of each pixel point corresponding to the cell element in the cellular neural network; when the output of each pixel point is only in the range of [0,1], if the sum of the pixel values of other pixel points in the corresponding neighborhood is greater than a preset threshold value, the pixel is not an edge pixel, otherwise, the pixel is an edge pixel point; and when the output value is in the range of [ -1,0), the pixel is not an edge pixel.
Preferably, in step S14, the extracted features include: the proportion between the connected line segments, the position of the inflection point, the bending curvature of the line segments, the spacing between the line segments, the proportion between the line segments and the lengths of the first pen and the last pen.
Preferably, in step S3, the sensor built in the intelligent blackboard acquires handwriting data, the dynamic handwriting database includes a chinese database and an english database, and the dynamic handwriting database establishes a corresponding dynamic handwriting database according to the teacher.
Preferably, in the step S4, the preprocessing of the handwriting data includes rotation, smoothing, denoising, and size and position normalization of the handwriting.
Preferably, in step S6, when the text algorithm calculates the accumulated distortion, the coordinate of one point on the matching path is (m, n), the coordinate of the next point is any one point of (m +1, n), (m, n +1), or (m +1, n +1), and the point with the minimum distance from the point (m, n) to the 3 points is taken as the next starting point, where the distance recurrence formula is as follows:
Figure BDA0002784088920000041
wherein, D (R)m,Tn) And the accumulated distortion factor after point-by-point matching from the starting end point, matching of the m component in the reference template R and the n component in the template T to be tested is shown.
Preferably, said D (R)m,Tn) The accumulated distortion degree of a complete matching path is represented, so that the maximum accumulated distortion degree D (R) can be obtainedM,TN) The calculation formula is as follows:
Figure BDA0002784088920000042
preferably, in step S7, the input database template is matched with the template to be detected, the distortion degree is compared with a threshold value, and if the distortion degree is smaller than the threshold value, it is determined that the handwriting asks real handwriting; otherwise, judging the handwriting as false handwriting.
The invention has the following beneficial effects:
(1) according to the method, template characteristic data are established by collecting a large number of sample chirographs, the intelligent blackboard performs preprocessing characteristic extraction on the chirographs of the teacher, performs chirograph characteristic matching with the template characteristic database, feeds back a correct matching result and stores the result into the dynamic chirograph database, and therefore the recognition efficiency and accuracy of the chirographs of the intelligent blackboard are improved;
(2) according to the invention, an independent dynamic handwriting database is established for each subject teacher according to different subjects, the intelligent blackboard identifies the extracted features while acquiring the handwriting, and firstly, a teacher giving lessons on the handwriting is judged to match the features with the dynamic handwriting database, so that the matching range is reduced, and the handwriting identification efficiency is improved;
(3) according to the method, histogram equalization processing is carried out on the low-noise-reduced handwriting gray level image, a cellular neural network model of the handwriting gray level image is established for processing, and the gray level value of each pixel point in the equalized handwriting gray level image is used as corresponding input in the cellular neural network model; and traversing the output value of each pixel point in the cellular neural network corresponding to the cell element to judge whether the handwriting belongs to the edge pixel point or not, so that the redundant handwriting of the teacher is deleted, and the accuracy of handwriting recognition is improved.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a step diagram of a dynamic handwriting recognition method based on an intelligent blackboard according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention is a method for identifying dynamic handwriting based on an intelligent blackboard, comprising the following steps:
step S1: the server processes a large number of collected sample chirographis and establishes a template characteristic database;
step S2: the intelligent blackboard remotely accesses a server and updates a local template characteristic database in real time;
step S3: a sensor arranged in the intelligent blackboard acquires handwriting data and establishes a dynamic handwriting database;
step S4: preprocessing the acquired handwriting data;
step S5: preprocessing the handwriting, and then extracting the characteristics of the handwriting;
step S6: matching the handwriting characteristics aiming at the extracted characteristics and the template characteristic database, and calculating the accumulated distortion degree through a text algorithm;
step S7: comparing the calculated total distortion degree with a threshold value to judge the authenticity of the handwriting;
step S8: and feeding back the result of correct matching to the dynamic handwriting database to find out and store the corresponding handwriting data.
In step S1, the server processes the collected large number of sample scripts as follows:
step S11: distinguishing and detecting noise points and edge points by adopting a pulse coupling neural network;
step S12: processing the noise points by utilizing a composite denoising algorithm;
step S13: extracting edge points in the handwriting image by adopting a cellular neural network;
step S14: obtaining connected line segments according to the extracted edge points, and extracting the characteristics of each connected line segment by using the curvature;
step S15: inputting the extracted features into a template feature database, and matching the extracted features with corresponding characters;
step S16: and training the cellular neural network according to the handwriting characteristics of the handwriting image training sample.
In step S13, histogram equalization is performed on the de-noised handwriting grayscale image in step S12, and a cellular neural network model of the handwriting grayscale image is established for processing: taking the gray value of each pixel point in the equalized handwriting gray image as the corresponding input in the cellular neural network model; traversing the output value of each pixel point corresponding to the cell element in the cellular neural network; when the output of each pixel point is only in the range of [0,1], if the sum of the pixel values of other pixel points in the corresponding neighborhood is greater than a preset threshold value, the pixel is not an edge pixel, otherwise, the pixel is an edge pixel point; and when the output value is in the range of [ -1,0), the pixel is not an edge pixel.
In step S14, the extracted features include: the proportion between the connected line segments, the position of the inflection point, the bending curvature of the line segments, the spacing between the line segments, the proportion between the line segments and the lengths of the first pen and the last pen.
In step S3, the sensor built in the intelligent blackboard acquires handwriting data, the dynamic handwriting database includes a chinese database and an english database, and the dynamic handwriting database establishes a corresponding dynamic handwriting database according to the teacher.
In step S4, the preprocessing of the handwriting data includes rotation, smoothing, denoising, and size and position normalization of the handwriting.
In step S6, when the text algorithm calculates the accumulated distortion, the coordinate of one point on the matching path is (m, n), the coordinate of the next point is any one point of (m +1, n), (m, n +1), or (m +1, n +1), the point with the minimum distance from the point (m, n) to the 3 points is taken as the next starting point, and the distance recurrence formula is as follows:
Figure BDA0002784088920000071
wherein, D (R)m,Tn) And the accumulated distortion factor after point-by-point matching from the starting end point, matching of the m component in the reference template R and the n component in the template T to be tested is shown.
Wherein, D (R)m,Tn) The accumulated distortion degree of a complete matching path is represented, so that the maximum accumulated distortion degree D (R) can be obtainedM,TN) The calculation formula is as follows:
Figure BDA0002784088920000081
in step S7, the input database template is matched with the template to be detected, the distortion degree is compared with a threshold value, and if the distortion degree is smaller than the threshold value, the handwriting is judged to ask real handwriting; otherwise, judging the handwriting as false handwriting.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In addition, it is understood by those skilled in the art that all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing associated hardware, and the corresponding program may be stored in a computer-readable storage medium.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims (9)

