CN116386066A - Handwriting recognition system for error correction of choice questions - Google Patents
Handwriting recognition system for error correction of choice questions Download PDFInfo
- Publication number
- CN116386066A CN116386066A CN202310372852.2A CN202310372852A CN116386066A CN 116386066 A CN116386066 A CN 116386066A CN 202310372852 A CN202310372852 A CN 202310372852A CN 116386066 A CN116386066 A CN 116386066A
- Authority
- CN
- China
- Prior art keywords
- data
- database
- handwriting
- error
- module
- 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
- 238000012937 correction Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000013519 translation Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000000034 method Methods 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 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
- G06V30/24—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
- G06V30/245—Font recognition
-
- 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
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- 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
- G06V30/248—Character recognition characterised by the processing or recognition method involving plural approaches, e.g. verification by template match; Resolving confusion among similar patterns, e.g. "O" versus "Q"
- G06V30/2528—Combination of methods, e.g. classifiers, working on the same input data
-
- 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
- G06V30/30—Character recognition based on the type of data
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a handwriting recognition system for correcting wrong drawing of a selection question, which comprises a central processing module, wherein the central processing module is used for processing the selection question; the database module is used for inputting and storing data, collecting and acquiring data resources of handwritten characters in a mode of downloading and simulating the handwritten characters on the internet, and dividing the data resources into a single-option error database, a double-option error database, a three-option error database, a four-option error database and a five-option error database; a data enhancement module; and a handwriting character recognition module. According to the scheme, the database is divided into the option error-correcting databases of various types, and when the handwriting character data corrected by error is identified, the handwriting character data are compared with the option error-correcting databases of various types in the database module to obtain correct options, and further the follow-up judgment is carried out, so that error correction of single options is supported, and error correction of multiple options is realized.
Description
Technical Field
The invention relates to the technical field of test paper correction, in particular to a handwriting recognition system for correcting wrong drawing of a selection question.
Background
Examination reforms and questions are required to be modern. The system is practical and easy to use, can assist in online education and online examination paper judgment, can store and manage examination questions in a classified mode, and can automatically judge selected questions in online examination paper according to certain settings. Meanwhile, the question is always just needed by the teacher group. Although the choice question judging system can recognize handwritten characters, in the case of a correction of a scratch in the choice questions, the recognition accuracy is significantly lowered.
The Chinese patent discloses a handwriting recognition system based on error correction of choice questions, the publication number is: CN113254689a, which can only identify the choice questions of single option, and when the examination is actually performed, there are multiple choice questions, which results in a significant decrease in the accuracy of the identification of the original system.
Disclosure of Invention
The invention mainly aims to provide a handwriting recognition system for error correction of a selection question, which aims to solve the problem that in the related art, the error correction exists in the selection question, and multiple selection questions exist, so that the recognition accuracy of the original system is obviously reduced.
In order to achieve the above-mentioned purpose, the present invention provides a handwriting recognition system for correcting wrong questions, a central processing module, a plurality of processing modules and a plurality of processing modules, wherein the central processing module is used for managing call connection among the modules of the whole system;
the database module is electrically connected with the central processing module and is used for inputting and storing data, collecting and acquiring data resources of handwritten characters in a mode of downloading and simulating the handwritten characters on the internet, and dividing the data resources into a single-option error database, a double-option error database, a three-option error database, a four-option error database and a five-option error database;
the data enhancement module is electrically connected with the central processing module and is used for simulating the diversity of the error correction scene, simulating the handwriting error correction format and the randomness of the corrected positions, and randomly generating batch error correction data by using image operation and the like;
the handwriting character recognition module is electrically connected with the central processing module, and the handwriting character recognition module uses the data after data enhancement to divide a data set, select a model, and train, test and evaluate the model.
In one embodiment of the present invention, the single option error-drawing database includes an a sub-database for storing handwriting character data of a;
the single-option error-drawing database comprises a sub-database B for storing handwriting character data of the sub-database B;
the single-option error-drawing database comprises a sub-database C for storing handwriting character data of C;
the single-option error-drawing database comprises a D sub-database for storing the handwriting character data of D;
the single-option error-drawing database comprises an E sub-database for storing E handwriting character data.
