CN116483243B - Intelligent handwriting practicing system based on electronic induction pen and dot matrix paper - Google Patents
Intelligent handwriting practicing system based on electronic induction pen and dot matrix paper Download PDFInfo
- Publication number
- CN116483243B CN116483243B CN202310218663.XA CN202310218663A CN116483243B CN 116483243 B CN116483243 B CN 116483243B CN 202310218663 A CN202310218663 A CN 202310218663A CN 116483243 B CN116483243 B CN 116483243B
- Authority
- CN
- China
- Prior art keywords
- font
- module
- dot matrix
- electronic
- matrix paper
- 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.)
- Active
Links
- 239000011159 matrix material Substances 0.000 title claims abstract description 75
- 230000006698 induction Effects 0.000 title claims abstract description 49
- 238000011156 evaluation Methods 0.000 claims abstract description 30
- 238000012937 correction Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000004044 response Effects 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 230000007246 mechanism Effects 0.000 claims abstract description 7
- 239000010410 layer Substances 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 239000011521 glass Substances 0.000 claims description 6
- 239000011229 interlayer Substances 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 239000003990 capacitor Substances 0.000 claims description 4
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical group O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 3
- 239000011248 coating agent Substances 0.000 claims description 3
- 238000000576 coating method Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- -1 indium tin metal oxide Chemical class 0.000 claims description 3
- 229910044991 metal oxide Inorganic materials 0.000 claims description 3
- 230000010355 oscillation Effects 0.000 claims description 3
- 239000011241 protective layer Substances 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 7
- 238000005457 optimization Methods 0.000 abstract description 4
- 230000000295 complement effect Effects 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000002195 synergetic effect Effects 0.000 description 2
- 239000011449 brick Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B11/00—Teaching hand-writing, shorthand, drawing, or painting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/033—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor
- G06F3/0354—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor with detection of 2D relative movements between the device, or an operating part thereof, and a plane or surface, e.g. 2D mice, trackballs, pens or pucks
- G06F3/03545—Pens or stylus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/033—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor
- G06F3/038—Control and interface arrangements therefor, e.g. drivers or device-embedded control circuitry
- G06F3/0383—Signal control means within the pointing device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
- G06F3/0416—Control or interface arrangements specially adapted for digitisers
- G06F3/04164—Connections between sensors and controllers, e.g. routing lines between electrodes and connection pads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
- G06F3/0416—Control or interface arrangements specially adapted for digitisers
- G06F3/04166—Details of scanning methods, e.g. sampling time, grouping of sub areas or time sharing with display driving
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
- G06F3/044—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means by capacitive means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
- G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
- G06F3/04883—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
-
- 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
- G06V30/186—Extraction of features or characteristics of the image by deriving mathematical or geometrical properties from the whole image
- G06V30/188—Computation of moments
-
- 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
- G06V30/19—Recognition using electronic means
- G06V30/19007—Matching; Proximity measures
- G06V30/19093—Proximity measures, i.e. similarity or distance measures
-
- 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
- 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
- G06V30/347—Sampling; Contour coding; Stroke extraction
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/041—Indexing scheme relating to G06F3/041 - G06F3/045
- G06F2203/04104—Multi-touch detection in digitiser, i.e. details about the simultaneous detection of a plurality of touching locations, e.g. multiple fingers or pen and finger
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/048—Indexing scheme relating to G06F3/048
- G06F2203/04808—Several contacts: gestures triggering a specific function, e.g. scrolling, zooming, right-click, when the user establishes several contacts with the surface simultaneously; e.g. using several fingers or a combination of fingers and pen
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Educational Technology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Character Discrimination (AREA)
Abstract
An intelligent handwriting practicing system based on an electronic induction pen and dot matrix paper comprises an electronic induction pen input module, an electronic dot matrix paper response module, a font identification module, a font evaluation module and a font error correction module. The electronic handwriting pen and dot matrix paper collaborative system is matched with a font intelligent evaluation and optimization mechanism to realize automatic evaluation and error correction of handwriting fonts, the problems of handwriting font identification and evaluation are solved by utilizing a track identification algorithm model from the perspective of computer vision, an 8-area stroke identification method is developed, the defect that continuous fonts are difficult to identify in a traditional Sudoku identification model is overcome, writing environment gain parameters are introduced into clusters to complement the influence of writing environment, the application range is wide, the economic cost is low, and good social office and education benefits are brought.
Description
Technical Field
The invention relates to the field of cultural relics and literary education, in particular to an intelligent handwriting practicing system based on an electronic induction pen and dot matrix paper.
Background
The calligraphy art is inherited in a writing form, carries forward the Chinese traditional culture, records and witnesses the history. Along with the change and development of society and the change of emerging writing tools in the computer industry, handwriting is severely impacted as an ancient Chinese traditional art. Aiming at the current development situation, the country starts to promote the calligraphy art to the culture engineering height to grasp, affirms the artistic value and the culture value, and the calligraphy gradually becomes an interest of the modern society and becomes a knock brick on the artistic road. The writing of Chinese characters is more important, and especially the characteristics of the Chinese characters are recognized. However, the standard quantification of the writing of the fonts and the evaluation of the writing level still need to be explored at present, and the invention matches the cooperative system of the electronic handwriting pen and the dot matrix paper with the intelligent evaluation and optimization mechanism of the fonts to realize the automatic evaluation and error correction of the handwriting fonts, and solves the problems of handwriting font identification and evaluation by utilizing a track identification algorithm model from the perspective of computer vision. The method has the advantages of wide application range and low economic cost, can be popularized to wide social application, and brings good social office and educational benefits.