1. A dynamic handwriting recognition method based on an intelligent blackboard is characterized by comprising the following steps:
step S1: the server processes a large number of collected sample chirographis and establishes a template characteristic database;
step S2: the intelligent blackboard remotely accesses a server and updates a local template characteristic database in real time;
step S3: a sensor arranged in the intelligent blackboard acquires handwriting data and establishes a dynamic handwriting database;
step S4: preprocessing the acquired handwriting data;
step S5: preprocessing the handwriting, and then extracting the characteristics of the handwriting;
step S6: matching the handwriting characteristics aiming at the extracted characteristics and the template characteristic database, and calculating the accumulated distortion degree through a text algorithm;
step S7: comparing the calculated total distortion degree with a threshold value to judge the authenticity of the handwriting;
step S8: and feeding back the result of correct matching to the dynamic handwriting database to find out and store the corresponding handwriting data.
2. The method for dynamically recognizing handwriting on the intelligent blackboard according to claim 1, wherein in the step S1, the server processes the collected sample handwriting as follows:
step S11: distinguishing and detecting noise points and edge points by adopting a pulse coupling neural network;
step S12: processing the noise points by utilizing a composite denoising algorithm;
step S13: extracting edge points in the handwriting image by adopting a cellular neural network;
step S14: obtaining connected line segments according to the extracted edge points, and extracting the characteristics of each connected line segment by using the curvature;
step S15: inputting the extracted features into a template feature database, and matching the extracted features with corresponding characters;
step S16: and training the cellular neural network according to the handwriting characteristics of the handwriting image training sample.
3. The method for dynamically recognizing handwriting on the basis of the intelligent blackboard according to claim 2, wherein in the step S13, the handwriting gray level image subjected to the denoising in the step S12 is subjected to histogram equalization processing, and a cellular neural network model of the handwriting gray level image is established for processing: taking the gray value of each pixel point in the equalized handwriting gray image as the corresponding input in the cellular neural network model; traversing the output value of each pixel point corresponding to the cell element in the cellular neural network; when the output of each pixel point is only in the range of [0,1], if the sum of the pixel values of other pixel points in the corresponding neighborhood is greater than a preset threshold value, the pixel is not an edge pixel, otherwise, the pixel is an edge pixel point; and when the output value is in the range of [ -1,0), the pixel is not an edge pixel.
4. The method for dynamically handwriting recognition based on intelligent blackboard according to claim 2, wherein in said step S14, the extracted features include: the proportion between the connected line segments, the position of the inflection point, the bending curvature of the line segments, the spacing between the line segments, the proportion between the line segments and the lengths of the first pen and the last pen.
5. The method for recognizing dynamic handwriting on the intelligent blackboard according to claim 1, wherein in step S3, the sensor built in the intelligent blackboard acquires handwriting data, the dynamic handwriting database includes a chinese database and an english database, and the dynamic handwriting database establishes a corresponding dynamic handwriting database according to the teacher.
6. The method for dynamically recognizing handwriting on the intelligent blackboard according to claim 1, wherein in step S4, the preprocessing of handwriting data includes rotation, smoothing, denoising and size and position normalization of handwriting.
7. A method for recognizing dynamic handwriting on a smart blackboard according to claim 1, wherein in step S6, when the text algorithm calculates the accumulated distortion, the coordinate of one point on the matching path is (m, n), and the coordinate of the next point is any one of (m +1, n), (m, n +1) or (m +1, n +1), and the point with the minimum distance from the point (m, n) to the 3 points is taken as the next starting point, and the distance recurrence formula is as follows:
Figure FDA0002784088910000031
wherein, D (R)m,Tn) And the accumulated distortion factor after point-by-point matching from the starting end point, matching of the m component in the reference template R and the n component in the template T to be tested is shown.
8. A method for intelligent blackboard-based dynamic handwriting recognition according to claim 7, wherein D (R) is the same as Rm,Tn) The accumulated distortion degree of a complete matching path is represented, so that the maximum accumulated distortion degree D (R) can be obtainedM,TN) The calculation formula is as follows:
Figure FDA0002784088910000032
9. the method for dynamically recognizing handwriting based on the intelligent blackboard according to claim 1, wherein in the step S7, the input database template is matched with the template to be detected, the distortion degree is compared with a threshold value, and if the distortion degree is smaller than the threshold value, the handwriting is judged to be true handwriting; otherwise, judging the handwriting as false handwriting.
CN202011291885.7A 2020-11-18 2020-11-18 Dynamic handwriting recognition method based on intelligent blackboard Withdrawn CN112329695A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011291885.7A CN112329695A (en) 2020-11-18 2020-11-18 Dynamic handwriting recognition method based on intelligent blackboard

