CN111612007A - English second-level braille conversion system based on image acquisition and correction - Google Patents
English second-level braille conversion system based on image acquisition and correction Download PDFInfo
- Publication number
- CN111612007A CN111612007A CN202010423020.5A CN202010423020A CN111612007A CN 111612007 A CN111612007 A CN 111612007A CN 202010423020 A CN202010423020 A CN 202010423020A CN 111612007 A CN111612007 A CN 111612007A
- Authority
- CN
- China
- Prior art keywords
- image
- braille
- module
- correction
- unit
- 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
- 238000012937 correction Methods 0.000 title claims abstract description 62
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 52
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000001914 filtration Methods 0.000 claims abstract description 22
- 230000009467 reduction Effects 0.000 claims abstract description 9
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 8
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 8
- 238000012544 monitoring process Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 18
- 238000000354 decomposition reaction Methods 0.000 claims description 14
- 238000003702 image correction Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000008602 contraction Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000001771 impaired effect Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B21/00—Teaching, or communicating with, the blind, deaf or mute
- G09B21/001—Teaching or communicating with blind persons
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Character Discrimination (AREA)
Abstract
The invention discloses an English two-level Braille conversion system based on image acquisition and correction, which comprises an image acquisition processing device, wherein the image acquisition processing device comprises a scanning unit and an identification module, the identification module is electrically connected with a CCD/CMOS sensing module and an image conversion module, the CCD/CMOS sensing module is electrically connected with the scanning unit, the image conversion module is electrically connected with an image uploading module, the image uploading module is electrically connected with a cloud database, when the system runs, the scanning unit is required to perform original video acquisition firstly, the scanning unit comprises a monitoring camera, and when the scanning unit finishes the acquisition of first-hand video data and image data. Has the advantages that: the identification unit in the invention is electrically connected with a noise reduction module; the high-frequency sub-band coefficient and the low-frequency sub-band coefficient which are synthesized by the image synthesis filtering unit are used for obtaining an image without noise points, and the accuracy and the correctness of subsequent text recognition are ensured.
Description
Technical Field
The invention relates to the technical field of Braille conversion, in particular to an English two-level Braille conversion system based on image acquisition and correction.
Background
The braille, also called dot and convex, whose minimum unit is "square", is composed of six dots arranged and combined according to a certain concave-convex fluctuation rule, and is a character designed for visually impaired people and perceived by touch, and is also a main written communication tool for visually impaired people.
International active Braille "Braille (Braille)" was created in 1824 by louis Braille for french blind. According to the Braille system in 1952, on the basis of old blind characters such as 'Xingmming blind character', and the like, China proposes a scheme (commonly known as 'current Braille') for spelling new blind characters of the common Chinese by adopting a word segmentation continuous writing method on the basis of the common Chinese and the Beijing speech as a standard through adjustment and innovation, and the scheme is published and promoted in 1953 in China. It has 18 initials and 34 finals, and the initial consonants and vowels are double-spelled into a syllable, and another blind symbol is used as tone mark. Thus, China has unified braille. In 2018, in 7 months, the Chinese language and character work Committee is approved by the Standard approval Committee of the national language and character work Committee, and is formally implemented by the national Universal Braille project agreed by the Chinese disabled person Association, the education department and the national language and character work Committee. The method continues to use the initial consonant, the final sound, the tone and the mark symbol of the current braille, does not change, delete or add any symbol, only perfects the tone marking rule of the current braille, and standardizes the use of the tone symbol.
In order to enable vast blind people to learn and use English shorthand schemes, the publishing quantity of English second-level braille must be increased, but the current domestic English second-level braille publishing still stays in a manual stage, because the main source of the content of the braille publication is the publication of a naked eye person, the ordinary situation is that an input person takes a common English book and inputs the common English book into a publishing system in a braille form one by one according to the content of the book, and the process from English to braille is completed by the brain of the input person, so that the completion of the English second-level braille input is time-consuming and labor-consuming, the accuracy rate is not guaranteed well, and the publishing efficiency is seriously influenced.
The English second-level Braille conversion system based on image acquisition and correction realizes the quick input of English second-level Braille and improves the publishing efficiency of English second-level Braille books by scanning or shooting common English books and automatically translating the common English books into English second-level Braille.
Disclosure of Invention
The invention aims to solve the problem that the efficiency of converting the existing English books into English second-level braille is extremely low in the prior art, and provides an English second-level braille conversion system based on image acquisition and correction.
