CN111523455A - Evaluation method for Chinese character writing - Google Patents
Evaluation method for Chinese character writing Download PDFInfo
- Publication number
- CN111523455A CN111523455A CN202010322779.4A CN202010322779A CN111523455A CN 111523455 A CN111523455 A CN 111523455A CN 202010322779 A CN202010322779 A CN 202010322779A CN 111523455 A CN111523455 A CN 111523455A
- Authority
- CN
- China
- Prior art keywords
- stroke
- writing
- chinese character
- evaluation result
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 133
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 26
- 238000005516 engineering process Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 11
- 230000003287 optical effect Effects 0.000 claims description 5
- 230000005484 gravity Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 244000025254 Cannabis sativa Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000005477 standard model Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000003796 beauty Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/56—Information retrieval; Database structures therefor; File system structures therefor of still image data having vectorial format
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- G06V30/24—Character recognition characterised by the processing or recognition method
- G06V30/242—Division of the character sequences into groups prior to recognition; Selection of dictionaries
- G06V30/244—Division of the character sequences into groups prior to recognition; Selection of dictionaries using graphical properties, e.g. alphabet type or font
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Character Discrimination (AREA)
Abstract
The invention provides an evaluation method of Chinese character writing, which comprises the following steps: establishing a standard writing model of the Chinese characters; the standard writing model comprises a configuration table; the configuration table comprises strokes and stroke configuration items of each Chinese character in a plurality of Chinese characters; the stroke configuration item comprises a starting position, a closing position, a stroke length and a stroke angle; acquiring handwriting data of Chinese characters written by a user; processing handwriting data of the Chinese characters written by the user, and determining the Chinese characters written by the user as target Chinese characters and target Chinese character information of the target Chinese characters; the target Chinese character information comprises the stroke number, the stroke sequence, the stroke writing direction and the structural position information of the target Chinese character; and comparing the target Chinese character information with a configuration table in the standard writing model, and performing multidimensional evaluation on the stroke number, the stroke sequence, the stroke writing direction and the structural position information of the target Chinese character according to a comparison result. Therefore, more intelligent evaluation opinions and guidance opinions of the user can be provided, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an evaluation method for Chinese character writing.
Background
The aesthetic degree and the correctness of the writing structure of the Chinese character can only be evaluated by means of artificial observation, the uniform standard can not be achieved due to the difference of aesthetic concepts, emotional factors and capability levels of everyone, and meanwhile, due to the factors of time and energy, a plurality of writers can not obtain the correct evaluation of the writing result of the writers.
In the prior art, the evaluation of the writing of the Chinese characters only depends on visual inspection, experience and personal feeling, and the evaluation method has great subjective assumption, so that the evaluation of the writing of the Chinese characters is not accurate enough.
Disclosure of Invention
The embodiment of the invention aims to provide an evaluation method for Chinese character writing, which aims to solve the problem that the evaluation on the Chinese character writing in the prior art is not accurate enough.
In order to solve the above problems, the present invention provides a method for evaluating Chinese character writing, comprising:
establishing a standard writing model of the Chinese characters; the standard writing model comprises a configuration table; the configuration table comprises strokes and stroke configuration items of each Chinese character in a plurality of Chinese characters; the strokes comprise stroke names, stroke sequences, stroke writing directions and structural key points; the stroke configuration item comprises a starting position, a closing position, a stroke length and a stroke angle;
acquiring handwriting data of Chinese characters written by a user;
processing the handwriting data of the Chinese characters written by the user, determining the Chinese characters written by the user as target Chinese characters, and determining the target Chinese character information of the target Chinese characters; the target Chinese character information comprises stroke number, stroke sequence, stroke writing direction and structure position information of the target Chinese character;
and comparing the target Chinese character information with a configuration table in the standard writing model, and performing multidimensional evaluation on the stroke number, the stroke sequence, the stroke writing direction and the structural position information of the target Chinese character according to a comparison result.
In a possible implementation manner, the establishing a standard writing model of a chinese character specifically includes:
acquiring a contour vector structure diagram of each Chinese character according to the TTF font file;
according to the contour vector structure chart, obtaining strokes of each Chinese character by splitting strokes of the Chinese characters; the strokes comprise stroke names, stroke sequences, stroke writing directions and structural key points;
carrying out accurate position modeling on each Chinese character to obtain stroke configuration items of the Chinese characters; the stroke configuration item includes four dimensions: a pen starting position, a pen receiving position, a stroke length and a stroke angle; each of the four dimensions comprises: numerical values, allowable error ranges and normative words; the stroke angle is an angle between a connecting line of the starting position and the closing position and a horizontal line or a vertical line.
In one possible implementation, the structural key point includes a start point position and an end point position of the inflection point, a direction of the start point position of the inflection point, and a direction of the end point position of the inflection point; the direction of the end position of the inflection point is a direction of the end position of the inflection point relative to the start position.
In a possible implementation manner, the structure position information includes a start position, a fall position, and a stroke angle of each stroke, and a start position, an end position, a direction of the start position, and a direction of the end position of the structure key point of each stroke.
In one possible implementation, the handwriting data includes a position of writing, a time stamp of writing, a speed of writing, and a pressure of writing.
In a possible implementation manner, the processing handwriting data of the chinese character written by the user, determining that the chinese character written by the user is the target chinese character, and determining the target chinese character information of the target chinese character specifically includes:
determining a stroke sequence and a stroke writing direction according to a stroke lifting position, a stroke falling position and a writing timestamp in the writing positions;
the number of strokes is determined based on the stroke order.
