CN108830267A - A kind of method and system goed over examination papers based on image recognition - Google Patents
A kind of method and system goed over examination papers based on image recognition Download PDFInfo
- Publication number
- CN108830267A CN108830267A CN201810431331.9A CN201810431331A CN108830267A CN 108830267 A CN108830267 A CN 108830267A CN 201810431331 A CN201810431331 A CN 201810431331A CN 108830267 A CN108830267 A CN 108830267A
- Authority
- CN
- China
- Prior art keywords
- paper
- examination papers
- over examination
- layer
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013507 mapping Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 6
- 238000011020 pilot scale process Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 12
- 230000005540 biological transmission Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- 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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application discloses a kind of method and system goed over examination papers based on image recognition, and this method includes:In the logon rights for obtaining client in equipment of going over examination papers;When client has logon rights, in the image for being logged in equipment and calling image acquisition device acquisition paper of going over examination papers;The placement location of paper is obtained, and the placement location of paper is showed;Automatic identification is carried out to objective item, appraises and saves;When recognizing answer is subjective item, using answering as the first figure layer for subjective item and student;The second figure layer is generated in the first figure layer, and is goed over examination papers according to the generation of the second figure layer and corrected region;It receives in the handwriting trace for correcting region of going over examination papers, and handwriting trace correspondence is presented in the second figure layer, the second figure layer is synthetically generated the paper image corrected with the first figure layer and is saved;It will be shown on student's score reporting-form composing to the paper image corrected.The present invention greatly improves the efficiency goed over examination papers.
Description
Technical field
The present invention relates to the technical fields goed over examination papers, more particularly, to a kind of method goed over examination papers based on image recognition
And system.
Background technique
It is one of the groundwork of teacher that teacher, which go over examination papers to student examination test paper, in the present age of teaching information, always
Shi Yuejuan uses information-based means gradually also to promote the efficiency goed over examination papers.Marking system typically now is by the way of
It is:Teacher first corrects on the papery paper of student, after the completion of to be changed, reuse scanner scanning acquisition and corrects completion
Paper image afterwards;Alternatively, another way is:First using the paper image answered of scanner acquisition student, then by paper figure
Client as transferring to teacher, teacher save after line is corrected by client.
But above-mentioned working link is more complicated, has the following problems:(1) high speed A3 paper scanner is at high cost
It is high, it is difficult to which that batch configuration causes to need to be lined up use when concentrating examination, reduce working efficiency;(2) to the paper of collection
It needs repeatedly to be handled, increases the work load of teacher;(3) carry out batch scanning when, appearance abnormal conditions (including know
Not mistake, paper missing, scanner paper jam, batch upload clogging networks the problems such as) processing step it is cumbersome, and need it is higher
Academic program cost.
Therefore it provides a kind of scheme that quick, efficient informationization is goed over examination papers is this field technical problem urgently to be resolved.
Summary of the invention
In view of this, being solved existing the present invention provides a kind of method and system goed over examination papers based on image recognition
The technical issues of going over examination papers at high cost, cumbersome and low efficiency is scanned in technology.
In order to solve the above-mentioned technical problem, the present invention proposes a kind of method goed over examination papers based on image recognition, including:
It is going over examination papers in equipment, is receiving the request for logging in and going over examination papers, request of going over examination papers described in analysis obtains client-side information, will be described
The client-side information permission table of comparisons in client-side information and database compares to obtain the logon rights of the client;
When the client has logon rights, is logged in the equipment of going over examination papers and image acquisition device is called to adopt
Collect the image of paper;It identifies the identification information on the image of the paper, the examination of the paper is obtained from the identification information
Volume information obtains the placement position of the paper according to the corresponding relationship of the database pilot scale volume information and paper placement location
It sets, and the placement location of the paper is showed;
The model answer of the paper is transferred from database according to the paper information, and according to the model answer pair
Objective item carries out automatic identification, appraises and save;When recognizing answer is subjective item, with answering for the subjective item and student
As the first figure layer;The second figure layer is generated in first figure layer, and is goed over examination papers according to second figure layer generation and corrected region;
It receives and corrects the handwriting trace in region in described go over examination papers, and handwriting trace correspondence is presented in second figure
On layer, second figure layer is synthetically generated the paper image corrected with first figure layer and is saved;
The paper image corrected described in scanning obtains the score to the subjective item, the shape together with the score of the objective item
At student's score report, and will be shown on student's score reporting-form composing to the paper image corrected.
Optionally, wherein when recognizing answer is subjective item, using answering as the first figure for the subjective item and student
Layer, it is:
When recognizing answer is subjective item, using answering as the first figure layer for the subjective item and student;
The model answer mapping for transferring the subjective item from the database is shown in the white space of first figure layer.