In order to achieve the purpose, the invention adopts the following technical scheme: an English two-level Braille conversion system based on image acquisition and correction, comprising:
an image acquisition processing device, which comprises a scanning unit and an identification module, the identification module is electrically connected with a CCD/CMOS sensing module and an image conversion module, the CCD/CMOS sensing module is electrically connected with the scanning unit, the image conversion module is electrically connected with the image uploading module, the image uploading module is electrically connected with the cloud database, when the system is operated, firstly, a scanning unit is required to carry out original video acquisition, wherein the scanning unit comprises a monitoring camera, a camera and a video shooting device, after the scanning unit finishes the acquisition of the video data and the image data of a first hand, the image is transmitted to the recognition module through the CCD/CMOS sensing module for image recognition, after the image recognition is finished, the data is transmitted to the image processing module for image processing, and after the image processing is finished, the data is transmitted to the cloud database through the image uploading module for storage;
the character recognition module is electrically connected with the image acquisition processing device, receives an image to be recognized and then binarizes the processed image, and determines a binarization threshold value on a pixel position according to the pixel value distribution of a neighborhood block of the pixel; cutting characters based on the images, horizontally projecting the images to determine an upper limit and a lower limit of each line, cutting the lines based on the upper limit and the lower limit to obtain lines, vertically projecting the lines to obtain left and right boundaries of the characters, and cutting the lines based on the left and right boundaries to obtain single words;
the character recognition module reads a word model of a word to be recognized in the cloud database, the cut word is compared with the word model to obtain a recognition result, when the cloud database does not have the word model of the word to be recognized, image cutting characters are returned and cut again until the word model can be searched and compared in the cloud database to obtain the recognition result; then outputting the recognition result;
the text temporary storage unit is electrically connected with the character recognition module;
the Braille conversion device, the Braille conversion device is connected with the text temporary storage unit electricity, the Braille conversion device includes character scanning module and rule conversion module, character scanning module judges the english sentence of input in the text temporary storage unit character by character one by one and exports to the rule conversion module, character scanning module scans and judges that the character composition is letter, digit, punctuation or blank, the rule conversion module is according to the result that character scanning module judged to refer to corresponding conversion rule and convert the character into corresponding Braille.
In the above-mentioned english second-level braille conversion system based on image acquisition and correction, the recognition unit is electrically connected with a noise reduction module; the noise reduction module comprises an image decomposition filtering unit and an image synthesis filtering unit, wherein the decomposition filtering unit performs gray level conversion on an input image, converts an original image into a gray level image, performs coefficient decomposition through the decomposition filtering unit to obtain a high-frequency sub-band coefficient and a low-frequency sub-band coefficient, performs contraction threshold processing on the high-frequency sub-band coefficient, and performs median filtering processing on the low-frequency sub-band coefficient; and finally, synthesizing the processed high-frequency sub-band coefficient and low-frequency sub-band coefficient by an image synthesis filtering unit to obtain an image without noise points.
In the above-mentioned english two-level braille conversion system based on image collection and correction, further comprising an image correction device, the image correction device comprising:
a font calculation unit that calculates a distortion amount at each of a plurality of feature points from a captured image obtained by capturing a plurality of feature point calculation images of the image;
a font correction selecting unit that selects a font correction method corresponding to the amount of deformation at each of the feature points calculated by the amount-of-deformation calculating unit;
and an image correction processing unit that corrects the predetermined region of the font to be projected by the font correction method selected by the font correction method selecting unit.
In the above-mentioned english second grade braille conversion system based on image collection and correction, still include braille correction device, braille correction device includes:
the sequence locking module determines the Braille mark point position of the original Braille according to the corresponding rules of the Braille mark point symbols and the English mark point symbols so as to generate a mark point sequence, compares the mark point sequence with the mark point use rules, and marks the Braille mark point position which does not accord with the mark point use rules in the mark point sequence with a rule error index;
and the Braille correction module is used for completing correction on the position of the Braille point with the rule error index to obtain middle Braille, segmenting the middle Braille point by taking the point symbol as a node and inputting the segmented middle Braille point into the deep neural network model for semantic rule check, marking the blind position which does not accord with the semantic rule in the middle Braille text with the semantic error index as an error detection result of the Braille to be detected and outputting the blind position to a cloud database, and retrieving a cloud correction record and downloading corresponding correction information as a Braille correction result.
