CN113326813A - Electronic format conversion method for mathematics classroom blackboard writing - Google Patents
Electronic format conversion method for mathematics classroom blackboard writing Download PDFInfo
- Publication number
- CN113326813A CN113326813A CN202110774045.4A CN202110774045A CN113326813A CN 113326813 A CN113326813 A CN 113326813A CN 202110774045 A CN202110774045 A CN 202110774045A CN 113326813 A CN113326813 A CN 113326813A
- Authority
- CN
- China
- Prior art keywords
- image
- track
- writing
- characters
- character
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/32—Digital ink
- G06V30/333—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/32—Digital ink
- G06V30/36—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Drawing Aids And Blackboards (AREA)
Abstract
The invention discloses a mathematical classroom blackboard-writing electronic format conversion method, and belongs to the field of education. The electronic format conversion method for the math classroom blackboard writing comprises the following steps: s1, fixedly connecting the writing pen with the mobile conversion system; s2, setting a writing plane; s3, setting a feedback plane; s4, judging whether a complete sentence is formed; s5, converting the track image into characters by adopting a frame image recognition method; s6, carrying out cutting classification on the track images which cannot be converted by the frame image recognition method; s7, integrating and summarizing after classification, and placing the recognized characters in a virtual box according to the size of the original track image; s8, automatically changing pages after the feedback plane is filled with characters, wherein the page size is consistent with the size of the original plane; the method can realize the conversion of the equal proportion and the equal position of the blackboard writing draft in the math classroom into the electronic format, wherein the text part can be operated, and the content of the blackboard writing draft is easier to understand than the electronic document converted according to the writing sequence.
Description
Technical Field
The invention belongs to the field of education, and particularly relates to an electronic format conversion method for a math classroom blackboard-writing.
Background
The content of writing on blackboard in teaching classroom is an important part of the teaching content, and the writing on blackboard is a way of transmitting teaching information by writing characters and symbols on blackboard when teacher goes on class and a speech activity of teaching book nurses, also called teaching written language. From the static perspective, it is a general term of teaching information that teachers utilize blackboards to display concise and concise characters, symbols, diagrams and the like in order to help students understand and master knowledge during teaching.
Especially in the classroom of mathematics teaching, because the mathematics problem solving needs quick and sensitive thinking, the contents of the blackboard-writing can be updated quickly when the blackboard-writing is embodied, once students with slow thinking cannot keep up with the thought, the students can not understand the whole classroom, and the students can lose interest and enthusiasm for mathematics learning seriously.
Therefore, it is very necessary to store the contents of the blackboard writing in the mathematic classroom in an electronic format.
The existing method for converting the electronic format by handwriting can only completely rub the written characters or symbols in real time, and the characters or symbols are embodied in the electronic document, and the sequence of the characters in the electronic document is written in the order of writing.
However, due to the specific style of the blackboard writing, the writing sequence of each sentence is disordered, when a teacher writes on a blackboard, the teacher probably writes one place east and one place west, the character sequence is disordered, characters in the mathematical teaching are analyzed along with images, and the meaning of the character expression of each place is greatly related to the position of the character expression.
Therefore, the existing method for converting the electronic format by handwriting is not applicable to the classroom of mathematical education.
Disclosure of Invention
The invention aims to provide a math classroom blackboard-writing electronic format conversion method, which can realize the conversion of blackboard-writing drafts in math classrooms in equal proportion and equal positions into electronic formats, wherein the character part can be operated, and students can more easily understand the contents of the blackboard-writing drafts than electronic documents converted according to the writing sequence when using the blackboard-writing drafts in the electronic formats.