Optionally, wherein this method further includes:
The content for identifying first figure layer, extracts answering for the student;
Answering for the student is compared with the model answer, and by comparing result together with the model answer
Mapping is shown in the white space of first figure layer.
Optionally, wherein this method further includes:
When the dimension scale of the paper, no corresponding examination is compared with the paper dimension scale stored in the database
Roll up type;And/or in the type of the paper when image of each paper module and the paper cannot exactly match, automatically
Generate paper damage or prompting and the displaying of placement location exception.
Optionally, wherein the client-side information permission table of comparisons is:Two dimensional code and the logon rights table of comparisons, face are known
Other pattern and the logon rights table of comparisons and/or user name password and the logon rights table of comparisons.
On the other hand, the present invention also provides a kind of systems goed over examination papers based on image recognition, including:Go over examination papers logger,
Paper information identifier gos over examination papers and corrects device, gos over examination papers and correct image synthesizer and result display device of going over examination papers, wherein
The logger of going over examination papers is connected with the paper information identifier, reads for receiving to log in equipment of going over examination papers
The request of volume, request of going over examination papers described in analysis obtain client-side information, the client in the client-side information and database are believed
The breath permission table of comparisons compares to obtain the logon rights of the client;
The paper information identifier logger and gos over examination papers with described go over examination papers and corrects device and be connected, in the client
When end has logon rights, the image of image acquisition device acquisition paper is logged in and called in the equipment of going over examination papers;Analysis
The image of the paper obtains the dimension scale of paper, compares to obtain with the paper dimension scale stored in the database described
The type of paper;Paper module each in the type of the paper is matched with the image of the paper respectively, passes through examination
Volume module match cognization obtains the paper information of the paper and saves;
Described go over examination papers corrects device, and the paper information identifier and gos over examination papers and corrects image synthesizer and be connected, and is used for root
The model answer of the paper is transferred from database according to the paper information, and objective item is carried out according to the model answer
Automatic identification is appraised and is saved;When recognizing answer is subjective item, using answering as the first figure for the subjective item and student
Layer;The second figure layer is generated in first figure layer, and is goed over examination papers according to second figure layer generation and corrected region;
Described go over examination papers corrects image synthesizer, device is corrected and result display device of going over examination papers is connected with described go over examination papers, for connecing
It is received in described go over examination papers and corrects the handwriting trace in region, and handwriting trace correspondence is presented in second figure layer, by institute
The second figure layer is stated to be synthetically generated the paper image corrected with first figure layer and save;
The result display device of going over examination papers corrects image synthesizer and is connected with described go over examination papers, for scanning described correct
Paper image obtains the score to the subjective item, is formed together student's score report with the score of the objective item, and by institute
It states and is shown on student's score reporting-form composing to the paper image corrected.
Optionally, wherein described go over examination papers corrects device, including:Objective item corrects unit, subjective item recognition unit and subjective item
Correct unit;Wherein,
The objective item corrects unit, is connected with the paper information identifier and subjective item recognition unit, is used for root
The model answer of the paper is transferred from database according to the paper information, and objective item is carried out according to the model answer
Automatic identification is appraised and is saved;
The subjective item recognition unit corrects unit with the objective item and subjective item corrects unit and is connected, for working as
When to recognize answer be subjective item, using answering as the first figure layer for the subjective item and student;
The subjective item corrects unit, and the subjective item recognition unit and gos over examination papers and corrects image synthesizer and be connected, and uses
In generating the second figure layer in first figure layer, and is goed over examination papers according to second figure layer generation and correct region;From the data
The model answer mapping that the subjective item is transferred in library is shown in the white space of first figure layer.
Optionally, wherein described go over examination papers corrects device, further includes:Answer comparison unit;
The answer comparison unit corrects unit with the subjective item recognition unit and subjective item and is connected, for identification
The content of first figure layer, extracts answering for the student;
Answering for the student is compared with the model answer, and by comparing result together with the model answer
Mapping is shown in the white space of first figure layer.
Optionally, wherein further include:Paper malposition reminiscences is connected with the paper information identifier, uses
In:
It identifies the identification information on the image of the paper, the paper letter of the paper is obtained from the identification information
Breath obtains the placement location of the paper according to the corresponding relationship of the database pilot scale volume information and paper placement location, and
The placement location of the paper is showed;
Optionally, wherein the client-side information permission table of comparisons is:Two dimensional code and the logon rights table of comparisons, face are known
Other pattern and the logon rights table of comparisons and/or user name password and the logon rights table of comparisons.