In one embodiment of the present invention, the data enhancement module includes an image processing unit, an error-drawing model building unit, a bracketed unit, and a data set deriving unit;
the image processing unit shifts the whole pixels in the picture by using horizontal translation, and then carries out black edge removing treatment on the shifted image;
the staggered model building unit is used for inputting various handwriting staggered types, including the conditions of diagonal line scribing, cross line scribing and the like, and establishing a plurality of staggered models;
the bracketed unit stores all original data into bracketed data in a matrix operation mode;
and the data set deriving unit is used for traversing the bracketed data according to the obtained bracketed data, randomly selecting the error type at the same time, obtaining a new picture through matrix operation of two or more picture images, and storing to obtain the data set with the required diversity.
In one embodiment of the present invention, the handwriting character recognition module includes a data loading unit, a data dividing unit, and a data outputting unit;
the data loading unit is used for loading a data set, reading images and corresponding characters, counting the number of samples and displaying the number of samples;
the data dividing unit is used for dividing the data set, namely dividing training, verifying the set, selecting and training a model, testing the model, improving the model and evaluating the model, and selecting and training the model to select a deep neural network model.
The data output unit is used for outputting the recognized result.
In one embodiment of the present invention, the electronic device further includes a manual recognition module, and the manual recognition module is electrically connected to the central processing module, and is configured to manually recognize handwriting character data that is difficult to determine.
In one embodiment of the present invention, the handwriting recognition module recognizes the following steps:
s1, loaded handwriting data;
s2, comparing the handwriting character data in the database;
s3, listing handwriting character data with similarity larger than a preset value;
s4, counting the occupation ratio of the listed handwriting character data in each sub-database;
s5, outputting a result.
In one embodiment of the invention, the ratio of the listed handwriting character data in a certain sub-database is more than 85%, and when the listed handwriting character data are distributed in only 2 sub-databases, the data of the database with the number ratio more than 85% are directly output; and other conditions are sent to the manual identification module.
In one embodiment of the present invention, when the listed handwritten character data is distributed in more than 3 sub-databases, but the ratio of the listed handwritten character data in a certain sub-database is more than 90%; the data of the database with the number of the data accounting for more than 85% is output, and other conditions are sent to the manual identification module.
In one embodiment of the invention, the system further comprises a database optimization module, wherein the database optimization module is used for storing the result of manual auditing into a database as data, and in use, the data in the database is optimally updated.
In one embodiment of the invention, the method further comprises a scratch model auxiliary module; the error drawing model auxiliary module is electrically connected with the central processing module;
after the error drawing model is identified, detecting whether another piece of handwriting data exists near the error drawing model through an error drawing model auxiliary module, and if the other piece of handwriting data exists, taking the nearby piece of handwriting data as the reference; if there is no other handwriting data, the answer of the error-drawing model is used.
Compared with the prior art, the invention has the beneficial effects that: according to the handwriting recognition system for correcting the wrong drawing of the selection questions, the database is divided into the wrong drawing databases of the multiple types of options, and when the handwriting recognition system is used for recognizing, if the corrected handwritten character data of the wrong drawing is recognized, the corrected handwritten character data of the wrong drawing is compared with the wrong drawing databases of the multiple types of options in the database module to obtain correct options, and further, the subsequent judgment is carried out, so that the wrong drawing correction of single options is supported, and the wrong drawing correction of multiple options is realized.
Drawings
FIG. 1 is a block diagram of a handwriting recognition system for error correction of choice questions provided in accordance with an embodiment of the present invention;
FIG. 2 is a block diagram of a database module of a handwriting recognition system for error correction of choice questions provided in accordance with an embodiment of the present invention;
FIG. 3 is a block diagram showing a single-option error database of a handwriting recognition system for correcting error of choice questions according to an embodiment of the present invention
FIG. 4 is a block diagram illustrating a data enhancement module of a handwriting recognition system for error correction of choice questions according to an embodiment of the present invention;
FIG. 5 is a block diagram of a handwriting recognition module of a choice question error correction handwriting recognition system provided in accordance with an embodiment of the present application;
fig. 6 is a flow chart of a handwriting character recognition module of a handwriting recognition system for error correction of choice questions according to an embodiment of the present application.