Disclosure of Invention
The invention aims to provide an intelligent handwriting practicing system based on an electronic induction pen and dot matrix paper, so as to solve the problems in the background technology.
In order to achieve the above purpose, an intelligent handwriting practicing system based on an electronic induction pen and dot matrix paper comprises an electronic induction pen input module, an electronic dot matrix paper response module, a font identification module, a font evaluation module and a font error correction module; the user uses the electronic induction pen to replace the traditional physical hand pen as a writing tool, inputs the handwriting of the electronic induction pen into the corresponding electronic dot matrix paper for storage and display, and places a computer vision recognition algorithm model in the dot matrix paper auxiliary microcircuit controller, evaluates the handwriting and the pen point of the font according to the handwriting outline and the stressing degree of the dot matrix paper unit block on the premise that no wrongly written word is found, and gives an improved suggestion; when the wrongly written characters are recognized, the correction of the wrong parts is fed back by highlight and color character bars, and after the writing is correct, an evaluation mechanism is iterated, and finally, the wrongly written characters are presented to a user through a UI interface so as to improve the handwriting capability of the user.
Further, the electronic induction pen input module adopts an electronic induction pen comprising a capacitance pen module, a chip module, a pressure sensor module, a circuit module and a Bluetooth module; the pressure sensor module is arranged at the nib and used for collecting nib pressure information and then transmitting the nib pressure information to the chip, so that the amplitude of an output signal is changed, the Bluetooth module is connected with the chip to enable the capacitance pen to work, after the Bluetooth module is connected with the chip, the circuit module is powered on, when the circuit module is disconnected, the pressure sensor module of the nib is used for sensing the nib pressure, when the pressure is increased, the amplitude of the output signal is changed, so that the writing width is changed, a Venturi bridge oscillating circuit is used when signals in the capacitance pen module occur, and the Venturi bridge oscillating circuit can feed back sinusoidal signals required by a generating circuit through the resistance setting of a frequency selecting network and an amplifying circuit of the circuit. The analog-to-digital conversion module adopts a hysteresis voltage comparator to process the sine signal generated by the Venturi bridge and convert the sine wave into rectangular wave with the same frequency, and has the advantages of good anti-interference performance and stable output. The voltage comparator is used for comparing the voltage input by the non-inverting input terminal and the voltage input by the inverting input terminal and outputting high and low levels.
Furthermore, the signal generated by the signal generation in the electronic induction pen module is selected from the input signals through the LC parallel frequency-selecting network, the generated useless signals are filtered, the harmonic output is reduced, the values of the capacitance and the inductance depend on the frequency of the signal generated by the Venturi bridge oscillating circuit, and a circuit protection model is arranged in the LC frequency-selecting network, so that the module damage caused by the surge impact in the circuit is avoided, and the diode is selected to stabilize the output end.
Furthermore, the electronic dot matrix paper response module is used for realizing multi-point touch, the screen is divided into blocks by adding the electrodes with mutual capacitance, and a group of mutual capacitance modules are arranged in each area to independently work, so that the electronic dot matrix paper can independently detect the touch condition of each area and simply realize multi-point touch after processing. The electronic dot matrix paper is a four-layer composite glass screen, the inner surface and the interlayer of the glass screen are respectively coated with an ITO (nanometer indium tin metal oxide), the outermost layer is a silica glass protective layer with the thickness of only 0.0015mm, the interlayer ITO coating is used as a working surface, and unlike the traditional nine Gong Gewang grids, an 8-area triangular grid is arranged, namely 8 lines to the center exist in a writing font unit square, so that 8 electrodes are led out from four corners, namely positive and negative electrodes are led out from each corner, and the inner ITO layer is a screen layer to ensure the working environment. When the electronic dot matrix paper is contacted, the electronic induction pen and the working surface form a coupling capacitor, because the working surface is connected with a high-frequency signal, the electronic induction pen absorbs a small current, the current flows out of electrodes on four corners of the screen respectively, the current flowing through 8 electrodes is in proportion to the distance from the electronic induction pen to four corners theoretically, and the controller obtains the position through precise calculation of the proportion of the 8 currents.
Further, in the electronic dot matrix paper response module, eight electrodes are led out from four corners of the electronic dot matrix paper, namely, positive and negative electrodes are led out from each corner, and eight boundary lines are formed along eight area dot matrix lines in a unit square.
Further, the invention uses the font recognition method of improved LLE dimension reduction representation, the original data in the high dimensional space structure is represented by the low dimensional space through transformation mapping, in the process of extracting the font characteristics, firstly, the size normalization is carried out on the image, the size of the processed image pixels is 32×32×1/8 in the 32× 32,8 area, the image is grayed, and the R=G=B three-way data are consistent; and (3) carrying out binarization processing on the image on the basis of the gray-scale image, so that the fonts and the background are completely black and white.
