CN107480667A - The method and its system of intelligent topic image acquisition and processing based on template - Google Patents
The method and its system of intelligent topic image acquisition and processing based on template Download PDFInfo
- Publication number
- CN107480667A CN107480667A CN201710695038.9A CN201710695038A CN107480667A CN 107480667 A CN107480667 A CN 107480667A CN 201710695038 A CN201710695038 A CN 201710695038A CN 107480667 A CN107480667 A CN 107480667A
- Authority
- CN
- China
- Prior art keywords
- information
- answer
- topic
- student
- single mode
- 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
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
- G06V10/225—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 based on a marking or identifier characterising the area
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
Abstract
The invention discloses a kind of method of the intelligent topic image acquisition and processing based on template, generation topic single mode plate；The topic single mode plate is scanned or taken pictures, obtains answer scanned copy or answer photo；Carry out graphics process；If identifying image content completely, it is student information or answering information to judge image content, otherwise carries out human assistance processing；For student information, then corresponding student is inquired, records the student information；For answering information, then carry out sentencing volume, and record and sentence clove hitch fruit.The invention also discloses a kind of system of the intelligent topic image acquisition and processing based on template, including template generation module, topic single sweep module, pattern process module, picture recognition judge module, image content judge module, student information logging modle, sentence clove hitch fruit logging modle and prosthetic processing module.The present invention can effectively automatically obtain text filed in image, obtained by interactive mode required text filed, reduce the calculating time of system, improve the accuracy rate of positioning.
Description
Technical field
The present invention relates to image procossing and area of pattern recognition, and in particular to a kind of intelligent topic image based on template is adopted
Collect the method and its system of processing.
Background technology
Present OCR technique be applied to more and more mobile intelligent terminal with image scanning (or shooting) function and
In the equipment such as PDA, but because often background is complex, during such as video image, in the String localization problem before OCR also
There is certain technological difficulties, cause the result of String localization deviation occur, it is impossible to easily and accurately detect required knowledge
Other character, or a text filed company for being mistakenly divided into multiple related text subregions, influenceing OCR recognition results
Continuous property and computing cost, along with Text region rate is relatively low, cause final result not highly desirable, thus at this time with regard to need into
The mode of some auxiliary positionings of row improves text location accuracy rate and recognition accuracy.
At present, the basic process of existing image (or video) text identification, passes through the text diagram to being collected first
As (or certain two field picture in video), the pretreatment (enhancing filtering etc.) of image, and the analysis and understanding of the space of a whole page are carried out, with this
Detect and orient text filed, then to each text filed carry out character recognition, recognition result can further be post-processed
The operation such as correction, " text filed positioning " therein directly affects final recognition result, and the computational efficiency of whole system.
The content of the invention
Based on this, in view of the above-mentioned problems, being necessary to propose a kind of side of the intelligent topic image acquisition and processing based on template
Method and its system, it is text filed in image that the present invention can effectively be such that user automatically obtains, and is obtained by interactive mode
To interested text filed of user, the calculating run time of system is reduced, improves the accuracy rate of positioning.
The present invention provides a kind of method of the intelligent topic image acquisition and processing based on template, and its technical scheme is as follows：
A kind of method of the intelligent topic image acquisition and processing based on template, comprises the following steps：
A, generate and print including the page number, student information, answering information, identifier, area type and area coordinate
Topic single mode plate, wherein, identifier positioned at topic single mode plate upper left side, lower right and lower left opening position；
B, complete to inscribe single mode plate answer after, the topic single mode plate is scanned or taken pictures, obtain answer scanned copy or
Answer photo；
C, graphics process is carried out to answer scanned copy or answer photo, obtains picture content information；
D, the image content after graphics process is identified, judges whether to identify image content completely, if it is, into step
e；If it is not, then into step h；
If image content e, identified is student information, into step f；If the image content identified is to answer
Information is inscribed, then into step g；
F, pass through the number of examining or name or class's information of identified student, inquire corresponding student, and record should automatically
The information of student；
G, answering information is carried out sentencing volume, and record sentences the result of volume automatically；
H, human assistance processing is carried out, student information is recorded according to image content or sentences clove hitch fruit.
During image acquisition and processing, first start image pickup mode, 3 identifiers inscribed on single mode plate are put into shooting frame
Interior, auto-focusing shoots and captures the topic single image comprising topic, answer and student information after system identification；To image district
Domain scans for, and carries out text filed detection and positioning, automatically tips out the text filed of obtained candidate；Then
It is text filed for the candidate that provides, user click on or moving focal point by way of it is required text filed to select；To quilt
Word during the candidate of selection is text filed carries out OCR identifications；And student information is carried out according to the result of identification and sentences clove hitch fruit
Record, and the present invention has alternative scheme, can carry out human assistance operation for the region of None- identified, effectively prevent and sentence volume
Mistake or situation about failing to judge.
