Nothing Special   »   [go: up one dir, main page]

CN101840648A - Automatic braille marking system - Google Patents

Automatic braille marking system Download PDF

Info

Publication number
CN101840648A
CN101840648A CN 201010157756 CN201010157756A CN101840648A CN 101840648 A CN101840648 A CN 101840648A CN 201010157756 CN201010157756 CN 201010157756 CN 201010157756 A CN201010157756 A CN 201010157756A CN 101840648 A CN101840648 A CN 101840648A
Authority
CN
China
Prior art keywords
braille
paper
module
information
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN 201010157756
Other languages
Chinese (zh)
Other versions
CN101840648B (en
Inventor
王丽荣
李念峰
李�杰
张超
邹稷
尹佳
王晓丽
史丽娟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changchun University
Original Assignee
Changchun University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changchun University filed Critical Changchun University
Priority to CN 201010157756 priority Critical patent/CN101840648B/en
Publication of CN101840648A publication Critical patent/CN101840648A/en
Application granted granted Critical
Publication of CN101840648B publication Critical patent/CN101840648B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Character Discrimination (AREA)
  • Machine Translation (AREA)

Abstract

The invention relates to an automatic braille marking system and belongs to the class of information technology. The system transmits image information to a computer by adopting an optical imaging system; a software system preprocesses examination paper image information, partitions braille through an image recognition algorithm, extracts braille characteristics, and codes the braille characteristics; the coded braille is converted into pinyin and characters by combining a knowledge information bank; the system gives voice output at the same time and gives examination paper scores by the methods for automatically marking objective items and marking subjective items by teachers; and the system can analyze, print and store the examination paper. The system consists of an examination paper image input module, a examination paper image preprocessing module, an image recognition module, a braille-to-pinyin-and-character conversion module, an error correction and marking module, a voice output module, an examination paper analysis, score list and print module, an information storage module, an Excel interface module, and a knowledge information bank interface module. The system has the advantages of simple and economical hardware structure, strong practicality, reasonable and ingenious software design and simple operation.