In a possible implementation manner, the comparing the target chinese character information with the configuration table in the standard writing model, and performing multidimensional evaluation on the number of strokes, the stroke order, the stroke writing direction, and the structural position information of the target chinese character according to the comparison result specifically includes:
comparing the stroke number of the target Chinese character with the stroke number in the standard writing model to obtain a first evaluation result;
comparing the stroke sequence of the target Chinese character with the stroke sequence in the standard writing model to obtain a second evaluation result;
comparing the stroke writing direction of the target Chinese character with the stroke writing direction in the standard writing model to obtain a third evaluation result;
comparing the structural position information of the target Chinese character with the stroke configuration items in the standard writing model to obtain a fourth evaluation result;
and combining the first evaluation result, the second evaluation result, the third evaluation result and the fourth evaluation result to obtain a target evaluation result.
In a possible implementation manner, the comparing the structural position information of the target chinese character with the structural position information in the standard writing model to obtain the fourth evaluation result specifically includes:
comparing the starting position and the falling position of each stroke in the structural position information with the starting abscissa and the starting ordinate of each stroke in the starting position of each stroke of the target Chinese character in the standard writing model respectively to obtain a writing goodness-of-fit evaluation result; and/or the presence of a gas in the gas,
comparing the starting position, the falling position and the stroke angle of each stroke in the structural position information with the starting abscissa, the starting ordinate and the stroke angle of each stroke in the starting position of each stroke of the target Chinese character in the standard writing model respectively to obtain an accurate position evaluation result; and/or the presence of a gas in the gas,
sending the handwriting data to a handwriting recognition interface of other equipment to obtain a target Chinese character returned by the handwriting recognition interface, and comparing the target Chinese character with the standard writing model to obtain whether the result recognized by the handwriting recognition interface is a correct evaluation result; and/or the presence of a gas in the gas,
comparing the starting position, the end position, the direction of the starting position and the direction of the end position of the structural key point in the structural position information with the starting position, the end position, the direction of the starting position and the direction of the end position of the structural key point of each stroke of the target Chinese character in a standard writing model respectively to obtain an evaluation result of the key point;
and determining a fourth evaluation result according to the writing goodness-of-fit evaluation result, and/or the accurate position evaluation result, and/or whether the result of the handwriting recognition interface recognition is a correct evaluation result, and/or the evaluation result of the key point.
In one possible implementation mode, acquiring handwriting data sent by a writing device or an input device; the writing device comprises a writing device based on the working principle of the digital optical dot matrix technology and a writing device based on the working principle of the electromagnetic pressure sensing technology; the input device comprises an input device based on an infrared technology working principle, an input device based on a touch screen technology working principle and an input device based on mouse handwriting input.
By applying the evaluation method for Chinese character writing provided by the embodiment of the invention, the Chinese character writing can be intelligently evaluated through the standard writing model and the intelligent writing information acquisition hardware, the intelligent evaluation dimension is more and more along with the continuous expansion of the standard writing model, the evaluation result is more and more accurate, so that more intelligent evaluation suggestions and guidance suggestions of a user can be given, and the user experience is improved.
Drawings
Fig. 1 is a schematic flow chart of an evaluation method for writing Chinese characters according to an embodiment of the present invention;
FIG. 2A is a schematic diagram of splitting strokes of "standing grain" in a TTF word stock file;
FIG. 2B is a partial enlarged view of FIG. 2A;
FIG. 3 is a schematic diagram illustrating the adjustment of stroke sequence of the strokes taken out of the standing grain;
FIG. 4 is a schematic diagram of the overall Chinese character layout of a page.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be further noted that, for the convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 is a schematic flow chart of an evaluation method for chinese character writing according to an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
and step 110, establishing a standard writing model of the Chinese characters.
Wherein the standard writing model comprises a configuration table; the configuration table comprises strokes and stroke configuration items of each Chinese character in a plurality of Chinese characters; the strokes comprise stroke names, stroke sequences, stroke writing directions and structural key points; the stroke configuration item comprises a starting position, a closing position, a stroke length and a stroke angle.
The standard writing model of Chinese characters is based on the computer word library file. A computer (TrueType Font, TTF) Font file belongs to a static vector picture file, each Chinese character has a contour vector structure diagram, valuable writing information is extracted from the static contour vector structure diagram file through certain processing on the TTF Font file, and more detailed data are supplemented to obtain a standard writing model. The valuable writing information extracted comprises the writing sequence of the strokes, the stroke moving direction of the strokes, the accurate positions of the strokes, the corner radians of the strokes, the sizes and the positions of the Chinese character structure blocks and the like.
The standard writing model of Chinese characters can be established by the following method.
1. Stroke splitting and ordering
Referring to fig. 2A and 2B, stroke splitting is illustrated. Fig. 2A is a schematic diagram of splitting strokes of a Chinese character standing grain in a TTF word stock file, and fig. 2B is a partially enlarged view of fig. 2A. The existing TTF word stock file can be imported first, and after a specific chinese character is selected, for example, the outline vector structure diagram of the chinese character is displayed, the chinese character at this time is in the main form of the outline, and there is no concept of the so-called "stroke", and the outline is composed of a plurality of outline points, see the outline and outline points on the "word" in fig. 2A and 2B, and the outline points can refer to dots with numbers. The contour points can be configured at will on the Chinese character contour, and the contour points are dragged and deformed, so that the adjustment of the Chinese character stroke contour can be realized. Thereby changing the font of the Chinese character. The method has the advantages that the forced cutting can be carried out by connecting any two contour points, so that the original whole stroke contour is split into a plurality of different contours, and the stroke connection part of the Chinese character is forcibly cut according to the principle, so that each independent stroke in each Chinese character is split.
The original Chinese character outline is cut off by configuring corresponding points on the Chinese character outline and connecting the corresponding points to form a line; meanwhile, new contour points can be added, the original contour line is connected to the new contour points, and points on the original contour line can be dragged, so that the shape of the contour line is influenced, and finally the contour of the Chinese character is changed. The newly added contour points have the following main functions: the method comprises the following steps of firstly, cutting off original intersected and connected strokes to form a plurality of independent strokes; secondly, the connecting and closing device is used for connecting and closing the incomplete stroke after being cut off, so that the complete stroke is restored; and thirdly, the method is used for dragging deformation and adjusting the original stroke outline so as to change the form of the Chinese character.