In the high-dimensional sample space, the samples zi can be represented by linear combinations of adjacent samples z j、zk、zl, and w ij、wik、wil represents weight parameters occupied by linear combinations of three adjacent samples of horizontal, vertical and depth in the written square, respectively:
zi=wijzj+wikzk+wilzl
in order that the relative positional relationship of local points in the low-dimensional space can still be maintained, deduction can be performed as follows:
Step1, selecting k adjacent points Z i1,zi2,…,zik for each sample point Z i in the high-dimensional data Z;
Step2, calculating a set of weights w i for each sample point, and reconstructing z i by using the weights z ik according to i epsilon [ i, k ];
Step3, expanding W i, i epsilon [ i, k ] into W i.
Further, the font recognition module divides the Chinese character font recognition method based on LLE dimension reduction representation into two parts.
(1) Extracting font characteristics; firstly, performing triangle gridding treatment on an 8 area of dot matrix paper, vectorizing font image data, converting high-dimensional font data into 2-dimensional data, calculating a clustering center and a clustering radius R k of each font in a low-dimensional data space, and reserving the clustering center and the clustering radius R k to a font characteristic dataset;
(2) Adjacent classification word recognition; in the same 2-dimensional coordinate space, the Euclidean distance between a single character image point and a font clustering center point in a font characteristic data set is used as a font similarity judging basis, a font characteristic data set is firstly constructed, then a Chinese character single character image to be recognized is reduced to 2 dimensions, the similarity between each font and a single character in the font characteristic data set is calculated, and the single character is classified as the font with the highest similarity;
(3) Constructing a font characteristic data set; let x be the character vector of the font after dimension reduction, K be the number of font types, R k be the cluster radius of the kth font, certer k be the cluster center of the kth font, dist (x i,xj) be the Euclidean distance of the two-font characters at the low dimension coordinates, C k be the standard font of the kth class, t be the single-word test picture, t ' be the single-word test picture after dimension reduction, and delta (t ', K) represent the similarity of the single-word t ' and the kth class of fonts:
Step1, randomly selecting 1 center point for each cluster of the clusters, namely, the triangle center in the 8 areas;
Step2, traversing the characteristic data, and dividing each data into a corresponding class group central point set;
Step3, calculating the average value of each group center point set and taking the average value as a new center point;
step4, repeating Step2 and Step3 until the central point is no longer converged;
Step5, calculating the radius R k of each cluster, wherein the Euclidean distance formula between two points is as follows:
Wherein δ represents a gain parameter of an environmental impact, which is used to complement the impact of ambient light, temperature and vibration on the clustering process, x represents a vector of data with m attributes, and x represents a vector of data with m attributes:
wherein, C k is a standard font of a k-type group; c k represents the number of standard font data objects in the kth class; certer k denotes a k-class center point, R k=max(dist(xk,Certerk), where x i∈Ck.
Furthermore, the font evaluation module performs the compartment matching degree research by using a square frame and a nine square frame, performs the compartment matching degree research by using a square frame 8 area mode after extracting the image moment of the calligraphy character frame, and can solve the problem of recognition of continuous fonts compared with the traditional 9 square frames, and the similarity between the calculated calligraphy character frames becomes the similarity between calculated moments after extracting the image moment of the calligraphy character frame. The correlation coefficient provides processing steps with different value ranges of variables, the correlation coefficient is adopted to calculate the correlation degree of invariant moment between the calligraphy character frameworks, the correlation coefficient is used for testing the similarity degree between the two calligraphy character frameworks, and when similarity calculation is carried out on the two groups of data X and Y, the correlation coefficient P of the two groups of data X and Y is as follows:
Wherein n represents the number of samples; p is the degree of correlation strength between X and Y; xi represents the value of the ith sample in X; Is the average of the X samples; yi represents the value of the ith sample in Y; /(I) Is the average of the Y samples.
Furthermore, the font evaluation module evaluates the fonts by using a correlation coefficient, the quantity value of the covariance cannot well reflect the correlation degree between two variables, the correlation coefficient is obtained by dividing the standard deviation of the two variables on the basis of the covariance result to obtain a final correlation result, and after the target handwritten character skeleton is extracted, the target handwritten character skeleton is respectively judged with the same character in the standard fonts in the source font library to obtain the font level evaluation, and finally the standard font is evaluated to determine the level.
Further, the font error correction module extracts the target handwritten character skeleton and respectively judges the similarity of the skeleton 8 area with the same character in the standard character in the source font library, so that after the character level evaluation is obtained, error detection is carried out on characters with bad scores, error part of the character is detected, error display feedback is carried out through electronic dot matrix paper, and error correction is carried out on the part.