The invention relates to a method for converting an electronic format of a math classroom blackboard-writing, which comprises the following steps:
s1, fixedly connecting the writing pen with a mobile conversion system, and wirelessly connecting the mobile conversion system with a background cloud end;
s2, the movement conversion system records the track signal generated when the writing pen moves, and sets the writing plane, the setting standard of the writing plane is: writing a set track signal in a certain plane by a writing pen for the first time, wherein the plane is a writing plane;
s3, the background cloud end receives and records the effective track signal fed back by the mobile conversion system, and converts the effective track signal into a track image; wherein, the effective track signal is the track signal generated by the writing pen only on the writing plane; meanwhile, a feedback plane is set at the background cloud end, the feedback plane is a virtual plane which is consistent with the size of the blackboard for writing on the blackboard in the classroom, and the track images are mapped on the feedback plane in equal proportion and at the same position;
s4, judging whether the track image forms a complete sentence or not by the background cloud;
s5, when the track image forms a complete sentence, the background cloud end adopts a frame image recognition method to convert the track image of the complete sentence, and the image is replaced by operable characters;
s6, carrying out cutting classification on the track images which cannot be converted by the frame image recognition method;
s7, integrating and summarizing the classified track images, defining the track images as re-judgment character blocks, extracting the re-judgment character blocks, comparing the re-judgment character blocks with characters stored in a dictionary pool, replacing the re-judgment character blocks with characters when the re-judgment character blocks are the existing characters in the dictionary pool, and placing the identified characters in virtual boxes according to the size of the original track images; the dictionary pool stores the existing Chinese, English and mathematical symbol set;
and S8, automatically changing pages after the feedback plane is filled with characters, wherein the page size is consistent with the size of the original plane.
As a further improvement of the invention, the setting method of the writing plane comprises the following steps: s201, drawing a special track image on a plane by using a writing pen, wherein the special track image comprises characters, lines or symbols.
As a further improvement of the present invention, the special track image is a "start" character.
As a further improvement of the invention, the setting method of the writing plane comprises the following steps: s201, continuously stopping for 3-5S on one point on a plane by using the writing pen.
As a further improvement of the present invention, the setting method of the feedback plane includes the steps of: s301, after the writing plane is determined, drawing a box on the writing plane by using the writing pen, wherein the size and the shape of the box are the size and the shape of the feedback plane.
As a further improvement of the invention, the writing pen draws a square on the writing plane as a border of the blackboard ready for writing.
As a further improvement of the present invention, when there are a plurality of different blackboards or there is a movable blackboard, it is necessary to redetermine the writing plane and the feedback plane every time a blackboard is written on a different blackboard or every time a blackboard is written after moving the blackboard.
As a further improvement of the invention, the method for judging the complete sentence formed by the track image by the background cloud comprises the following steps: s401, when the blank gap between two adjacent track images exceeds 2-3cm, the track image before the blank gap is the end of one complete sentence, and the track image after the blank gap is the beginning of another complete sentence.
As a further improvement of the invention, the method for judging the complete sentence formed by the track image by the background cloud comprises the following steps: s401, after one blackboard writing, blackboard writing is performed again at intervals of 5-8S, the content of the previous blackboard writing is a complete sentence, and the content of the blackboard writing is another complete sentence.
As a further improvement of the invention, the frame image recognition method comprises the following steps:
s501, recognizing a track image of a complete sentence from left to right;
s502, calculating the overall height size X of the track image, defining the track image in a virtual box as a character block when the track image is in the virtual box with the height size X and the width size X, and extracting the character block;
s503, comparing the dictionary pool according to the block image, judging whether the block content is the characters stored in the dictionary pool, replacing the block with the characters when the block is the existing characters in the dictionary pool, and placing the recognized characters in a virtual box according to the size of the original track image;
s504, when the content of the word block is not in the character range stored in the dictionary pool, the content of the original track image is kept unchanged, and the next track image is continuously identified.
As a further improvement of the invention, the cutting classification of the track image comprises the following steps:
s601, comparing the track image with the character image in the dictionary pool;
s602, finding out a character image in a dictionary pool closest to the track image;
s603, extracting character images in a dictionary pool from the track images, and defining the character images as character type sub-characters;
s604, independently extracting other images from the track image and defining the images as other sub-characters;
and S605, dividing the characters into component type sub characters, symbol type sub characters, punctuation type sub characters and line type sub characters according to the images of other sub characters and by referring to character images in a dictionary pool.