The stroke sequence of each Chinese character is given by numbering and sequencing the split strokes, and the numbering of the strokes can be carried out according to the regulation in the modern Chinese universal character stroke order standard of the 1 st edition of 8 months in 1997. Referring to fig. 3, fig. 3 is a schematic diagram illustrating adjustment of stroke order of the strokes taken apart from the "grass", as shown in fig. 3, for five strokes of the "grass": the left-falling, horizontal, vertical, left-falling and right-falling strokes are numbered, the numbers are sequentially 1-5, the sequence is consistent with the numbers, and the sequence corresponding to the strokes can also be considered to be sequentially 1-5, so that the sequence of the split strokes after the numbers are numbered is realized.
2. Stroke structure accurate position modeling
When Chinese characters are evaluated, besides basic right and wrong and basic structural layout, the shapes and positions of strokes and structures often reflect the personalized teaching and evaluation requirements of calligraphers. Therefore, for the personalized teaching and teaching method, the TTF word stock file can be formed by performing word stock processing on the personalized hard-pen calligraphy words, and the strokes, namely the stroke sequence and the stroke names, are formed according to the stroke splitting step. And modeling the accurate position of the stroke structure to extract the basic structure information of the Chinese character, and storing the basic structure information, the previous stroke sequence and the stroke name in a configuration table mode.
The accurate position modeling needs to provide accurate coordinates for Chinese characters in a standard shading frame, and a plurality of Chinese character teaching shading frame forms such as common grid and Chinese character grid, backword grid and golden grid are available in the market, and no matter whether the grid shading forms are the same, the grid shading forms have coordinate values relative to the horizontal and longitudinal coordinate origins, so that the grid shading forms can be used as the basis for accurate position modeling.
The precise location modeling is described below:
with the help of a developed Chinese character structure configuration tool, after a TTF font file is imported, Chinese characters are called, a specific shading is used as a background, a standard coordinate system is matched, and related numerical values are used as basic structure information to be stored. The basic structure information, together with stroke order and stroke name, form a configuration table.
In the following, a permanent word in a certain field grid coordinate method is taken as an example, see table 1, where table 1 is a configuration table of "permanent" words.
TABLE 1
The configuration table is divided into three parts: chinese characters, strokes (including stroke sequence and stroke name), and stroke configuration items. The stroke configuration item mainly has four dimensions: starting position, closing position, stroke length and stroke angle. There are three items per dimension: numerical values, allowable error ranges, normative words. If the allowable error range is not filled, the default parameters of the system are directly taken, and if the allowable error range is filled, the error range is filled. Normative dialogs are used to: and when the numerical value of each dimension exceeds the allowable error range, giving a prompt. Stroke angle: the angle of the horizontal line or the vertical line is clamped after the pen is started and retracted. Wherein, for strokes from left to right, the stroke angle refers to the horizontal line angle, and for strokes from top to bottom, the stroke angle refers to the vertical line angle.
Meanwhile, the position precision of hundreds is difficult to achieve in actual writing, so that the evaluation is too severe, and therefore an error allowable range is added in the embodiment, the error range allowed to occur in the precise position of the structural key point, the error range allowed to occur in the length of the stroke and the range allowed to occur in the angle of the stroke. And when the actually collected points, line segments and angles are within the error tolerance range with the standard model requirement, the model is considered to be qualified. The parameter is self-adjusted by an evaluator, and the smaller the parameter value is, the more rigorous the evaluation is, and otherwise, the more relaxed the evaluation is.
3. Stroke inflection point identification modeling
In the standard modeling of Chinese characters, for Chinese characters with strokes of inflection points, if the processing of the inflection points is not good, the evaluation exception occurs. For example, "do" and "do" may inform that the degree of matching is only slightly insufficient in the evaluation, but the inflection point is very important in the writing requirement of the Chinese character. Therefore, modeling of stroke corners is required.
In the configuration for the stroke dimension in the configuration table, a plurality of structural key points can be configured for the inflection point position. By way of example and not limitation, a "structural keypoint a" may be arranged at the start position of an inflection point and labeled with its "inflection point characteristic", while a "structural keypoint B" may be arranged at the end (end position) after the inflection point and labeled with its "inflection point characteristic".
Besides the structural key points are arranged at the positions of the inflection points, the directions of the inflection points are marked. The directions are eight directions including upper, lower, left, right, upper left, lower left, upper right and lower right, and the relativity of the abscissa and the ordinate of the structural key point A and the structural key point B is different, wherein the leftmost upper corner in the Chinese writing frame is taken as the origin, the right abscissa is positive, and the downward ordinate is positive.
For example, if the direction of the inflection point of the point B with respect to the point a is "lower right", the coordinates of the point B can be represented by the inflection point directionality, for example, the abscissa of the point B > the abscissa of the point a, and the ordinate of the point B > the ordinate of the point a.
Therefore, the standard writing model of the Chinese characters can be established through the three points.
And step 120, acquiring handwriting data of the Chinese characters written by the user.
The handwriting data comprises written strokes, written positions, written time, written speed and written pressure.
The dynamic writing track of the pen point can be captured by means of a writing digital technology, and therefore written handwriting data can be recorded. The handwriting data comprises written strokes, written accurate positions, written time, written speed, written pressure and other data. For example, handwriting data sent by a writing device or an input device may be obtained. The writing device includes, but is not limited to, a writing device based on the working principle of the digital optical dot matrix technology, and a writing device based on the working principle of the electromagnetic pressure sensing technology. The input device comprises an input device based on an infrared technology working principle, an input device based on a touch screen technology working principle and an input device based on mouse handwriting input.
The writing device based on the working principle of the digital optical dot matrix technology comprises but is not limited to a dot matrix digital pen, the digital optical dot matrix technology is that a layer of special dots or lines, called as a dot matrix, are printed on common paper, and according to a certain special algorithm, the dots or lines are irregularly arranged to form a dot matrix coordinate system with extremely high precision. By means of the digital writing technology, digital pen and other hardware product, dynamic handwriting data of Chinese character may be captured.