The invention has the beneficial effects that: the invention discloses an intelligent handwriting practicing system based on an electronic induction pen and dot matrix paper, which comprises an electronic induction pen input module, an electronic dot matrix paper response module, a font identification module, a font evaluation module and a font error correction module. The electronic induction pen comprises a capacitance pen module, a chip module, a pressure sensor module and a Bluetooth module. The pressure sensor is arranged at the nib and is used for collecting nib pressure information and transmitting the nib pressure information to the chip so as to change the amplitude of an output signal. The Bluetooth module is connected with the chip to enable the capacitance pen to work. When the Bluetooth module is connected with the chip, power is supplied to the circuit module, and when the Bluetooth module is not connected with the chip, the circuit is disconnected, and no signal is output. The pressure sensor of the pen point is used for sensing the pressure of the pen point, and the amplitude of the output signal is changed when the pressure is larger, so that the writing width is changed. The signal generated by the voltage comparator of the electronic induction pen is used for selecting a required signal from input signals through an LC parallel frequency-selecting network, filtering out generated useless signals and reducing harmonic output. The values of the capacitance and the inductance depend on the frequency of the signal generated in the venturi bridge oscillating circuit. The electronic dot matrix paper response module used in the invention has the advantages that touch control positioning can be realized only by lightly touching, the electronic dot matrix paper can be normally used only once or without correction after production, and meanwhile, the service life of the electronic dot matrix paper is longer, so that the production cost of users and manufacturers is reduced. And the sensitivity of the electronic dot matrix paper is higher than that of the resistive screen, so that the electronic dot matrix paper supports multi-point touch control and is convenient to write. And simultaneously, an improved handwriting word skeletonization algorithm is used, firstly, a handwriting word image is input, then image preprocessing is carried out, an image refinement algorithm is used for traversing the handwriting word skeletons, diagonal redundant pixel elimination templates are used for removing redundancy of skeleton details, and after traversing is finished, the processed handwriting word skeletons are output. The invention uses the improved Chinese character font identification method of LLE dimension reduction representation, the original data in the high-dimensional space structure is represented by the low-dimensional space through transformation mapping, in the font characteristic extraction process, firstly, the size of the processed image pixel is 32 multiplied by 32,8 region triangle gridding, wherein each region unit pixel is 32 multiplied by 1/8, the rule matching degree research is carried out by using a rectangular frame 8 region mode, compared with the traditional 9 palace, the identification problem of continuous strokes can be solved, and after the image moment of the handwriting character frame is extracted, the similarity between the handwriting character frames is calculated to become the similarity between the calculation moments. According to the invention, a font intelligent evaluation and optimization mechanism is matched with a synergistic system of the electronic handwriting pen and the dot matrix paper, so that automatic evaluation and error correction of handwriting fonts are realized, and the problems of handwriting font identification and evaluation are solved by utilizing a track identification algorithm model from the perspective of computer vision.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation on the invention, and other drawings can be obtained by one of ordinary skill in the art without undue effort from the following drawings.
Fig. 1 is a schematic diagram of the structure of the present invention.
FIG. 2 is a schematic diagram of 8-zone stroke matching according to the present invention.
Detailed Description
The invention is further described in connection with the following examples.
Referring to fig. 1, the present invention aims to provide an intelligent handwriting practicing system based on an electronic induction pen and dot matrix paper, so as to solve the problems set forth in the background art.
In order to achieve the above purpose, an intelligent handwriting practicing system based on an electronic induction pen and dot matrix paper is provided, which comprises an electronic induction pen input module, an electronic dot matrix paper response module, a font identification module, a font evaluation module and a font error correction module;
The electronic induction pen input module comprises a capacitance pen module, a chip module, a pressure sensor module and a Bluetooth module; the pressure sensor is arranged at the nib and used for collecting nib pressure information and then transmitting the nib pressure information to the chip so as to change the amplitude of an output signal, the Bluetooth module is connected with the chip to enable the capacitance pen to work, when the Bluetooth module is connected with the chip, the circuit module is powered, when the Bluetooth module is not connected with the chip, the circuit is disconnected, no output signal is output, the pressure sensor of the nib is used for sensing the nib pressure, when the pressure is larger, the amplitude of the output signal is changed, and therefore the writing width is changed; the signal in the capacitance pen module is used as a venturi bridge oscillation circuit, the sine signal required by the circuit can be fed back and generated by the circuit through the arrangement of a frequency-selecting network of the circuit and the resistor of the amplifying circuit, the analog-to-digital conversion module adopts a hysteresis voltage comparator, the sine signal generated by the venturi bridge is processed, the sine wave is converted into a rectangular wave with the same frequency, and the handwriting signal is transmitted. The signal generated by the voltage comparator of the electronic induction pen is used for selecting a required signal from input signals through an LC parallel frequency-selecting network, filtering out generated useless signals and reducing harmonic output. The values of the capacitance and the inductance depend on the frequency of the signal generated in the venturi bridge oscillating circuit. The circuit protection module is arranged in the LC frequency-selecting network, and the LC frequency-selecting network output signal is connected with the pen point, so that the damage of an internal circuit caused by overlarge counter current of the pen point can be prevented; and in order to avoid module damage caused by surge impact in the circuit, a diode is selected to stabilize the voltage of the output end.
The electronic dot matrix paper response module is used for realizing multi-point touch control, the screen is divided into blocks by adding electrodes with mutual capacitance, and a group of mutual capacitance modules are arranged in each area and work independently, so that the electronic dot matrix paper can independently detect the touch control condition of each area and realize multi-point touch control simply after processing. The electronic dot matrix paper is a four-layer composite glass screen, the inner surface and the interlayer of the glass screen are respectively coated with an ITO (nanometer indium tin metal oxide), the outermost layer is a silica glass protective layer with the thickness of only 0.0015mm, the interlayer ITO coating is used as a working surface, and unlike the traditional nine Gong Gewang grids, an 8-area triangular grid is arranged, namely 8 lines to the center exist in a writing font unit grid, so that 8 electrodes are led out from four corners, and the inner layer ITO is a screen layer to ensure the working environment. When the electronic dot matrix paper is contacted, the electronic induction pen and the working surface form a coupling capacitor, because the working surface is connected with a high-frequency signal, the electronic induction pen absorbs a small current, the current flows out of electrodes on four corners of the screen respectively, the current flowing through 8 electrodes is in proportion to the distance from the electronic induction pen to four corners theoretically, and the controller obtains the position through the precise calculation of the four pairs of current proportions. 99% accuracy can be achieved with a response speed of less than 3 ms. The used electronic dot matrix paper response module has the advantages that: the touch control positioning can be realized only by lightly touching, the electronic dot matrix paper can be normally used only once or completely without correction after production, and meanwhile, the service life of the electronic dot matrix paper is longer, because the electronic dot matrix paper cannot be greatly deformed when touched, compared with the deformation of a resistance screen caused by pressure, the internal structure of the screen is easily damaged, or the screen is scratched, so that the electronic dot matrix paper also reduces the production cost of users and manufacturers. The electronic dot matrix paper is superior to the resistive screen in light loss and power consumption, and has higher sensitivity than the resistive screen, and the electronic dot matrix paper supports multi-point touch control, so that writing is facilitated.