In the above-mentioned english two-level braille conversion system based on image collection and correction, when the sequence locking module performs error indexing, it first determines whether the braille before and after it meets the preset english, digital, and consonant and vowel combination rule for each braille ASCII in the original braille text, and if not, labels the rule for error indexing the position corresponding to the non-met braille ASCII.
In the above-mentioned english braille conversion system of second class based on image collection and correction, the image correction processing unit has: a function of determining the magnitude of the deformation amount at each of the feature points; and a function of selecting a font correction method corresponding to the distortion amount at each feature point from among a plurality of font correction methods different in correction accuracy set in accordance with the magnitude of the distortion amount.
Compared with the prior art, the invention has the advantages that:
1. the identification unit in the invention is electrically connected with a noise reduction module; the noise reduction module converts an original image into a gray image, then performs coefficient decomposition through a decomposition filtering unit to obtain a high-frequency sub-band coefficient and a low-frequency sub-band coefficient, performs contraction threshold processing on the high-frequency sub-band coefficient, and performs median filtering processing on the low-frequency sub-band coefficient; the high-frequency sub-band coefficient and the low-frequency sub-band coefficient which are synthesized by the image synthesis filtering unit are used for obtaining an image without noise points, so that the accuracy and the correctness of subsequent text identification are ensured;
2. the Braille correction device corrects the image, ensures that English documents with different fonts can be recognized more accurately, and reduces the influence of dirt on the documents on the recognition accuracy.
Drawings
FIG. 1 is a system block diagram of an English two-level Braille conversion system based on image acquisition and correction according to the present invention;
FIG. 2 is a system block diagram of an image correction device and a Braille correction device in an English two-level Braille conversion system based on image collection and correction according to the present invention.
Detailed Description
The following examples are for illustrative purposes only and are not intended to limit the scope of the present invention.
Examples
Referring to fig. 1-2, an english two-level braille conversion system based on image acquisition and correction includes:
the image acquisition and processing device comprises a scanning unit and an identification module, the identification module is electrically connected with a CCD/CMOS sensing module and an image conversion module, the CCD/CMOS sensing module is electrically connected with the scanning unit, the image conversion module is electrically connected with an image uploading module which is electrically connected with a cloud database, when the system is operated, firstly, a scanning unit is required to carry out original video acquisition, wherein the scanning unit comprises a monitoring camera, a camera and a video shooting device, after the scanning unit finishes the acquisition of the video data and the image data of a first hand, the image is transmitted to the recognition module through the CCD/CMOS sensing module for image recognition, after the image recognition is finished, the data is transmitted to the image processing module for image processing, and after the image processing is finished, the data is transmitted to the cloud database through the image uploading module for storage;
the character recognition module is electrically connected with the image acquisition processing device, receives an image to be recognized and then binarizes the processed image, and determines a binarization threshold value at a pixel position according to the pixel value distribution of a neighborhood block of the pixel; cutting characters based on the images, horizontally projecting the images to determine an upper limit and a lower limit of each line, cutting the lines based on the upper limit and the lower limit to obtain lines, vertically projecting the lines to obtain left and right boundaries of the characters, and cutting the lines based on the left and right boundaries to obtain single words;
the character recognition module reads a word model of a word to be recognized in the cloud database, the cut word is compared with the word model to obtain a recognition result, when the cloud database does not have the word model of the word to be recognized, image cutting characters are returned and cut again until the word model can be searched and compared in the cloud database to obtain the recognition result; then outputting the recognition result;
the text temporary storage unit is electrically connected with the character recognition module;
the Braille conversion device is electrically connected with the text temporary storage unit and comprises a character scanning module and a rule conversion module, the character scanning module judges English sentences input in the text temporary storage unit one by one and outputs the English sentences to the rule conversion module, the character scanning module scans and judges whether character components are letters, numbers, punctuations or spaces, and the rule conversion module converts the characters into corresponding Braille according to the result judged by the character scanning module and by referring to the corresponding conversion rule.
The identification unit is electrically connected with the noise reduction module; the noise reduction module comprises an image decomposition filtering unit and an image synthesis filtering unit, wherein the decomposition filtering unit performs gray level conversion on an input image, converts an original image into a gray level image, performs coefficient decomposition through the decomposition filtering unit to obtain a high-frequency sub-band coefficient and a low-frequency sub-band coefficient, performs contraction threshold processing on the high-frequency sub-band coefficient, and performs median filtering processing on the low-frequency sub-band coefficient; and finally, synthesizing the processed high-frequency sub-band coefficient and low-frequency sub-band coefficient by an image synthesis filtering unit to obtain an image without noise points.