The working principle of the dot matrix digital pen is as follows: when the nib is pressed down, the pressure sensor is triggered, a built-in high-speed camera is started, the dot matrix passed by the nib is photographed at a speed of about 100 sheets per second, and the photographed dot matrix is transmitted to a built-in processor in the digital pen, so that information such as dot matrix coordinates, handwriting sequence, pressure data and movement speed is calculated, and finally, the photographed dot matrix coordinates, the handwriting sequence, the pressure data and the movement speed are output outwards through a Bluetooth, WIFI or USB communication unit. In the working principle of the digital pen, points between the pen falling and the pen lifting are connected into a line, and the line displayed after certain rendering is defined as a writing stroke.
The writing device based on the working principle of the electromagnetic pressure sensing technology comprises but is not limited to an electromagnetic pen, the electromagnetic pen is a common computer peripheral product, and the device matched with the electromagnetic pen is an electromagnetic plate. The data such as the track coordinate, the pressure size that the electromagnetic pen moved on the electromagnetic board can pass through the electromagnetic board and convey to the computer, and then realize writing the purpose.
Input devices based on the operating principle of infrared technology include, but are not limited to, infrared electronic boards.
The input device based on the operating principle of the touch screen technology includes, but is not limited to, an infrared touch screen, a capacitive touch screen, a resistive touch screen, or an electromagnetic touch screen. The infrared touch screen comprises but is not limited to an infrared pair tube touch screen and an infrared imaging touch screen, the capacitive touch screen comprises but is not limited to a surface capacitive touch screen and a projective capacitive touch screen, and the resistive touch screen comprises but is not limited to a four-wire touch screen, a five-wire touch screen, a seven-wire touch screen and an eight-wire touch screen.
The input device based on mouse handwriting input is a device for collecting the writing information input by the mouse.
The following describes how to obtain handwriting data by taking a writing device as a dot matrix digital pen as an example.
For the paper for writing Chinese characters, a layer of dot matrix background pattern is laid on the paper for writing Chinese characters in electronic files through a special interface, and then the paper is printed or printed. Like this digital pen writes on such paper, just can catch the relevant information of dot matrix to obtain accurate positional information, the dot matrix information that every page of paper laid is different moreover, and the serial number of its paper is different, thereby can realize switching and location between page number or even different teaching assistance teaching materials.
Because the lattice has very fine position information, the position of the area needing to be written is often determined, and the area is written in the specified position area, so that the collected and recorded Chinese characters are submitted to the system as a complete Chinese character. The method comprises the steps of configuring the area where each Chinese character should be written, namely performing area cutting on an electronic file through a design tool, drawing the position and the size of each area, and then configuring the area to mark the Chinese characters which should be corresponding, wherein the information comprises information of different versions of the Chinese characters and the like, and the information is used as a basis for later-stage display and evaluation.
Referring to fig. 4, fig. 4 is a schematic diagram of the layout of the whole chinese characters on the page, and each region box is set as an attribute chinese character. The position and size of each region frame are set.
The writing precision of the digital pen reaches micron level, and the X and Y coordinate values of the pen point in the writing process can be recorded, so that the accurate collection of the stroke structure is realized; recording the time stamp of the pen point movement at the same time, thereby realizing the writing sequence and the writing speed of each stroke; meanwhile, a pressure sensor arranged in the digital pen can record the pressing force of the pen point, so that the pressing force is converted into the weight and thickness of the written strokes. Namely: based on micron-sized X and Y coordinates, acquiring and recording the writing structure and stroke accurate positions of the Chinese characters; based on the coordinate points of the timestamp, the stroke sequence and speed of writing the Chinese characters are collected and recorded; based on a pen point pressure sensor, the weight and thickness of the Chinese character stroke writing are collected and recorded;
take writing a Chinese character "mountain" as an example.
First stroke of Chinese character "mountain": the pen-down and pen-up Penup of the middle vertical, and coordinate point coordinate information: including pen serial number, type, timestamp, point serial number, coordinate X, coordinate Y, paper serial number, pressure value information, etc.
When a user writes, the handwriting data collected by the digital pen also comprises Chinese character writing information, such as information of writing paper. The information on the writing paper includes information on the number of the paper, the page number of the paper, the background content of the paper, the writing area (specific writing area) of the chinese character, and the like. The handwriting data also includes information from the digital pen. The information of the digital pen includes information such as the number of the digital pen, position coordinates (X, Y coordinate values) of paper where the pen point is located, time (T timestamp) when the position coordinates appear, pen drop for writing, pen lift for writing, and pressure (PRESS value) for writing.
The information can be converted into information which is further valuable to Chinese character writing evaluation in combination. For example, generating stroke writing speed information through the coordinate position and the time stamp; cutting the handwriting information into stroke information according to the pen falling information and the pen lifting information; combining the stroke information with the Chinese character writing area information to generate written Chinese character information and the like; and generating stroke movement and force change information of stroke writing through the change of continuous coordinate pressure, generating writing structure information of Chinese characters through the combination of strokes, and the like.
And step 130, processing the handwriting data of the Chinese characters written by the user, determining the Chinese characters written by the user as target Chinese characters, and determining the target Chinese character information of the target Chinese characters.
The target Chinese character information comprises the stroke number, the stroke sequence, the stroke writing direction and the structure position information of the target Chinese character.
Specifically, the stroke sequence and the stroke writing direction can be determined according to the pen-up position, the pen-down position and the writing timestamp in the writing position; the number of strokes is determined based on the stroke order.
And step 140, comparing the target Chinese character information with a configuration table in the standard writing model, and performing multidimensional evaluation on the stroke number, the stroke sequence, the stroke writing direction and the structural position information of the target Chinese character according to the comparison result.