Description

Automatic braille marking system
Technical field
The present invention relates to the infotech class, be particularly related to a kind of automatic braille marking system, especially refer to that a kind of optical imaging system or scanner of utilizing obtains the paper image information, and by image pre-service, braille image recognition, and the combining information storehouse can realize that braille to the automatic conversion of phonetic and Chinese character and can provide the system of voice suggestion, is to be the blind automatic braille marking system that education facilitates of giving birth to.
Background technology
According to national development of educational cause statistical communiques in 2008 of Ministry of Education's issue on July 17th, 2009,1640 of the now total special-education schools in the whole nation, blind person's sum 1,691 ten thousand.Be engaged in the blind teacher who gives birth to education, recognize the teacher who reads except that specialty religion braille, majority is ignorant of braille, and how to bear volume, go over examination papers be that these are engaged in the blind problem that teachers of educating have to solve of giving birth to for blind rapidly and accurately.According to investigations, present way generally is: teacher go out the Chinese paper-by specific full-time staff translate into braille and type a test paper-the blind examination-full-time staff of giving birth to or blind life finish the translation of braille paper and read to the teacher that the gos over examination papers-teacher that gos over examination papers to being achieved the result.Not only link is loaded down with trivial details for this way, time and effort consuming and easily introduce not objective factor.The present invention utilizes image recognition technology and Computer Processing to realize automatic braille marking exactly, and solving braille, to touch answer that the method to go over files read causes objective and the speed of going over examination papers is slow, the problem of wasting a large amount of manpowers.According to investigations, also there are not relevant automatic braille marking system or device at present.
Summary of the invention
The objective of the invention is to develop a kind of automatic braille marking system.Be intended to solve in present blind person's course of education, it is to touch by the blind person to read that the teacher of school for the blind gos over examination papers, and it is not objective and to touch read rate slow, the problem of wasting a large amount of manpowers because of touching the readership level and understanding the different answers that occur to touch the result that reads.The present invention can realize that the braille paper directly read and made comments by the normal person.
Automatic braille marking system mainly is made up of two parts, hardware system and software systems.Hardware system mainly is to obtain braille paper image, can adopt optical imaging system, promptly utilizes CCD to obtain the paper image information, or utilizes scanner to obtain image information, sends image information to computing machine.Software systems are carried out pre-service such as denoising, correction, image binaryzation to the paper image information.By image recognition algorithm Braille is cut apart, extracted the Braille feature, and the braille feature is encoded.Braille behind the coding is converted to phonetic and Chinese character in conjunction with the knowledge information storehouse with Braille, can provide voice output simultaneously.And by objective item read and make comments automatically, the person in charge inscribes the method that the teacher reads and makes comments, and provides the paper achievement.Can analyze, print, store paper, and can store, conveniently search comparison in the future original paper information and translation information and student performance.Software systems comprise: the paper image input module, the image pretreatment module, the braille picture recognition module, Braille is to phonetic and Chinese character modular converter, error correction and read and make comments module, the voice output module, examination paper analysis, achievement tabulation and print module, information storage module, Excel interface module, knowledge information bank interface module.Final automatic braille ocr software possesses the braille paper and reads and makes comments required basic function, recognizer reaches the practical level requirement, has function of reading aloud, and software and Excel interface are good, be convenient to the teacher student performance is implemented management, and have functions such as storage, printing.
The automatic braille marking system specific operation process is as follows:
1. early-stage preparations are that student information imports, and generate student's essential information, as information such as student's name, class, student number, specialty, test subjects;
2. obtain braille paper image, can obtain blind living paper image information by optical imaging system or scanner;
3. the pre-service of paper image is carried out denoising to the braille image that obtains, correction, binary conversion treatment;
4. the automatic identification of paper is at first cut apart the Braille after the binaryzation, and next extracts the Braille feature, and the Braille feature is encoded;
5. the Braille behind the coding is translated as phonetic or Chinese character by the knowledge information storehouse, realizes that braille is converted to phonetic and Chinese character, and can be by software according to relevant knowledge information storehouse from the normal moveout correction translation result, transformation result can be passed through voice output;
6. paper is read and made comments, and objective item adopts automatically and the model answer comparison directly provides score, and subjective item provides score by teacher's normative reference answer of going over examination papers;
7. output paper achievement is exported in the tabulation mode student performance, and paper is analyzed, prints, stored;
8. storage student information, original braille paper information, translation result and student performance can be stored, and conveniently search comparison in the future.
Automatically the optical imaging system of blind person's marking system is made up of the objective table of placing the braille paper, optical lens CCD, imaging device, data line and the computer system of obtaining the paper image information.
Automatically the optical imaging system of blind person's marking system obtains the paper image information and can utilize scanner replacement objective table, optical lens CCD and imaging device.
The invention has the advantages that: hardware configuration simple economy, practical, easy to use; Software design is rationally ingenious, the interface is short and sweet, simple to operate, have that the braille image information is translated automatically, paper is read and made comments automatically and the result stored automatically, analyze, functions such as printing.
Description of drawings
Fig. 1 is a structural representation of the present invention.
Fig. 2 is a software processing module synoptic diagram of the present invention.
Fig. 3 is an embodiments of the invention program circuit synoptic diagram.
Embodiment
As shown in Figure 1, automatic marking papers system of the present invention is made up of objective table 1, optical lens CCD2, imaging device 3, data line 4, computer system 5.Need to prove that objective table 1, optical lens CCD2, imaging device 3 can be replaced by scanner, but processing speed is slower than said method.
Blind living paper is put on the objective table 1, adjusts optical lens CCD2, guarantees that paper within sweep of the eye, starts camera head 3, obtains braille paper image information, delivers on the computer system 5 by data line 4.The automatic braille marking software systems are carried out pre-service to the image that photographs in the computer system, to the braille image recognition, are translated into phonetic and Chinese character in conjunction with the knowledge information storehouse, and provide voice output.System and Excel interface are good, can manage student information, provide student performance, print student performance, can analyze paper.
As shown in Figure 2, software processing module synoptic diagram of the present invention.Comprise the paper image input module, the image pretreatment module, the braille picture recognition module, Braille is to phonetic and Chinese character modular converter, error correction and read and make comments module, the voice output module, examination paper analysis, achievement tabulation and print module, information storage module, Excel interface module, knowledge information bank interface module.
As shown in Figure 3, embodiment program circuit synoptic diagram.At first automatic braille marking system is carried out initialization, by the Excel interface module, import student information, start imaging device 3 by the paper image input module, gather the paper image, after image information is sent to computing machine, start the image pretreatment module, this module major function is to remedy paper to draw damage, distortion, effectively reduces the stochastic error that machinery, human factor are brought in paper answer and the scanning process.At first image that paper becomes is carried out denoising, the image of distortion is proofreaied and correct, with image binaryzation, make things convenient for follow-up identification after the processing.Enter the braille picture recognition module then, the braille picture recognition module is that the image after the top processing is cut apart, and extracts the Braille feature, and the Braille feature is encoded.Braille feature coding after the identification enters Braille to phonetic and Chinese character modular converter, because braille is a language understanding process to the Chinese character translation process, the method that adopts rule to quantize, morphological rule, phrase rule and syntactic rule are joined statistical model, the hybrid language model that formation rule and statistics combine is realized the automatic conversion of braille to phonetic and Chinese character.And when braille is converted to phonetic and Chinese character, error correction and read and make comments module and utilize knowledge base, statistical information storehouses such as the phonetic knowledge of knowledge information bank interface module and Chinese, speech knowledge, the knowledge of grammar and semanteme to link, translation result is carried out multi-level ambiguity proofread and correct and correction process, finish the automatic translation of braille.Translation can be selected voice output after finishing, and exports the paper answer by the voice output module with voice mode.By error correction and read and make comments module paper is read and made comments, objective item adopts automatically and model answer is compared, and subjective item provides score by the teacher that gos over examination papers, and provides this paper achievement then.If paper is read and made comments end, by examination paper analysis, achievement tabulation and print module, provide the student performance tabulation, carry out examination paper analysis.If print student performance, this system can connect the direct print result of printer.Braille paper original image, translation result and achievement information can be stored by information storage module simultaneously.