Compared with prior art, the method and system provided by the invention goed over examination papers based on image recognition, are at least realized
One of following beneficial effect:
(1) method and system of the present invention goed over examination papers based on image recognition, using inexpensive hardware plan, greatly
Width reduces the cost that teacher gos over examination papers.
(2) method and system of the present invention goed over examination papers based on image recognition, it is during teacher gos over examination papers, i.e., complete
At acquisition and work is saved, the efficiency goed over examination papers greatly improved;Objective item is judged automatically, the workload of teacher is reduced;It is main
Sight topic is compared with model answer automatically, is rapidly found out the key point that student answers, is improved the efficiency of subjective question marking.
(3) method and system of the present invention goed over examination papers based on image recognition, it is single using image recognition and synthesis
Paper transmission is opened, the requirement to network bandwidth is reduced;Result of going over examination papers can be stored in cloud, be convenient for big data analysis, research
User's usage behavior refines rule, preferably service user.
Detailed description of the invention
It is combined in the description and the attached drawing for constituting part of specification shows the embodiment of the present invention, and even
With its explanation together principle for explaining the present invention.By reading referring to made by the following drawings to non-limiting embodiment institute
The detailed description of work, other features, objects and advantages will become more apparent upon:
Fig. 1 is the flow diagram for the method goed over examination papers described in the embodiment of the present invention based on image recognition;
Fig. 2 is the process signal for the method that another kind described in the embodiment of the present invention is goed over examination papers based on image recognition
Figure;
Fig. 3 is the process signal of another method goed over examination papers based on image recognition described in the embodiment of the present invention
Figure;
Fig. 4 is the process signal of another method goed over examination papers based on image recognition described in the embodiment of the present invention
Figure;
Fig. 5 is the structural schematic diagram for the system goed over examination papers described in the embodiment of the present invention based on image recognition;
Fig. 6 is the structural representation for the system that another kind described in the embodiment of the present invention is goed over examination papers based on image recognition
Figure;
Fig. 7 is the structural representation of another system goed over examination papers based on image recognition described in the embodiment of the present invention
Figure;
Fig. 8 is the structural representation of another system goed over examination papers based on image recognition described in the embodiment of the present invention
Figure;
Fig. 9 is that the paper for the system goed over examination papers described in the embodiment of the present invention based on image recognition identifies the structure in face
Schematic diagram.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related application, rather than the restriction to this application.It also should be noted that in order to
Convenient for description, part relevant to the application is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
As shown in FIG. 1, FIG. 1 is the flow diagrams of the method goed over examination papers based on image recognition described in the present embodiment.
The technology for combining image recognition and image to synthesize in the present embodiment completes the Image Acquisition to correct an examination paper while teacher gos over examination papers
And preservation, the efficiency goed over examination papers is improved, and reduce cost of going over examination papers, this method includes the following steps, namely:
Step 101 is being goed over examination papers in equipment, and the request for logging in and going over examination papers is received, and is analyzed request of going over examination papers and is obtained client-side information, will
The client-side information permission table of comparisons in client-side information and database compares to obtain the logon rights of client.
Using preceding needs, in equipment of going over examination papers, (such as tablet computer can rely on the wired or wireless network of user to user first
Connection internet) interface on carry out register.Logging in includes three kinds of modes:Two-dimensional code scanning logs in, recognition of face logs in
With user name password login mode.And its two-dimensional code display can be set in equipment of going over examination papers in the standby state, user uses mobile phone
Register can be completed in end client scan two dimensional code, to facilitate user to be rapidly introduced into the interface goed over examination papers.It gos over examination papers and sets
It is standby to support recognition of face login mode, position is adjusted by user, will acquire and protect in advance in face and formulation region
After the facial image matching deposited, login can be completed.Traditional user name password login mode is also supported simultaneously, by by user
The user name and password of input compare to obtain logon rights with the user name and password pre-saved.
Optionally, the client-side information permission table of comparisons is:Two dimensional code and the logon rights table of comparisons, recognition of face pattern with
The logon rights table of comparisons and/or user name password and the logon rights table of comparisons.
Step 102, when client has logon rights, logged in equipment going over examination papers and image acquisition device called to adopt
Collect the image of paper;It identifies the identification information on the image of the paper, the examination of the paper is obtained from the identification information
Volume information obtains the placement position of the paper according to the corresponding relationship of the database pilot scale volume information and paper placement location
It sets, and the placement location of the paper is showed.