The target Chinese character can be evaluated in a multidimensional way according to the stroke number, the stroke sequence, the stroke writing method, the structure position and the like.
Specifically, step 140 includes the following steps:
comparing the stroke number of the target Chinese character with the stroke number in the standard writing model to obtain a first evaluation result;
comparing the stroke sequence of the target Chinese character with the stroke sequence in the standard writing model to obtain a second evaluation result;
comparing the stroke writing direction of the target Chinese character with the stroke writing direction in the standard writing model to obtain a third evaluation result;
comparing the structural position information of the target Chinese character with the stroke configuration items in the standard writing model to obtain a fourth evaluation result;
and combining the first evaluation result, the second evaluation result, the third evaluation result and the fourth evaluation result to obtain a target evaluation result.
Next, how to obtain the first to fourth evaluation results will be specifically described.
1. Obtaining a first evaluation result by evaluation of stroke number dimension
The number of times of writing strokes and lifting strokes of the target Chinese character is acquired, and the number of times of writing strokes and lifting strokes of the target Chinese character is compared with the number of each stroke of the Chinese character in the standard model, so that a first evaluation result of the number of strokes of the target Chinese character is given.
In the process, necessary noise information needs to be filtered, and the noise refers to lines and points with non-standard stroke shapes. For example, a pen tip clicks on the area rather than forming a continuous collection point, such a point does not participate in the calculation of the number of strokes nor in the data collection of the writing.
For the first evaluation result, different scores can be given according to the matching degree, for example, the comparison result can be completely consistent for the stroke number, and the comparison result can be given that the stroke number is inconsistent, and the larger the inconsistency, the smaller the score of the comparison result or the lower the evaluation.
2. Obtaining a second evaluation result by evaluation of stroke order dimensions
When the evaluation of the stroke writing sequence dimension is carried out, matching can be carried out according to stroke information collected when the target Chinese character is written, the occurrence sequence information of the strokes and the stroke sequence in the standard writing model, and if the occurrence sequence of the strokes is inconsistent, a second evaluation result is given and is output outwards.
The evaluation of stroke order is based on the fact that the dimension of stroke number is correct, and if the stroke number is wrong, the situation that the written stroke is inconsistent with the standard stroke can occur. Namely, if the first evaluation result is that the stroke numbers are consistent, the evaluation of the stroke order dimension is carried out, and if the first evaluation result is that the stroke numbers are inconsistent, the second evaluation result of the stroke order dimension is inevitably that the stroke orders are inconsistent.
3. Obtaining a third evaluation result through evaluation of stroke writing direction dimensionality
When the evaluation of stroke writing direction dimension is carried out, the stroke writing of the target Chinese character is taught by the basic stroke directions from left to right and from top to bottom, when writing information is extracted from handwriting data, each stroke is composed of a plurality of points, each point is marked by a time stamp TIMESTAMP when appearing, if the condition of violating the stroke writing direction of the Chinese character appears, a third evaluation result is given, for example, the third evaluation result can be the name and the number of inconsistent stroke writing directions.
4. Obtaining a fourth evaluation result through evaluation of structural position information dimension
The evaluation of the Chinese character writing structure dimension can be subdivided into a plurality of different angles, and the angles are as follows:
comparing the starting position and the falling position of each stroke in the structural position information with the starting abscissa and the starting ordinate of each stroke of the target Chinese character in the standard writing model respectively to obtain a writing goodness evaluation result; and/or the presence of a gas in the gas,
comparing the starting position, the falling position and the stroke angle of each stroke in the structural position information with the starting abscissa, the starting ordinate and the stroke angle of each stroke of the target Chinese character in the standard writing model respectively to obtain an accurate position evaluation result; and/or the presence of a gas in the gas,
sending the handwriting data to a handwriting recognition interface of other equipment to obtain a target Chinese character returned by the handwriting recognition interface, and comparing the target Chinese character with a standard writing model to obtain whether the result recognized by the handwriting recognition interface is a correct evaluation result; and/or the presence of a gas in the gas,
and comparing the starting position, the end position, the direction of the starting position and the direction of the end position of the structural key point in the structural position information with the starting position, the end position, the direction of the starting position and the direction of the end position of the structural key point of each stroke of the target Chinese character in the standard writing model respectively to obtain the evaluation result of the key point.
The fourth point will be described more specifically below:
(1) evaluation of degree of coincidence in writing
In a specific writing area, a TTF (text to film) font file is loaded, the outline of a Chinese character is used as a background, handwriting data of a target Chinese character is called, so that handwriting is obtained, the handwriting is covered on the standard Chinese character outline background, and the coincidence degree calculation is performed on the coverage area of the handwriting, so that coincidence degree evaluation is given, for example, evaluation results such as percentage are given.
The goodness of the Chinese characters is calculated by comparing the covered background area of each stroke with the area of the outline of the standard Chinese character according to the whole Chinese character, namely the goodness of fit is given. The method may also provide final average or weighted average (weighted by stroke length or importance) to calculate final goodness of fit per stroke, as desired.
In the process of goodness of fit evaluation, an algorithm of automatic gravity center shifting is added, namely, the gravity centers of all handwriting written by the target Chinese character are calculated, so that the gravity centers are dragged, the gravity centers of the target Chinese character are moved to the positions where the gravity centers of the standard Chinese characters are consistent, goodness of fit evaluation is carried out, and the problem that the whole shifting occurs in the actual writing process but the writing per se is more standard can be solved.
The gravity center of the Chinese character is the average value of the added coordinates of all points of the Chinese character.
In the process of evaluating the matching degree, the matching degree of the coverage area considers two conditions of insufficient coverage and excessive coverage, namely when each stroke does not completely cover the outline of the standard stroke, the coverage percentage is given; if there is over-coverage, the coverage is calculated also according to the algorithm of standard stroke outline covering handwriting.
It can be understood that the goodness of fit evaluation can be evaluated based on the goodness of fit of the whole Chinese character, also can be evaluated for the goodness of fit of each stroke, and finally an average value is calculated to serve as the goodness of fit evaluation result of the whole Chinese character.