Description of the embodiments
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present invention, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are only used to better describe the present invention and its embodiments and are not intended to limit the scope of the indicated devices, elements or components to the particular orientations or to configure and operate in the particular orientations.
Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the present invention will be understood by those of ordinary skill in the art according to the specific circumstances.
In addition, the term "plurality" shall mean two as well as more than two.
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
Examples
Referring to fig. 1-6, the invention provides a handwriting recognition system for correcting error of choice questions, which comprises a central processing module, a control module and a control module, wherein the central processing module is used for managing call connection among modules of the whole system;
the database module is electrically connected with the central processing module and is used for inputting and storing data, collecting and acquiring data resources of handwritten characters in a mode of downloading and simulating the handwritten characters on the internet, and dividing the data resources into a single-option error database, a double-option error database, a three-option error database, a four-option error database and a five-option error database;
the data enhancement module is electrically connected with the central processing module and is used for simulating the diversity of the error correction scene, simulating the handwriting error correction format and the randomness of the corrected positions, and randomly generating batch error correction data by using image operation and the like;
the handwriting character recognition module is electrically connected with the central processing module, and the handwriting character recognition module uses the data after data enhancement to divide a data set, select a model, and train, test and evaluate the model.
Specifically, the data enhancement module comprises an image processing unit, an error-drawing model building unit, a bracketed unit and a data set deriving unit;
the image processing unit shifts the whole pixels in the picture by using horizontal translation, and then carries out black edge removing treatment on the shifted image;
the staggered model building unit is used for inputting various handwriting staggered types (the conditions of staggered categories such as diagonal lines, staggered numbers, vertical lines, horizontal lines, rectangular blocks and the like) and building a plurality of staggered models;
the bracketed unit considers the actual situation of the choice questions, and the brackets are unavoidable and need to avoid recognition, so that all original data are stored as bracketed data in a matrix operation mode;
and the data set deriving unit is used for traversing the bracketed data according to the obtained bracketed data, randomly selecting the error type at the same time, obtaining a new picture through matrix operation of two or more picture images, and storing to obtain the data set with the required diversity.
Specifically, for most exams, the basic options are A-E, so that the single option error-drawing database comprises an A sub-database for storing handwriting character data of A;
the single-option error-drawing database comprises a sub-database B for storing handwriting character data of the sub-database B;
the single-option error-drawing database comprises a sub-database C for storing handwriting character data of C;
the single-option error-drawing database comprises a D sub-database for storing the handwriting character data of D;
the single-option error-drawing database comprises an E sub-database for storing E handwriting character data.
If the question is a multi-choice question, the corresponding answer is a plurality of characters, the answer picture is required to be cut according to the characters to obtain a plurality of single character pictures, the single character pictures are input into the handwriting character recognition module, the recognition result of the single character is obtained, and the single character pictures are spliced into a plurality of characters to be output.
The cutting mode is as follows:
1. the minimum width of a single character is defined as 2 pixels.
2. The number of black pixel values from the first column of pixels to the last column of pixels in the picture is calculated.
3. When a column with the number of black pixel values larger than 2 appears, the column is considered as a character picture, and the position of the character picture is recorded.
4. And merging the character pictures with continuous positions to obtain the starting position and the ending position of the character pictures, wherein the width of the character pictures is required to be larger than or equal to the minimum width of the single character pictures.
And cutting out the corresponding starting position and ending position in the picture to obtain the picture with single character.
Specifically, the handwriting character recognition module comprises a data loading unit, a data dividing unit and a data output unit;
the data loading unit is used for loading a data set, reading images and corresponding characters, counting the number of samples and displaying the number of samples;
the data dividing unit is used for dividing a data set, namely dividing training, verifying set, selecting and training a model (constructing a deep neural network model), testing the model, improving the model and evaluating the model.
The data output unit is used for outputting the recognized result.
Further, the system also comprises a manual identification module, wherein the manual identification module is electrically connected with the central processing module and is used for manually identifying the handwriting character data which is difficult to determine.