Claims (3)

1. automatic braille marking system, it is characterized in that: form by hardware system and software systems, at first adopt optical imaging system, send image information to computing machine, software systems are carried out denoising to the paper image information, proofread and correct, the image binaryzation pre-service, by image recognition algorithm Braille is cut apart again, the Braille feature extraction, and the braille feature encoded, Braille behind the coding is converted to phonetic and Chinese character in conjunction with the knowledge information storehouse with Braille, simultaneously can provide voice output, and read and make comments automatically by objective item, the person in charge inscribes the method that the teacher reads and makes comments, and provides the paper achievement, and paper is analyzed, print, storage, and original paper information and translation information stored, conveniently search comparison in the future; Software systems comprise: the paper image input module, the image pretreatment module, braille picture recognition module, Braille be to phonetic and Chinese character modular converter, error correction and read and make comments module, the voice output module, examination paper analysis, achievement tabulation and print module, information storage module, Excel interface module, knowledge information bank interface module, specific operation process is as follows:
A. early-stage preparations are that student information imports, and generate student's essential information, as student's name, class, student number, specialty, test subject information;
B. obtain braille paper image, obtain blind living paper image information by optical imaging system or scanner;
C. the pre-service of paper image is carried out denoising to the image that obtains, correction, binary conversion treatment;
D. the automatic identification of paper is at first cut apart the Braille after the binaryzation, and next extracts the Braille feature, and the Braille feature is encoded;
E. the Braille behind the coding is translated as phonetic or Chinese character by the knowledge information storehouse, realizes that braille is converted to phonetic and Chinese character, and can be by software according to relevant knowledge information storehouse from the normal moveout correction translation result, transformation result can be passed through voice output;
F. paper is read and made comments, and objective item adopts automatically and the model answer comparison directly provides score, and subjective item provides score by teacher's normative reference answer of going over examination papers;
G. export the paper achievement, student performance is exported in the tabulation mode, and paper is analyzed, prints, stored;
H. store the original braille paper of student information, translation result and student performance, can make things convenient for and search comparison in the future.
2. according to the described automatic braille marking system of claim 1, it is characterized in that: optical imaging system is made up of the objective table of placing the braille paper, optical lens CCD, imaging device, data line and the computer system of obtaining the paper image information.
3. according to the described automatic braille marking system of claim 2, it is characterized in that: obtain the paper image information and can utilize scanner to replace objective table, optical lens CCD and imaging device.
CN 201010157756 2010-04-28 2010-04-28 Automatic braille marking method Expired - Fee Related CN101840648B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201010157756 CN101840648B (en) 2010-04-28 2010-04-28 Automatic braille marking method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201010157756 CN101840648B (en) 2010-04-28 2010-04-28 Automatic braille marking method

Publications (2)

Publication Number Publication Date
CN101840648A true CN101840648A (en) 2010-09-22
CN101840648B CN101840648B (en) 2011-09-28

Family

ID=42744003

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201010157756 Expired - Fee Related CN101840648B (en) 2010-04-28 2010-04-28 Automatic braille marking method

Country Status (1)

Country Link
CN (1) CN101840648B (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102063628A (en) * 2011-01-14 2011-05-18 长春大学 Method for extracting double-sided braille
CN102682217A (en) * 2012-05-17 2012-09-19 长春大学 Dedicated cursor scoring system for blind exam
CN103218933A (en) * 2013-02-26 2013-07-24 天津职业技术师范大学 Handheld test paper score automatic statistic device
CN107368828A (en) * 2017-07-24 2017-11-21 中国人民解放军装甲兵工程学院 High definition paper IMAQ decomposing system and method
CN108052936A (en) * 2017-11-03 2018-05-18 中国科学院计算技术研究所 A kind of braille image wing drop bearing calibration and system
CN108062886A (en) * 2017-11-03 2018-05-22 中国科学院计算技术研究所 Braille point interactive mode mask method and system
CN110498268A (en) * 2019-08-22 2019-11-26 深圳市俊达通办公智能科技有限公司 A kind of exam paper marking equipment for educational business based on artificial intelligence
CN114115542A (en) * 2021-11-29 2022-03-01 云知声智能科技股份有限公司 Braille processing method, device, storage medium and electronic device
CN114120769A (en) * 2021-11-29 2022-03-01 云知声智能科技股份有限公司 Braille reading method, device, storage medium and electronic device
CN114627730A (en) * 2022-03-31 2022-06-14 北京科技大学 Braille electronic book