As a further improvement of the invention, the classified track images are integrated and summarized and comprise the following steps:
s701, converting the character type sub-characters into characters corresponding to character images in a dictionary pool, and placing the recognized characters in a virtual box according to the size of an original track image;
s702, combining the component sub-characters with a previous character, a previous sub-character, a next character and a next sub-character in sequence, comparing a track image obtained in four combination forms with a character image in a dictionary pool to obtain a combination with a consistent image, converting the image obtained by the combination into a character, and placing the recognized character in a virtual box where the track image is located according to the size of the track image with the maximum size in two combination items;
s703, comparing the image of the symbol type sub-character with the character image in the dictionary pool, finding out a symbol corresponding to the symbol, replacing the image of the symbol type sub-character with the symbol character, and placing the image in a virtual box according to the size of the original track image;
s704, comparing the image of the punctuation type sub-characters with the character image in the dictionary pool, finding out corresponding punctuation, replacing the image of the punctuation type sub-characters with the punctuation characters, and placing the punctuation characters in a virtual box according to the size of the original track image;
s705, combining adjacent line type sub characters in the complete sentence to obtain a continuous line image, comparing the continuous line image with the character image in the dictionary pool to find out the line character corresponding to the continuous line image, replacing the image of the line type sub character with the line character, and placing the image in a virtual box according to the size of the original track image.
As a further improvement of the invention, when the track image can not be identified after the integration and induction, the track image of the complete sentence is converted into a picture format and is arranged in the virtual box according to the size of the original track image.
As a further improvement of the invention, when the feedback plane does not completely cover the full track image, a new complete sentence track image or a new complete sentence partial track image is covered in the writing plane area occupying the complete sentence, the background cloud copies the content of the feedback plane before the new complete sentence which is not written and covered, inserts a new page, sticks the copied content in the new page, replaces the covered new complete sentence track image to the covered area, and identifies the content of the new complete sentence track image and replaces the new complete sentence track image into characters; when a new complete sentence track image or a new complete sentence partial track image is covered in a writing plane area occupying a complete sentence in a previous page, the covered new complete sentence track image is directly replaced to the covered area.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention maps the recognized complete sentence on the feedback plane in equal proportion and equal positions, and converts the track image of the complete sentence into operable characters, so that students can more clearly understand the expression significance of the blackboard-writing content, and can freely copy, paste, change and the like the blackboard-writing content, thereby facilitating the students to self-card the blackboard-writing content.
2. According to the invention, only after the writing plane is determined, the movement of the writing pen can be converted into the effective track signal, so that the phenomenon that the background cloud converts the invalid early-stage action into the track signal to cause the misreading of the book content is effectively avoided.
3. According to the invention, only the track on the writing plane can be converted into the effective track signal and transmitted to the background cloud end, so that the phenomenon that the background cloud end converts the invalid writing continuous action into the track signal to cause misreading of the book content is effectively avoided.
4. The feedback plane is the virtual plane with the same size as the blackboard for writing blackboard in a classroom, and when the blackboard is full, the feedback plane automatically changes pages, so that the problems that the blackboard writing contents are overlapped and cannot be identified are effectively avoided.
5. The invention firstly uses the frame image recognition method to carry out image-character replacement on the complete sentence, then cuts and classifies the track image which can not be recognized by the frame image recognition method, integrates and summarizes the classified sub-characters again, recognizes by referring to the character image in the dictionary pool, further completes the image-character replacement, enables the characters, the letters and the symbols to be converted into operable characters, and lines to be converted into images, and provides the function of assisting understanding for the characters, the letters and the symbols.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a flow chart of a method for setting a composition plane according to the present invention;
FIG. 3 is a flow chart of a method for setting a feedback plane according to the present invention;
FIG. 4 is a schematic flow chart of a method of frame image recognition according to the present invention;
FIG. 5 is a flow chart illustrating a method of cutting classification according to the present invention;
FIG. 6 is a schematic flow chart of the method of the present invention;
FIG. 7 is a flowchart illustrating a method for feeding back plane paging according to the present invention.
Detailed Description
The first embodiment is as follows: please refer to fig. 1-7, which shows an electronic format conversion method for a math classroom blackboard book, comprising the following steps:
s1, fixedly connecting the writing pen with a mobile conversion system, and wirelessly connecting the mobile conversion system with a background cloud.
S2, the movement conversion system records the track signal generated when the writing pen moves, and sets the writing plane, the setting standard of the writing plane is: the writing pen writes a set character track signal of 'start' in a certain plane for the first time, and the plane is a writing plane.