The invention uses a Chinese character font recognition method based on LLE dimension reduction representation, which uses a low dimension space to represent original data in a high dimension space structure through transformation mapping, in the process of extracting font characteristics, firstly, the size of an image is normalized, the processed image pixel size is 32× 32,8 area triangle gridding, wherein each area unit pixel is 32×32×1/8, in order to reduce the influence on the image quality caused by processing equipment, filtering smoothing denoising processing is adopted, in order to reduce the influence of factors such as font color, the image is grayed, and R=G=B; and (3) carrying out binarization processing on the image on the basis of the gray-scale image, so that the fonts and the background are completely black and white. The LLE used in the invention is a nonlinear dimension reduction method, and maintains the linear relation among samples in the neighborhood.
The samples zi may be represented by a linear combination of adjacent samples z j、zk、zl in a high-dimensional sample space.
zi=wijzl+wikzk+wilzl
In order that the relative positional relationship of local points in the low-dimensional space can still be maintained, deduction can be performed as follows:
Step1, selecting k adjacent points Z i1,zi2,…,zik for each sample point Z i in the high-dimensional data Z;
Step2, calculating a set of weights w i for each sample point, and reconstructing z i by using the weights z ik according to i epsilon [ i, k ];
Step3, expanding W i, i epsilon [ i, k ] into W i.
The Chinese character font identification method based on improved LLE dimension reduction representation in the invention comprises the following steps:
(1) Extracting font characteristics; firstly, performing triangle gridding treatment on an 8 area of dot matrix paper, vectorizing font image data, converting high-dimensional font data into 2-dimensional data, calculating a clustering center and a clustering radius R k of each font in a low-dimensional data space, and reserving the clustering center and the clustering radius R k to a font characteristic dataset;
(2) Adjacent classification word recognition; in the same 2-dimensional coordinate space, the Euclidean distance between a single character image point and a font clustering center point in a font characteristic data set is used as a font similarity judging basis, a font characteristic data set is firstly constructed, then a Chinese character single character image to be recognized is reduced to 2 dimensions, the similarity between each font and a single character in the font characteristic data set is calculated, and the single character is classified as the font with the highest similarity;
(3) Constructing a font characteristic data set; let x be the character vector of the font after dimension reduction, K be the number of font types, R k be the cluster radius of the kth font, certer k be the cluster center of the kth font, dist (x i,xj) be the Euclidean distance of the two-font characters at the low dimension coordinates, C k be the standard font of the kth class, t be the single-word test picture, t ' be the single-word test picture after dimension reduction, and delta (t ', K) represent the similarity of the single-word t ' and the kth class of fonts:
Step1, randomly selecting 1 center point for each cluster of the clusters, namely, the triangle center in the 8 areas;
Step2, traversing the characteristic data, and dividing each data into a corresponding class group central point set;
Step3, calculating the average value of each group center point set and taking the average value as a new center point;
step4, repeating Step2 and Step3 until the central point is no longer converged;
Step5, calculating the radius R k of each cluster, wherein the Euclidean distance formula between two points is as follows:
Wherein δ represents a gain parameter of an environmental impact, which is used to complement the impact of ambient light, temperature and vibration on the clustering process, x represents a vector of data with m attributes, and x represents a vector of data with m attributes:
wherein, C k is a standard font of a k-type group; c k represents the number of standard font data objects in the kth class; certer k denotes a k-class center point, R k=max(dist(xk,Certerk), where x i∈Ck.
And the font evaluation module performs stroke matching degree research by using the area of the rectangular framework 8, and after extracting the image moments of the calligraphy character frameworks, the similarity between the calligraphy character frameworks is calculated to become the similarity between the calculated moments. The invention adopts the correlation coefficient to calculate the correlation degree of invariant moment between the calligraphy character skeletons, and is used for testing the similarity degree between the two calligraphy character skeletons. The correlation coefficient output ranges from-1 to +1, 0 represents uncorrelation, a negative value represents negative correlation, and a positive value represents positive correlation. When similarity calculation is performed on the two groups of data X and Y, the correlation coefficient P of the two groups of data X and Y is as follows:
Wherein n represents the number of samples; p is the degree of correlation strength between X and Y; xi represents the value of the ith sample in X; Is the average of the X samples; yi represents the value of the ith sample in Y; /(I) Is the average of the Y samples. And evaluating the fonts by using a correlation coefficient, wherein the quantity value of the covariance cannot well reflect the correlation degree between two variables, the correlation coefficient is obtained by dividing the standard deviation of the two variables on the basis of the covariance result to obtain a final correlation result, and after the target handwritten character skeleton is extracted, the final correlation result is respectively judged by using the final correlation result and the final standard character skeleton and the standard character skeleton such as the source font library and the like are used for judging the similarity of the skeleton nine-square lattice.