It is text filed in image that the present invention can effectively be such that user automatically obtains, and is used by interactive mode
Interested text filed in family, topic single mode plate can be based on and fast and accurately be carried out IMAQ, and to answering information
Judged and student information is acquired, reduce the calculating run time of system, improve the accuracy rate of positioning.
As the further optimization of such scheme, the step b comprises the following steps：
B1, unlatching are taken pictures or scanned, and form 3 cog regions for corresponding respectively to inscribe 3 identifiers on single mode plate；
B2, judge whether to recognize three identifiers, if it is, determining that the central point of three identifiers corresponds to topic list
The position of template, and enter step b3；If it is not, then reenter step b1；
B3, completion are taken pictures or scanned, and obtain with student information, inscribe the answer scanned copy of single information and answer information or answer
Inscribe photo.
After unlatching is taken pictures or scanned, 3 identifiers inscribed on single mode plate are put into corresponding cog region inframe, system identification
Auto-focusing shoots and captures the image comprising word afterwards, confirms that image corresponds to the central point of three identifiers, that is, completes
Take pictures or scan, obtain the image with student information, the single information of topic and answer information；It is quick, accurate that it gathers the process of image
Really, all information in topic single mode plate can be got, for follow-up image recognition and volume is sentenced to provide template basic, ensure that figure
The definition and integrality of picture, it is convenient to carry out automatic message recording.
As the further optimization of such scheme, the step c comprises the following steps：
C1, after getting answer scanned copy or answer photo, according to the original aspect ratio of topic single mode plate, answer is scanned
Part or answer photo carry out affine transformation；
C2, area type and area coordinate according to recorded answering pattern plate, by coordinate pair answer scanned copy or answer
Each region of photo carries out automatic segmentation, obtains each region picture after cutting；
C3, Slant Rectify and image enhaucament are carried out to each region picture after cutting, the image content letter after being handled
Breath.
Graphics process is carried out to the image collected after taking pictures or scanning, image-region scanned for first, according to topic
The original aspect ratio of single mode plate, affine transformation is carried out to the image collected, then carries out text filed detection and positioning,
Automatically the text filed of obtained candidate is tipped out, it is text filed for the candidate that provides, user can by clicking on or
The mode of moving focal point selects cutting text filed, and carries out Slant Rectify and image enhaucament to each region picture after cutting；
During the graphics process, the candidate being had detected that to user's prompting is text filed, and user is by clicking on or moving
The mode of focus, it is text filed to select, and support to select multiple text filed, further increase the accurate of figure
Degree and easy recognition, it is convenient to carry out image recognition and judgement.
As the further optimization of such scheme, the step f specifically includes following steps：
Judge whether identified student information is correct, if it is, recording the information of the student automatically；If it is not, then
Into step h.The student information identified is judged, makes to form one-to-one relationship between topic single mode plate and student, keeps away
Exempt from mistake occur in answer review process, ensure that the accuracy rate that system is singly corrected to topic automatically.
As the further optimization of such scheme, the step g specifically includes following steps：
Sentence whether clove hitch fruit is credible, if it is, recording the result for sentencing volume automatically；If it is not, then into step
h.According to the result for sentencing volume, sentence the record of clove hitch fruit, and can carry out confidence level discrimination, inspection to sentencing clove hitch fruit before recording
Look into the result for sentencing volume, it is ensured that sentence the authenticity and reliability of clove hitch fruit, once occurring sentencing clove hitch fruit mistake, then carry out human assistance
Clove hitch fruit is sentenced in operation corrigendum, makes final result 100% accurate.
The present invention also provides a kind of system of the intelligent topic image acquisition and processing based on template, and its technical scheme is as follows：
A kind of system of the intelligent topic image acquisition and processing based on template, including template generation module, topic single sweep mould
Block, pattern process module, picture recognition judge module, image content judge module, student information logging modle, sentence clove hitch fruit note
Module and prosthetic processing module are recorded, wherein：
Template generation module, for generating and printing including the page number, student information, answering information, identifier, region class
The topic single mode plate of type and area coordinate, wherein, identifier is positioned at upper left side, lower right and the lower left position of topic single mode plate
Place；
Single sweep module is inscribed, after completing the answer to inscribing single mode plate, the topic single mode plate is scanned or taken pictures, is obtained
Obtain answer scanned copy or answer photo；
Pattern process module, for carrying out graphics process to answer scanned copy or answer photo, obtain picture content information；
Picture recognition judge module, for identifying the image content after graphics process, judge whether to identify in picture completely
Hold, if it is, carrying out image content judgement；If it is not, then carry out human assistance processing；
Image content identification module, if the image content for being identified is student information, carries out student information and look into
Ask；If the image content identified is answering information, carry out sentencing volume operation；
Student information logging modle, for passing through the number of examining or name or class's information of identified student, inquire correspondingly
Student, and record the information of the student automatically；
Sentence clove hitch fruit logging modle, for carrying out sentencing volume to answering information, and record sentences the result of volume automatically；
Prosthetic processing module, for carrying out human assistance processing, student information is recorded according to image content or sentences clove hitch fruit.