(2) Precision position assessment
The standard writing model corresponding to the target Chinese character is called, and accurate evaluation is carried out on the standard writing model and the writing handwriting information of the target Chinese character, and the evaluation value is more detailed than 'goodness of fit evaluation'.
The position, the length and the angle of the key structure point of each stroke are calculated to match with the stroke configuration items in the standard writing model, the allowable deviation range is taken out from the allowable error table, the evaluation of the key structure point of each stroke is given, and finally the standard dialect is thrown outwards.
(3) Handwriting recognition evaluation
The handwriting data is transmitted to the handwriting recognition interface, so that recognized Chinese characters returned by the handwriting recognition interface are obtained, the recognized target Chinese characters are matched with strokes of Chinese characters in a standard writing model, if the recognized target Chinese characters are consistent with the strokes of the Chinese characters in the standard writing model, the recognition result of the handwriting recognition interface can be determined to be correct, and if the recognized target Chinese characters do not pass through the standard writing model, the recognition result of the handwriting recognition interface can be determined to be wrong.
Since the evaluation directly calls an extrinsic handwriting recognition interface which depends on the recognition capability and accuracy of the handwriting recognition interface, the evaluation corresponding to different handwriting recognition interfaces may be different.
(4) Stroke keypoint evaluation
As before, if the writing evaluation of "dry" and "on" appears, only on the evaluation of goodness of fit, the evaluation result may be given only that the beauty degree has deviation, but the difference is an important element of the correctness of Chinese character writing.
If a certain stroke is configured with structural key point information, namely inflection point information, identifying a modeled model through a stroke inflection point, comparing information of the handwriting of the Chinese character, judging whether the characteristic of the inflection point can be found, if so, judging whether the characteristic passes, otherwise, pertinently giving an evaluation result, including information such as whether the inflection point appears, the direction of the inflection point and the like.
Subsequently, one or more of goodness of fit evaluation, accurate position evaluation, handwriting recognition evaluation, and stroke inflection point evaluation may be selected as a fourth evaluation result as needed.
By applying the evaluation method for Chinese character writing provided by the embodiment of the invention, the Chinese character writing can be intelligently evaluated through the standard writing model and the intelligent writing information acquisition hardware, the intelligent evaluation dimension is more and more along with the continuous expansion of the standard writing model, the evaluation result is more and more accurate, so that more intelligent evaluation suggestions and guidance suggestions of a user can be given, and the user experience is improved.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A method for evaluating Chinese character writing, which is characterized by comprising the following steps:
establishing a standard writing model of the Chinese characters; the standard writing model comprises a configuration table; the configuration table comprises strokes and stroke configuration items of each Chinese character in a plurality of Chinese characters; the strokes comprise stroke names, stroke sequences, stroke writing directions and structural key points; the stroke configuration item comprises a starting position, a closing position, a stroke length and a stroke angle;
acquiring handwriting data of Chinese characters written by a user;
processing the handwriting data of the Chinese characters written by the user, determining the Chinese characters written by the user as target Chinese characters, and determining the target Chinese character information of the target Chinese characters; the target Chinese character information comprises stroke number, stroke sequence, stroke writing direction and structure position information of the target Chinese character;
and comparing the target Chinese character information with a configuration table in the standard writing model, and performing multidimensional evaluation on the stroke number, the stroke sequence, the stroke writing direction and the structural position information of the target Chinese character according to a comparison result.
2. The method of claim 1, wherein the establishing of the standard writing model of the chinese character specifically comprises:
acquiring a contour vector structure diagram of each Chinese character according to the TTF font file;
according to the contour vector structure chart, obtaining strokes of each Chinese character by splitting strokes of the Chinese characters; the strokes comprise stroke names, stroke sequences, stroke writing directions and structural key points;
carrying out accurate position modeling on each Chinese character to obtain stroke configuration items of the Chinese characters; the stroke configuration item includes four dimensions: a pen starting position, a pen receiving position, a stroke length and a stroke angle; each of the four dimensions comprises: numerical values, allowable error ranges and normative words; the stroke angle is an angle between a connecting line of the starting position and the closing position and a horizontal line or a vertical line.
3. The method of claim 1, wherein the structural keypoints comprise a start position and an end position of an inflection point, a direction of a start position of an inflection point, a direction of an end position of an inflection point; the direction of the end position of the inflection point is a direction of the end position of the inflection point relative to the start position.
4. The method of claim 1, wherein the structural position information comprises a start position, a fall position, and a stroke angle for each stroke, a start position, an end position, a direction of the start position, and a direction of the end position for a structural keypoint for each stroke.
5. A method as claimed in claim 1, wherein the handwriting data comprises a position of writing, a time stamp of writing, a speed of writing and a pressure of writing.
6. The method as claimed in claim 5, wherein the processing handwriting data of the user-written chinese character to determine the user-written chinese character as the target chinese character, and the determining the target chinese character information of the target chinese character specifically comprises:
determining a stroke sequence and a stroke writing direction according to a stroke lifting position, a stroke falling position and a writing timestamp in the writing positions;
the number of strokes is determined based on the stroke order.
7. The method of claim 4, wherein comparing the target Chinese character information with the configuration table in the standard writing model, and performing multidimensional evaluation on the number of strokes, the stroke order, the stroke writing direction and the structural position information of the target Chinese character according to the comparison result specifically comprises:
comparing the stroke number of the target Chinese character with the stroke number in the standard writing model to obtain a first evaluation result;
comparing the stroke sequence of the target Chinese character with the stroke sequence in the standard writing model to obtain a second evaluation result;
comparing the stroke writing direction of the target Chinese character with the stroke writing direction in the standard writing model to obtain a third evaluation result;
comparing the structural position information of the target Chinese character with the stroke configuration items in the standard writing model to obtain a fourth evaluation result;
and combining the first evaluation result, the second evaluation result, the third evaluation result and the fourth evaluation result to obtain a target evaluation result.