And the font error correction module is used for extracting the target handwritten character skeleton and respectively judging the similarity of the skeleton 8 area with the same character in the standard character in the source font library, so that after the character level evaluation is obtained, error detection is carried out on characters with bad scores, error part of the character is detected, error display feedback is carried out through the electronic dot matrix paper, and error correction is carried out on the part.
The user uses the electronic induction pen to replace the traditional physical hand pen as a writing tool, inputs the handwriting of the electronic induction pen into the corresponding electronic dot matrix paper for storage and display, and places a computer vision recognition algorithm model in the dot matrix paper auxiliary microcircuit controller, evaluates the handwriting and the pen point of the font according to the handwriting outline and the stressing degree of the dot matrix paper unit block on the premise that no wrongly written word is found, and gives an improved suggestion; when the wrongly written characters are recognized, the correction of the wrong parts is fed back by highlight and color character bars, and after the writing is correct, an evaluation mechanism is iterated, and finally, the wrongly written characters are presented to a user through a UI interface so as to improve the handwriting capability of the user.
The invention has the beneficial effects that: the invention discloses an intelligent handwriting practicing system based on an electronic induction pen and dot matrix paper, which comprises an electronic induction pen input module, an electronic dot matrix paper response module, a font identification module, a font evaluation module and a font error correction module. The electronic induction pen comprises a capacitance pen module, a chip module, a pressure sensor module and a Bluetooth module. The pressure sensor is arranged at the nib and is used for collecting nib pressure information and transmitting the nib pressure information to the chip so as to change the amplitude of an output signal. The Bluetooth module is connected with the chip to enable the capacitance pen to work. When the Bluetooth module is connected with the chip, power is supplied to the circuit module, and when the Bluetooth module is not connected with the chip, the circuit is disconnected, and no signal is output. The pressure sensor of the pen point is used for sensing the pressure of the pen point, and the amplitude of the output signal is changed when the pressure is larger, so that the writing width is changed. The signal generated by the voltage comparator of the electronic induction pen is used for selecting a required signal from input signals through an LC parallel frequency-selecting network, filtering out generated useless signals and reducing harmonic output. The values of the capacitance and the inductance depend on the frequency of the signal generated in the venturi bridge oscillating circuit. The electronic dot matrix paper response module used in the invention has the advantages that touch control positioning can be realized only by lightly touching, the electronic dot matrix paper can be normally used only once or without correction after production, and meanwhile, the service life of the electronic dot matrix paper is longer, so that the production cost of users and manufacturers is reduced. And the sensitivity of the electronic dot matrix paper is higher than that of the resistive screen, so that the electronic dot matrix paper supports multi-point touch control and is convenient to write. And simultaneously, an improved handwriting word skeletonization algorithm is used, firstly, a handwriting word image is input, then image preprocessing is carried out, an image refinement algorithm is used for traversing the handwriting word skeletons, diagonal redundant pixel elimination templates are used for removing redundancy of skeleton details, and after traversing is finished, the processed handwriting word skeletons are output. The invention uses the improved Chinese character font identification method of LLE dimension reduction representation, the original data in the high-dimensional space structure is represented by the low-dimensional space through transformation mapping, in the font characteristic extraction process, firstly, the size of the processed image pixel is 32 multiplied by 32,8 region triangle gridding, wherein each region unit pixel is 32 multiplied by 1/8, the rule matching degree research is carried out by using a rectangular frame 8 region mode, compared with the traditional 9 palace, the identification problem of continuous strokes can be solved, and after the image moment of the handwriting character frame is extracted, the similarity between the handwriting character frames is calculated to become the similarity between the calculation moments. According to the invention, a font intelligent evaluation and optimization mechanism is matched with a synergistic system of the electronic handwriting pen and the dot matrix paper, so that automatic evaluation and error correction of handwriting fonts are realized, and the problems of handwriting font identification and evaluation are solved by utilizing a track identification algorithm model from the perspective of computer vision.
