CN105590101A - Hand-written answer sheet automatic processing and marking method and system based on mobile phone photographing - Google Patents
Hand-written answer sheet automatic processing and marking method and system based on mobile phone photographing Download PDFInfo
- Publication number
- CN105590101A CN105590101A CN201511002637.5A CN201511002637A CN105590101A CN 105590101 A CN105590101 A CN 105590101A CN 201511002637 A CN201511002637 A CN 201511002637A CN 105590101 A CN105590101 A CN 105590101A
- Authority
- CN
- China
- Prior art keywords
- answer
- cutting
- content area
- hardware device
- level content
- 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
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/412—Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a hand-written answer sheet automatic processing and marking method based on mobile phone photographing, comprising: preserving standard answers corresponding to test paper at a server side; preserving the blank answer sheet area segmentation information corresponding to the test paper at the server side; photographing answer sheets, sending images of the answer sheets to the server side, and automatically performing step-by-step fine locating and segmenting on the image; automatically identifying partial exercise answer images after segmentation; comparing identified answers with the standard answers and forming an automatic marking result; and preserving the automatic marking result, and sending the automatic marking result to a hardware device according to needs. The method separates answer sheets and blank paper, designs the answer sheets in the pattern meeting automatic processing requirements, can perform automatic calibration and segmentation even the images of answer sheets photographed by a mobile phone change a lot in position, shape and measuring scale, and does not need a scanner, thereby reducing requirements for an image collection device, and expanding the application scope of answer sheets.
Description
Technical field
The present invention relates to a kind of computer marking field, particularly relate to a kind of automatic processing of hand-written answering card and method to go over files and system based on mobile phone photograph.
Background technology
Existing computer marking system, taking computer networking technology and image processing techniques as support, in conjunction with Traditional Man is goed over examination papers for many years experience and modern high technology, the mode that adopts paper to separate with test paper, objective item is appraised automatically by computer, subjective item is marked respectively to the electronic image of examinee test paper by network on computers by the difference teacher that gos over examination papers, and finally automatically carries out core by computer system and divides and the one of the achievement verification mode of going over examination papers. Computer conventionally can not the hand-written subjective item answer of identification. Current computer marking mode pilot scale volume information collection is used scanner scanning each paper of examinee conventionally, scanned picture is inputted to computer and preserve, computer system is carried out inner cutting process the picture of paper according to the physical distribution of exercise question answer automatically.
Application number is that 201410321944.9 application for a patent for invention discloses a kind of paper automatic marking processing method and system without answering card, by using image blurring knowledge method for distinguishing first the paper image scanning to be positioned, then from the paper image of having located, identify objective item region and the subjective item region answered on paper, utilize handwriting digital or the answer of recognition technology to objective item region of letter and the identification of hand-written student number to carry out automatic marking, and the image uploading in subjective item region is carried out to network grading to server. In this application, for answer paper not and answer paper all need to use scanner to carry out scan image to upload, wholely sentence volume process need and focus on, in the situation that there is no scanner, can not complete to sentence licking journey. That is to say that answer person can not upload fast answered paper answer in the situation that completing paper answer, immediately know and sentence clove hitch fruit.
Application number is that 201510239535.9 application for a patent for invention discloses a kind of automatic marking method of grasping situation based on statistics and analysis knowledge point, comprises paper information gathering, uploads paper picture and subjective item and read and make comments that information, unified automatic marking, finishing leave a question open and examination result statistics. In this application, the technical problem mainly solving is that existing examination need to be by specific answering card answer; The analysis result of examination can not carry out the statistics and analysis of knowledge point grasp situation etc., the paper information gathering of this application is also to take to use the mode that scanner scans paper locating area to gather paper information, can not complete to sentence licking journey in the situation that there is no scanner. That is to say that answer person can not upload fast answered paper answer in the situation that completing paper answer, immediately know and sentence clove hitch fruit.
Summary of the invention
For above-mentioned problems of the prior art, the present invention proposes a kind of technical scheme, can upload easily and fast answer person's answer answer, can be immediately send back in answer person's hand sentencing clove hitch fruit completing after sentencing volume, having solved in prior art to use scanner to carry out paper information gathering, equipment configuration expense is high, and establishes easy wasting problem more.
The technical solution used in the present invention is:
Hand-written answering card based on mobile phone photograph is processed and a method to go over files automatically, and the system of implementing the method comprises server end, said method comprising the steps of:
Preserve the model answer corresponding with paper at server end;
Preserve the blank answering card Region Segmentation information corresponding with paper at server end;
After printed answering card is by hand filling answer, answering card is taken pictures, and the image of clapping is sent to server end, and server end receives described image;
At server end, image automatically being carried out to meticulous location step by step cuts apart;
At server end, the part exercise answer image after cutting apart is identified automatically;
Compare and form automatic grading result identifying answer and model answer at server end;
Preserve automatic grading result at server end, and will sentence as required clove hitch fruit and send to hardware device.
Preferably, described blank answering card Region Segmentation information comprises,
Content area is provided with page marker pattern, and every page is provided with some by above-below direction, and each is provided with piece indicia patterns;
As required, each is provided with several rows by above-below direction, and every row is provided with row labels pattern; As required, every row is provided with some row by left and right directions, and every row are provided with row indicia patterns;
As required, answering card is provided with direct answer unit, and each unit is provided with unit indicia patterns; As required, in each answer unit, be provided with several rows; As required, the every row in answer unit is provided with some row.
In above-mentioned arbitrary scheme, preferably, describedly image is carried out step by step to meticulous location cut apart and comprise the steps:
Page level content area directional correction: answer sheet picture is carried out to overall directional correction;
Page level content area cutting: the answer sheet picture of carrying out after directional correction is carried out to cutting according to certain rule, obtain page level content area;
Piece level content area cutting: page level content area is carried out carrying out cutting according to certain rule after directional correction, obtain piece level content area;
Content cutting in piece: piece level content area is carried out carrying out cutting according to certain rule after directional correction, obtain final cutting unit.
In above-mentioned arbitrary scheme, preferably, the cutting of described page level content area specifically comprises the steps:
According to page marker pattern, estimate the border up and down of whole page content area;
Content area border is suitably relaxed, avoid piecemeal cutting contents lost;
Whole page content area is carried out to cutting and obtain page level content area.
In above-mentioned arbitrary scheme, preferably, the cutting of described level content area specifically comprises the steps:
Page level content area is carried out to directional correction;
With the up-and-down boundary of every of piece indicia patterns estimation;
According to the border, left and right of the up-and-down boundary of every and page level content area, estimate the partial left right margin of this piece;
The border up and down of every is suitably relaxed, avoid cutting contents lost;
Page level content area is carried out to cutting and obtain piece level content area.
In above-mentioned arbitrary scheme, preferably, described content cutting specifically comprises the steps:
Piece level content area is carried out to directional correction, if current region is final cutting unit, cut apart end;
In if block level content area, there is multirow, utilize row labels pattern and border, piece level left and right to carry out the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
If have multiple row in row level content area, utilize row indicia patterns and row level up-and-down boundary to enter the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end.
In above-mentioned arbitrary scheme, preferably, in if block level content area, there is direct answer unit, carry out the cutting of cell level content according to answer unit indicia patterns; If current region is final cutting unit, cut apart end; If answer unit needs cutting, as required, according to content cutting step in piece, answer unit is carried out to multiple lines and multiple rows cutting processing.
In above-mentioned arbitrary scheme, preferably, described automatic grading resultant content comprises model answer, objective item answer image, the automatic recognition result of objective item and automatic comparison result, subjective item answer image.
In above-mentioned arbitrary scheme preferably, described image is carried out step by step meticulous location segmentation step and the elementary area after cutting apart is carried out to automatic identification step being completed by the second hardware device automatically, described the second hardware device is to server end request model answer, and forms automatic grading result by identifying after answer and model answer are compared.