Further comprising an image correction device, the image correction device comprising:
a font calculating unit that calculates a distortion amount at each of a plurality of feature points from a captured image obtained by capturing a plurality of feature point calculation images of the image;
a font correction selecting unit that selects a font correction method corresponding to the amount of deformation at each feature point calculated by the amount-of-deformation calculating unit;
and an image correction processing unit which corrects the predetermined region of the projected font by the font correction method selected by the font correction method selecting unit.
Still include braille correcting unit, braille correcting unit includes:
the sequence locking module determines the Braille mark point position of the original Braille according to the corresponding rules of the Braille mark point symbols and the English mark point symbols so as to generate a mark point sequence, compares the mark point sequence with the mark point use rules, and marks the Braille mark point position which does not accord with the mark point use rules in the mark point sequence with a rule error index;
the Braille correction module is used for completing correction on the Braille point position with the rule error index to obtain middle Braille, segmenting the middle Braille by taking a point symbol as a node and inputting the segmented middle Braille into the deep neural network model to check semantic rules, marking the blind position which does not accord with the semantic rules in the middle Braille text with the semantic error index as an error detection result of the Braille to be detected and outputting the blind position to the cloud database, and retrieving a cloud correction record and downloading corresponding correction information as a Braille correction result.
When the sequence locking module performs error indexing, each braille ASCII in the original braille text is firstly judged whether the braille before and after the braille meets the preset English, digital and consonant-vowel combination rule, and if the braille does not meet the preset English, the rule error indexing is marked on the position corresponding to the non-met braille ASCII.
The image correction processing unit includes: a function of determining the magnitude of the deformation amount at each feature point; and a function of selecting a font correction method corresponding to the distortion amount at each feature point from among a plurality of font correction methods different in correction accuracy set in accordance with the magnitude of the distortion amount.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical scope of the present invention and the equivalent alternatives or modifications according to the technical solution and the inventive concept of the present invention within the technical scope of the present invention.
Claims (6)
1. An English two-level Braille conversion system based on image acquisition and correction, comprising:
an image acquisition processing device, which comprises a scanning unit and an identification module, the identification module is electrically connected with a CCD/CMOS sensing module and an image conversion module, the CCD/CMOS sensing module is electrically connected with the scanning unit, the image conversion module is electrically connected with the image uploading module, the image uploading module is electrically connected with the cloud database, when the system is operated, firstly, a scanning unit is required to carry out original video acquisition, wherein the scanning unit comprises a monitoring camera, a camera and a video shooting device, after the scanning unit finishes the acquisition of the video data and the image data of a first hand, the image is transmitted to the recognition module through the CCD/CMOS sensing module for image recognition, after the image recognition is finished, the data is transmitted to the image processing module for image processing, and after the image processing is finished, the data is transmitted to the cloud database through the image uploading module for storage;
the character recognition module is electrically connected with the image acquisition processing device, receives an image to be recognized and then binarizes the processed image, and determines a binarization threshold value on a pixel position according to the pixel value distribution of a neighborhood block of the pixel; cutting characters based on the images, horizontally projecting the images to determine an upper limit and a lower limit of each line, cutting the lines based on the upper limit and the lower limit to obtain lines, vertically projecting the lines to obtain left and right boundaries of the characters, and cutting the lines based on the left and right boundaries to obtain single words;
the character recognition module reads a word model of a word to be recognized in the cloud database, the cut word is compared with the word model to obtain a recognition result, when the cloud database does not have the word model of the word to be recognized, image cutting characters are returned and cut again until the word model can be searched and compared in the cloud database to obtain the recognition result; then outputting the recognition result;
the text temporary storage unit is electrically connected with the character recognition module;
the Braille conversion device, the Braille conversion device is connected with the text temporary storage unit electricity, the Braille conversion device includes character scanning module and rule conversion module, character scanning module judges the english sentence of input in the text temporary storage unit character by character one by one and exports to the rule conversion module, character scanning module scans and judges that the character composition is letter, digit, punctuation or blank, the rule conversion module is according to the result that character scanning module judged to refer to corresponding conversion rule and convert the character into corresponding Braille.