The present invention also provides a computer readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement the above-described method. The computer readable storage medium may be, among other things, ROM, random access memory, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. The instructions stored therein may be loaded by a processor in the terminal and perform the methods described above.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. An intelligent handwriting practicing system based on an electronic induction pen and dot matrix paper comprises an electronic induction pen input module, an electronic dot matrix paper response module, a font identification module, a font evaluation module and a font error correction module; the user uses the electronic induction pen to replace the traditional physical hand pen as a writing tool, inputs the handwriting of the electronic induction pen into the corresponding electronic dot matrix paper for storage and display, and places a computer vision recognition algorithm model in the dot matrix paper auxiliary microcircuit controller, evaluates the handwriting and the pen point of the font according to the handwriting outline and the stressing degree of the dot matrix paper unit block on the premise that no wrongly written word is found, and gives an improved suggestion; when the wrongly written characters are identified, correcting the feedback error parts of the highlighted and colored character bars, and iterating an evaluation mechanism after the writing is correct, and finally presenting the corrected character bars to a user through a UI interface so as to improve the handwriting capability of the user;
the electronic induction pen input module comprises a capacitance pen module, a chip module, a pressure sensor module, a circuit module and a Bluetooth module; the pressure sensor module is arranged at the nib and used for collecting nib pressure information and then transmitting the nib pressure information to the chip so as to change the amplitude of an output signal, the Bluetooth module is connected with the chip to enable the capacitance pen to work, the pressure sensor module of the nib is used for sensing the pressure of the nib, when the pressure is increased, the amplitude of the output signal is changed so as to change the writing width, a Venturi bridge oscillation circuit is used when a signal in the capacitance pen module occurs, and the Venturi bridge oscillation circuit can feed back sine signals required by the circuit through the setting of a frequency selection network of the circuit and the resistance of the amplifying circuit;
The electronic induction pen input module is characterized in that a signal generated by a signal in the electronic induction pen input module is selected from input signals through an LC frequency-selective network, generated useless signals are filtered, harmonic output is reduced, the values of capacitance and inductance depend on the frequency of the signal generated by a Venturi bridge oscillating circuit, a circuit protection model is arranged in the LC frequency-selective network, and a diode is selected to stabilize the output end in order to avoid damage of the electronic induction pen input module caused by surge impact in the circuit;
The electronic dot matrix paper response module is used for realizing a multi-point touch function by increasing the number of electrodes, dividing a screen into blocks, setting a group of independent working mutual capacitors in each region, and simply realizing multi-point touch after the electronic dot matrix paper independently detects and processes the touch conditions of each region; the electronic dot matrix paper is a four-layer composite glass screen, the inner surface of the glass screen and the interlayer are respectively coated with a layer of nanometer indium tin metal oxide, the outermost layer is a silica glass protective layer with the thickness of only 0.0015mm, the interlayer coating is used as a working surface, and unlike the traditional nine Gong Gewang grids, an 8-area triangular grid is arranged, namely 8 lines to the center exist in a writing font unit square, so eight electrodes are led out from four corners, namely positive and negative electrodes are led out from each corner, and the inner layer is a screen layer so as to ensure the working environment; when the electronic dot matrix paper is contacted, the electronic induction pen and the working surface form a coupling capacitor, and because the working surface is connected with a high-frequency signal, the electronic induction pen absorbs a small current, the current flows out of electrodes at four corners of the screen respectively, the current flowing through eight electrodes is proportional to the distance from the electronic induction pen to four corners, and the eight current ratios are calculated by the controller.
2. The intelligent handwriting practicing system based on the electronic induction pen and the dot matrix paper according to claim 1, wherein the electronic dot matrix paper response module is characterized in that eight electrodes are led out from four corners of the electronic dot matrix paper, namely positive and negative electrodes are led out from each corner, and eight boundary lines are formed along eight area dot matrix lines in a unit square.
3. The intelligent handwriting practicing system based on the electronic induction pen and the dot matrix paper according to claim 2, wherein the font recognition module uses a font recognition method of improved LLE dimension reduction representation to represent raw data in a high-dimensional space structure by a low-dimensional space through transformation mapping, in the font feature extraction process, firstly, the size normalization is carried out on an image, the pixel size of the processed image is 32× 32,8 area triangle gridding, wherein each area unit pixel is 32×32×1/8, and the image is grayed, so that r=g=b three-way data are consistent; the image is subjected to binarization processing on the basis of the gray-scale image, so that fonts and backgrounds are completely black and white, a high-dimensional sample space sample z i is represented by a linear combination of adjacent samples z j、zk、zl, and w ij、wik、wil represents weight parameters occupied when three adjacent samples of horizontal, vertical and depth are linearly combined in a writing square respectively:
zi=wijzj+wikzk+wilzl
In order that the relative positional relationship of local points in the low-dimensional space can still be maintained, there are the steps of:
Step1, selecting k adjacent points Z i1,zi2,…,zik for each sample point Z i in the high-dimensional data Z;
Step2, calculating a set of weights w i for each sample point, and reconstructing z i by using the weights z ik according to i epsilon [ i, k ];
Step3, expanding W i, i epsilon [ i, k ] into W i.
4. The intelligent handwriting practicing system based on the electronic induction pen and the dot matrix paper according to claim 1, wherein the font evaluation module performs a compartment matching degree study by using an area mode of the dot matrix paper 8, compared with a traditional 9-grid, the recognition problem of continuous fonts is solved, after the image moment of the handwriting frameworks is extracted, the similarity between the handwriting frameworks is updated into the similarity between the calculated moments, the correlation coefficient provides the processing steps of different value ranges of variables, the correlation coefficient is adopted to calculate the correlation degree of invariant moment between the handwriting frameworks, the similarity between the two handwriting frameworks is tested, and when the similarity calculation is performed on two groups of data X and Y, the correlation coefficient P is as follows:
Wherein n represents the number of samples; p is the degree of correlation strength between X and Y; xi represents the value of the ith sample in X; Is the average of the X samples; yi represents the value of the ith sample in Y; /(I) Is the average of the Y samples.