In above-mentioned arbitrary scheme, preferably, described the second hardware device comprises the one in mobile phone, panel computer or digital camera.
In above-mentioned arbitrary scheme preferably, described paper exercise question comprises objective item and subjective item, describedly at server end, the image after cutting apart is carried out to automatic identification step and further comprise: objective item answer image and model answer are directly compared, automatically identification; Handwritten form and the model answer of subjective item answer image are compared, Direct Recognition, or identify under the information guiding of subjective item model answer.
In above-mentioned arbitrary scheme, preferably, the information of described subjective item model answer comprises, the character information relating to when character types, character quantity and other examinations; Described character types comprise Arabic numerals, English capitalization, English lower case, Chinese-character digital, Roman number, to mismark and other examination characters.
In above-mentioned arbitrary scheme, preferably, described server end comprises at least one in set a question/Pan Juan of examination question mechanism, school or software supplier.
Hand-written answering card based on mobile phone photograph is processed and a method to go over files automatically, and the system of implementing the method comprises the first hardware device and the second hardware device, said method comprising the steps of:
The first hardware device output papery blank coil and blank answering card;
The second hardware device is taken pictures the answering card of hand filling answer, and the image of taking pictures sends to server end;
Carried out at answering card that meticulous location is step by step cut apart, identification automatically, compare and form after automatic grading result with model answer, described in sentence that clove hitch fruit is transmitted to the first hardware device or/and the second hardware device,
The first hardware device is sentenced clove hitch fruit or/and the second hardware device receives and shows.
Hand-written answering card based on mobile phone photograph is processed and a method to go over files automatically, and the system of implementing the method comprises the first hardware device and the second hardware device, said method comprising the steps of:
The first hardware device output papery blank coil and blank answering card;
After the model answer corresponding with paper is saved; The second hardware device is to server end request model answer;
The second hardware device is preserved the blank answering card Region Segmentation information corresponding with paper;
After printed answering card is by hand filling answer, answering card is taken pictures by the second hardware device;
The second hardware device automatically carries out meticulous location step by step to image to be cut apart;
The second hardware device is identified automatically to the part exercise answer image after cutting apart;
The second hardware device is compared and forms automatic grading result identifying answer and model answer;
The second hardware device is preserved automatic grading result, shows to sentence clove hitch fruit and will sentence as required clove hitch fruit to send the first hardware device to.
In above-mentioned arbitrary scheme, preferably, described automatic grading resultant content comprises model answer, objective item answer image, the automatic recognition result of objective item and automatic comparison result, subjective item answer image.
In above-mentioned arbitrary scheme, preferably, described the first hardware device comprises the computer with printer; Described the second equipment comprises the one in mobile phone, panel computer, digital camera.
Hand-written answering card based on mobile phone photograph is processed and a marking system automatically, and described system comprises the first hardware device, the second hardware device and server end, and described the first hardware device comprises receiving system, printer and the first display screen; Described the second hardware device comprises camera arrangement, picture transmitter device and second display screen; Described server end comprises that memory module, image receiver module, framing cut apart module, picture recognition module, answer comparing module and sentence clove hitch fruit delivery module.
A kind of hand-written answering card based on mobile phone photograph is processed and marking system automatically, described system comprises the first hardware device, the second hardware device and server end, described the first hardware device comprises receiving system, printer and the first display screen, and described the second hardware device comprises that camera arrangement, hardware device stores module, framing cut apart module, picture recognition module, answer comparing module, sentence clove hitch fruit delivery module and second display screen; Described server end comprises memory module.
Preferably, described receiving system is used for blank coil, the answering card of reception server end transmission and sentences clove hitch fruit; Described printer is used for printing blank coil, answering card and sentences clove hitch fruit; Described the first display screen is used for showing paper and sentences clove hitch fruit, and described second display screen is sentenced clove hitch fruit for showing; Described camera arrangement is for taking pictures to the answering card of fill out answers; Described picture transmitter device sends to server end for the image of taking pictures.
In above-mentioned arbitrary scheme, preferably, described memory module is used for preserving blank coil, answering card, model answer and sentences clove hitch fruit, and described memory module or hardware device stores module are for preserving the blank answering card Region Segmentation information corresponding with paper.
In above-mentioned arbitrary scheme, preferably, described blank answering card Region Segmentation information comprises:
Content area is provided with page marker pattern, and every page is provided with some by above-below direction, and each is provided with piece indicia patterns;
As required, each is provided with several rows by above-below direction, and every row is provided with row labels pattern; As required, every row is provided with some row by left and right directions, and every row are provided with row indicia patterns;
As required, answering card is provided with direct answer unit, and each unit is provided with unit indicia patterns; As required, in each answer unit, be provided with several rows; As required, the every row in answer unit is provided with some row.
In above-mentioned arbitrary scheme, preferably, described image receiver module is for receiving paper or the answering card image of the second hardware device transmission.
In above-mentioned arbitrary scheme, preferably, described framing is cut apart module and is cut apart for paper or answering card image are carried out to meticulous location step by step.
In above-mentioned arbitrary scheme, preferably, describedly image is carried out step by step to meticulous location cut apart and comprise:
Page level content area directional correction: answer sheet picture is carried out to overall directional correction;
Page level content area cutting: the answer sheet picture of carrying out after directional correction is carried out to cutting according to certain rule, obtain page level content area;
Piece level content area cutting: page level content area is carried out carrying out cutting according to certain rule after directional correction, obtain piece level content area;
Content cutting in piece: piece level content area is carried out carrying out cutting according to certain rule after directional correction, obtain final cutting unit.
In above-mentioned arbitrary scheme, preferably, the cutting of described page level content area specifically comprises:
According to page marker pattern, estimate the border up and down of whole page content area;
Content area border is suitably relaxed, avoid cutting contents lost;
Whole page content area is carried out to cutting and obtain page level content area.
In above-mentioned arbitrary scheme, preferably, the cutting of described level content area specifically comprises:
Page level content area is carried out to directional correction;
With the up-and-down boundary of every of piece indicia patterns estimation;
According to the border, left and right of the up-and-down boundary of every and page level content area, estimate the partial left right margin of this piece;
The border up and down of every is suitably relaxed, avoid cutting contents lost;
Page level content area is carried out to cutting and obtain piece level content area.
In above-mentioned arbitrary scheme, preferably, described content cutting specifically comprises the steps:
Piece level content area is carried out to directional correction, if current region is final cutting unit, cut apart end;
In if block level content area, there is multirow, utilize row labels pattern and border, piece level left and right to carry out the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
If have multiple row in row level content area, utilize row indicia patterns and row level up-and-down boundary to enter the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
In if block level content area, there is direct answer unit, carry out the cutting of cell level content according to answer unit indicia patterns; If current region is final cutting unit, cut apart end; If answer unit needs cutting, as required, according to content cutting step in piece, answer unit is carried out to multiple lines and multiple rows cutting processing.
In above-mentioned arbitrary scheme, preferably, described picture recognition module is for automatically identifying the image after cutting apart.
In above-mentioned arbitrary scheme, preferably, described image automatic identification after cutting apart is further comprised, objective item answer image and model answer are directly compared, automatically identification; Handwritten form and the model answer of subjective item answer image are compared, Direct Recognition, or identify under the guiding of subjective item model answer information.
In above-mentioned arbitrary scheme, preferably, the information of described subjective item model answer comprises, the character information relating to when character types, character quantity and other examinations; Described character types comprise Arabic numerals, English capitalization, English lower case, Chinese-character digital, Roman number, to mismark and other examination characters.
In above-mentioned arbitrary scheme, preferably, described picture recognition module is for identifying the image of location dividing processing.