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011291885.7A CN112329695A (en) 2020-11-18 2020-11-18 Dynamic handwriting recognition method based on intelligent blackboard

Publications (1)

Publication Number Publication Date
CN112329695A true CN112329695A (en) 2021-02-05

Family

ID=74321267

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011291885.7A Withdrawn CN112329695A (en) 2020-11-18 2020-11-18 Dynamic handwriting recognition method based on intelligent blackboard

Country Status (1)

Country Link
CN (1) CN112329695A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114327148A (en) * 2021-12-31 2022-04-12 深圳市泓宇星科技有限公司 Handwriting point reporting prediction method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114327148A (en) * 2021-12-31 2022-04-12 深圳市泓宇星科技有限公司 Handwriting point reporting prediction method
CN114327148B (en) * 2021-12-31 2022-08-12 深圳市泓宇星科技有限公司 Handwriting point reporting prediction method

Similar Documents

Publication Publication Date Title
CN108664996B (en) Ancient character recognition method and system based on deep learning
CN112115736B (en) Job correction method and system based on image recognition and intelligent terminal
WO2021042505A1 (en) Note generation method and apparatus based on character recognition technology, and computer device
CN109472249A (en) A kind of method and device of determining script superiority and inferiority grade
CN111626297A (en) Character writing quality evaluation method and device, electronic equipment and recording medium
WO2021208617A1 (en) Method and apparatus for recognizing station entering and exiting, terminal, and storage medium
CN114549993B (en) Method, system and device for grading line segment image in experiment and readable storage medium
CN110598686A (en) Invoice identification method, system, electronic equipment and medium
CN113673432A (en) Handwriting recognition method, touch display device, computer device and storage medium
CN114092938B (en) Image recognition processing method and device, electronic equipment and storage medium
CN112668541A (en) Intelligent dictation system based on dot matrix pen and method thereof
CN115620312A (en) Cross-modal character handwriting verification method, system, equipment and storage medium
CN102592142A (en) Computer-system-based handwritten signature stability evaluation method
CN112116840B (en) Job correction method and system based on image recognition and intelligent terminal
CN110414622B (en) Classifier training method and device based on semi-supervised learning
CN113361666B (en) Handwritten character recognition method, system and medium
Saraf et al. Devnagari script character recognition using genetic algorithm for get better efficiency
CN110705521A (en) Character-searching and stroke order teaching method and teaching interactive terminal
CN112329695A (en) Dynamic handwriting recognition method based on intelligent blackboard
CN112528799B (en) Teaching live broadcast method and device, computer equipment and storage medium
CN116645683A (en) Signature handwriting identification method, system and storage medium based on prompt learning
CN112580574A (en) Intelligent learning method and device based on handwritten character recognition
CN108830217B (en) Automatic signature distinguishing method based on fuzzy mean hash learning
Dahake et al. On segmentation of words from online handwritten Gurmukhi sentences
KR20230036674A (en) Character recognition method using HOG,SVM image processing

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20210205

WW01 Invention patent application withdrawn after publication