S3, the background cloud end receives and records the effective track signal fed back by the mobile conversion system, and converts the effective track signal into a track image; wherein, the effective track signal is the track signal generated by the writing pen only on the writing plane; meanwhile, a feedback plane is set at the background cloud end, the feedback plane is a virtual plane which is consistent with the size of the blackboard for writing on the blackboard in the classroom, and the track images are mapped on the feedback plane in equal proportion and at the same position; the plane where the first square image recorded after the writing plane is determined is a feedback plane; the setting of the feedback plane needs to draw a box on the writing plane by using the writing pen after determining the writing plane, wherein the size and the shape of the box are the size and the shape of the feedback plane. The writing pen draws a square frame on the writing plane as a border of the blackboard ready for writing. When a plurality of different blackboards exist or a movable blackboard exists, the writing plane and the feedback plane need to be determined again every time when a user writes on the different blackboards or every time when the user writes on the movable blackboard.
S4, judging whether the track image forms a complete sentence or not by the background cloud; the method for judging the complete sentence formed by the track image by the background cloud comprises the following steps: when the blank gap between two adjacent track images exceeds 2-3cm, the track image before the blank gap is the end of one complete sentence, and the track image after the blank gap is the beginning of another complete sentence.
S5, when the track image forms a complete sentence, the background cloud end adopts a frame image recognition method to convert the track image of the complete sentence, and the image is replaced by operable characters; operable means that: the user can carry out editing means such as copying, pasting, deleting and the like on the characters;
the frame image recognition method comprises the following steps:
s501, recognizing a track image of a complete sentence from left to right;
s502, calculating the overall height size X of the track image, defining the track image in a virtual box as a character block when the track image is in the virtual box with the height size X and the width size X, and extracting the character block;
s503, comparing the dictionary pool according to the block image, judging whether the block content is the characters stored in the dictionary pool, replacing the block with the characters when the block is the existing characters in the dictionary pool, and placing the recognized characters in a virtual box according to the size of the original track image; the dictionary pool stores the existing Chinese, English and mathematical symbol set;
s504, when the content of the word block is not in the character range stored in the dictionary pool, the content of the original track image is kept unchanged, and the next track image is continuously identified.
S6, carrying out cutting classification on the track images which cannot be converted by the frame image recognition method; the cutting classification of the track image comprises the following steps:
s601, comparing the track image with the character image in the dictionary pool;
s602, finding out a character image in a dictionary pool closest to the track image;
s603, extracting character images in a dictionary pool from the track images, and defining the character images as character type sub-characters;
s604, independently extracting other images from the track image and defining the images as other sub-characters;
and S605, dividing the characters into component type sub characters, symbol type sub characters, punctuation type sub characters and line type sub characters according to the images of other sub characters and by referring to character images in a dictionary pool.
S7, integrating and summarizing the classified track images, wherein the integrated and summarized classified track images comprise the following steps:
s701, converting the character type sub-characters into characters corresponding to character images in a dictionary pool, and placing the recognized characters in a virtual box according to the size of an original track image;
s702, combining the component sub-characters with a previous character, a previous sub-character, a next character and a next sub-character in sequence, comparing a track image obtained in four combination forms with a character image in a dictionary pool to obtain a combination with a consistent image, converting the image obtained by the combination into a character, and placing the recognized character in a virtual box where the track image is located according to the size of the track image with the maximum size in two combination items;
s703, comparing the image of the symbol type sub-character with the character image in the dictionary pool, finding out a symbol corresponding to the symbol, replacing the image of the symbol type sub-character with the symbol character, and placing the image in a virtual box according to the size of the original track image;
s704, comparing the image of the punctuation type sub-characters with the character image in the dictionary pool, finding out corresponding punctuation, replacing the image of the punctuation type sub-characters with the punctuation characters, and placing the punctuation characters in a virtual box according to the size of the original track image;
s705, combining adjacent line type sub characters in the complete sentence to obtain a continuous line image, comparing the continuous line image with the character image in the dictionary pool to find out the line character corresponding to the continuous line image, replacing the image of the line type sub character with the line character, and placing the image in a virtual box according to the size of the original track image.