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1323004A (en) * 2001-06-08 2001-11-21 清华大学 Automatic conversion method from Chinese braille to Chinese character
JP2005108125A (en) * 2003-10-01 2005-04-21 Murata Mach Ltd Image processing system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1323004A (en) * 2001-06-08 2001-11-21 清华大学 Automatic conversion method from Chinese braille to Chinese character
JP2005108125A (en) * 2003-10-01 2005-04-21 Murata Mach Ltd Image processing system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
《中国特殊教育》 20040229 安俊英,付百文 视障学生练习与考试系统的应用 31-36 1-3 , 第2期 2 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102063628A (en) * 2011-01-14 2011-05-18 长春大学 Method for extracting double-sided braille
CN102063628B (en) * 2011-01-14 2012-10-03 长春大学 Method for extracting double-sided braille
CN102682217A (en) * 2012-05-17 2012-09-19 长春大学 Dedicated cursor scoring system for blind exam
CN102682217B (en) * 2012-05-17 2016-01-27 长春大学 The special cursor marking system of blind raw examination
CN103218933A (en) * 2013-02-26 2013-07-24 天津职业技术师范大学 Handheld test paper score automatic statistic device
CN107368828A (en) * 2017-07-24 2017-11-21 中国人民解放军装甲兵工程学院 High definition paper IMAQ decomposing system and method
CN108052936A (en) * 2017-11-03 2018-05-18 中国科学院计算技术研究所 A kind of braille image wing drop bearing calibration and system
CN108062886A (en) * 2017-11-03 2018-05-22 中国科学院计算技术研究所 Braille point interactive mode mask method and system
CN110498268A (en) * 2019-08-22 2019-11-26 深圳市俊达通办公智能科技有限公司 A kind of exam paper marking equipment for educational business based on artificial intelligence
CN114115542A (en) * 2021-11-29 2022-03-01 云知声智能科技股份有限公司 Braille processing method, device, storage medium and electronic device
CN114120769A (en) * 2021-11-29 2022-03-01 云知声智能科技股份有限公司 Braille reading method, device, storage medium and electronic device
CN114627730A (en) * 2022-03-31 2022-06-14 北京科技大学 Braille electronic book

Also Published As

Publication number Publication date
CN101840648B (en) 2011-09-28

Similar Documents

Publication Publication Date Title
CN101840648B (en) Automatic braille marking method
CN110110585B (en) Intelligent paper reading implementation method and system based on deep learning and computer program
CN110750959B (en) Text information processing method, model training method and related device
Mithe et al. Optical character recognition
AU2015318386B2 (en) Intelligent scoring method and system for text objective question
KR101376863B1 (en) Grammatical parsing of document visual structures
CN110322379A (en) Paper processing method and paper processing system
US8538087B2 (en) Aiding device for reading a printed text
CN103838866B (en) Text conversion method and device
Sanchez et al. ICDAR 2015 competition HTRtS: Handwritten Text Recognition on the tranScriptorium dataset
CN110096987B (en) Dual-path 3DCNN model-based mute action recognition method
CN111523316A (en) Medicine identification method based on machine learning and related equipment
KR102344144B1 (en) Early childhood learning system using by handwriting recognition
CN106650664A (en) Collection system and method for college and university enrollment book data
Wang et al. ICFHR 2020 competition on offline recognition and spotting of handwritten mathematical expressions-OffRaSHME
Engin et al. Multimodal deep neural networks for banking document classification
CN107146489A (en) Pupil exercise book automatic score system
Alrasheed et al. Character Recognition Of Seventeenth-Century Spanish American Notary Records Using Deep Learning.
Nederhof et al. OCR of handwritten transcriptions of Ancient Egyptian hieroglyphic text
Stiehl et al. Towards a SignWriting recognition system
CN111079489B (en) Content identification method and electronic equipment
CN201892959U (en) Automatic homework checking device
Decerbo et al. The bbn byblos pashto ocr system
US10971148B2 (en) Information providing device, information providing method, and recording medium for presenting words extracted from different word groups
Yeh et al. Chinese word spelling correction based on rule induction

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
C17 Cessation of patent right
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20110928

Termination date: 20130428