Optionally, the identification information on the image of paper can be two dimensional code mark, and being also possible to others can carry
The mark of identification information.Equipment of going over examination papers can support volume face no more than all size papers, in advance in the database of equipment of going over examination papers
In preserve dimension information, paper module information and paper content information of various papers etc..User will meet call format
Paper selects the position of suitable paper size that paper is placed on specified region (as schemed according to the paper placement location showed
Shown in 9, the structural schematic diagram in face is identified for the paper for the system goed over examination papers in the present embodiment based on image recognition, is convenient for
Image recognition obtains paper image), equipment of going over examination papers control image capture device acquire paper picture, and to collected picture into
Row intelligent recognition, including:The corresponding examination title of paper, test paper classifying, the paper page number, the student that answers etc..According to what is recognized
Paper information transfers the paper answer for being stored in database (database can be cloud database), accordingly in this page
Objective item carries out automatic identification, appraises.
Step 103, the model answer for transferring paper from database according to paper information, and according to model answer to objective
Topic carries out automatic identification, appraises and save;When recognizing answer is subjective item, using answering as first for subjective item and student
Figure layer;The second figure layer is generated in the first figure layer, and is goed over examination papers according to the generation of the second figure layer and corrected region.
Subjective item needs teacher to sentence volume manually, by the cooperation of handwriting pad and smart pen, when teacher holds smart pen, in paper
Specified region is normally write, and plate is by the action recognition of smart pen, and subregion shows that student answers result in screen automatically
With the topic model answer, reference is used as when sentencing volume for teacher.
Step 104 is received in the handwriting trace for correcting region of going over examination papers, and handwriting trace correspondence is presented in the second figure layer
On, the second figure layer is synthetically generated the paper image corrected with the first figure layer and is saved.
Handwriting trace of the teacher on paper, after handwriting pad and smart pen acquisition, in the form of trajectory coordinates, automatically
It is transferred in equipment of going over examination papers.Teacher is taken down notes into report there are paper designated position according to Grid Track information, is synthesized with original image,
100% saves teacher's person's handwriting, forms the picture after sentencing volume.Meanwhile by identification technology, automatic identification teacher sentences the topic
Point, summarize with the objective item score judged automatically, forms the report of student's score.
The paper image that step 105, scanning are corrected obtains the score to subjective item, is formed together with the score of objective item
Raw score report, and will be shown on student's score reporting-form composing to the paper image corrected.
After teacher completes a paper, the paper information is shown automatically, including:Corresponding exam information, examinee information, at
Achievement information.Teacher can select a key to upload in equipment of going over examination papers, and above- mentioned information are saved by network transmission to cloud, and carries out
Big data analysis.
In some alternative embodiments, as shown in Fig. 2, being goed over examination papers to be another in the present embodiment based on image recognition
Method flow diagram, unlike method in Fig. 1, when recognize answer be subjective item when, with subjective item and student
Answer as the first figure layer, be:
Step 201, when recognizing answer is subjective item, using answering as the first figure layer for subjective item and student.
Step 202, the model answer mapping that the subjective item is transferred from database are shown in the white space of the first figure layer.
In some alternative embodiments, it gos over examination papers as shown in figure 3, being based on image recognition for another in the present embodiment
The flow diagram of method further include unlike method in Fig. 1:
Step 301, the content for identifying the first figure layer, extract answering for student.
Answering for student is compared with model answer, and comparing result is mapped together with model answer by step 302
It is shown in the white space of the first figure layer.
In some alternative embodiments, it gos over examination papers as shown in figure 4, being based on image recognition for another in the present embodiment
The flow diagram of method further include unlike method in Fig. 1:
Step 401, the dimension scale and paper module for detecting paper.
Step 402, the dimension scale when paper compare no corresponding examination with the paper dimension scale stored in database
Roll up type;And/or paper is automatically generated when the image of each paper module and paper cannot exactly match in the type of paper
Damage or prompting and the displaying of placement location exception.
As shown in figure 5, for a kind of structural schematic diagram for the system 500 goed over examination papers based on image recognition in the present embodiment,
The system is used to implement the method goed over examination papers based on image recognition in above-described embodiment, which includes:It gos over examination papers logger
501, paper information identifier 502, go over examination papers and correct device 503, go over examination papers and correct image synthesizer 504 and result display device 505 of going over examination papers.
Wherein, it gos over examination papers logger 501, is connected with paper information identifier 502, in equipment of going over examination papers, reception to be stepped on
The request goed over examination papers is recorded, request of going over examination papers is analyzed and obtains client-side information, the client-side information in client-side information and database is weighed
The limit table of comparisons compares to obtain the logon rights of client.