In above-mentioned arbitrary scheme, preferably, described answer comparing module is sentenced clove hitch really for recognition image and model answer being compared and forming.
In above-mentioned arbitrary scheme preferably, described in sentence volume resultant content comprise model answer, objective item answer image, the automatic recognition result of objective item and automatic comparison result, subjective item answer image.
In above-mentioned arbitrary scheme preferably, described in sentence clove hitch fruit delivery module and send the first hardware device to for sentencing clove hitch fruit.
In above-mentioned arbitrary scheme, preferably, described the first hardware device comprises the computer with printer; Described the second equipment comprises the one in mobile phone, panel computer, digital camera.
In above-mentioned arbitrary scheme, preferably, described server end comprises examination question set a question mechanism or software supplier.
According to the feasible technical scheme of the present invention, there is following some beneficial effect:
The automatic processing of hand-written answering card that the present invention is based on mobile phone photograph separates answering card with method to go over files and system with blank coil, can meet to answer card the design of automatic processing requirements, can automatic calibration and cut apart even if the answering card image of mobile phone photograph has position by a relatively large margin, shape and engineer's scale to change also, do not need scanner. Reduce the requirement to image capture device, expanded the applicable scene of answering card.
The present invention is based on the automatic processing of hand-written answering card of mobile phone photograph and method to go over files and system the objective item content of answering card is carried out to handwritten form identification, be different from the answering card of tinting. Meaning is that answer person is by the answer of nature word, than convenient by the fill out answers of tinting.
Brief description of the drawings
Fig. 1 is according to the schematic flow sheet of the automatic processing of the hand-written answering card that the present invention is based on mobile phone photograph and method to go over files;
Fig. 2 is according to the flow chart of a preferred embodiment of server end of the present invention;
Fig. 3 is according to the flow chart of a preferred embodiment of hardware device end of the present invention;
Fig. 4 is according to the flow chart of another preferred embodiment of hardware device end of the present invention.
Detailed description of the invention
Below in conjunction with accompanying drawing with preferred embodiment the present invention is described in further detail. Corresponding relation between instantiation illustration as follows in constitutive requirements and embodiment in claim. The description intention is here to confirm to have described to be in an embodiment used for supporting the instantiation of the theme of statement in the claims, owing to having described in an embodiment example, does not mean that this instantiation does not represent constitutive requirements. On the contrary, even comprised the element characteristic of instantiation as corresponding constitutive requirements at this, do not mean that this instantiation does not represent any other constitutive requirements yet.
In addition, the description does not here mean that corresponding to all themes of the instantiation of stating in embodiment and has all quoted in the claims. In other words, this entity is not denied in the description here, the instantiation that corresponding embodiment comprises, but be not included in its any one claim, that is and, correction that can be is afterwards by division application or the entity that may invent that increases.
Embodiment 1:
As shown in Figures 1 and 2, a kind of hand-written answering card based on mobile phone photograph is processed and method to go over files automatically, and the system of implementing the method comprises server end, said method comprising the steps of:
(1) preserve the model answer corresponding with paper at server end;
(2) preserve the blank answering card Region Segmentation information corresponding with paper at server end;
(3) after printed answering card is by hand filling answer, answering card is taken pictures, and the image of clapping is sent to server end, and server end receives described image;
(4) at server end, image automatically being carried out to meticulous location step by step cuts apart;
(5) at server end, the part exercise answer image after cutting apart is identified automatically;
(6) compare and form automatic grading result identifying answer and model answer at server end;
(7) preserve automatic grading result at server end, and will sentence as required clove hitch fruit and send to hardware device.
In above-mentioned steps, step (1) can be exchanged with the order of step (2).
The group volume of examination paper is made up of blank coil, answering card and model answer, and blank coil exists with digitlization or paper-based form, for setting a question to answer people; Answering card exists with paper-based form, and answer people is manual exercise question answer corresponding to volume of filling on answering card; Model answer is preserved in digital form, the comparison during for the hand-written answer of automatic identification. Answer people, with natural language, as Arabic numerals, English alphabet, Chinese character, mathematic sign etc., carries out answer and fills on blank coil or answering card. To the hand-written answering card collection image of taking pictures, and do not need scanner by terminals such as mobile phone, pad, digital cameras. By software, take pictures gathered hand-written answering card or blank coil are carried out to auto Segmentation processing, cutting apart is for the answer region of different exercise questions is separated. Cut apart independently and carry out, or carry out under the guiding of digitlization model answer. Automatically identify for the objective item answer in model answer, identification is independently carried out, or carries out under model answer guiding. Except full width image, will cut apart rear answering card topography taking exercise question as unit and preserve, form and sentence clove hitch fruit wherein having identified answer comparison model answer.
Described blank answering card Region Segmentation information comprises,
Content area is provided with page marker pattern, and every page is provided with some by above-below direction, and each is provided with piece indicia patterns;
As required, each is provided with several rows by above-below direction, and every row is provided with row labels pattern; As required, every row is provided with some row by left and right directions, and every row are provided with row indicia patterns;
As required, answering card is provided with direct answer unit, and each unit is provided with unit indicia patterns; As required, in each answer unit, be provided with several rows; As required, the every row in answer unit is provided with some row.
Describedly image is carried out step by step to meticulous location cut apart and comprise the steps:
Page level content area directional correction: answer sheet picture is carried out to overall directional correction;
Page level content area cutting: the answer sheet picture of carrying out after directional correction is carried out to cutting according to certain rule, obtain page level content area;
Piece level content area cutting: page level content area is carried out carrying out cutting according to certain rule after directional correction, obtain piece level content area;
Content cutting in piece: piece level content area is carried out carrying out cutting according to certain rule after directional correction, obtain final cutting unit.
The cutting of described page level content area specifically comprises the steps:
According to page marker pattern, estimate the border up and down of whole page content area;
Content area border is suitably relaxed, avoid piecemeal cutting contents lost;
Whole page content area is carried out to cutting and obtain page level content area.
The cutting of described level content area specifically comprises the steps:
Page level content area is carried out to directional correction;
With the up-and-down boundary of every of piece indicia patterns estimation;
According to the border, left and right of the up-and-down boundary of every and page level content area, estimate the partial left right margin of this piece;
The border up and down of every is suitably relaxed, avoid the contents lost of branch's cutting;
Page level content area is carried out to cutting and obtain piece level content area.
Described content cutting specifically comprises the steps:
Piece level content area is carried out to directional correction, if current region is final cutting unit, cut apart end;
In if block level content area, there is multirow, utilize row labels pattern and border, piece level left and right to carry out the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
If have multiple row in row level content area, utilize row indicia patterns and row level up-and-down boundary to enter the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end.
In if block level content area, there is direct answer unit, carry out the cutting of cell level content according to answer unit indicia patterns; If current region is final cutting unit, cut apart end; If answer unit needs cutting, as required, according to content cutting step in piece, answer unit is carried out to multiple lines and multiple rows cutting processing.
Described image is carried out step by step meticulous location segmentation step and the elementary area after cutting apart is carried out to automatic identification step being completed by the second hardware device automatically, described the second hardware device is to server end request model answer, and forms automatic grading result by identifying after answer and model answer are compared.
Described automatic grading resultant content comprises model answer, objective item answer image, the automatic recognition result of objective item and automatic comparison result, subjective item answer image. In the application, automatic grading the possibility of result is not the final clove hitch fruit of sentencing, server end or the second hardware device terminal will show at the first or second hardware device by the automatic grading result of comparing formation with model answer, check and subjective item is sentenced again by sentencing volume teacher, forming the final clove hitch fruit of sentencing in conjunction with automatic grading result.
Described the second hardware device comprises the one in mobile phone, panel computer or digital camera.