And S706, when the track images cannot be identified after integration and induction, converting the track images of the complete sentence into a picture format, and placing the track images into a virtual box according to the size of the original track images.
And S8, automatically changing pages after the feedback plane is filled with characters, wherein the page size is consistent with the size of the original plane. When the feedback plane does not completely cover the full track image, a new complete sentence track image or a new complete sentence partial track image is covered in a writing plane area occupying a complete sentence, the background cloud copies the content of the feedback plane before the new complete sentence which is not written and covered, inserts a new page, sticks the copied content in the new page, replaces the covered new complete sentence track image to the covered area, and simultaneously identifies the content of the new complete sentence track image and replaces the new complete sentence track image into characters; when a new complete sentence track image or a new complete sentence partial track image is covered in a writing plane area occupying a complete sentence in a previous page, the covered new complete sentence track image is directly replaced to the covered area.
The second embodiment is as follows: unlike the specific embodiment, the setting of the writing plane requires a continuous dwell of 3-5 seconds at a point on a plane using the writing pen.
The third concrete embodiment: different from the specific embodiment, the method for judging that the track image forms the complete sentence by the background cloud comprises the following steps: after one blackboard-writing, the blackboard-writing is performed again after the interval of 5-8s, the content of the previous blackboard-writing is a complete sentence, and the content of the blackboard-writing is another complete sentence.
The fourth concrete embodiment: fixedly connecting a writing pen with a mobile conversion system, wirelessly connecting the mobile conversion system with a background cloud end, setting a writing plane and a feedback plane, writing on the writing plane with the writing pen, referring to a function curve in a figure 1-A, solving the contents of a complete sentence of 'equation Z' input and output ^ and converting the contents of the writing on the writing plane into an electronic format, and comprising the following steps of:
s1, identifying the track image of the complete sentence from left to right by using a frame image identification method;
preliminarily recognizing the track image, namely a reference image, a function curve, a calculation program, a program, an output and a straight, replacing the track image with corresponding characters, and placing the corresponding characters at an original position;
the method comprises the following steps that (1) a track image 1-A, a line, an input and an input are not recognized, an original estimation image is kept unchanged and is placed at an original position;
s2, cutting and classifying the track images which cannot be identified in S1 to segment out '1', ',' A ',' line ',', 'square', 'Z', ',', and 'alpha';
wherein, the '1', 'line', 'square' and 'input' are character type sub-characters;
wherein, "[ alpha ] is a radical type sub-character;
wherein, "A" and "Z" are symbolic class sub-characters;
wherein, "," ', and "'" are punctuation-type sub-characters;
wherein, "-" is a line type sub-character;
s3, comparing the images of the character type characters, the symbol type sub-characters and the punctuation type sub-characters with the character images in the dictionary pool, finding out corresponding characters, replacing the characters with the images, and placing the characters in a virtual box according to the size of the original track image;
s4, combining the first character and the next character to get two combination forms of the first and the second, comparing the images of the two combination forms with the character images in the dictionary pool to find the corresponding character of the value, converting the images of the first and the second into the character of the value, and putting the recognized character in the virtual box of the track image according to the size of the track image with the largest size in the two combination items; wherein, the size of the 'straight' image is larger than that of the 'alpha' image, and the 'value' character is arranged in the virtual box of the 'straight' track image according to the size of the 'straight' track image;
s5, combining adjacent line type sub-characters in the complete sentence, comparing the line image with the character image in the dictionary pool because the complete sentence only has one line image, finding out the corresponding line character, replacing the image of the line type sub-character with the line character, and placing the image in a virtual box according to the size of the original track image;
and S6, converting the track image of the complete sentence into an electronic format of 'referring to the function curve in the figure 1-A, solving the input and output values of the equation Z', wherein any character in the electronic format can be operated.