Paper information identifier 502 logger 501 and gos over examination papers with going over examination papers and corrects device 503 and be connected, for having in client
When having logon rights, in the image for being logged in equipment and calling image acquisition device acquisition paper of going over examination papers;Identify the paper
Image on identification information, the paper information of the paper is obtained from the identification information, according to the database pilot scale
The corresponding relationship of volume information and paper placement location obtains the placement location of the paper, and by the placement location of the paper into
Row shows.
It gos over examination papers and corrects device 503, and paper information identifier 502 and go over examination papers and correct image synthesizer 504 and be connected, be used for root
The model answer of paper is transferred from database according to paper information, and automatic identification is carried out to objective item according to model answer, is sentenced
Divide and saves;When recognizing answer is subjective item, using answering as the first figure layer for subjective item and student;In the first figure layer
The second figure layer is generated, and is goed over examination papers according to the generation of the second figure layer and corrects region.
It gos over examination papers and corrects image synthesizer 504, device 503 is corrected and result display device 505 of going over examination papers is connected with going over examination papers, for connecing
It is received in go over examination papers and corrects the handwriting trace in region, and handwriting trace correspondence is presented in the second figure layer, by the second figure layer and first
Figure layer is synthetically generated the paper image corrected and saves.
Result of going over examination papers display device 505 corrects image synthesizer 504 and is connected, for scanning the paper figure corrected with going over examination papers
As obtaining the score to subjective item, student's score report is formed together with the score of objective item, and by student's score reporting-form composing
It is shown on to the paper image corrected.
In some alternative embodiments, it gos over examination papers as shown in fig. 6, being based on image recognition for another in the present embodiment
The structural schematic diagram of system 600 go over examination papers unlike system in Fig. 5 and correct device 503, including:Objective item corrects unit
531, subjective item recognition unit 532 and subjective item correct unit 533.
Wherein, objective item corrects unit 531, is connected with paper information identifier 502 and subjective item recognition unit 532,
Objective item is known automatically for transferring the model answer of paper from database according to paper information, and according to model answer
Not, it appraises and saves.
Subjective item recognition unit 532 corrects unit 531 with objective item and subjective item corrects unit 533 and is connected, for working as
When to recognize answer be subjective item, using answering as the first figure layer for subjective item and student.
Subjective item corrects unit 533, and subjective item recognition unit 532 and gos over examination papers and corrects image synthesizer 504 and be connected, and uses
In generating the second figure layer in the first figure layer, and is goed over examination papers according to the generation of the second figure layer and correct region;The master is transferred from database
The model answer mapping of sight topic is shown in the white space of the first figure layer.
In some alternative embodiments, it gos over examination papers as shown in fig. 7, being based on image recognition for another in the present embodiment
The structural schematic diagram of system 700 go over examination papers unlike system in Fig. 6 and correct device 503, further include:Answer comparison unit
534.Answer comparison unit 534 corrects unit 533 with subjective item recognition unit 532 and subjective item and is connected, and for identification first
The content of figure layer extracts answering for student;Answering for student is compared with model answer, and comparing result and standard are answered
Case maps the white space for being shown in the first figure layer together.
In some alternative embodiments, it gos over examination papers as shown in figure 8, being based on image recognition for another in the present embodiment
The structural schematic diagram of system 800 further include unlike system in Fig. 5:Paper malposition reminiscences 801, with paper
Information identifier 502 is connected, and is used for:When the dimension scale of paper, do not have with the paper dimension scale comparison stored in database
There is corresponding paper type;And/or in the type of paper when the image of each paper module and paper cannot exactly match, from
It is dynamic to generate paper damage or prompting and the displaying of placement location exception.
Optionally, in the above-described embodiments, the client-side information permission table of comparisons is:Two dimensional code and the logon rights table of comparisons,
Recognition of face pattern and the logon rights table of comparisons and/or user name password and the logon rights table of comparisons.
Through the foregoing embodiment it is found that the method and system of the invention goed over examination papers based on image recognition, reached as
Under beneficial effect:
(1) method and system of the present invention goed over examination papers based on image recognition, using inexpensive hardware plan, greatly
Width reduces the cost that teacher gos over examination papers.
(2) method and system of the present invention goed over examination papers based on image recognition, it is during teacher gos over examination papers, i.e., complete
At acquisition and work is saved, the efficiency goed over examination papers greatly improved;Objective item is judged automatically, the workload of teacher is reduced;It is main
Sight topic is compared with model answer automatically, is rapidly found out the key point that student answers, is improved the efficiency of subjective question marking.