Described paper exercise question comprises objective item and subjective item, describedly at server end, the image after cutting apart is carried out to automatic identification step and further comprises: objective item answer image and model answer are directly compared, automatically identification; Handwritten form and the model answer of subjective item answer image are compared, Direct Recognition, or identify under the information guiding of subjective item model answer. The answer of cutting apart rear objective item is carried out to handwritten form identification, can be general multiclass identification, is also the boolean's identification under model answer guiding.
The information of described subjective item model answer comprises, the character information relating to when character types, character quantity and other examinations; Described character types comprise Arabic numerals, English capitalization, English lower case, Chinese-character digital, Roman number, to mismark and other examination characters.
Described server end comprises at least one in set a question/Pan Juan of examination question mechanism, school or software supplier.
Embodiment 2:
As shown in accompanying drawing 1 and accompanying drawing 3, a kind of hand-written answering card based on mobile phone photograph is processed and method to go over files automatically, and the system of implementing the method comprises the first hardware device and the second hardware device, said method comprising the steps of:
The first hardware device output papery blank coil and blank answering card;
The second hardware device is taken pictures the answering card of hand filling answer, and the image of taking pictures sends to server end;
Carried out at answering card that meticulous location is step by step cut apart, identification automatically, compare and form after automatic grading result with model answer, described in sentence that clove hitch fruit is transmitted to the first hardware device or/and the second hardware device,
The first hardware device is sentenced clove hitch fruit or/and the second hardware device receives and shows.
Described the first hardware device comprises the computer with printer; Described the second equipment comprises mobile phone.
Described blank answering card Region Segmentation information comprises,
Content area is provided with page marker pattern, and every page is provided with some by above-below direction, and each is provided with piece indicia patterns;
As required, each is provided with several rows by above-below direction, and every row is provided with row labels pattern; As required, every row is provided with some row by left and right directions, and every row are provided with row indicia patterns;
As required, answering card is provided with direct answer unit, and each unit is provided with unit indicia patterns; As required, in each answer unit, be provided with several rows; As required, the every row in answer unit is provided with some row.
Describedly image is carried out step by step to meticulous location cut apart and comprise the steps:
Page level content area directional correction: answer sheet picture is carried out to overall directional correction;
Page level content area cutting: the answer sheet picture of carrying out after directional correction is carried out to cutting according to certain rule, obtain page level content area;
Piece level content area cutting: page level content area is carried out carrying out cutting according to certain rule after directional correction, obtain piece level content area;
Content cutting in piece: piece level content area is carried out carrying out cutting according to certain rule after directional correction, obtain final cutting unit.
The cutting of described page level content area specifically comprises the steps:
According to page marker pattern, estimate the border up and down of whole page content area;
Content area border is suitably relaxed, avoid piecemeal cutting contents lost;
Whole page content area is carried out to cutting and obtain page level content area.
The cutting of described level content area specifically comprises the steps:
Page level content area is carried out to directional correction;
With the up-and-down boundary of every of piece indicia patterns estimation;
According to the border, left and right of the up-and-down boundary of every and page level content area, estimate the partial left right margin of this piece;
The border up and down of every is suitably relaxed, avoid the contents lost of branch's cutting;
Page level content area is carried out to cutting and obtain piece level content area.
Described content cutting specifically comprises the steps:
Piece level content area is carried out to directional correction, if current region is final cutting unit, cut apart end;
In if block level content area, there is multirow, utilize row labels pattern and border, piece level left and right to carry out the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
If have multiple row in row level content area, utilize row indicia patterns and row level up-and-down boundary to enter the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end.
In if block level content area, there is direct answer unit, carry out the cutting of cell level content according to answer unit indicia patterns; If current region is final cutting unit, cut apart end; If answer unit needs cutting, as required, according to content cutting step in piece, answer unit is carried out to multiple lines and multiple rows cutting processing.
Described image is carried out step by step meticulous location segmentation step and the elementary area after cutting apart is carried out to automatic identification step being completed by the second hardware device automatically, described the second hardware device is to server end request model answer, and forms automatic grading result by identifying after answer and model answer are compared.
Described automatic grading resultant content comprises model answer, objective item answer image, the automatic recognition result of objective item and automatic comparison result, subjective item answer image. In the application, automatic grading the possibility of result is not the final clove hitch fruit of sentencing, server end or the second hardware device terminal will show at the first or second hardware device by the automatic grading result of comparing formation with model answer, check and subjective item is sentenced again by sentencing volume teacher, forming the final clove hitch fruit of sentencing in conjunction with automatic grading result.
Described the second hardware device comprises the one in mobile phone, panel computer or digital camera.
Described paper exercise question comprises objective item and subjective item, describedly at server end, the image after cutting apart is carried out to automatic identification step and further comprises: objective item answer image and model answer are directly compared, automatically identification; Handwritten form and the model answer of subjective item answer image are compared, Direct Recognition, or identify under the information guiding of subjective item model answer. The answer of cutting apart rear objective item is carried out to handwritten form identification, can be general multiclass identification, is also the boolean's identification under model answer guiding.
The information of described subjective item model answer comprises, the character information relating to when character types, character quantity and other examinations; Described character types comprise Arabic numerals, English capitalization, English lower case, Chinese-character digital, Roman number, to mismark and other examination characters.
Described server end comprises at least one in set a question/Pan Juan of examination question mechanism, school or software supplier.
Embodiment 3:
As shown in accompanying drawing 1 and accompanying drawing 4, a kind of hand-written answering card based on mobile phone photograph is processed and method to go over files automatically, and the system of implementing the method comprises the first hardware device and the second hardware device, said method comprising the steps of:
The first hardware device output papery blank coil and blank answering card;
After the model answer corresponding with paper is saved; The second hardware device request model answer;
The second hardware device is preserved the blank answering card Region Segmentation information corresponding with paper;
After printed answering card is by hand filling answer, answering card is taken pictures by the second hardware device;
The second hardware device automatically carries out meticulous location step by step to image to be cut apart;
The second hardware device is identified automatically to the part exercise answer image after cutting apart;
The second hardware device is compared and forms automatic grading result identifying answer and model answer;
The second hardware device is preserved automatic grading result, shows to sentence clove hitch fruit and will sentence as required clove hitch fruit to send the first hardware device to.
Described the first hardware device comprises the computer with printer; Described the second equipment comprises panel computer.
Described blank answering card Region Segmentation information comprises,
Content area is provided with page marker pattern, and every page is provided with some by above-below direction, and each is provided with piece indicia patterns;
As required, each is provided with several rows by above-below direction, and every row is provided with row labels pattern; As required, every row is provided with some row by left and right directions, and every row are provided with row indicia patterns;
As required, answering card is provided with direct answer unit, and each unit is provided with unit indicia patterns; As required, in each answer unit, be provided with several rows; As required, the every row in answer unit is provided with some row.
Describedly image is carried out step by step to meticulous location cut apart and comprise the steps:
Page level content area directional correction: answer sheet picture is carried out to overall directional correction;
Page level content area cutting: the answer sheet picture of carrying out after directional correction is carried out to cutting according to certain rule, obtain page level content area;
Piece level content area cutting: page level content area is carried out carrying out cutting according to certain rule after directional correction, obtain piece level content area;
Content cutting in piece: piece level content area is carried out carrying out cutting according to certain rule after directional correction, obtain final cutting unit.
The cutting of described page level content area specifically comprises the steps:
According to page marker pattern, estimate the border up and down of whole page content area;
Content area border is suitably relaxed, avoid piecemeal cutting contents lost;
Whole page content area is carried out to cutting and obtain page level content area.
The cutting of described level content area specifically comprises the steps:
Page level content area is carried out to directional correction;
With the up-and-down boundary of every of piece indicia patterns estimation;
According to the border, left and right of the up-and-down boundary of every and page level content area, estimate the partial left right margin of this piece;
The border up and down of every is suitably relaxed, avoid the contents lost of branch's cutting;
Page level content area is carried out to cutting and obtain piece level content area.
