CN109165652A - Paper method to go over files based on label - Google Patents
Paper method to go over files based on label Download PDFInfo
- Publication number
- CN109165652A CN109165652A CN201810797045.4A CN201810797045A CN109165652A CN 109165652 A CN109165652 A CN 109165652A CN 201810797045 A CN201810797045 A CN 201810797045A CN 109165652 A CN109165652 A CN 109165652A
- Authority
- CN
- China
- Prior art keywords
- text
- point
- objective
- answer
- objective indicia
- 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 34
- 238000012512 characterization method Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 7
- 238000000926 separation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000004069 differentiation Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000010893 paper waste Substances 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Character Discrimination (AREA)
Abstract
The present invention relates to a kind of paper method to go over files based on label, wherein, the first objective indicia is equipped on paper before each objective item, the respective option of each objective item is equipped with the second objective indicia and the answer frame for examinee's full-filling, first objective indicia is different from second objective indicia, the starting point of each subjective item is equipped with first area identification point on paper, the first area identification point is different from first objective indicia and second objective indicia, and the first area identification point and subsequent region identification point of subjective item are the answer range of the subjective item.The above-mentioned paper method to go over files based on label, examinee are not necessarily to filling answer sheets in examination, after improving examination efficiency, also reduce the probability of examinee's filling answer sheets error.
Description
Technical field
The present invention relates to paper method to go over files, more particularly to the paper method to go over files based on label.
Background technique
Current paper automatic identification technology carries out automatic identification mainly for answering card, and although this mode saves reads
The time is rolled up, improves accuracy rate of going over examination papers, but there is also certain problems: waste paper, simultaneously because examinee needs in answer
Card-coating is carried out on card, it is therefore desirable to the ancillary cost time, and it is easy to appear the situation that answer is coated on errors present by examinee.
Large-scale examination in recent years when carrying out subjective question marking mainly by the image of acquisition subjective item answering card come into
The more people's network gradings of row, this method can reduce error of going over examination papers, and shortening is goed over examination papers the time, but is also deposited when practical application
In problem above, and since the teacher that gos over examination papers can only see the answer in answering card limited area, dislocation is filled out into answer in examinee
When setting or answering out limited area, the teacher that gos over examination papers can not just see complete answer.
At this stage for the fewer of the automatic marking technique study of non-answering card, the prior art mainly passes through handwritten form number
The identification of word or letter realizes to the identification of objective item region answer to carry out automatic marking, but practical application when
It waits, is influenced by the recognition accuracy of handwriting digital or letter, this technology is very difficult to apply in large-scale examination.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of paper method to go over files based on label, examinee is examining
It is not necessarily to filling answer sheets in examination, after improving examination efficiency, also reduces the probability of examinee's filling answer sheets error.
A kind of paper method to go over files based on label, wherein be equipped with the first objective indicia on paper before each objective item, often
The respective option of a objective item is equipped with the second objective indicia and the answer frame for examinee's full-filling, and first objective indicia is different from
Second objective indicia, the starting point of each subjective item is equipped with first area identification point, the first area identification point on paper
Different from first objective indicia and second objective indicia, the first area identification point and subsequent region of subjective item are identified
Point is the answer range of the subjective item, comprising:
The image for obtaining paper carries out the first objective indicia, the second objective indicia, answer index point and the firstth area to image
The extraction of domain identification point, wherein answer index point is the answer frame of examinee's full-filling, to the first objective indicia of extraction, second objective
Label, answer index point and first area identification point carry out identification differentiation, and the first objective indicia distinguished to identification is arranged
Sequence;
For each first objective indicia, according between the first objective indicia and the second objective indicia, answer index point
Positional relationship determines associated second objective indicia of first objective indicia and answer index point, and to the associated second objective mark
Note is ranked up, and then calculates associated answer index point the distance between to each associated second objective indicia, distance is most
The second objective indicia that is small and meeting design of test proportionate relationship is denoted as examinee's answer, by the sequence serial number of second objective indicia
It is compared with model answer, judges whether examinee's answer is correct according to comparison result;
After identifying first area identification point, cutting is carried out to image and goes out the text of subjective item according to the image recognition of cutting
Word, to go over examination papers to subjective item.
The above-mentioned paper method to go over files based on label, examinee are not necessarily to filling answer sheets in examination, are improving efficiency of taking an examination
After, also reduce the probability of examinee's filling answer sheets error.