(3) method and system of the present invention goed over examination papers based on image recognition, it is single using image recognition and synthesis
Paper transmission is opened, the requirement to network bandwidth is reduced;Result of going over examination papers can be stored in cloud, be convenient for big data analysis, research
User's usage behavior refines rule, preferably service user.
Although some specific embodiments of the invention are described in detail by example, the skill of this field
Art personnel it should be understood that example above merely to being illustrated, the range being not intended to be limiting of the invention.The skill of this field
Art personnel are it should be understood that can without departing from the scope and spirit of the present invention modify to above embodiments.This hair
Bright range is defined by the following claims.
Claims (10)
1. a kind of method goed over examination papers based on image recognition, which is characterized in that including:
It is going over examination papers in equipment, is receiving the request for logging in and going over examination papers, request of going over examination papers described in analysis obtains client-side information, by the client
The client-side information permission table of comparisons in client information and database compares to obtain the logon rights of the client;
When the client has logon rights, is logged in the equipment of going over examination papers and call image acquisition device acquisition examination
The image of volume;It identifies the identification information on the image of the paper, the paper letter of the paper is obtained from the identification information
Breath obtains the placement location of the paper according to the corresponding relationship of the database pilot scale volume information and paper placement location, and
The placement location of the paper is showed;
The model answer of the paper is transferred from database according to the paper information, and according to the model answer to objective
Topic carries out automatic identification, appraises and save;When recognizing answer is subjective item, using the subjective item and student answer as
First figure layer;The second figure layer is generated in first figure layer, and is goed over examination papers according to second figure layer generation and corrected region;
It receives and corrects the handwriting trace in region in described go over examination papers, and handwriting trace correspondence is presented in second figure layer
On, second figure layer is synthetically generated the paper image corrected with first figure layer and is saved;
The paper image corrected described in scanning obtains the score to the subjective item, is formed together with the score of the objective item
Raw score report, and will be shown on student's score reporting-form composing to the paper image corrected.
2. the method according to claim 1 goed over examination papers based on image recognition, which is characterized in that be when recognizing answer
When subjective item, using answering as the first figure layer for the subjective item and student, it is:
When recognizing answer is subjective item, using answering as the first figure layer for the subjective item and student;
The model answer mapping for transferring the subjective item from the database is shown in the white space of first figure layer.
3. the method according to claim 2 goed over examination papers based on image recognition, which is characterized in that further include:
The content for identifying first figure layer, extracts answering for the student;
Answering for the student is compared with the model answer, and comparing result is mapped together with the model answer
It is shown in the white space of first figure layer.
4. the method according to claim 1 goed over examination papers based on image recognition, which is characterized in that further include:
When the dimension scale of the paper, no corresponding paper class is compared with the paper dimension scale stored in the database
Type;And/or it is automatically generated when the image of each paper module and the paper cannot exactly match in the type of the paper
Paper damage or prompting and the displaying of placement location exception.
5. the method as claimed in any of claims 1 to 4 goed over examination papers based on image recognition, which is characterized in that
The client-side information permission table of comparisons is:Two dimensional code is compareed with the logon rights table of comparisons, recognition of face pattern with logon rights
Table and/or user name password and the logon rights table of comparisons.
6. a kind of system goed over examination papers based on image recognition, which is characterized in that including:Logger, the paper information of going over examination papers identify
Device gos over examination papers and corrects device, gos over examination papers and correct image synthesizer and result display device of going over examination papers, wherein
The logger of going over examination papers is connected with the paper information identifier, for receiving what login was goed over examination papers in equipment of going over examination papers
It requests, request of going over examination papers described in analysis obtains client-side information, and the client-side information in the client-side information and database is weighed
The limit table of comparisons compares to obtain the logon rights of the client;
The paper information identifier logger and gos over examination papers with described go over examination papers and corrects device and be connected, for having in the client
When there are logon rights, the image of image acquisition device acquisition paper is logged in and called in the equipment of going over examination papers;Described in identification
Identification information on the image of paper obtains the paper information of the paper, according to the database from the identification information
The corresponding relationship of pilot scale volume information and paper placement location obtains the placement location of the paper, and by the placement position of the paper
It sets and is showed;
Described go over examination papers corrects device, and the paper information identifier and gos over examination papers and corrects image synthesizer and be connected, for according to institute
The model answer that paper information transfers the paper from database is stated, and objective item is carried out automatically according to the model answer
It identifies, appraise and save;When recognizing answer is subjective item, using answering as the first figure layer for the subjective item and student;
The second figure layer is generated in first figure layer, and is goed over examination papers according to second figure layer generation and corrected region;
Described go over examination papers corrects image synthesizer, corrects device and result display device of going over examination papers is connected with described go over examination papers, exists for receiving
Described go over examination papers corrects the handwriting trace in region, and handwriting trace correspondence is presented in second figure layer, by described the
Two figure layers are synthetically generated the paper image corrected with first figure layer and save;
The result display device of going over examination papers corrects image synthesizer and is connected with described go over examination papers, for scanning the paper corrected
Image obtains the score to the subjective item, is formed together student's score report with the score of the objective item, and by
It is shown on raw score reporting-form composing to the paper image corrected.