2. The image acquisition and correction based English two-level Braille conversion system according to claim 1, wherein the recognition unit is electrically connected with a noise reduction module; the noise reduction module comprises an image decomposition filtering unit and an image synthesis filtering unit, wherein the decomposition filtering unit performs gray level conversion on an input image, converts an original image into a gray level image, performs coefficient decomposition through the decomposition filtering unit to obtain a high-frequency sub-band coefficient and a low-frequency sub-band coefficient, performs contraction threshold processing on the high-frequency sub-band coefficient, and performs median filtering processing on the low-frequency sub-band coefficient; and finally, synthesizing the processed high-frequency sub-band coefficient and low-frequency sub-band coefficient by an image synthesis filtering unit to obtain an image without noise points.
3. The image acquisition and correction based english braille conversion system according to claim 1, characterized by further comprising an image correction device, the image correction device comprising:
a font calculation unit that calculates a distortion amount at each of a plurality of feature points from a captured image obtained by capturing a plurality of feature point calculation images of the image;
a font correction selecting unit that selects a font correction method corresponding to the amount of deformation at each of the feature points calculated by the amount-of-deformation calculating unit;
and an image correction processing unit that corrects the predetermined region of the font to be projected by the font correction method selected by the font correction method selecting unit.
4. The English two-level Braille conversion system based on image collection and correction according to claim 1, further comprising a Braille correction device comprising:
the sequence locking module determines the Braille mark point position of the original Braille according to the corresponding rules of the Braille mark point symbols and the English mark point symbols so as to generate a mark point sequence, compares the mark point sequence with the mark point use rules, and marks the Braille mark point position which does not accord with the mark point use rules in the mark point sequence with a rule error index;
and the Braille correction module is used for completing correction on the position of the Braille point with the rule error index to obtain middle Braille, segmenting the middle Braille point by taking the point symbol as a node and inputting the segmented middle Braille point into the deep neural network model for semantic rule check, marking the blind position which does not accord with the semantic rule in the middle Braille text with the semantic error index as an error detection result of the Braille to be detected and outputting the blind position to a cloud database, and retrieving a cloud correction record and downloading corresponding correction information as a Braille correction result.
5. The English two-level Braille conversion system based on image acquisition and correction as claimed in claim 4, characterized in that when the sequence locking module performs error indexing, each Braille ASCII in the original Braille text is firstly judged whether the Braille before and after the Braille ASCII meets the preset English, digital and consonant combination rule, and if not, the wrong indexing is performed according to the labeling rule of the corresponding position of the non-met Braille ASCII.
6. The English two-level Braille conversion system based on image collection and correction according to claim 3, wherein the image correction processing unit has: a function of determining the magnitude of the deformation amount at each of the feature points; and a function of selecting a font correction method corresponding to the distortion amount at each feature point from among a plurality of font correction methods different in correction accuracy set in accordance with the magnitude of the distortion amount.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010423020.5A CN111612007A (en) | 2020-05-19 | 2020-05-19 | English second-level braille conversion system based on image acquisition and correction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010423020.5A CN111612007A (en) | 2020-05-19 | 2020-05-19 | English second-level braille conversion system based on image acquisition and correction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111612007A true CN111612007A (en) | 2020-09-01 |
Family
ID=72200330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010423020.5A Pending CN111612007A (en) | 2020-05-19 | 2020-05-19 | English second-level braille conversion system based on image acquisition and correction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111612007A (en) |
Citations (10)
| 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 |
| CN101631219A (en) * | 2008-07-18 | 2010-01-20 | 精工爱普生株式会社 | Image correcting apparatus, image correcting method, projector and projection system |