In other one embodiment, " after identification first area identification point, cutting is carried out to image and according to cutting
Image recognition go out the text of subjective item, to go over examination papers to subjective item." in identify the text of subjective item, specifically include:
Images to be recognized is pre-processed, target image only comprising text is obtained;
Extract the text in the target image;
For each text extracted, the connection feature of each text is obtained;
For each text, each row abscissa and each column ordinate in all pixels point for constituting text are extracted respectively
Minimum and maximum pixel, constitute the contour feature of each text;
According to the connection feature and the contour feature of established matrix magazine and each text, to institute
Each text is stated to be identified.
In other one embodiment, the text extracted in the target image, comprising:
According to the separation condition of text in the target image, the first area where each text is obtained;
In the first area, the pixel abscissa of characterization text and the minimum and maximum vertex of ordinate are obtained
Coordinate points
Image that all pixels point in the rectangular area that is made of the apex coordinate point forms is extracted as described the
Text in one region.
In other one embodiment, the separation condition according to text in the target image,
Obtain the first area where each text, comprising:
Obtain the cut-off rule that at least one column in the target image are all background pixel point;
According to the background width of background at left and right sides of the target image, obtain in the target image where all texts
Second area;
In the second region, according to text minimum widith and the cut-off rule, each text place is obtained
First area.
It is described for each text extracted in other one embodiment, obtain the connection of each text
Feature, comprising:
It obtains and respectively characterizes connected component and the connected component that the continuous image vegetarian refreshments of text is constituted in each text
Attribute information;
All connected components are connected to feature with the attribute information of the connected component as described.
In other one embodiment, the attribute information of the connected component comprises at least one of the following information: respectively connecting
The relative position information of logical part, the pixel number of each connected component, the stroke and each connected component that each connected component includes
Edge gradient value.
In other one embodiment, when the text is Chinese character, the stroke that each connected component includes passes through
Following method obtains:
The orientation angle for the straight line that pixel based on characterization text is constituted, obtains stroke: horizontal, vertical;
The orientation angle and length for the straight line that pixel based on characterization text is fitted to, obtain stroke: skim, right-falling stroke, roll over,
Point.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
The step of computer program, the processor realizes any one the method when executing described program.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
The step of any one the method.
A kind of processor, the processor is for running program, wherein described program executes described in any item when running
Method.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the paper method to go over files based on label provided by the embodiments of the present application.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Refering to fig. 1, a kind of paper method to go over files based on label, wherein be equipped with the first visitor on paper before each objective item
Label is seen, the respective option of each objective item is equipped with the second objective indicia and the answer frame for examinee's full-filling, and described first is objective
Label is different from second objective indicia, and the starting point of each subjective item is equipped with first area identification point on paper, and described first
Region recognition point is different from first objective indicia and second objective indicia, and the first area identification point of subjective item is under
Region recognition point is the answer range of the subjective item, comprising:
S110, obtain paper image, to image carry out the first objective indicia, the second objective indicia, answer index point and
The extraction of first area identification point, wherein answer index point is the answer frame of examinee's full-filling, to the first objective indicia of extraction, the
Two objective indicias, answer index point and first area identification point carry out identification differentiation, and to the first objective indicia that identification is distinguished
It is ranked up;
S120, for each first objective indicia, according to the first objective indicia and the second objective indicia, answer index point it
Between positional relationship determine associated second objective indicia of first objective indicia and answer index point, and to associated second visitor
It sees label to be ranked up, then calculates associated answer index point the distance between to each associated second objective indicia, away from
From minimum and the second objective indicia for meeting design of test proportionate relationship is denoted as examinee's answer, by the sequence of second objective indicia
Serial number is compared with model answer, judges whether examinee's answer is correct according to comparison result;
After S130, identification first area identification point, cutting is carried out to image and subjectivity is gone out according to the image recognition of cutting
The text of topic, to go over examination papers to subjective item.
The above-mentioned paper method to go over files based on label, examinee are not necessarily to filling answer sheets in examination, are improving efficiency of taking an examination
After, also reduce the probability of examinee's filling answer sheets error.
In other one embodiment, " after identification first area identification point, cutting is carried out to image and according to cutting
Image recognition go out the text of subjective item, to go over examination papers to subjective item." in identify the text of subjective item, specifically include:
Images to be recognized is pre-processed, target image only comprising text is obtained;
Extract the text in the target image;
For each text extracted, the connection feature of each text is obtained;
For each text, each row abscissa and each column ordinate in all pixels point for constituting text are extracted respectively
Minimum and maximum pixel, constitute the contour feature of each text;
According to the connection feature and the contour feature of established matrix magazine and each text, to institute
Each text is stated to be identified.