Specifically, the recognition steps of the handwriting character recognition module are as follows:
s1, loaded handwriting data;
s2, comparing the handwriting character data in the database;
s3, listing handwriting character data with similarity larger than a preset value;
s4, counting the occupation ratio of the listed handwriting character data in each sub-database;
s5, outputting a result.
For example, when the ratio of the listed handwritten character data in a certain sub-database is more than 85%, and the listed handwritten character data is only distributed in 2 sub-databases, the data of the database with the number ratio of more than 85% is directly output; other conditions are sent to the manual identification module, and identification is more accurate.
Further, the system also comprises a database optimization module, wherein the database optimization module is used for storing the result of manual auditing as data into a database, and in use, the data in the database is optimized and updated.
Further, the answer is written in the brackets, and if the handwritten character answer is written on one side of the brackets, the handwritten character answer is easily recognized as a wrong drawing model;
handwriting answers on the transverse lines, if the handwriting character answers are truncated by the transverse lines, the handwriting character answers are easily recognized as a wrong drawing model;
so a scratch model auxiliary module is arranged; the error-dividing model auxiliary module is electrically connected with the central processing module.
After the error drawing model is identified, detecting whether another piece of handwriting data exists near the error drawing model through an error drawing model auxiliary module, and if the other piece of handwriting data exists, taking the nearby piece of handwriting data as the reference; if there is no other handwriting data, the answer of the error-drawing model is used.
Examples
A handwriting recognition system for correcting wrong drawing of a selection question comprises a central processing module and a control module, wherein the central processing module is used for managing call connection among modules of the whole system;
the database module is electrically connected with the central processing module and is used for inputting and storing data, collecting and acquiring data resources of handwritten characters in a mode of downloading and simulating the handwritten characters on the internet, and dividing the data resources into a single-option error database, a double-option error database, a three-option error database, a four-option error database and a five-option error database;
the data enhancement module is electrically connected with the central processing module and is used for simulating the diversity of the error correction scene, simulating the handwriting error correction format and the randomness of the corrected positions, and randomly generating batch error correction data by using image operation and the like;
the handwriting character recognition module is electrically connected with the central processing module, and the handwriting character recognition module uses the data after data enhancement to divide a data set, select a model, and train, test and evaluate the model.
Specifically, the data enhancement module comprises an image processing unit, an error-drawing model building unit, a bracketed unit and a data set deriving unit;
the image processing unit shifts the whole pixels in the picture by using horizontal translation, and then carries out black edge removing treatment on the shifted image;
the staggered model building unit is used for inputting various handwriting staggered types (the conditions of staggered categories such as diagonal lines, staggered numbers, vertical lines, horizontal lines, rectangular blocks and the like) and building a plurality of staggered models;
the bracketed unit considers the actual situation of the choice questions, and the brackets are unavoidable and need to avoid recognition, so that all original data are stored as bracketed data in a matrix operation mode;
and the data set deriving unit is used for traversing the bracketed data according to the obtained bracketed data, randomly selecting the error type at the same time, obtaining a new picture through matrix operation of two or more picture images, and storing to obtain the data set with the required diversity.
The single-option error-drawing database comprises an A sub-database for storing handwriting character data of A;
the single-option error-drawing database comprises a sub-database B for storing handwriting character data of the sub-database B;
the single-option error-drawing database comprises a sub-database C for storing handwriting character data of C;
the single-option error-drawing database comprises a D sub-database for storing the handwriting character data of D;
the single-option error-drawing database comprises an E sub-database for storing E handwriting character data.
Specifically, the handwriting character recognition module comprises a data loading unit, a data dividing unit and a data output unit;
the data loading unit is used for loading a data set, reading images and corresponding characters, counting the number of samples and displaying the number of samples;
the data dividing unit is used for dividing a data set, namely dividing training, verifying set, selecting and training a model (constructing a deep neural network model), testing the model, improving the model and evaluating the model.
The data output unit is used for outputting the recognized result.
Further, the system also comprises a manual identification module, wherein the manual identification module is electrically connected with the central processing module and is used for manually identifying the handwriting character data which is difficult to determine.
Specifically, the recognition steps of the handwriting character recognition module are as follows:
s1, loaded handwriting data;
s2, comparing the handwriting character data in the database;
s3, listing handwriting character data with similarity larger than a preset value;
s4, counting the occupation ratio of the listed handwriting character data in each sub-database;
s5, outputting a result.
Illustratively, when the listed handwritten character data is distributed in more than 3 sub-databases, the ratio of the listed handwritten character data in a certain sub-database is greater than 90%; the data of the database with the number of the data accounting for more than 85% is output, and other conditions are sent to the manual identification module.
Further, the system also comprises a database optimization module, wherein the database optimization module is used for storing the result of manual auditing as data into a database, and in use, the data in the database is optimized and updated.
Further, the answer is written in the brackets, and if the handwritten character answer is written on one side of the brackets, the handwritten character answer is easily recognized as a wrong drawing model;
handwriting answers on the transverse lines, if the handwriting character answers are truncated by the transverse lines, the handwriting character answers are easily recognized as a wrong drawing model;
so a scratch model auxiliary module is arranged; the error-dividing model auxiliary module is electrically connected with the central processing module.
After the error drawing model is identified, detecting whether another piece of handwriting data exists near the error drawing model through an error drawing model auxiliary module, and if the other piece of handwriting data exists, taking the nearby piece of handwriting data as the reference; if there is no other handwriting data, the answer of the error-drawing model is used.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A handwriting recognition system for error correction of a selected question, comprising:
the central processing module is used for taking charge of call connection management among modules of the whole system;
the database module is electrically connected with the central processing module and is used for inputting and storing data, collecting and acquiring data resources of handwritten characters in a mode of downloading and simulating the handwritten characters on the internet, and dividing the data resources into a single-option error database, a double-option error database, a three-option error database, a four-option error database and a five-option error database;
the data enhancement module is electrically connected with the central processing module and is used for simulating the diversity of the error correction scene, simulating the handwriting error correction format and the randomness of the corrected positions, and randomly generating batch error correction data by using image operation and the like;
the handwriting character recognition module is electrically connected with the central processing module, and the handwriting character recognition module uses the data after data enhancement to divide a data set, select a model, and train, test and evaluate the model.
2. A choice question mark-off correction handwriting recognition system as recited in claim 1, wherein:
the single-option error-drawing database comprises an A sub-database for storing handwriting character data of A;
the single-option error-drawing database comprises a sub-database B for storing handwriting character data of the sub-database B;
the single-option error-drawing database comprises a sub-database C for storing handwriting character data of C;
the single-option error-drawing database comprises a D sub-database for storing the handwriting character data of D;
the single-option error-drawing database comprises an E sub-database for storing E handwriting character data.
3. A handwriting recognition system for error correction of choice questions as claimed in claim 1 or 2, wherein:
the data enhancement module comprises an image processing unit, an error-drawing model building unit, a bracketed unit and a data set deriving unit;
the image processing unit shifts the whole pixels in the picture by using horizontal translation, and then carries out black edge removing treatment on the shifted image;
the error drawing model building unit is used for inputting various handwriting error drawing types and building a plurality of error drawing models;
the bracketed unit stores all original data into bracketed data in a matrix operation mode;
and the data set deriving unit is used for traversing the bracketed data according to the obtained bracketed data, randomly selecting the error type at the same time, obtaining a new picture through matrix operation of two or more picture images, and storing to obtain the data set with the required diversity.
4. A choice question mark-off correction handwriting recognition system as recited in claim 3, wherein:
the handwriting character recognition module comprises a data loading unit, a data dividing unit and a data output unit;
the data loading unit is used for loading a data set, reading images and corresponding characters, counting the number of samples and displaying the number of samples;
the data dividing unit is used for dividing a data set, namely dividing training, verifying a set, selecting and training a model, testing the model, improving the model and evaluating the model, and the data output unit is used for outputting the recognized result.
5. A choice question mark-off correction handwriting recognition system as recited in claim 1, wherein:
the system also comprises a manual identification module, wherein the manual identification module is electrically connected with the central processing module and is used for manually identifying the handwriting character data which is difficult to determine.
6. A choice question mark-off correction handwriting recognition system as recited in claim 1, wherein:
the recognition steps of the handwriting character recognition module are as follows:
s1, loaded handwriting data;
s2, comparing the handwriting character data in the database;
s3, listing handwriting character data with similarity larger than a preset value;
s4, counting the occupation ratio of the listed handwriting character data in each sub-database;
s5, outputting a result.