As the further optimization of such scheme, the topic single sweep module includes sweep start submodule, identifier is known
Other judging submodule and answering information acquisition submodule, wherein：
Sweep start submodule, take pictures or scan for opening, formed and correspond respectively to inscribe 3 identifiers on single mode plate
3 cog regions；
Identifier identifies judging submodule, for judging whether to recognize three identifiers, if it is, determining three marks
The central point for knowing symbol corresponds to the position of topic single mode plate；Take pictures or scan if it is not, then reopening；
Answering information acquisition submodule, for completing to take pictures or scan, obtain with student information, the single information of topic and answer
The answer scanned copy or answer photo of information.
As the further optimization of such scheme, the pattern process module includes figure affine transformation submodule, figure
Region cutting submodule and figure correction enhancing submodule, wherein：
Figure affine transformation submodule, after getting answer scanned copy or answer photo, according to the original of topic single mode plate
Beginning Aspect Ratio, affine transformation is carried out to answer scanned copy or answer photo；
Graphics field cutting submodule, for the area type and area coordinate according to recorded answering pattern plate, by seat
Mark carries out automatic segmentation to each region of answer scanned copy or answer photo, obtains each region picture after cutting；
Figure correction enhancing submodule, for carrying out Slant Rectify and image enhaucament to each region picture after cutting, is obtained
Picture content information after to processing.
As the further optimization of such scheme, the student information logging modle judges submodule including student information
Block, whether the student information for judging identified is correct, if it is, recording the information of the student automatically；If it is not, then enter
Pedestrian's work aid in treatment.
It is described to sentence clove hitch fruit logging modle and include sentencing clove hitch fruit and judging submodule as the further optimization of such scheme
Block, for sentencing whether clove hitch fruit is credible, if it is, recording the result for sentencing volume automatically；If it is not, then carry out artificial auxiliary
Help processing.
The beneficial effects of the invention are as follows：
1st, the present invention can effectively be such that user automatically obtains text filed in image, be obtained by interactive mode
Interested text filed of user, topic single mode plate can be based on and fast and accurately be carried out IMAQ, reduce system
Run time is calculated, improves the accuracy rate of positioning.
2nd, 3 identifiers inscribed on single mode plate are put into corresponding cog region inframe in the present invention, confirm that image corresponds to
The central point of three identifiers, that is, complete to take pictures or scan, obtain the figure with student information, the single information of topic and answer information
Picture；It gathers that the process of image is quick, accurate, can get all information in topic single mode plate, be follow-up image recognition and
Sentence volume and provide template basis, ensure that the definition and integrality of image, it is convenient to carry out automatic message recording.
3rd, the image collected is handled, the candidate being had detected that to user's prompting is text filed, and user is led to
The mode of click or moving focal point is crossed, it is text filed to select, and support that multiple text filed, further raising can be selected
The accuracy and easy recognition of figure, it is convenient to carry out image recognition and judgement.
4th, recorded to sentencing the result of volume and the information of student, and to student information and clove hitch can be sentenced before recording
Fruit carries out confidence level discrimination, makes to sentence between clove hitch fruit and student and forms one-to-one relationship, it is ensured that sentence clove hitch fruit authenticity and
Reliability, once occurring sentencing clove hitch fruit or student information mistake, then human assistance operation corrigendum is carried out, avoids checking in answer
Occur mistake in journey, the degree of accuracy of final result is reached 100%.
Brief description of the drawings
Fig. 1 is the flow chart of the method for the intelligent topic image acquisition and processing based on template described in the embodiment of the present invention；
Fig. 2 is the theory diagram of the system of the intelligent topic image acquisition and processing based on template described in the embodiment of the present invention.
Description of reference numerals：
10- template generation modules；20- inscribes single sweep module；201- sweep start submodules；The identification of 202- identifiers judges
Submodule；203- answering information acquisition submodules；30- pattern process modules；301- figure affine transformation submodules；302- figures
Region cutting submodule；303- figures correction enhancing submodule；40- picture recognition judge modules；50- image contents judge mould
Block；60- student information logging modles；601- student information judging submodules；70- sentences clove hitch fruit logging modle；701- sentences clove hitch
Fruit judging submodule；80- prosthetic processing modules.
Embodiment
Embodiments of the invention are described in detail below in conjunction with the accompanying drawings.