Claims (10)
1. The electronic format conversion method for the math classroom blackboard writing is characterized by comprising the following steps: the method comprises the following steps:
s1, fixedly connecting the writing pen with a mobile conversion system, and wirelessly connecting the mobile conversion system with a background cloud end;
s2, the movement conversion system records the track signal generated when the writing pen moves, and sets the writing plane, the setting standard of the writing plane is: writing a set track signal in a certain plane by a writing pen for the first time, wherein the plane is a writing plane;
s3, the background cloud end receives and records the effective track signal fed back by the mobile conversion system, and converts the effective track signal into a track image; wherein, the effective track signal is the track signal generated by the writing pen only on the writing plane; meanwhile, a feedback plane is set at the background cloud end, the feedback plane is a virtual plane which is consistent with the size of the blackboard for writing on the blackboard in the classroom, and the track images are mapped on the feedback plane in equal proportion and at the same position;
s4, judging whether the track image forms a complete sentence or not by the background cloud;
s5, when the track image forms a complete sentence, the background cloud end adopts a frame image recognition method to convert the track image of the complete sentence, and the image is replaced by operable characters;
s6, carrying out cutting classification on the track images which cannot be converted by the frame image recognition method;
s7, integrating and summarizing the classified track images, defining the track images as re-judgment character blocks, extracting the re-judgment character blocks, comparing the re-judgment character blocks with characters stored in a dictionary pool, replacing the re-judgment character blocks with characters when the re-judgment character blocks are the existing characters in the dictionary pool, and placing the identified characters in virtual boxes according to the size of the original track images;
and S8, automatically changing pages after the feedback plane is filled with characters, wherein the page size is consistent with the size of the original plane.
2. The electronic format conversion method for the math classroom blackboard-writing of claim 1, wherein: the setting method of the writing plane comprises the following steps: s201, drawing a special track image on a plane by using a writing pen, wherein the special track image comprises characters, lines or symbols.
3. The electronic format conversion method for the math classroom blackboard-writing of claim 1, wherein: the setting method of the writing plane comprises the following steps: s201, continuously stopping for 3-5S on one point on a plane by using the writing pen.
4. The electronic format conversion method for the math classroom blackboard-writing of claim 1, wherein: the setting method of the feedback plane comprises the following steps: s301, after the writing plane is determined, drawing a box on the writing plane by using the writing pen, wherein the size and the shape of the box are the size and the shape of the feedback plane.
5. The electronic format conversion method for the math classroom blackboard-writing of claim 1, wherein: the method for judging the complete sentence formed by the track image by the background cloud comprises the following steps: s401, when the blank gap between two adjacent track images exceeds 2-3cm, the track image before the blank gap is the end of one complete sentence, and the track image after the blank gap is the beginning of another complete sentence.
6. The electronic format conversion method for the math classroom blackboard-writing of claim 1, wherein: the frame image recognition method comprises the following steps:
s501, recognizing a track image of a complete sentence from left to right;
s502, calculating the overall height size X of the track image, defining the track image in a virtual box as a character block when the track image is in the virtual box with the height size X and the width size X, and extracting the character block;
s503, comparing the dictionary pool according to the block image, judging whether the block content is the characters stored in the dictionary pool, replacing the block with the characters when the block is the existing characters in the dictionary pool, and placing the recognized characters in a virtual box according to the size of the original track image;
s504, when the content of the word block is not in the character range stored in the dictionary pool, the content of the original track image is kept unchanged, and the next track image is continuously identified.
7. The electronic format conversion method for the math classroom blackboard-writing of claim 1, wherein: the cutting classification of the track image comprises the following steps:
s601, comparing the track image with the character image in the dictionary pool;
s602, finding out a character image in a dictionary pool closest to the track image;
s603, extracting character images in a dictionary pool from the track images, and defining the character images as character type sub-characters;
s604, independently extracting other images from the track image and defining the images as other sub-characters;
and S605, dividing the characters into component type sub characters, symbol type sub characters, punctuation type sub characters and line type sub characters according to the images of other sub characters and by referring to character images in a dictionary pool.