7. The choice question-marking correction handwriting recognition system of claim 6, wherein: luo Liechu, when the ratio of the handwriting character data in a certain sub-database is more than 85%, and the listed handwriting character data are only distributed in 2 sub-databases, directly outputting the data of the databases with the number ratio of more than 85%; and other conditions are sent to the manual identification module.
8. The choice question-marking correction handwriting recognition system of claim 6, wherein: when the listed handwritten character data are distributed in more than 3 sub-databases, the ratio of the listed handwritten character data in a certain sub-database is more than 90 percent; the data of the database with the number of the data accounting for more than 85% is output, and other conditions are sent to the manual identification module.
9. A choice question mark-off correction handwriting recognition system as recited in claim 1, wherein: the system also comprises a database optimizing module, wherein the database optimizing module is used for storing the result of manual auditing into a database as data, and in use, the data in the database is optimized and updated.
10. The handwriting recognition system for error correction of a choice question of claim 3, further comprising an error correction model assistance module; the error drawing model auxiliary module is electrically connected with the central processing module;
after the error drawing model is identified, detecting whether another piece of handwriting data exists near the error drawing model through an error drawing model auxiliary module, and if the other piece of handwriting data exists, taking the nearby piece of handwriting data as the reference; if there is no other handwriting data, the answer of the error-drawing model is used.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310372852.2A CN116386066A (en) | 2023-04-10 | 2023-04-10 | Handwriting recognition system for error correction of choice questions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310372852.2A CN116386066A (en) | 2023-04-10 | 2023-04-10 | Handwriting recognition system for error correction of choice questions |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116386066A true CN116386066A (en) | 2023-07-04 |
Family
ID=86972918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310372852.2A Pending CN116386066A (en) | 2023-04-10 | 2023-04-10 | Handwriting recognition system for error correction of choice questions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116386066A (en) |
-
2023
- 2023-04-10 CN CN202310372852.2A patent/CN116386066A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11790641B2 (en) | Answer evaluation method, answer evaluation system, electronic device, and medium | |
| CN109815932B (en) | Test paper correcting method and device, electronic equipment and storage medium | |
| CN112115736B (en) | Job correction method and system based on image recognition and intelligent terminal | |
| CN111144191A (en) | Font identification method and device, electronic equipment and storage medium | |
| CN110222195B (en) | Method and electronic device for mining relation between question answering result and knowledge point | |
| CN105096677A (en) | Teaching system and work method thereof | |
| CN109242856A (en) | A kind of papery operation electronization reads and makes comments method and device | |
| CN111737478B (en) | Text detection method, electronic device and computer readable medium | |
| JP4807489B2 (en) | Teaching material processing apparatus, teaching material processing method, and teaching material processing program | |
| CN112766247B (en) | Question processing method and device, electronic equipment and computer storage medium | |
| CN111242045A (en) | Automatic operation exercise right and wrong indication method and system | |
| CN111783855A (en) | Intelligent marking method and device | |
| CN112116840B (en) | Job correction method and system based on image recognition and intelligent terminal | |
| CN110738576B (en) | Method and device for generating damage assessment file for damaged vehicle | |
| CN113793538B (en) | Method and system for collecting teaching assistance operation wrong questions | |
| CN112989768B (en) | Method and device for correcting connection questions, electronic equipment and storage medium | |
| US20060194187A1 (en) | Material processing apparatus, material processing method, and program product | |
| CN113095312A (en) | Method for acquiring handwritten answer area in test paper based on identification code | |
| CN111639630A (en) | Operation correcting method and device | |
| CN116386066A (en) | Handwriting recognition system for error correction of choice questions | |
| CN115482535A (en) | Test paper automatic correction method, storage medium and equipment | |
| JP4807487B2 (en) | Teaching material processing apparatus, teaching material processing method, and teaching material processing program | |
| CN111291591A (en) | Intelligent test paper reading and printing method and device | |
| CN114332898A (en) | Automatic correcting method and device for connection test questions and storage medium | |
| CN112308062B (en) | Medical image access number identification method in complex background image |
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 |