Embodiment 1
As shown in figure 1, a kind of method of the intelligent topic image acquisition and processing based on template, comprises the following steps：
A, generate and print including the page number, student information, answering information, identifier, area type and area coordinate
Topic single mode plate, wherein, identifier positioned at topic single mode plate upper left side, lower right and lower left opening position；
B, complete to inscribe single mode plate answer after, the topic single mode plate is scanned or taken pictures, obtain answer scanned copy or
Answer photo；
C, graphics process is carried out to answer scanned copy or answer photo, obtains picture content information；
D, the image content after graphics process is identified, judges whether to identify image content completely, if it is, into step
e；If it is not, then into step h；
If image content e, identified is student information, into step f；If the image content identified is to answer
Information is inscribed, then into step g；
F, pass through the number of examining or name or class's information of identified student, inquire corresponding student, and record should automatically
The information of student；
G, answering information is carried out sentencing volume, and record sentences the result of volume automatically；
H, human assistance processing is carried out, student information is recorded according to image content or sentences clove hitch fruit.
During image acquisition and processing, first start image pickup mode, 3 identifiers inscribed on single mode plate are put into shooting frame
Interior, auto-focusing shoots and captures the topic single image comprising topic, answer and student information after system identification；To image district
Domain scans for, and carries out text filed detection and positioning, automatically tips out the text filed of obtained candidate；Then
It is text filed for the candidate that provides, user click on or moving focal point by way of it is required text filed to select；To quilt
Word during the candidate of selection is text filed carries out OCR identifications；And student information is carried out according to the result of identification and sentences clove hitch fruit
Record, and the present invention has alternative scheme, can carry out human assistance operation for the region of None- identified, effectively prevent and sentence volume
Mistake or situation about failing to judge.
It is text filed in image that the present invention can effectively be such that user automatically obtains, and is used by interactive mode
Interested text filed in family, topic single mode plate can be based on and fast and accurately be carried out IMAQ, and to answering information
Judged and student information is acquired, reduce the calculating run time of system, improve the accuracy rate of positioning.
Embodiment 2
On the basis of embodiment 1, the step b comprises the following steps the present embodiment：
B1, unlatching are taken pictures or scanned, and form 3 cog regions for corresponding respectively to inscribe 3 identifiers on single mode plate；
B2, judge whether to recognize three identifiers, if it is, determining that the central point of three identifiers corresponds to topic list
The position of template, and enter step b3；If it is not, then reenter step b1；
B3, completion are taken pictures or scanned, and obtain with student information, inscribe the answer scanned copy of single information and answer information or answer
Inscribe photo.
After unlatching is taken pictures or scanned, 3 identifiers inscribed on single mode plate are put into corresponding cog region inframe, system identification
Auto-focusing shoots and captures the image comprising word afterwards, confirms that image corresponds to the central point of three identifiers, that is, completes
Take pictures or scan, obtain the image with student information, the single information of topic and answer information；It is quick, accurate that it gathers the process of image
Really, all information in topic single mode plate can be got, for follow-up image recognition and volume is sentenced to provide template basic, ensure that figure
The definition and integrality of picture, it is convenient to carry out automatic message recording.
Embodiment 3
On the basis of embodiment 1, the step c comprises the following steps the present embodiment：
C1, after getting answer scanned copy or answer photo, according to the original aspect ratio of topic single mode plate, answer is scanned
Part or answer photo carry out affine transformation；
C2, area type and area coordinate according to recorded answering pattern plate, by coordinate pair answer scanned copy or answer
Each region of photo carries out automatic segmentation, obtains each region picture after cutting；
C3, Slant Rectify and image enhaucament are carried out to each region picture after cutting, the image content letter after being handled
Breath.
Graphics process is carried out to the image collected after taking pictures or scanning, image-region scanned for first, according to topic
The original aspect ratio of single mode plate, affine transformation is carried out to the image collected, then carries out text filed detection and positioning,
Automatically the text filed of obtained candidate is tipped out, it is text filed for the candidate that provides, user can by clicking on or
The mode of moving focal point selects cutting text filed, and carries out Slant Rectify and image enhaucament to each region picture after cutting；
During the graphics process, the candidate being had detected that to user's prompting is text filed, and user is by clicking on or moving
The mode of focus, it is text filed to select, and support to select multiple text filed, further increase the accurate of figure
Degree and easy recognition, it is convenient to carry out image recognition and judgement.
Embodiment 4
For the present embodiment on the basis of embodiment 1, the step f specifically includes following steps：
Judge whether identified student information is correct, if it is, recording the information of the student automatically；If it is not, then
Into step h.The student information identified is judged, makes to form one-to-one relationship between topic single mode plate and student, keeps away
Exempt from mistake occur in answer review process, ensure that the accuracy rate that system is singly corrected to topic automatically.