Described content cutting specifically comprises the steps:
Piece level content area is carried out to directional correction, if current region is final cutting unit, cut apart end;
In if block level content area, there is multirow, utilize row labels pattern and border, piece level left and right to carry out the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
If have multiple row in row level content area, utilize row indicia patterns and row level up-and-down boundary to enter the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end.
In if block level content area, there is direct answer unit, carry out the cutting of cell level content according to answer unit indicia patterns; If current region is final cutting unit, cut apart end; If answer unit needs cutting, as required, according to content cutting step in piece, answer unit is carried out to multiple lines and multiple rows cutting processing.
Described image is carried out step by step meticulous location segmentation step and the elementary area after cutting apart is carried out to automatic identification step being completed by the second hardware device automatically, described the second hardware device is to server end request model answer, and forms automatic grading result by identifying after answer and model answer are compared.
Described automatic grading resultant content comprises model answer, objective item answer image, the automatic recognition result of objective item and automatic comparison result, subjective item answer image. In the application, automatic grading the possibility of result is not the final clove hitch fruit of sentencing, server end or the second hardware device terminal will show at the first or second hardware device by the automatic grading result of comparing formation with model answer, check and subjective item is sentenced again by sentencing volume teacher, forming the final clove hitch fruit of sentencing in conjunction with automatic grading result.
Described the second hardware device comprises the one in mobile phone, panel computer or digital camera.
Described paper exercise question comprises objective item and subjective item, describedly at server end, the image after cutting apart is carried out to automatic identification step and further comprises: objective item answer image and model answer are directly compared, automatically identification; Handwritten form and the model answer of subjective item answer image are compared, Direct Recognition, or identify under the information guiding of subjective item model answer. The answer of cutting apart rear objective item is carried out to handwritten form identification, can be general multiclass identification, is also the boolean's identification under model answer guiding.
The information of described subjective item model answer comprises, the character information relating to when character types, character quantity and other examinations; Described character types comprise Arabic numerals, English capitalization, English lower case, Chinese-character digital, Roman number, to mismark and other examination characters.
Described server end comprises at least one in set a question/Pan Juan of examination question mechanism, school or software supplier.
Embodiment 4:
Hand-written answering card based on mobile phone photograph is processed and a marking system automatically, and described system comprises the first hardware device, and the second hardware device and server end, is characterized in that, described the first hardware device comprises receiving system, printer and the first display screen; Described the second hardware device comprises camera arrangement, picture transmitter device and second display screen; Described server end comprises that memory module, image receiver module, framing cut apart module, picture recognition module, answer comparing module and sentence clove hitch fruit delivery module.
Described receiving system is used for blank coil, the answering card of reception server end transmission and sentences clove hitch fruit; Described printer is used for printing blank coil, answering card and sentences clove hitch fruit; Described the first display screen is used for showing paper and sentences clove hitch fruit, and described second display screen is sentenced clove hitch fruit for showing; Described camera arrangement is for taking pictures to the answering card of fill out answers; Described picture transmitter device sends to server end for the image of taking pictures.
Described memory module is used for preserving blank coil, answering card, model answer and sentences clove hitch fruit, and described memory module or hardware device stores module are for preserving the blank answering card Region Segmentation information corresponding with paper.
Described blank answering card Region Segmentation information comprises:
Content area is provided with page marker pattern, and every page is provided with some by above-below direction, and each is provided with piece indicia patterns;
As required, each is provided with several rows by above-below direction, and every row is provided with row labels pattern; As required, every row is provided with some row by left and right directions, and every row are provided with row indicia patterns;
As required, answering card is provided with direct answer unit, and each unit is provided with unit indicia patterns; As required, in each answer unit, be provided with several rows; As required, the every row in answer unit is provided with some row.
Paper or answering card image that described image receiver module sends for receiving the second hardware device.
Described framing is cut apart module and is cut apart for paper or answering card image are carried out to meticulous location step by step.
Describedly image is carried out step by step to meticulous location cut apart and comprise:
Page level content area directional correction: answer sheet picture is carried out to overall directional correction;
Page level content area cutting: the answer sheet picture of carrying out after directional correction is carried out to cutting according to certain rule, obtain page level content area;
Piece level content area cutting: page level content area is carried out carrying out cutting according to certain rule after directional correction, obtain piece level content area;
Content cutting in piece: piece level content area is carried out carrying out cutting according to certain rule after directional correction, obtain final cutting unit.
The cutting of described page level content area specifically comprises:
According to page marker pattern, estimate the border up and down of whole page content area;
Content area border is suitably relaxed, avoid piecemeal cutting contents lost;
Whole page content area is carried out to cutting and obtain page level content area.
The cutting of described level content area specifically comprises:
Page level content area is carried out to directional correction;
With the up-and-down boundary of every of piece indicia patterns estimation;
According to the border, left and right of the up-and-down boundary of every and page level content area, estimate the partial left right margin of this piece;
The border up and down of every is suitably relaxed, avoid the contents lost of branch's cutting;
Page level content area is carried out to cutting and obtain piece level content area.
Described content cutting specifically comprises the steps:
Piece level content area is carried out to directional correction, if current region is final cutting unit, cut apart end;
In if block level content area, there is multirow, utilize row labels pattern and border, piece level left and right to carry out the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
If have multiple row in row level content area, utilize row indicia patterns and row level up-and-down boundary to enter the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
In if block level content area, there is direct answer unit, carry out the cutting of cell level content according to answer unit indicia patterns; If current region is final cutting unit, cut apart end; If answer unit needs cutting, as required, according to content cutting step in piece, answer unit is carried out to multiple lines and multiple rows cutting processing.
Described picture recognition module is for automatically identifying the image after cutting apart.
Described image automatic identification after cutting apart is further comprised, objective item answer image and model answer are directly compared, automatically identification; Handwritten form and the model answer of subjective item answer image are compared, Direct Recognition, or identify under the guiding of subjective item model answer information. The answer of cutting apart rear objective item is carried out to handwritten form identification, can be general multiclass identification, is also the boolean's identification under model answer guiding.
The information of described subjective item model answer comprises, the character information relating to when character types, character quantity and other examinations; Described character types comprise Arabic numerals, English capitalization, English lower case, Chinese-character digital, Roman number, to mismark and other examination characters.
Described picture recognition module is for identifying the image of location dividing processing.
Described answer comparing module is sentenced clove hitch really for recognition image and model answer being compared and forming.
Describedly sentence clove hitch fruit delivery module and send the first hardware device to for sentencing clove hitch fruit.
Described the first hardware device comprises the computer with printer; Described the second equipment digital camera.
Described server end comprises the examination question mechanism of setting a question/go over examination papers.
Described automatic grading resultant content comprises model answer, objective item answer image, the automatic recognition result of objective item and automatic comparison result, subjective item answer image. In the application, automatic grading the possibility of result is not the final clove hitch fruit of sentencing, server end or the second hardware device terminal will show at the first or second hardware device by the automatic grading result of comparing formation with model answer, check and subjective item is sentenced again by sentencing volume teacher, forming the final clove hitch fruit of sentencing in conjunction with automatic grading result.
Embodiment 5:
A kind of hand-written answering card based on mobile phone photograph is processed and marking system automatically, described system comprises the first hardware device, the second hardware device and server end, it is characterized in that, described the first hardware device comprises receiving system, printer and the first display screen, and described the second hardware device comprises that camera arrangement, hardware device stores module, framing cut apart module, picture recognition module, answer comparing module, sentence clove hitch fruit delivery module and second display screen; Described server end comprises memory module.
Described receiving system is used for blank coil, the answering card of reception server end transmission and sentences clove hitch fruit; Described printer is used for printing blank coil, answering card and sentences clove hitch fruit; Described the first display screen is used for showing paper and sentences clove hitch fruit, and described second display screen is sentenced clove hitch fruit for showing; Described camera arrangement is for taking pictures to the answering card of fill out answers; Described picture transmitter device sends to server end for the image of taking pictures.
Described memory module is used for preserving blank coil, answering card, model answer and sentences clove hitch fruit, and described memory module or hardware device stores module are for preserving the blank answering card Region Segmentation information corresponding with paper.
Described blank answering card Region Segmentation information comprises:
Content area is provided with page marker pattern, and every page is provided with some by above-below direction, and each is provided with piece indicia patterns;
As required, each is provided with several rows by above-below direction, and every row is provided with row labels pattern; As required, every row is provided with some row by left and right directions, and every row are provided with row indicia patterns;
As required, answering card is provided with direct answer unit, and each unit is provided with unit indicia patterns; As required, in each answer unit, be provided with several rows; As required, the every row in answer unit is provided with some row.
Described framing is cut apart module and is cut apart for paper or answering card image are carried out to meticulous location step by step.
Describedly image is carried out step by step to meticulous location cut apart and comprise:
Page level content area directional correction: answer sheet picture is carried out to overall directional correction;
Page level content area cutting: the answer sheet picture of carrying out after directional correction is carried out to cutting according to certain rule, obtain page level content area;
Piece level content area cutting: page level content area is carried out carrying out cutting according to certain rule after directional correction, obtain piece level content area;
Content cutting in piece: piece level content area is carried out carrying out cutting according to certain rule after directional correction, obtain final cutting unit.
The cutting of described page level content area specifically comprises:
According to page marker pattern, estimate the border up and down of whole page content area;
Content area border is suitably relaxed, avoid piecemeal cutting contents lost;
Whole page content area is carried out to cutting and obtain page level content area.
The cutting of described level content area specifically comprises:
Page level content area is carried out to directional correction;
With the up-and-down boundary of every of piece indicia patterns estimation;
According to the border, left and right of the up-and-down boundary of every and page level content area, estimate the partial left right margin of this piece;
The border up and down of every is suitably relaxed, avoid the contents lost of branch's cutting;
Page level content area is carried out to cutting and obtain piece level content area.
Described content cutting specifically comprises the steps:
Piece level content area is carried out to directional correction, if current region is final cutting unit, cut apart end;
In if block level content area, there is multirow, utilize row labels pattern and border, piece level left and right to carry out the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
If have multiple row in row level content area, utilize row indicia patterns and row level up-and-down boundary to enter the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
In if block level content area, there is direct answer unit, carry out the cutting of cell level content according to answer unit indicia patterns; If current region is final cutting unit, cut apart end; If answer unit needs cutting, as required, according to content cutting step in piece, answer unit is carried out to multiple lines and multiple rows cutting processing.
Described picture recognition module is for automatically identifying the image after cutting apart.
Described image automatic identification after cutting apart is further comprised, objective item answer image and model answer are directly compared, automatically identification; Handwritten form and the model answer of subjective item answer image are compared, Direct Recognition, or identify under the guiding of subjective item model answer information.
The information of described subjective item model answer comprises, the character information relating to when character types, character quantity and other examinations; Described character types comprise Arabic numerals, English capitalization, English lower case, Chinese-character digital, Roman number, to mismark and other examination characters.
Described picture recognition module is for identifying the image of location dividing processing.
Described answer comparing module is sentenced clove hitch really for recognition image and model answer being compared and forming.
Describedly sentence clove hitch fruit delivery module and send the first hardware device to for sentencing clove hitch fruit.
Described automatic grading resultant content comprises model answer, objective item answer image, the automatic recognition result of objective item and automatic comparison result, subjective item answer image. In the application, automatic grading the possibility of result is not the final clove hitch fruit of sentencing, server end or the second hardware device terminal will show at the first or second hardware device by the automatic grading result of comparing formation with model answer, check and subjective item is sentenced again by sentencing volume teacher, forming the final clove hitch fruit of sentencing in conjunction with automatic grading result.
Described the first hardware device comprises the computer with printer; Described the second equipment comprises digital camera. Described server end comprises school.
The above, be only preferred embodiment of the present invention, not structure of the present invention done to any pro forma restriction. Any simple modification, equivalent variations and modification that every foundation technical spirit of the present invention is done above embodiment, all belong within the scope of technical scheme of the present invention.
Claims (10)
1. the hand-written answering card based on mobile phone photograph is processed and a method to go over files automatically, and the system of implementing the method comprises server end, it is characterized in that, said method comprising the steps of:
Preserve the model answer corresponding with paper at server end;
Preserve the blank answering card Region Segmentation information corresponding with paper at server end;
After printed answering card is by hand filling answer, answering card is taken pictures, and the image of clapping is sent to server end, and server end receives described image;
At server end, image being carried out to meticulous location step by step automatically cuts apart;
At server end, the part exercise answer image after cutting apart is identified automatically;
Compare and form automatic grading result identifying answer and model answer at server end;
Preserve automatic grading result at server end, and will sentence as required clove hitch fruit and send to hardware device.
2. a kind of hand-written answering card based on mobile phone photograph according to claim 1 is automatically processed and method to go over files, it is characterized in that, described blank answering card Region Segmentation information comprises,
Content area is provided with page marker pattern, and every page is provided with some by above-below direction, and each is provided with piece indicia patterns;
As required, each is provided with several rows by above-below direction, and every row is provided with row labels pattern; As required, every row is provided with some row by left and right directions, and every row are provided with row indicia patterns;
As required, answering card is provided with direct answer unit, and each unit is provided with unit indicia patterns; As required, in each answer unit, be provided with several rows; As required, the every row in answer unit is provided with some row.
3. a kind of hand-written answering card based on mobile phone photograph according to claim 1 is automatically processed and method to go over files, it is characterized in that, describedly image is carried out step by step to meticulous location cuts apart and comprises the steps:
Page level content area directional correction: answer sheet picture is carried out to overall directional correction;
Page level content area cutting: the answer sheet picture of carrying out after directional correction is carried out to cutting according to certain rule, obtain page level content area;
Piece level content area cutting: page level content area is carried out carrying out cutting according to certain rule after directional correction, obtain piece level content area;
Content cutting in piece: piece level content area is carried out carrying out cutting according to certain rule after directional correction, obtain final cutting unit.
4. a kind of hand-written answering card based on mobile phone photograph according to claim 3 is processed and method to go over files automatically, it is characterized in that, the cutting of described page level content area specifically comprises the steps:
According to page marker pattern, estimate the border up and down of whole page content area;
Content area border is suitably relaxed, avoid cutting contents lost;
Whole page content area is carried out to cutting and obtain page level content area.
5. a kind of hand-written answering card based on mobile phone photograph according to claim 3 is processed and method to go over files automatically, it is characterized in that, the cutting of described level content area specifically comprises the steps:
Page level content area is carried out to directional correction;
With the up-and-down boundary of every of piece indicia patterns estimation;
According to the border, left and right of the up-and-down boundary of every and page level content area, estimate the partial left right margin of this piece;
The border up and down of every is suitably relaxed, avoid the contents lost of cutting;
Page level content area is carried out to cutting and obtain piece level content area.
6. a kind of hand-written answering card based on mobile phone photograph according to claim 3 is processed and method to go over files automatically, it is characterized in that, described content cutting specifically comprises the steps:
Piece level content area is carried out to directional correction, if current region is final cutting unit, cut apart end;
In if block level content area, there is multirow, utilize row labels pattern and border, piece level left and right to carry out the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end;
If have multiple row in row level content area, utilize row indicia patterns and row level up-and-down boundary to enter the processing of similar level content area cutting, obtain row level content area, if current region is final cutting unit, cut apart end.
7. a kind of hand-written answering card based on mobile phone photograph according to claim 6 is processed and method to go over files automatically, it is characterized in that, has direct answer unit in if block level content area, carries out the cutting of cell level content according to answer unit indicia patterns; If current region is final cutting unit, cut apart end; If answer unit needs cutting, as required, according to content cutting step in piece, answer unit is carried out to multiple lines and multiple rows cutting processing.
8. a kind of hand-written answering card based on mobile phone photograph according to claim 1 is processed and method to go over files automatically, it is characterized in that, described automatic grading resultant content comprises model answer, objective item answer image, the automatic recognition result of objective item and automatic comparison result, subjective item answer image.
9. the hand-written answering card based on mobile phone photograph is processed and a method to go over files automatically, and the system of implementing the method comprises the first hardware device and the second hardware device, it is characterized in that, said method comprising the steps of:
The first hardware device output papery blank coil and blank answering card;
The second hardware device is taken pictures the answering card of hand filling answer, and the image of taking pictures sends to server end;
Carried out at answering card that meticulous location is step by step cut apart, identification automatically, compare and form after automatic grading result with model answer, described in sentence that clove hitch fruit is transmitted to the first hardware device or/and the second hardware device,
The first hardware device is sentenced clove hitch fruit or/and the second hardware device receives and shows.
10. the hand-written answering card based on mobile phone photograph is processed and a method to go over files automatically, and the system of implementing the method comprises the first hardware device and the second hardware device, it is characterized in that, said method comprising the steps of:
The first hardware device output papery blank coil and blank answering card;
After the model answer corresponding with paper is saved; The second hardware device is to server end request model answer;
The second hardware device is preserved the blank answering card Region Segmentation information corresponding with paper;
After printed answering card is by hand filling answer, answering card is taken pictures by the second hardware device;
The second hardware device automatically carries out meticulous location step by step to image to be cut apart;
The second hardware device is identified automatically to the part exercise answer image after cutting apart;
The second hardware device is compared and forms automatic grading result identifying answer and model answer;
The second hardware device is preserved automatic grading result, shows to sentence clove hitch fruit and will sentence as required clove hitch fruit to send the first hardware device to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511002637.5A CN105590101A (en) | 2015-12-28 | 2015-12-28 | Hand-written answer sheet automatic processing and marking method and system based on mobile phone photographing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511002637.5A CN105590101A (en) | 2015-12-28 | 2015-12-28 | Hand-written answer sheet automatic processing and marking method and system based on mobile phone photographing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105590101A true CN105590101A (en) | 2016-05-18 |
Family
ID=55929671
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511002637.5A Pending CN105590101A (en) | 2015-12-28 | 2015-12-28 | Hand-written answer sheet automatic processing and marking method and system based on mobile phone photographing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105590101A (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869464A (en) * | 2016-06-24 | 2016-08-17 | 苏州美丽澄电子技术有限公司 | Photographing type family education robot |
| CN106023698A (en) * | 2016-07-29 | 2016-10-12 | 李铧 | Automatic reading and amending method for homework and exercise books |
| CN106096564A (en) * | 2016-06-17 | 2016-11-09 | 福建网龙计算机网络信息技术有限公司 | A kind of mathematics corrects method automatically |
| CN106355176A (en) * | 2016-11-11 | 2017-01-25 | 赵耕伯 | Test question checking system |
| CN106446886A (en) * | 2016-10-13 | 2017-02-22 | 广东文讯科技有限公司 | Multipoint positioning identification method in use of camera of intelligent terminal |
| CN106599887A (en) * | 2016-11-16 | 2017-04-26 | 东莞优闪电子科技有限公司 | Test paper answering area identifying and test question marking method and system |
| CN106651876A (en) * | 2016-12-13 | 2017-05-10 | 深圳市海云天科技股份有限公司 | Image processing method and system for answer sheets |
| CN106709492A (en) * | 2016-12-15 | 2017-05-24 | 网易（杭州）网络有限公司 | Examination paper image processing method and device, and computer readable storage medium |
| CN106778703A (en) * | 2017-01-25 | 2017-05-31 | 华中师范大学 | The method and apparatus of electric marking |
| CN106846961A (en) * | 2017-01-25 | 2017-06-13 | 华中师范大学 | The treating method and apparatus of electronic test paper |
| CN107368800A (en) * | 2017-07-13 | 2017-11-21 | 上海携程商务有限公司 | Order confirmation method, system, equipment and storage medium based on fax identification |
| CN107909067A (en) * | 2017-11-06 | 2018-04-13 | 泉州市雄蓝教育科技有限公司 | The examination system of intelligence generation answering card and mobile terminal Automated Assessment |
| CN108230308A (en) * | 2017-12-29 | 2018-06-29 | 武汉璞华大数据技术有限公司 | A kind of handbill proofreading method, device and equipment |
| CN109325401A (en) * | 2018-08-03 | 2019-02-12 | 成都准星云学科技有限公司 | The method and system for being labeled, identifying to title field are positioned based on edge |
| CN109741273A (en) * | 2018-12-26 | 2019-05-10 | 江苏优胜信息技术有限公司 | A kind of mobile phone photograph low-quality images automatically process and methods of marking |
| CN109740515A (en) * | 2018-12-29 | 2019-05-10 | 科大讯飞股份有限公司 | One kind reading and appraising method and device |
| CN110210465A (en) * | 2018-02-28 | 2019-09-06 | 彼乐智慧科技（北京）有限公司 | A kind of method and system of data acquisition |
| CN110969152A (en) * | 2019-12-30 | 2020-04-07 | 福建天晴数码有限公司 | Exercise book content identification method |
| CN111081093A (en) * | 2019-07-11 | 2020-04-28 | 广东小天才科技有限公司 | Dictation content identification method and electronic equipment |
| CN111144343A (en) * | 2019-12-30 | 2020-05-12 | 福建天晴数码有限公司 | Answer sheet content identification system |
| CN111144342A (en) * | 2019-12-30 | 2020-05-12 | 福建天晴数码有限公司 | Page content identification system |
| CN111178269A (en) * | 2019-12-30 | 2020-05-19 | 福建天晴数码有限公司 | Answer sheet content identification method |
| CN111178268A (en) * | 2019-12-30 | 2020-05-19 | 福建天晴数码有限公司 | Exercise book content identification system |
| CN112700414A (en) * | 2020-12-30 | 2021-04-23 | 广东德诚大数据科技有限公司 | Blank answer detection method and system for examination paper marking |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866415A (en) * | 2009-08-24 | 2010-10-20 | 深圳市海云天科技股份有限公司 | Answer sheet recognition device and method of computer marking system |
| CN102360419A (en) * | 2011-09-28 | 2012-02-22 | 广东启明科技发展有限公司 | Method and system for computer scanning reading management |
| CN103065146A (en) * | 2012-12-24 | 2013-04-24 | 广东电网公司电力调度控制中心 | Character recognition method for power communication machine room dumb equipment signboards |
| CN104143094A (en) * | 2014-07-08 | 2014-11-12 | 北京彩云动力教育科技有限公司 | Test paper automatic test paper marking processing method and system without answer sheet |
| CN104268603A (en) * | 2014-09-16 | 2015-01-07 | 科大讯飞股份有限公司 | Intelligent marking method and system for text objective questions |
-
2015
- 2015-12-28 CN CN201511002637.5A patent/CN105590101A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866415A (en) * | 2009-08-24 | 2010-10-20 | 深圳市海云天科技股份有限公司 | Answer sheet recognition device and method of computer marking system |
| CN102360419A (en) * | 2011-09-28 | 2012-02-22 | 广东启明科技发展有限公司 | Method and system for computer scanning reading management |
| CN103065146A (en) * | 2012-12-24 | 2013-04-24 | 广东电网公司电力调度控制中心 | Character recognition method for power communication machine room dumb equipment signboards |
| CN104143094A (en) * | 2014-07-08 | 2014-11-12 | 北京彩云动力教育科技有限公司 | Test paper automatic test paper marking processing method and system without answer sheet |
| CN104268603A (en) * | 2014-09-16 | 2015-01-07 | 科大讯飞股份有限公司 | Intelligent marking method and system for text objective questions |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096564A (en) * | 2016-06-17 | 2016-11-09 | 福建网龙计算机网络信息技术有限公司 | A kind of mathematics corrects method automatically |
| CN105869464A (en) * | 2016-06-24 | 2016-08-17 | 苏州美丽澄电子技术有限公司 | Photographing type family education robot |
| CN106023698A (en) * | 2016-07-29 | 2016-10-12 | 李铧 | Automatic reading and amending method for homework and exercise books |
| CN106446886B (en) * | 2016-10-13 | 2019-08-20 | 广东文讯科技有限公司 | It is a kind of to use the multipoint positioning recognition methods of intelligent terminal camera |
| CN106446886A (en) * | 2016-10-13 | 2017-02-22 | 广东文讯科技有限公司 | Multipoint positioning identification method in use of camera of intelligent terminal |
| CN106355176A (en) * | 2016-11-11 | 2017-01-25 | 赵耕伯 | Test question checking system |
| CN106599887A (en) * | 2016-11-16 | 2017-04-26 | 东莞优闪电子科技有限公司 | Test paper answering area identifying and test question marking method and system |
| CN106599887B (en) * | 2016-11-16 | 2019-10-18 | 广东墨痕教育科技有限公司 | Paper answer region recognition and examination question read and appraise method, system |
| CN106651876A (en) * | 2016-12-13 | 2017-05-10 | 深圳市海云天科技股份有限公司 | Image processing method and system for answer sheets |
| CN106709492A (en) * | 2016-12-15 | 2017-05-24 | 网易（杭州）网络有限公司 | Examination paper image processing method and device, and computer readable storage medium |
| CN106778703A (en) * | 2017-01-25 | 2017-05-31 | 华中师范大学 | The method and apparatus of electric marking |
| CN106846961A (en) * | 2017-01-25 | 2017-06-13 | 华中师范大学 | The treating method and apparatus of electronic test paper |
| CN106846961B (en) * | 2017-01-25 | 2020-03-27 | 华中师范大学 | Electronic test paper processing method and device |
| CN107368800A (en) * | 2017-07-13 | 2017-11-21 | 上海携程商务有限公司 | Order confirmation method, system, equipment and storage medium based on fax identification |
| CN107368800B (en) * | 2017-07-13 | 2020-02-21 | 上海携程商务有限公司 | Order confirmation method, system, equipment and storage medium based on fax identification |
| CN107909067A (en) * | 2017-11-06 | 2018-04-13 | 泉州市雄蓝教育科技有限公司 | The examination system of intelligence generation answering card and mobile terminal Automated Assessment |
| CN108230308B (en) * | 2017-12-29 | 2021-02-09 | 武汉璞华大数据技术有限公司 | Method, device and equipment for checking advertisement bill |
| CN108230308A (en) * | 2017-12-29 | 2018-06-29 | 武汉璞华大数据技术有限公司 | A kind of handbill proofreading method, device and equipment |
| CN110210465A (en) * | 2018-02-28 | 2019-09-06 | 彼乐智慧科技（北京）有限公司 | A kind of method and system of data acquisition |
| CN109325401A (en) * | 2018-08-03 | 2019-02-12 | 成都准星云学科技有限公司 | The method and system for being labeled, identifying to title field are positioned based on edge |
| CN109741273A (en) * | 2018-12-26 | 2019-05-10 | 江苏优胜信息技术有限公司 | A kind of mobile phone photograph low-quality images automatically process and methods of marking |
| CN109740515A (en) * | 2018-12-29 | 2019-05-10 | 科大讯飞股份有限公司 | One kind reading and appraising method and device |
| CN111081093A (en) * | 2019-07-11 | 2020-04-28 | 广东小天才科技有限公司 | Dictation content identification method and electronic equipment |
| CN110969152A (en) * | 2019-12-30 | 2020-04-07 | 福建天晴数码有限公司 | Exercise book content identification method |
| CN111144342A (en) * | 2019-12-30 | 2020-05-12 | 福建天晴数码有限公司 | Page content identification system |
| CN111178269A (en) * | 2019-12-30 | 2020-05-19 | 福建天晴数码有限公司 | Answer sheet content identification method |
| CN111178268A (en) * | 2019-12-30 | 2020-05-19 | 福建天晴数码有限公司 | Exercise book content identification system |
| CN111144343A (en) * | 2019-12-30 | 2020-05-12 | 福建天晴数码有限公司 | Answer sheet content identification system |
| CN111178269B (en) * | 2019-12-30 | 2023-04-18 | 福建天晴数码有限公司 | Answer sheet content identification method |
| CN110969152B (en) * | 2019-12-30 | 2023-04-18 | 福建天晴数码有限公司 | Exercise book content identification method |
| CN111144343B (en) * | 2019-12-30 | 2023-04-18 | 福建天晴数码有限公司 | Answer sheet content identification system |
| CN111178268B (en) * | 2019-12-30 | 2023-04-18 | 福建天晴数码有限公司 | Exercise book content identification system |
| CN112700414A (en) * | 2020-12-30 | 2021-04-23 | 广东德诚大数据科技有限公司 | Blank answer detection method and system for examination paper marking |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105590101A (en) | Hand-written answer sheet automatic processing and marking method and system based on mobile phone photographing | |
| CN109993112B (en) | Method and device for identifying table in picture | |
| US20210020059A1 (en) | Answer evaluation method, answer evaluation system, electronic device, and medium | |
| CN104143094B (en) | A kind of paper automatic marking processing method and system without answering card | |
| CN106781784A (en) | A kind of intelligence correction system | |
| CN106033544B (en) | Template matching-based test paper content area extraction method | |
| CN108416352A (en) | A kind of computer network marking system and method to go over files | |
| CN108090445A (en) | The electronics of a kind of papery operation or paper corrects method | |
| CN105046200B (en) | Electronic paper marking method based on straight line detection | |
| CN107657255A (en) | Network scoring method, apparatus, readable storage medium storing program for executing and electronic equipment | |
| CN112308063B (en) | Character recognition device, translation pen, image translation method, and image translation device | |
| CN101866415A (en) | Answer sheet recognition device and method of computer marking system | |
| CN111814616A (en) | Automatic examination paper marking processing system without answer sheet and implementation method thereof | |
| CN108564079A (en) | A kind of portable character recognition device and method | |
| CN106651876A (en) | Image processing method and system for answer sheets | |
| CN113159014A (en) | Objective question reading method, device, equipment and storage medium based on handwritten question numbers | |
| CN107622264A (en) | A kind of intelligence reads and makes comments method and device | |
| US7227997B2 (en) | Image recognition apparatus, image recognition method, and image recognition program | |
| CN106033534B (en) | Electronic paper marking method based on straight line detection | |
| CN110298236B (en) | Automatic Braille image identification method and system based on deep learning | |
| CN111008594A (en) | Error correction evaluation method, related equipment and readable storage medium | |
| CN106528820A (en) | Picture annotation processing method and system, and terminal | |
| CN108062548B (en) | Braille square self-adaptive positioning method and system | |
| CN109165652A (en) | Paper method to go over files based on label | |
| US7853194B2 (en) | Material processing apparatus, material processing method and material processing program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160518 |
|
| WD01 | Invention patent application deemed withdrawn after publication |