In other one embodiment, the text extracted in the target image, comprising:
According to the separation condition of text in the target image, the first area where each text is obtained;
In the first area, the pixel abscissa of characterization text and the minimum and maximum vertex of ordinate are obtained
Coordinate points
Image that all pixels point in the rectangular area that is made of the apex coordinate point forms is extracted as described the
Text in one region.
In other one embodiment, the separation condition according to text in the target image,
Obtain the first area where each text, comprising:
Obtain the cut-off rule that at least one column in the target image are all background pixel point;
According to the background width of background at left and right sides of the target image, obtain in the target image where all texts
Second area;
In the second region, according to text minimum widith and the cut-off rule, each text place is obtained
First area.
It is described for each text extracted in other one embodiment, obtain the connection of each text
Feature, comprising:
It obtains and respectively characterizes connected component and the connected component that the continuous image vegetarian refreshments of text is constituted in each text
Attribute information;
All connected components are connected to feature with the attribute information of the connected component as described.
In other one embodiment, the attribute information of the connected component comprises at least one of the following information: respectively connecting
The relative position information of logical part, the pixel number of each connected component, the stroke and each connected component that each connected component includes
Edge gradient value.
In other one embodiment, when the text is Chinese character, the stroke that each connected component includes passes through
Following method obtains:
The orientation angle for the straight line that pixel based on characterization text is constituted, obtains stroke: horizontal, vertical;
The orientation angle and length for the straight line that pixel based on characterization text is fitted to, obtain stroke: skim, right-falling stroke, roll over,
Point.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
The step of computer program, the processor realizes any one the method when executing described program.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
The step of any one the method.
A kind of processor, the processor is for running program, wherein described program executes described in any item when running
Method.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of paper method to go over files based on label, which is characterized in that wherein, be equipped with the first visitor on paper before each objective item
Label is seen, the respective option of each objective item is equipped with the second objective indicia and the answer frame for examinee's full-filling, and described first is objective
Label is different from second objective indicia, and the starting point of each subjective item is equipped with first area identification point on paper, and described first
Region recognition point is different from first objective indicia and second objective indicia, and the first area identification point of subjective item is under
Region recognition point is the answer range of the subjective item, comprising:
The image for obtaining paper carries out the first objective indicia, the second objective indicia, answer index point and first area to image and knows
The extraction of other point, wherein answer index point is the answer frame of examinee's full-filling, the first objective indicia, the second objective mark to extraction
Note, answer index point and first area identification point carry out identification differentiation, and the first objective indicia distinguished to identification is ranked up;
For each first objective indicia, according to the position between the first objective indicia and the second objective indicia, answer index point
Relationship determines associated second objective indicia of first objective indicia and answer index point, and to associated second objective indicia into
Then row sequence calculates associated answer index point the distance between to each associated second objective indicia, distance minimum is simultaneously
The second objective indicia for meeting design of test proportionate relationship is denoted as examinee's answer, by the sequence serial number of second objective indicia and mark
Quasi- answer is compared, and judges whether examinee's answer is correct according to comparison result;
After identifying first area identification point, cutting is carried out to image and goes out the text of subjective item according to the image recognition of cutting,
To go over examination papers to subjective item.
2. the paper method to go over files according to claim 1 based on label, which is characterized in that " identification first area identification
After point, cutting is carried out to image and goes out the text of subjective item according to the image recognition of cutting, to be read to subjective item
Volume." in identify the text of subjective item, specifically include:
Images to be recognized is pre-processed, target image only comprising text is obtained;
Extract the text in the target image;
For each text extracted, the connection feature of each text is obtained;
For each text, each row abscissa and each column ordinate are extracted in all pixels point for constituting text respectively most
Big and the smallest pixel constitutes the contour feature of each text;
According to the connection feature and the contour feature of established matrix magazine and each text, to described every
A text is identified.
3. the paper method to go over files according to claim 2 based on label, which is characterized in that described to extract the target figure
Text as in, comprising:
According to the separation condition of text in the target image, the first area where each text is obtained;
In the first area, the pixel abscissa of characterization text and the minimum and maximum apex coordinate of ordinate are obtained
Point
The image that all pixels point in rectangular area that extraction is made of the apex coordinate point forms is as firstth area
Text in domain.
4. the paper method to go over files according to claim 3 based on label, which is characterized in that described according to the target figure
The separation condition of text as in,
Obtain the first area where each text, comprising:
Obtain the cut-off rule that at least one column in the target image are all background pixel point;
According to the background width of background at left and right sides of the target image, the where all texts is obtained in the target image
Two regions;
In the second region, according to text minimum widith and the cut-off rule, the where each text is obtained
One region.