Embodiment 5
For the present embodiment on the basis of embodiment 1, the step g specifically includes following steps：
Sentence whether clove hitch fruit is credible, if it is, recording the result for sentencing volume automatically；If it is not, then into step
h.According to the result for sentencing volume, sentence the record of clove hitch fruit, and can carry out confidence level discrimination, inspection to sentencing clove hitch fruit before recording
Look into the result for sentencing volume, it is ensured that sentence the authenticity and reliability of clove hitch fruit, once occurring sentencing clove hitch fruit mistake, then carry out human assistance
Clove hitch fruit is sentenced in operation corrigendum, makes final result 100% accurate.
Embodiment 6
The present embodiment is the system of embodiment 1,
As shown in Fig. 2 a kind of system of the intelligent topic image acquisition and processing based on template, including template generation module
10th, single sweep module 20, pattern process module 30, picture recognition judge module 40, image content judge module 50, Xue Shengxin are inscribed
Breath logging modle 60, sentence clove hitch fruit logging modle 70 and prosthetic processing module 80, wherein：
Template generation module 10, for generating and printing including the page number, student information, answering information, identifier, region
The topic single mode plate of type and area coordinate, wherein, identifier is positioned at upper left side, lower right and the lower-left orientation of topic single mode plate
Put place；
Single sweep module 20 is inscribed, after completing the answer to inscribing single mode plate, the topic single mode plate is scanned or taken pictures,
Obtain answer scanned copy or answer photo；
Pattern process module 30, for carrying out graphics process to answer scanned copy or answer photo, obtain image content letter
Breath；
Picture recognition judge module 40, for identifying the image content after graphics process, judge whether to identify picture completely
Content, if it is, carrying out image content judgement；If it is not, then carry out human assistance processing；
Image content identification module 50, if the image content for being identified is student information, carry out student information
Inquiry；If the image content identified is answering information, carry out sentencing volume operation；
Student information logging modle 60, for passing through the number of examining or name or class's information of identified student, inquire pair
The student answered, and the information of the student is recorded automatically；
Sentence clove hitch fruit logging modle 70, for carrying out sentencing volume to answering information, and record sentences the result of volume automatically；
Prosthetic processing module 80, for carrying out human assistance processing, record student information according to image content or sentence clove hitch
Fruit.
Embodiment 7
The present embodiment be embodiment 2 system, its on the basis of embodiment 6,
The topic single sweep module 20 includes sweep start submodule 201, identifier identification judging submodule 202 and answered
Acquisition of information submodule 203 is inscribed, wherein：
Sweep start submodule 201, take pictures or scan for opening, formation corresponds respectively to inscribe 3 marks on single mode plate
3 cog regions of symbol；
Identifier identifies judging submodule 202, for judging whether to recognize three identifiers, if it is, determining three
The central point of individual identifier corresponds to the position of topic single mode plate；Take pictures or scan if it is not, then reopening；
Answering information acquisition submodule 203, for completing to take pictures or scan, obtain with student information, the single information of topic and
The answer scanned copy or answer photo of answer information.
Embodiment 8
The present embodiment be embodiment 3 system, its on the basis of embodiment 6,
The pattern process module 30 include figure affine transformation submodule 301, graphics field cutting submodule 302 and
Figure correction enhancing submodule 303, wherein：
Figure affine transformation submodule 301, after getting answer scanned copy or answer photo, according to topic single mode plate
Original aspect ratio, affine transformation is carried out to answer scanned copy or answer photo；
Graphics field cutting submodule 302, for the area type and area coordinate according to recorded answering pattern plate, press
Each region of coordinate pair answer scanned copy or answer photo carries out automatic segmentation, obtains each region picture after cutting；
Figure correction enhancing submodule 303, for carrying out Slant Rectify and image enhaucament to each region picture after cutting,
Picture content information after being handled.
Embodiment 9
The present embodiment be embodiment 4 system, its on the basis of embodiment 6,
The student information logging modle 60 includes student information judging submodule 601, for judging identified student
Whether information is correct, if it is, recording the information of the student automatically；If it is not, then carry out human assistance processing.
Embodiment 10
The present embodiment be embodiment 5 system, its on the basis of embodiment 6,
It is described to sentence clove hitch fruit logging modle 70 including sentencing clove hitch fruit judging submodule 701, for whether sentencing clove hitch fruit
It is credible, if it is, recording the result for sentencing volume automatically；If it is not, then carry out human assistance processing.
The inventive system comprises interactive unit, operation processing unit and memory cell composition, wherein：
Interactive unit is the text image or video of identification required for collection, receives and shows that user clicks on the operation such as selection
Relevant information, the user received input information is sent to operation processing unit, and receive simultaneously from operation processing unit
Display information；
Operation processing unit is text image to being inputted from interactive unit and user input information carry out it is text filed
Detection and positioning, and the word in text filed is identified, wherein text filed refer to comprising one or more texts
The circumscribed rectangular region of block；
Memory cell is used to store the relevant information needed for unit operation, and it includes text image to be identified, used
Family click on the relevant informations of operation such as selection, text filed positioning result, Text region the apparatus and method such as result needed for
Information.