5. The intelligent handwriting practicing system based on the electronic induction pen and the dot matrix paper according to claim 1, wherein the font error correction module extracts a target handwriting skeleton and makes a skeleton 8 region similarity judgment with the same character in a standard font in a source font library respectively, so that after the font level evaluation is obtained, error detection is carried out on characters which are not scored, an error part of the font is detected, error display feedback is carried out through the electronic dot matrix paper, and then error correction is carried out on the error part.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310218663.XA CN116483243B (en) | 2023-03-08 | 2023-03-08 | Intelligent handwriting practicing system based on electronic induction pen and dot matrix paper |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310218663.XA CN116483243B (en) | 2023-03-08 | 2023-03-08 | Intelligent handwriting practicing system based on electronic induction pen and dot matrix paper |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116483243A CN116483243A (en) | 2023-07-25 |
CN116483243B true CN116483243B (en) | 2024-06-04 |
Family
ID=87210895
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310218663.XA Active CN116483243B (en) | 2023-03-08 | 2023-03-08 | Intelligent handwriting practicing system based on electronic induction pen and dot matrix paper |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116483243B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107240330A (en) * | 2017-06-27 | 2017-10-10 | 北京新国人智慧科技股份有限公司 | System that handwriting display method and system, the intelligence of practising handwriting practise handwriting terminal and intelligence is practised handwriting |
CN110431517A (en) * | 2018-01-05 | 2019-11-08 | 深圳市汇顶科技股份有限公司 | Pressure detection method, device and the active pen of active pen |
CN110930129A (en) * | 2019-12-04 | 2020-03-27 | 广州云蝶科技有限公司 | Dot matrix paper pen technology application method combined with weekly work plan |
CN112668541A (en) * | 2021-01-06 | 2021-04-16 | 青岛鱼之乐教育科技有限公司 | Intelligent dictation system based on dot matrix pen and method thereof |
CN112836542A (en) * | 2021-02-07 | 2021-05-25 | 深圳柔果信息科技有限公司 | Method, system and computer readable medium for practicing calligraphy based on dot matrix code |
CN115620312A (en) * | 2022-09-09 | 2023-01-17 | 重庆傲雄在线信息技术有限公司 | Cross-modal character handwriting verification method, system, equipment and storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11042247B2 (en) * | 2019-06-14 | 2021-06-22 | Valve Corporation | Cluster-based sensor assignment |
-
2023
- 2023-03-08 CN CN202310218663.XA patent/CN116483243B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107240330A (en) * | 2017-06-27 | 2017-10-10 | 北京新国人智慧科技股份有限公司 | System that handwriting display method and system, the intelligence of practising handwriting practise handwriting terminal and intelligence is practised handwriting |
CN110431517A (en) * | 2018-01-05 | 2019-11-08 | 深圳市汇顶科技股份有限公司 | Pressure detection method, device and the active pen of active pen |
CN110930129A (en) * | 2019-12-04 | 2020-03-27 | 广州云蝶科技有限公司 | Dot matrix paper pen technology application method combined with weekly work plan |
CN112668541A (en) * | 2021-01-06 | 2021-04-16 | 青岛鱼之乐教育科技有限公司 | Intelligent dictation system based on dot matrix pen and method thereof |
CN112836542A (en) * | 2021-02-07 | 2021-05-25 | 深圳柔果信息科技有限公司 | Method, system and computer readable medium for practicing calligraphy based on dot matrix code |
CN115620312A (en) * | 2022-09-09 | 2023-01-17 | 重庆傲雄在线信息技术有限公司 | Cross-modal character handwriting verification method, system, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN116483243A (en) | 2023-07-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108288088B (en) | Scene text detection method based on end-to-end full convolution neural network | |
CN106960208A (en) | A kind of instrument liquid crystal digital automatic segmentation and the method and system of identification | |
CN111931710B (en) | Online handwritten character recognition method and device, electronic equipment and storage medium | |
CN109033954A (en) | A kind of aerial hand-written discrimination system and method based on machine vision | |
CN111539437B (en) | Detection and identification method of oracle-bone inscription components based on deep learning | |
CN101447017A (en) | Method and system for quickly identifying and counting votes on the basis of layout analysis | |
CN110197224B (en) | Method for recovering handwritten character track in air based on feature space depth counterstudy | |
CN107818577A (en) | A kind of Parts Recognition and localization method based on mixed model | |
CN109635687B (en) | Chinese character text line writing quality automatic evaluation method and system based on time sequence point set calculation | |
CN105005769A (en) | Deep information based sign language recognition method | |
CN106650648A (en) | Identification method and system for erasing handwriting | |
CN109002803B (en) | Intelligent watch-based pen holding posture detection and Chinese character stroke order identification method | |
CN109993154A (en) | The lithium sulfur type instrument intelligent identification Method of substation's simple pointer formula | |
CN101477426A (en) | Method and system for recognizing hand-written character input | |
KR20180104678A (en) | System and method for recognizing multiple object structures | |
CN111738167A (en) | Method for recognizing unconstrained handwritten text image | |
CN116483243B (en) | Intelligent handwriting practicing system based on electronic induction pen and dot matrix paper | |
CN101477425A (en) | Method and system for recognizing hand-written character input | |
CN101364271B (en) | Method for recognizing hand-written Chinese character strokes and recognition device | |
CN114463425A (en) | Workpiece surface featureless point positioning method based on probability Hough linear detection | |
Fan et al. | Automated steel bar counting and center localization with convolutional neural networks | |
CN108921006A (en) | The handwritten signature image true and false identifies method for establishing model and distinguishing method between true and false | |
CN103226698B (en) | A kind of method for detecting human face | |
CN111488897A (en) | Method and device for detecting and identifying touch object | |
CN114998262A (en) | Classroom off-line calligraphy teaching and evaluation system based on eighth teaching method |
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 |