7. the system according to claim 6 goed over examination papers based on image recognition, which is characterized in that described go over examination papers is corrected
Device, including:Objective item corrects unit, subjective item recognition unit and subjective item and corrects unit;Wherein,
The objective item corrects unit, is connected with the paper information identifier and subjective item recognition unit, for according to institute
The model answer that paper information transfers the paper from database is stated, and objective item is carried out automatically according to the model answer
It identifies, appraise and save;
The subjective item recognition unit corrects unit with the objective item and subjective item corrects unit and is connected, for when identification
When to answer being subjective item, using answering as the first figure layer for the subjective item and student;
The subjective item corrects unit, and the subjective item recognition unit and gos over examination papers and corrects image synthesizer and be connected, for
The second figure layer is generated in first figure layer, and is goed over examination papers according to second figure layer generation and corrected region;From the database
The model answer mapping for transferring the subjective item is shown in the white space of first figure layer.
8. the system according to claim 7 goed over examination papers based on image recognition, which is characterized in that described go over examination papers is corrected
Device further includes:Answer comparison unit;
The answer comparison unit corrects unit with the subjective item recognition unit and subjective item and is connected, described for identification
The content of first figure layer extracts answering for the student;
Answering for the student is compared with the model answer, and comparing result is mapped together with the model answer
It is shown in the white space of first figure layer.
9. the system according to claim 6 goed over examination papers based on image recognition, which is characterized in that further include:Paper position
Abnormity prompt device is set, is connected with the paper information identifier, is used for:
When the dimension scale of the paper, no corresponding paper class is compared with the paper dimension scale stored in the database
Type;And/or it is automatically generated when the image of each paper module and the paper cannot exactly match in the type of the paper
Paper damage or prompting and the displaying of placement location exception.
10. the system according to any one of claims 6 to 9 goed over examination papers based on image recognition, which is characterized in that
The client-side information permission table of comparisons is:Two dimensional code is compareed with the logon rights table of comparisons, recognition of face pattern with logon rights
Table and/or user name password and the logon rights table of comparisons.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810431331.9A CN108830267A (en) | 2018-05-08 | 2018-05-08 | A kind of method and system goed over examination papers based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810431331.9A CN108830267A (en) | 2018-05-08 | 2018-05-08 | A kind of method and system goed over examination papers based on image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108830267A true CN108830267A (en) | 2018-11-16 |
Family
ID=64147707
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810431331.9A Pending CN108830267A (en) | 2018-05-08 | 2018-05-08 | A kind of method and system goed over examination papers based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108830267A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008780A (en) * | 2019-04-03 | 2019-07-12 | 李佳旺 | A method of the intelligent operation realized based on two dimensional code |
CN110175612A (en) * | 2019-05-30 | 2019-08-27 | 北京爱尖子教育科技有限责任公司 | Online testing method and system based on OCR technique |
CN110245640A (en) * | 2019-06-21 | 2019-09-17 | 深圳市采集科技有限公司 | For being automatically positioned the method and work correction method, system and storage medium of topic in work correction |
CN110443772A (en) * | 2019-08-20 | 2019-11-12 | 百度在线网络技术(北京)有限公司 | Image processing method, device, computer equipment and storage medium |
CN110490074A (en) * | 2019-07-17 | 2019-11-22 | 广州学邦信息技术有限公司 | Method, system and device are corrected in a kind of classroom based on image recognition in real time |
CN112287925A (en) * | 2020-10-19 | 2021-01-29 | 南京数件技术研究院有限公司 | Mathematics system of judging questions based on real-time orbit is gathered |
CN112733674A (en) * | 2020-12-31 | 2021-04-30 | 北京华图宏阳网络科技有限公司 | Intelligent correction method and system for official application examination application documents |
CN113095187A (en) * | 2021-04-01 | 2021-07-09 | 杭州云梯科技有限公司 | Examination paper correction method based on image feature matching alignment |