Include image acquisition units, display unit and user's input detection unit in interactive unit, wherein：
Image acquisition units are to gather the text image or video of required identification, such as PAD, scanner etc.；
Display unit is for showing text image or video to be identified, and user clicks on the relevant information of selection, text
The detection in region and positioning result, and the result of Text region；
User's input detection unit is the relevant information that the operations such as selection are clicked on for receiving user；
Include text detection positioning unit and word recognition unit in operation processing unit, wherein：
Detection positioning unit is according to the information received from interactive unit, carries out text filed detection and positioning, defeated
Go out corresponding text filed location coordinate information to word recognition unit；
Word recognition unit is according to the text image and position coordinates received from interactive unit and detection positioning unit
Information, the word in text filed is identified, and exported to display unit.
Embodiment described above only expresses the embodiment of the present invention, and its description is more specific and detailed, but simultaneously
Therefore the limitation to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the guarantor of the present invention
Protect scope.
Claims (10)
- A kind of 1. method of the intelligent topic image acquisition and processing based on template, it is characterised in that comprise the following steps：A, generate and print the topic for including the page number, student information, answering information, identifier, area type and area coordinate Single mode plate, wherein, upper left side, lower right and lower left opening position of the identifier positioned at topic single mode plate；B, after completing the answer to inscribing single mode plate, the topic single mode plate is scanned or taken pictures, obtain answer scanned copy or answer Photo；C, graphics process is carried out to answer scanned copy or answer photo, obtains picture content information；D, the image content after graphics process is identified, judges whether to identify image content completely, if it is, into step e；Such as Fruit is no, then into step h；If image content e, identified is student information, into step f；If the image content identified is answer letter Breath, then into step g；F, pass through the number of examining or name or class's information of identified student, inquire corresponding student, and record the student automatically Information；G, answering information is carried out sentencing volume, and record sentences the result of volume automatically；H, human assistance processing is carried out, student information is recorded according to image content or sentences clove hitch fruit.
- 2. the method for the intelligent topic image acquisition and processing according to claim 1 based on template, it is characterised in that described Step b comprises the following steps：B1, unlatching are taken pictures or scanned, and form 3 cog regions for corresponding respectively to inscribe 3 identifiers on single mode plate；B2, judge whether to recognize three identifiers, if it is, determining that the central point of three identifiers corresponds to topic single mode plate Position, and enter step b3；If it is not, then reenter step b1；B3, completion are taken pictures or scanned, and obtain and are shone with student information, the single information of topic and the answer scanned copy of answer information or answer Piece.
- 3. the method for the intelligent topic image acquisition and processing according to claim 1 or 2 based on template, it is characterised in that The step c comprises the following steps：C1, after getting answer scanned copy or answer photo, according to the original aspect ratio of topic single mode plate, to answer scanned copy or Answer photo carries out affine transformation；C2, area type and area coordinate according to recorded answering pattern plate, by coordinate pair answer scanned copy or answer photo Each region carry out automatic segmentation, obtain each region picture after cutting；C3, Slant Rectify and image enhaucament, the picture content information after being handled are carried out to each region picture after cutting.
- 4. the method for the intelligent topic image acquisition and processing according to claim 1 based on template, it is characterised in that described Step f specifically includes following steps：Judge whether identified student information is correct, if it is, recording the information of the student automatically；If it is not, then into Step h.
- 5. the method for the intelligent topic image acquisition and processing according to claim 1 based on template, it is characterised in that described Step g specifically includes following steps：Sentence whether clove hitch fruit is credible, if it is, recording the result for sentencing volume automatically；If it is not, then into step h.
- 6. a kind of system of the intelligent topic image acquisition and processing based on template, it is characterised in that including template generation module, topic Single sweep module, pattern process module, picture recognition judge module, image content judge module, student information logging modle, sentence Clove hitch fruit logging modle and prosthetic processing module, wherein：Template generation module, for generate and print including the page number, student information, answering information, identifier, area type with And the topic single mode plate of area coordinate, wherein, upper left side, lower right and lower left opening position of the identifier positioned at topic single mode plate；Single sweep module is inscribed, after completing the answer to inscribing single mode plate, the topic single mode plate is scanned or taken pictures, is answered Inscribe scanned copy or answer photo；Pattern process module, for carrying out graphics process to answer scanned copy or answer photo, obtain picture content information；Picture recognition judge module, for identifying the image content after graphics process, judge whether to identify image content completely, such as Fruit is then to carry out image content judgement；If it is not, then carry out human assistance processing；Image content identification module, if the image content for being identified is student information, carry out student information inquiry；Such as The image content that fruit is identified is answering information, then carries out sentencing volume operation；Student information logging modle, for passing through the number of examining or name or class's information of identified student, inquire corresponding It is raw, and the information of the student is recorded automatically；Sentence clove hitch fruit logging modle, for carrying out sentencing volume to answering information, and record sentences the result of volume automatically；Prosthetic processing module, for carrying out human assistance processing, student information is recorded according to image content or sentences clove hitch fruit.