8. The method according to claim 7, wherein the comparing the structural position information of the target Chinese character with the structural position information in the standard writing model to obtain the fourth evaluation result specifically comprises:
comparing the starting position and the falling position of each stroke in the structural position information with the starting abscissa and the starting ordinate of each stroke in the starting position of each stroke of the target Chinese character in the standard writing model respectively to obtain a writing goodness-of-fit evaluation result; and/or the presence of a gas in the gas,
comparing the starting position, the falling position and the stroke angle of each stroke in the structural position information with the starting abscissa, the starting ordinate and the stroke angle of each stroke in the starting position of each stroke of the target Chinese character in the standard writing model respectively to obtain an accurate position evaluation result; and/or the presence of a gas in the gas,
sending the handwriting data to a handwriting recognition interface of other equipment to obtain a target Chinese character returned by the handwriting recognition interface, and comparing the target Chinese character with the standard writing model to obtain whether the result recognized by the handwriting recognition interface is a correct evaluation result; and/or the presence of a gas in the gas,
comparing the starting position, the end position, the direction of the starting position and the direction of the end position of the structural key point in the structural position information with the starting position, the end position, the direction of the starting position and the direction of the end position of the structural key point of each stroke of the target Chinese character in a standard writing model respectively to obtain an evaluation result of the key point;
and determining a fourth evaluation result according to the writing goodness-of-fit evaluation result, and/or the accurate position evaluation result, and/or whether the result of the handwriting recognition interface recognition is a correct evaluation result, and/or the evaluation result of the key point.
9. The method according to claim 1, characterized by acquiring handwriting data sent by a writing device or an input device; the writing device comprises a writing device based on the working principle of the digital optical dot matrix technology and a writing device based on the working principle of the electromagnetic pressure sensing technology; the input device comprises an input device based on an infrared technology working principle, an input device based on a touch screen technology working principle and an input device based on mouse handwriting input.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010322779.4A CN111523455A (en) | 2020-04-22 | 2020-04-22 | Evaluation method for Chinese character writing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010322779.4A CN111523455A (en) | 2020-04-22 | 2020-04-22 | Evaluation method for Chinese character writing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111523455A true CN111523455A (en) | 2020-08-11 |
Family
ID=71903068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010322779.4A Pending CN111523455A (en) | 2020-04-22 | 2020-04-22 | Evaluation method for Chinese character writing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111523455A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016419A (en) * | 2020-08-19 | 2020-12-01 | 浙江无极互联科技有限公司 | Intelligent handwritten Chinese character planimetric algorithm |
| CN112183046A (en) * | 2020-09-25 | 2021-01-05 | 北京有竹居网络技术有限公司 | Method, device and equipment for evaluating quality of handwriting and storage medium |
| CN112215061A (en) * | 2020-08-27 | 2021-01-12 | 拓尔思信息技术股份有限公司 | Detection method and device for copying on handwriting screen, electronic equipment and storage medium |
| CN112446349A (en) * | 2020-12-09 | 2021-03-05 | 北京有竹居网络技术有限公司 | Handwriting detection method and device |
| CN112541328A (en) * | 2020-12-07 | 2021-03-23 | 四川大学 | Handwriting storage method, device, equipment and storage medium |
| CN112686212A (en) * | 2021-01-26 | 2021-04-20 | 吉林省华粹文化传播有限公司 | Five-point coordinate positioning grid, positioning method and online writing evaluation system |
| CN112861694A (en) * | 2021-02-02 | 2021-05-28 | 周斌 | Template-based online writing scoring method |
| CN113420983A (en) * | 2021-06-23 | 2021-09-21 | 科大讯飞股份有限公司 | Writing evaluation method, device, equipment and storage medium |
| CN114022885A (en) * | 2021-10-13 | 2022-02-08 | 深圳腾千里科技有限公司 | Intelligent pen, method, device and medium for handwriting scoring |
| CN114419627A (en) * | 2021-12-03 | 2022-04-29 | 陈颖 | Handwritten Chinese character evaluation method and device, computer equipment and readable storage medium |
| CN116561601A (en) * | 2023-07-07 | 2023-08-08 | 深圳棒棒帮科技有限公司 | Writing scoring method, device and storage medium |
| WO2024065891A1 (en) * | 2022-09-30 | 2024-04-04 | 朱芮叶 | Written font analysis method and apparatus, computer device, and storage medium |
| CN118629056A (en) * | 2024-08-15 | 2024-09-10 | 深圳润方创新技术有限公司 | Handwriting recognition method and system for electronic drawing board for children |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390358A (en) * | 2013-07-03 | 2013-11-13 | 广东小天才科技有限公司 | Method and device for judging normativity of character writing operation of electronic equipment |
| CN103927535A (en) * | 2014-05-08 | 2014-07-16 | 北京汉仪科印信息技术有限公司 | Recognition method and device for Chinese character writing |
| CN104050453A (en) * | 2014-06-24 | 2014-09-17 | 南京师范大学 | Evaluation method for handwritten Chinese character handwriting |
| CN104063723A (en) * | 2014-06-25 | 2014-09-24 | 北京语言大学 | Stroke reduction method of offline handwritten Chinese character and device thereof |
| CN105718965A (en) * | 2014-12-02 | 2016-06-29 | 北京汉仪科印信息技术有限公司 | Chinese character writing font identification method and Chinese character writing font identification device |