8. The electronic format conversion method for the math classroom blackboard-writing of claim 1, wherein: the classified track image integration and induction comprises the following steps:
s701, converting the character type sub-characters into characters corresponding to character images in a dictionary pool, and placing the recognized characters in a virtual box according to the size of an original track image;
s702, combining the component sub-characters with a previous character, a previous sub-character, a next character and a next sub-character in sequence, comparing a track image obtained in four combination forms with a character image in a dictionary pool to obtain a combination with a consistent image, converting the image obtained by the combination into a character, and placing the recognized character in a virtual box where the track image is located according to the size of the track image with the maximum size in two combination items;
s703, comparing the image of the symbol type sub-character with the character image in the dictionary pool, finding out a symbol corresponding to the symbol, replacing the image of the symbol type sub-character with the symbol character, and placing the image in a virtual box according to the size of the original track image;
s704, comparing the image of the punctuation type sub-characters with the character image in the dictionary pool, finding out corresponding punctuation, replacing the image of the punctuation type sub-characters with the punctuation characters, and placing the punctuation characters in a virtual box according to the size of the original track image;
s705, combining adjacent line type sub characters in the complete sentence to obtain a continuous line image, comparing the continuous line image with the character image in the dictionary pool to find out the line character corresponding to the continuous line image, replacing the image of the line type sub character with the line character, and placing the image in a virtual box according to the size of the original track image.
9. The electronic format conversion method for the math classroom blackboard-writing of claim 8, wherein: and when the track images cannot be identified after integration and induction, converting the track images of the complete sentence into a picture format, and placing the track images in a virtual box according to the size of the original track images.
10. The electronic format conversion method for the math classroom blackboard-writing of claim 1, wherein: when the feedback plane does not completely cover the full track image, a new complete sentence track image or a new complete sentence partial track image is covered in a writing plane area occupying a complete sentence, the background cloud copies the content of the feedback plane before the new complete sentence which is not written and covered, inserts a new page, sticks the copied content in the new page, replaces the covered new complete sentence track image to the covered area, and simultaneously identifies the content of the new complete sentence track image and replaces the new complete sentence track image into characters; when a new complete sentence track image or a new complete sentence partial track image is covered in a writing plane area occupying a complete sentence in a previous page, the covered new complete sentence track image is directly replaced to the covered area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110774045.4A CN113326813B (en) | 2021-07-08 | 2021-07-08 | Electronic format conversion method for mathematics classroom blackboard writing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110774045.4A CN113326813B (en) | 2021-07-08 | 2021-07-08 | Electronic format conversion method for mathematics classroom blackboard writing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113326813A true CN113326813A (en) | 2021-08-31 |
| CN113326813B CN113326813B (en) | 2022-10-21 |
Family
ID=77426020
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110774045.4A Active CN113326813B (en) | 2021-07-08 | 2021-07-08 | Electronic format conversion method for mathematics classroom blackboard writing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113326813B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006162692A (en) * | 2004-12-02 | 2006-06-22 | Hosei Univ | Automatic lecture content creating system |
| JP2008097370A (en) * | 2006-10-12 | 2008-04-24 | Canon Inc | Hand written character recognizer, and hand-written character recognition method |
| CN101316356A (en) * | 2007-05-29 | 2008-12-03 | 北京大学 | Blackboard writing dynamic image compression method facing remote education |
| JP2012196847A (en) * | 2011-03-22 | 2012-10-18 | Casio Computer Co Ltd | Electronic blackboard, student terminal, server, and program |
| CN107506720A (en) * | 2017-08-18 | 2017-12-22 | 广州视源电子科技股份有限公司 | Writing on the blackboard processing method, device, equipment and computer-readable recording medium |