5. the paper method to go over files according to claim 2 based on label, which is characterized in that described every for extracting
A text obtains the connection feature of each text, comprising:
Obtain the connected component for the continuous image vegetarian refreshments composition that text is respectively characterized in each text and the category of the connected component
Property information;
All connected components are connected to feature with the attribute information of the connected component as described.
6. the paper method to go over files according to claim 5 based on label, which is characterized in that the attribute of the connected component
Information comprises at least one of the following information: the relative position information of each connected component, the pixel number of each connected component, each to be connected to
The edge gradient value of stroke and each connected component that part includes.
7. the paper method to go over files according to claim 6 based on label, which is characterized in that when the text is Chinese character
When, the stroke that each connected component includes obtains by the following method:
The orientation angle for the straight line that pixel based on characterization text is constituted, obtains stroke: horizontal, vertical;
The orientation angle and length for the straight line that pixel based on characterization text is fitted to, obtain stroke: skimming, right-falling stroke, folding, point.
8. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any one of claims 1 to 7 the method when executing described program
Step.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claims 1 to 7 the method is realized when row.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit requires 1 to 7 described in any item methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810797045.4A CN109165652A (en) | 2018-07-19 | 2018-07-19 | Paper method to go over files based on label |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810797045.4A CN109165652A (en) | 2018-07-19 | 2018-07-19 | Paper method to go over files based on label |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109165652A true CN109165652A (en) | 2019-01-08 |
Family
ID=64897823
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810797045.4A Pending CN109165652A (en) | 2018-07-19 | 2018-07-19 | Paper method to go over files based on label |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109165652A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111192171A (en) * | 2019-12-27 | 2020-05-22 | 创而新(北京)教育科技有限公司 | Teaching assistance method, teaching assistance device, teaching assistance equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104820835A (en) * | 2015-04-29 | 2015-08-05 | 岭南师范学院 | Automatic examination paper marking method for examination papers |
CN107977659A (en) * | 2016-10-25 | 2018-05-01 | 北京搜狗科技发展有限公司 | A kind of character recognition method, device and electronic equipment |
-
2018
- 2018-07-19 CN CN201810797045.4A patent/CN109165652A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104820835A (en) * | 2015-04-29 | 2015-08-05 | 岭南师范学院 | Automatic examination paper marking method for examination papers |
CN107977659A (en) * | 2016-10-25 | 2018-05-01 | 北京搜狗科技发展有限公司 | A kind of character recognition method, device and electronic equipment |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111192171A (en) * | 2019-12-27 | 2020-05-22 | 创而新(北京)教育科技有限公司 | Teaching assistance method, teaching assistance device, teaching assistance equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110766014B (en) | Bill information positioning method, system and computer readable storage medium | |
CN109740548B (en) | Reimbursement bill image segmentation method and system | |
JP6484333B2 (en) | Intelligent scoring method and system for descriptive problems | |
CN105590101A (en) | Hand-written answer sheet automatic processing and marking method and system based on mobile phone photographing | |
CN101901338A (en) | Method and system for calculating scores of test paper | |
CN110503054B (en) | Text image processing method and device | |
CN110210413A (en) | A kind of multidisciplinary paper content detection based on deep learning and identifying system and method | |
CN103034848B (en) | A kind of recognition methods of form types | |
CN105787522B (en) | Handwriting-based writing attitude evaluation method and system | |
CN101719142B (en) | Method for detecting picture characters by sparse representation based on classifying dictionary | |
CN105046200B (en) | Electronic paper marking method based on straight line detection | |
CN104820835A (en) | Automatic examination paper marking method for examination papers | |
CN107622271B (en) | Handwritten text line extraction method and system | |
CN103336961B (en) | A kind of interactively natural scene Method for text detection | |
CN111695555B (en) | Question number-based accurate question framing method, device, equipment and medium | |
CN104794479A (en) | Method for detecting text in natural scene picture based on local width change of strokes | |
CN106485710A (en) | A kind of element mistake part detection method and device | |
CN109146740A (en) | A kind of dynamic answer sheet template system based on intelligently reading | |
CN108875737A (en) | The method and system that whether detection check box is chosen in a kind of papery prescription document | |
CN111753120A (en) | Method and device for searching questions, electronic equipment and storage medium | |
CN110287959A (en) | A kind of licence plate recognition method based on recognition strategy again | |
CN110263739A (en) | Photo table recognition methods based on OCR technique | |
CN111079641A (en) | Answering content identification method, related device and readable storage medium | |
CN104408403B (en) | A kind of referee method that secondary typing is inconsistent and device | |
CN111008594A (en) | Error correction evaluation method, related equipment and readable storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190108 |