CN114663895A (en) * | 2022-04-01 | 2022-06-24 | 读书郎教育科技有限公司 | Multi-document operation detection method, storage medium and device |
CN114972724A (en) * | 2022-06-15 | 2022-08-30 | 读书郎教育科技有限公司 | Scanner-based abnormal operation picture removing method, storage medium and equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007041177A (en) * | 2005-08-02 | 2007-02-15 | Fuji Xerox Co Ltd | Device, method, program for processing educational material, and recording medium |
CN106781784A (en) * | 2017-01-04 | 2017-05-31 | 王骁乾 | A kind of intelligence correction system |
-
2018
- 2018-05-08 CN CN201810431331.9A patent/CN108830267A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007041177A (en) * | 2005-08-02 | 2007-02-15 | Fuji Xerox Co Ltd | Device, method, program for processing educational material, and recording medium |
CN106781784A (en) * | 2017-01-04 | 2017-05-31 | 王骁乾 | A kind of intelligence correction system |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008780A (en) * | 2019-04-03 | 2019-07-12 | 李佳旺 | A method of the intelligent operation realized based on two dimensional code |
CN110175612A (en) * | 2019-05-30 | 2019-08-27 | 北京爱尖子教育科技有限责任公司 | Online testing method and system based on OCR technique |
CN110245640A (en) * | 2019-06-21 | 2019-09-17 | 深圳市采集科技有限公司 | For being automatically positioned the method and work correction method, system and storage medium of topic in work correction |
CN110490074A (en) * | 2019-07-17 | 2019-11-22 | 广州学邦信息技术有限公司 | Method, system and device are corrected in a kind of classroom based on image recognition in real time |
CN110443772A (en) * | 2019-08-20 | 2019-11-12 | 百度在线网络技术(北京)有限公司 | Image processing method, device, computer equipment and storage medium |
CN112287925A (en) * | 2020-10-19 | 2021-01-29 | 南京数件技术研究院有限公司 | Mathematics system of judging questions based on real-time orbit is gathered |
CN112733674A (en) * | 2020-12-31 | 2021-04-30 | 北京华图宏阳网络科技有限公司 | Intelligent correction method and system for official application examination application documents |
CN113095187A (en) * | 2021-04-01 | 2021-07-09 | 杭州云梯科技有限公司 | Examination paper correction method based on image feature matching alignment |
CN114663895A (en) * | 2022-04-01 | 2022-06-24 | 读书郎教育科技有限公司 | Multi-document operation detection method, storage medium and device |
CN114972724A (en) * | 2022-06-15 | 2022-08-30 | 读书郎教育科技有限公司 | Scanner-based abnormal operation picture removing method, storage medium and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108830267A (en) | A kind of method and system goed over examination papers based on image recognition | |
CN104239866B (en) | Answering card information collecting method and equipment | |
CN104143094A (en) | Test paper automatic test paper marking processing method and system without answer sheet | |
CN110597806A (en) | Wrong question set generation and answer statistics system and method based on reading and amending identification | |
CN105590101A (en) | Hand-written answer sheet automatic processing and marking method and system based on mobile phone photographing | |
CN106033544B (en) | Template matching-based test paper content area extraction method | |
GB2331613A (en) | Apparatus for capturing a fingerprint | |
CN101901338A (en) | Method and system for calculating scores of test paper | |
CN110659612B (en) | Digital paper marking method and system based on paper pen improvement | |
CN106778703A (en) | The method and apparatus of electric marking | |
CN109509378B (en) | A kind of online testing method for supporting handwriting input | |
US7764923B2 (en) | Material processing apparatus and method for grading material | |
CN106033535A (en) | Electronic paper marking method | |
CN110659584A (en) | Intelligent trace marking system based on image recognition | |
CN106296513A (en) | System is read and appraised in a kind of online scanning | |
CN106373447A (en) | Intelligent paper marking system and method | |
CN105243383A (en) | Answer sheet processing method and system | |
CN109035101A (en) | One kind infecting experimental implementation examination assessment method and system | |
CN106056028A (en) | Rapid scanning and waybill recording method and device thereof | |
CN115205883A (en) | Data auditing method, device, equipment and storage medium based on OCR (optical character recognition) and NLP (non-line language) | |
CN107633201A (en) | A kind of answering card intelligent identification Method and system | |
CN108052955A (en) | A kind of high-precision braille recognition methods and system | |
US20060290999A1 (en) | Image processing apparatus and network system | |
US20060194187A1 (en) | Material processing apparatus, material processing method, and program product | |
CN109388935A (en) | Document verification method and device, electronic equipment and readable storage medium storing program for executing |
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: 20181116 |
|
RJ01 | Rejection of invention patent application after publication |