| CN109407892A (en) * | 2018-12-03 | 2019-03-01 | 姚苏栩 | A kind of shared blackboard, a kind of writing implement and a kind of writing induction panel |
| CN111160285A (en) * | 2019-12-31 | 2020-05-15 | 安博思华智能科技有限责任公司 | Method, device, medium and electronic equipment for acquiring blackboard writing information |
| CN111881904A (en) * | 2020-07-31 | 2020-11-03 | 城云科技（中国）有限公司 | Blackboard writing recording method and system |
| CN112507927A (en) * | 2020-12-16 | 2021-03-16 | 罗普特科技集团股份有限公司 | Automatic generation method and device for blackboard writing content |
| CN112506369A (en) * | 2020-11-20 | 2021-03-16 | 广州朗国电子科技有限公司 | Method for converting physical handwriting into electronic handwriting, electronic equipment and storage medium |
-
2021
- 2021-07-08 CN CN202110774045.4A patent/CN113326813B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006162692A (en) * | 2004-12-02 | 2006-06-22 | Hosei Univ | Automatic lecture content creating system |
| JP2008097370A (en) * | 2006-10-12 | 2008-04-24 | Canon Inc | Hand written character recognizer, and hand-written character recognition method |
| CN101316356A (en) * | 2007-05-29 | 2008-12-03 | 北京大学 | Blackboard writing dynamic image compression method facing remote education |
| JP2012196847A (en) * | 2011-03-22 | 2012-10-18 | Casio Computer Co Ltd | Electronic blackboard, student terminal, server, and program |
| CN107506720A (en) * | 2017-08-18 | 2017-12-22 | 广州视源电子科技股份有限公司 | Writing on the blackboard processing method, device, equipment and computer-readable recording medium |
| WO2019033656A1 (en) * | 2017-08-18 | 2019-02-21 | 广州视源电子科技股份有限公司 | Board-writing processing method, device and apparatus, and computer-readable storage medium |
| CN109407892A (en) * | 2018-12-03 | 2019-03-01 | 姚苏栩 | A kind of shared blackboard, a kind of writing implement and a kind of writing induction panel |
| CN111160285A (en) * | 2019-12-31 | 2020-05-15 | 安博思华智能科技有限责任公司 | Method, device, medium and electronic equipment for acquiring blackboard writing information |
| CN111881904A (en) * | 2020-07-31 | 2020-11-03 | 城云科技（中国）有限公司 | Blackboard writing recording method and system |
| CN112506369A (en) * | 2020-11-20 | 2021-03-16 | 广州朗国电子科技有限公司 | Method for converting physical handwriting into electronic handwriting, electronic equipment and storage medium |
| CN112507927A (en) * | 2020-12-16 | 2021-03-16 | 罗普特科技集团股份有限公司 | Automatic generation method and device for blackboard writing content |
Non-Patent Citations (2)
| Title |
|---|
| RUBEN TOLOSANA等: ""Exploring Recurrent Neural Networks for On-Line HandwrittenSignature Biometrics"", 《IEEE ACCESS》 * |
| 张行: ""人工智能在手写签字鉴定应用中的研究"", 《信息安全研究》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113326813B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5057020A (en) | Reading enabler | |
| Suzuki et al. | An integrated OCR software for mathematical documents and its output with accessibility | |
| US5556282A (en) | Method for the geographical processsing of graphic language texts | |
| Eddy | The shape of knowledge: Children and the visual culture of literacy and numeracy | |
| WO2022161293A1 (en) | Image processing method and apparatus, and electronic device and storage medium | |
| WO1995019616A9 (en) | Method for the geographical processing of graphic language texts | |
| KR102100811B1 (en) | Record mediumM marking for Hangul stage of Japanese pronunciation expression | |
| Berninger | Educating students in the computer age to be multilingual by hand | |
| CN113035026B (en) | Audio-visual tactile perception matching method without barriers for braille information | |
| CN113326813B (en) | Electronic format conversion method for mathematics classroom blackboard writing | |
| CN107515848A (en) | The bilingual mark and composition method of books or electronic document | |
| Almohimeed et al. | An Arabic Sign Language corpus for instructional language in school | |
| Frase et al. | Intuitions, algorithms, and a science of text design | |
| Brzostek-Pawlowska et al. | A concept of mobile technology for remotely supporting mathematical education of the blind | |
| Shao et al. | Braille-to-Chinese translation system based on optical braille recognition | |
| CN114816115B (en) | Screen auxiliary assembly for education and teaching | |
| Suzuki et al. | New tools to convert PDF math contents into accessible e-books efficiently | |
| CN113221563A (en) | Labeling method, device and equipment for PDF document | |
| Arjulayana | Google Translate As an Alternative Tool to Assist EFL Undergraduate’s Students’ Assignment | |
| JP6570163B1 (en) | Japanese language learning card | |
| Zatserkovnyi et al. | Analysis of Braille translation software | |
| Dilshoda | HOW TO IMPROVE ENGLISH WRITING SKILLS | |
| Sahrir | Penataran Pendidikan Bahasa Arab di IPT: Upgrading the Arabic Education at Higher Learning Institution | |
| Morales | 3.1 Document Design | |
| Fleming | 3.1 Document Design |
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 |