| CN106503756A (en) * | 2016-10-18 | 2017-03-15 | 上海子墨国际文化传播有限公司 | Based on the method that image outline sets up Chinese character handwriting model |
-
2020
- 2020-04-22 CN CN202010322779.4A patent/CN111523455A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390358A (en) * | 2013-07-03 | 2013-11-13 | 广东小天才科技有限公司 | Method and device for judging normativity of character writing operation of electronic equipment |
| CN103927535A (en) * | 2014-05-08 | 2014-07-16 | 北京汉仪科印信息技术有限公司 | Recognition method and device for Chinese character writing |
| CN104050453A (en) * | 2014-06-24 | 2014-09-17 | 南京师范大学 | Evaluation method for handwritten Chinese character handwriting |
| CN104063723A (en) * | 2014-06-25 | 2014-09-24 | 北京语言大学 | Stroke reduction method of offline handwritten Chinese character and device thereof |
| CN105718965A (en) * | 2014-12-02 | 2016-06-29 | 北京汉仪科印信息技术有限公司 | Chinese character writing font identification method and Chinese character writing font identification device |
| CN106503756A (en) * | 2016-10-18 | 2017-03-15 | 上海子墨国际文化传播有限公司 | Based on the method that image outline sets up Chinese character handwriting model |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016419A (en) * | 2020-08-19 | 2020-12-01 | 浙江无极互联科技有限公司 | Intelligent handwritten Chinese character planimetric algorithm |
| CN112215061A (en) * | 2020-08-27 | 2021-01-12 | 拓尔思信息技术股份有限公司 | Detection method and device for copying on handwriting screen, electronic equipment and storage medium |
| CN112215061B (en) * | 2020-08-27 | 2024-09-10 | 拓尔思信息技术股份有限公司 | Method and device for detecting copying on handwriting screen, electronic equipment and storage medium |
| CN112183046A (en) * | 2020-09-25 | 2021-01-05 | 北京有竹居网络技术有限公司 | Method, device and equipment for evaluating quality of handwriting and storage medium |
| CN112541328A (en) * | 2020-12-07 | 2021-03-23 | 四川大学 | Handwriting storage method, device, equipment and storage medium |
| CN112541328B (en) * | 2020-12-07 | 2022-04-01 | 四川大学 | Handwriting storage method, device, equipment and storage medium |
| CN112446349A (en) * | 2020-12-09 | 2021-03-05 | 北京有竹居网络技术有限公司 | Handwriting detection method and device |
| CN112686212A (en) * | 2021-01-26 | 2021-04-20 | 吉林省华粹文化传播有限公司 | Five-point coordinate positioning grid, positioning method and online writing evaluation system |
| CN112861694A (en) * | 2021-02-02 | 2021-05-28 | 周斌 | Template-based online writing scoring method |
| CN113420983B (en) * | 2021-06-23 | 2024-04-12 | 科大讯飞股份有限公司 | Writing evaluation method, device, equipment and storage medium |
| CN113420983A (en) * | 2021-06-23 | 2021-09-21 | 科大讯飞股份有限公司 | Writing evaluation method, device, equipment and storage medium |
| CN114022885A (en) * | 2021-10-13 | 2022-02-08 | 深圳腾千里科技有限公司 | Intelligent pen, method, device and medium for handwriting scoring |
| CN114419627A (en) * | 2021-12-03 | 2022-04-29 | 陈颖 | Handwritten Chinese character evaluation method and device, computer equipment and readable storage medium |
| WO2024065891A1 (en) * | 2022-09-30 | 2024-04-04 | 朱芮叶 | Written font analysis method and apparatus, computer device, and storage medium |
| CN116561601B (en) * | 2023-07-07 | 2023-10-03 | 深圳棒棒帮科技有限公司 | Writing scoring method, device and storage medium |
| CN116561601A (en) * | 2023-07-07 | 2023-08-08 | 深圳棒棒帮科技有限公司 | Writing scoring method, device and storage medium |
| CN118629056A (en) * | 2024-08-15 | 2024-09-10 | 深圳润方创新技术有限公司 | Handwriting recognition method and system for electronic drawing board for children |
| CN118629056B (en) * | 2024-08-15 | 2024-10-11 | 深圳润方创新技术有限公司 | Handwriting recognition method and system for electronic drawing board for children |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111523455A (en) | Evaluation method for Chinese character writing | |
| US10824801B2 (en) | Interactively predicting fields in a form | |
| JP4244614B2 (en) | Handwriting input device, program, and handwriting input method system | |
| US10127199B2 (en) | Automatic measure of visual similarity between fonts | |
| US6600834B1 (en) | Handwriting information processing system with character segmentation user interface | |
| CN107609489B (en) | Handwriting writing path evaluation device and method and electronic equipment | |
| US20070286486A1 (en) | System and method for automated reading of handwriting | |
| US20050100218A1 (en) | Recognition of electronic ink with late strokes | |
| US11587275B2 (en) | Method for generating a handwriting vector | |
| CN110060531B (en) | Computer online examination system and method using intelligent digital pen | |
| CN111695555B (en) | Question number-based accurate question framing method, device, equipment and medium | |
| CN113191309A (en) | Method and system for recognizing, scoring and correcting handwritten Chinese characters | |
| CN210038810U (en) | Intelligent evaluation equipment and system | |
| CN101364271B (en) | Method for recognizing hand-written Chinese character strokes and recognition device | |
| JP6694638B2 (en) | Program, information storage medium, and recognition device | |
| CN111310428A (en) | Automatic input and transmission system and method for handwriting of paper form | |
| CN117095414A (en) | Handwriting recognition system and recognition method based on dot matrix paper pen | |
| CN112101336A (en) | Intelligent data acquisition mode based on computer vision | |
| JP4807400B2 (en) | Handwriting input device, program, and handwriting input method system | |
| CN111027533A (en) | Conversion method and system of point-to-read coordinates, terminal device and storage medium | |
| JP2006309505A (en) | Terminal unit, program, and document for electronic pen | |
| KR102293361B1 (en) | Apparatus and method for providing handwriting calibration function | |
| TWI616355B (en) | Three-dimension printing modeling apparatus for hand-written characters and method thereof | |
| WO2005122062A1 (en) | Capturing data and establishing data capture areas | |
| JP3977473B2 (en) | Handwritten character recognition method and handwritten character recognition apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200811 |