- 7. the system of the intelligent topic image acquisition and processing according to claim 6 based on template, it is characterised in that described Inscribing single sweep module includes sweep start submodule, identifier identification judging submodule and answering information acquisition submodule, its In：Sweep start submodule, take pictures or scan for opening, formed and correspond respectively to 3 that inscribe 3 identifiers on single mode plate Cog region；Identifier identifies judging submodule, for judging whether to recognize three identifiers, if it is, determining three identifiers Central point correspond to topic single mode plate position；Take pictures or scan if it is not, then reopening；Answering information acquisition submodule, for completing to take pictures or scan, obtain with student information, the single information of topic and answer information Answer scanned copy or answer photo.
- 8. the system of the intelligent topic image acquisition and processing based on template according to claim 6 or 7, it is characterised in that The pattern process module includes figure affine transformation submodule, graphics field cutting submodule and figure correction enhancing submodule Block, wherein：Figure affine transformation submodule, after getting answer scanned copy or answer photo, according to the original length of topic single mode plate Wide ratio, affine transformation is carried out to answer scanned copy or answer photo；Graphics field cutting submodule, for the area type and area coordinate according to recorded answering pattern plate, by coordinate pair Each region of answer scanned copy or answer photo carries out automatic segmentation, obtains each region picture after cutting；Figure correction enhancing submodule, for carrying out Slant Rectify and image enhaucament to each region picture after cutting, is obtained everywhere Picture content information after reason.
- 9. the system of the intelligent topic image acquisition and processing according to claim 6 based on template, it is characterised in that described Student information logging modle includes student information judging submodule, and whether the student information for judging identified is correct, if It is then to record the information of the student automatically；If it is not, then carry out human assistance processing.
- 10. the system of the intelligent topic image acquisition and processing according to claim 6 based on template, it is characterised in that institute State and sentence clove hitch fruit logging modle including sentencing clove hitch fruit judging submodule, it is whether credible for sentencing clove hitch fruit, if it is, from It is dynamic to record the result for sentencing volume；If it is not, then carry out human assistance processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710695038.9A CN107480667A (en) | 2017-08-15 | 2017-08-15 | The method and its system of intelligent topic image acquisition and processing based on template |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710695038.9A CN107480667A (en) | 2017-08-15 | 2017-08-15 | The method and its system of intelligent topic image acquisition and processing based on template |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107480667A true CN107480667A (en) | 2017-12-15 |
Family
ID=60600476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710695038.9A Pending CN107480667A (en) | 2017-08-15 | 2017-08-15 | The method and its system of intelligent topic image acquisition and processing based on template |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107480667A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109190629A (en) * | 2018-08-28 | 2019-01-11 | 传化智联股份有限公司 | A kind of electronics waybill generation method and device |
| CN111401021A (en) * | 2018-12-17 | 2020-07-10 | 北大方正集团有限公司 | Publication template construction method, device, equipment and computer-readable storage medium |
| CN111950240A (en) * | 2020-08-26 | 2020-11-17 | 北京高途云集教育科技有限公司 | Data correction method, device and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751804A (en) * | 2008-12-01 | 2010-06-23 | 株式会社日本统计事务中心 | Electronic grading system and grade summing system |
| CN101826259A (en) * | 2009-11-30 | 2010-09-08 | 四川川大智胜软件股份有限公司 | Method for building embedded information management system of parking lot |
| US20140247965A1 (en) * | 2013-03-04 | 2014-09-04 | Design By Educators, Inc. | Indicator mark recognition |
| CN104239866A (en) * | 2014-09-16 | 2014-12-24 | 科大讯飞股份有限公司 | Answer sheet information collection method and device |
| CN105243383A (en) * | 2015-09-10 | 2016-01-13 | 上海五和文化传播有限公司 | Answer sheet processing method and system |
| CN105426879A (en) * | 2015-12-23 | 2016-03-23 | 深圳习习网络科技有限公司 | Method and system for identifying answer sheet |
| CN105809157A (en) * | 2014-12-29 | 2016-07-27 | 北京鸿合智能系统股份有限公司 | Answer sheet modeling method and device |
| US20160352934A1 (en) * | 2015-05-29 | 2016-12-01 | Kyocera Document Solutions Inc. | Information processing apparatus that creates other documents from read document |
| CN106781784A (en) * | 2017-01-04 | 2017-05-31 | 王骁乾 | A kind of intelligence correction system |
-
2017
- 2017-08-15 CN CN201710695038.9A patent/CN107480667A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751804A (en) * | 2008-12-01 | 2010-06-23 | 株式会社日本统计事务中心 | Electronic grading system and grade summing system |
| CN101826259A (en) * | 2009-11-30 | 2010-09-08 | 四川川大智胜软件股份有限公司 | Method for building embedded information management system of parking lot |
| US20140247965A1 (en) * | 2013-03-04 | 2014-09-04 | Design By Educators, Inc. | Indicator mark recognition |
| CN104239866A (en) * | 2014-09-16 | 2014-12-24 | 科大讯飞股份有限公司 | Answer sheet information collection method and device |
| CN105809157A (en) * | 2014-12-29 | 2016-07-27 | 北京鸿合智能系统股份有限公司 | Answer sheet modeling method and device |
| US20160352934A1 (en) * | 2015-05-29 | 2016-12-01 | Kyocera Document Solutions Inc. | Information processing apparatus that creates other documents from read document |
| CN105243383A (en) * | 2015-09-10 | 2016-01-13 | 上海五和文化传播有限公司 | Answer sheet processing method and system |
| CN105426879A (en) * | 2015-12-23 | 2016-03-23 | 深圳习习网络科技有限公司 | Method and system for identifying answer sheet |
| CN106781784A (en) * | 2017-01-04 | 2017-05-31 | 王骁乾 | A kind of intelligence correction system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109190629A (en) * | 2018-08-28 | 2019-01-11 | 传化智联股份有限公司 | A kind of electronics waybill generation method and device |
| CN111401021A (en) * | 2018-12-17 | 2020-07-10 | 北大方正集团有限公司 | Publication template construction method, device, equipment and computer-readable storage medium |
| CN111950240A (en) * | 2020-08-26 | 2020-11-17 | 北京高途云集教育科技有限公司 | Data correction method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008933B (en) | Universal intelligent marking system and method | |
| CN102542268B (en) | Method for detecting and positioning text area in video | |
| CN111091538B (en) | Automatic identification and defect detection method and device for pipeline welding seams | |
| US20210020059A1 (en) | Answer evaluation method, answer evaluation system, electronic device, and medium | |
| CN111160352B (en) | Workpiece metal surface character recognition method and system based on image segmentation | |
| CN104143094A (en) | Test paper automatic test paper marking processing method and system without answer sheet | |
| Yang et al. | Lecture video indexing and analysis using video ocr technology | |
| CN105913093A (en) | Template matching method for character recognizing and processing | |
| CN110705534B (en) | Wrong problem book generation method suitable for electronic typoscope | |
| CN104239866A (en) | Answer sheet information collection method and device | |
| CN106446882A (en) | method for intelligently marking paper with trace left based on 8-character code | |
| CN101866415A (en) | Answer sheet recognition device and method of computer marking system | |
| CN102855495A (en) | Method for implementing electronic edition standard answer, and application system thereof | |
| CN107480667A (en) | The method and its system of intelligent topic image acquisition and processing based on template | |
| CN110135225B (en) | Sample labeling method and computer storage medium | |
| CN108830267A (en) | A kind of method and system goed over examination papers based on image recognition | |
| CN105243383A (en) | Answer sheet processing method and system | |
| CN113222913B (en) | Circuit board defect detection positioning method, device and storage medium | |
| CN111860487B (en) | Inscription marking detection and recognition system based on deep neural network | |
| CN106778717A (en) | A kind of test and appraisal table recognition methods based on image recognition and k nearest neighbor | |
| CN114463770A (en) | Intelligent question-cutting method for general test paper questions | |
| US20070047815A1 (en) | Image recognition apparatus, image recognition method, and image recognition program | |
| CN112364687A (en) | Improved Faster R-CNN gas station electrostatic sign identification method and system | |
| CN109284702A (en) | A kind of answer sheet based on image model to point and marking system | |
| JP2008309961A (en) | Marking system and marking program |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190802 Address after: Room 11H, Building No. 33 Zizhuyuan Road, Haidian District, Beijing 100089 Applicant after: Lin Hui Address before: 610000 Fifth Floor, Building No. 5, Tianfu New Valley, 399 West Section of Fucheng Avenue, Chengdu High-tech Zone, Sichuan Province Applicant before: Chengdu foresight nehology Science and Technology Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191106 Address after: 315 800 C1437, Room 401, Block 88, Qixing Road, Meishan, Beilun District, Ningbo City, Zhejiang Province Applicant after: Ningbo Meishan Bonded Port Area Lisichen Investment Management Co., Ltd. Address before: Room 11H, Building No. 33 Zizhuyuan Road, Haidian District, Beijing 100089 Applicant before: Lin Hui |
|
| AD01 | Patent right deemed abandoned | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20201106 |