| CN103488488A (en) * | 2013-09-26 | 2014-01-01 | 贝壳网际（北京）安全技术有限公司 | Text input check method, device ad mobile terminal |
| CN105718450A (en) * | 2015-12-23 | 2016-06-29 | 华建宇通科技(北京)有限责任公司 | English two-level Braille converting method and device |
| CN106685972A (en) * | 2016-12-30 | 2017-05-17 | 中广热点云科技有限公司 | Fault-tolerant enhanced network video information processing system and method |
| CN109522746A (en) * | 2018-11-07 | 2019-03-26 | 平安医疗健康管理股份有限公司 | A kind of data processing method, electronic equipment and computer storage medium |
| CN109803130A (en) * | 2019-01-31 | 2019-05-24 | 温州大学 | A kind of image capturing system with color adjustment |
| CN110276069A (en) * | 2019-05-17 | 2019-09-24 | 中国科学院计算技术研究所 | A kind of Chinese braille mistake automatic testing method, system and storage medium |
| CN110503679A (en) * | 2019-08-29 | 2019-11-26 | 四川轻化工大学 | A kind of preparation of infrared reference figure and evaluation method |
| CN110705488A (en) * | 2019-10-09 | 2020-01-17 | 广州医药信息科技有限公司 | Image character recognition method |
-
2020
- 2020-05-19 CN CN202010423020.5A patent/CN111612007A/en active Pending
Patent Citations (10)
| 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 |
| CN101631219A (en) * | 2008-07-18 | 2010-01-20 | 精工爱普生株式会社 | Image correcting apparatus, image correcting method, projector and projection system |
| CN103488488A (en) * | 2013-09-26 | 2014-01-01 | 贝壳网际（北京）安全技术有限公司 | Text input check method, device ad mobile terminal |
| CN105718450A (en) * | 2015-12-23 | 2016-06-29 | 华建宇通科技(北京)有限责任公司 | English two-level Braille converting method and device |
| CN106685972A (en) * | 2016-12-30 | 2017-05-17 | 中广热点云科技有限公司 | Fault-tolerant enhanced network video information processing system and method |
| CN109522746A (en) * | 2018-11-07 | 2019-03-26 | 平安医疗健康管理股份有限公司 | A kind of data processing method, electronic equipment and computer storage medium |
| CN109803130A (en) * | 2019-01-31 | 2019-05-24 | 温州大学 | A kind of image capturing system with color adjustment |
| CN110276069A (en) * | 2019-05-17 | 2019-09-24 | 中国科学院计算技术研究所 | A kind of Chinese braille mistake automatic testing method, system and storage medium |
| CN110503679A (en) * | 2019-08-29 | 2019-11-26 | 四川轻化工大学 | A kind of preparation of infrared reference figure and evaluation method |
| CN110705488A (en) * | 2019-10-09 | 2020-01-17 | 广州医药信息科技有限公司 | Image character recognition method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105260727B (en) | Academic documents semanteme based on image procossing and sequence labelling structural method again | |
| Fischer et al. | Transcription alignment of Latin manuscripts using hidden Markov models | |
| CN103942550B (en) | A kind of scene text recognition methods based on sparse coding feature | |
| KR101376863B1 (en) | Grammatical parsing of document visual structures | |
| CN109241540B (en) | Hanblindness automatic conversion method and system based on deep neural network | |
| AU2010311067A1 (en) | System and method for increasing the accuracy of optical character recognition (OCR) | |
| Wong et al. | A software algorithm prototype for optical recognition of embossed Braille | |
| KR20210037280A (en) | Automatic font generating system and method by using hand-written | |
| Pal et al. | OCR error correction of an inflectional indian language using morphological parsing | |
| Garg et al. | Optical character recognition using artificial intelligence | |
| CN112036330A (en) | Text recognition method, text recognition device and readable storage medium | |
| CN111612007A (en) | English second-level braille conversion system based on image acquisition and correction | |
| Perera et al. | Optical braille translator for Sinhala braille system: paper communication tool between vision impaired and sighted persons | |
| Rajan et al. | Braille code conversion to voice in malayalam | |
| Khosrobeigi et al. | A rule-based post-processing approach to improve Persian OCR performance | |
| CN115311666A (en) | Image-text recognition method and device, computer equipment and storage medium | |
| KR102373358B1 (en) | System for translating judicial precedents and method of translating judicial precedents | |
| KR20090111202A (en) | The Optical Character Recognition method and device by the numbers of horizon, vertical and slant lines which is the element of Hanguel | |
| CN204856534U (en) | System of looking that helps is read to low eyesight based on OCR and TTS | |
| Ajao et al. | Yoruba handwriting word recognition quality evaluation of preprocessing attributes using information theory approach | |
| CN210895553U (en) | Automatic checking system and device for printing quality of braille readings | |
| Devi et al. | Braille Document Recognition in Southern Indian Languages–A Review | |
| CN113516041A (en) | Tibetan ancient book document image layout segmentation and identification method and system | |
| Jain et al. | Recognition of offline Gujarati handwritten disjoint consonants using pattern matching | |
| Tzogka et al. | OCR Workflow: Facing Printed Texts of Ancient, Medieval and Modern Greek Literature. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |