CN106097794A - The Chinese phonetic alphabet based on augmented reality combination is recognized reading learning system and recognizes reading method - Google Patents
The Chinese phonetic alphabet based on augmented reality combination is recognized reading learning system and recognizes reading method Download PDFInfo
- Publication number
- CN106097794A CN106097794A CN201610596888.9A CN201610596888A CN106097794A CN 106097794 A CN106097794 A CN 106097794A CN 201610596888 A CN201610596888 A CN 201610596888A CN 106097794 A CN106097794 A CN 106097794A
- Authority
- CN
- China
- Prior art keywords
- card
- phonetic
- pinyin
- coding
- information
- 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
- 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
- G09B5/00—Electrically-operated educational appliances
- G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
- G09B5/065—Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Document Processing Apparatus (AREA)
Abstract
Reading learning system is recognized in the Chinese phonetic alphabet based on augmented reality combination, including the Pinyin card recognizing reading with phonetic picture, phonetic picture recognition module, pinyin combinations processing module, phonetic recognizes read through model and multi-media module, wherein said phonetic picture recognition module can be in the case of many Pinyin cards, call described pinyin combinations processing module to process getting phonetic data, the input that the outfan of described phonetic picture recognition module recognizes read through model with described phonetic is connected, to indicate from the multimedia unit reading to obtain and identify phonetic initial consonant and simple or compound vowel of a Chinese syllable combination formation in Pinyin card of recognizing with phonetic picture, the input of outfan and described multi-media module that described phonetic recognizes read through model is connected, with the concrete pronunciation after output pinyin combinations and the multimedia image of this pronunciation relevant;The described readable ard sheet with phonetic picture, is to be printed on phonetic initial consonant or the card of simple or compound vowel of a Chinese syllable image, and every card has been imprinted with possessing unique phonetic pattern identifying feature.
Description
Technical field
The invention belongs to augmented reality field, be specifically related to the combination of a kind of Chinese phonetic alphabet based on augmented reality and recognize reading
Learning system and method.
Background technology
Augmented reality (Augmented Reality, be called for short AR) technology be on the basis of virtual reality technology development and
The new technique come, is an important branch of virtual reality research.Augmented reality is by by computer picture skill
Art and visualization technique produce in actual environment and non-existent virtual objects, and virtual objects is fused to true ring exactly
In border, by virtual Information application to real world, thus present to the new environment that one effect of user is true to nature, to realize existing
Real enhancing and extension, the final goal of this technology is on screen, virtual world to be inserted in real world and carry out mutually
Dynamic.Augmented reality possesses following characteristics: first deficiency and excess combines, and indicator screen can be expanded to true environment, make meter by it
Calculate aircraft window mouth and chart is folded and mirrored real-world object;It two is real-time, interactive, and it makes to expand to whole ring from accurate position alternately
Border, develops into oneself be blended in the space of surrounding and object from simple people in the face of screen exchange.In augmented reality system
Typically all comprise following 4 basic steps: obtain real scene information;Real scene and camera location information are analyzed;
Generate virtual scene;Merge video or directly display.
In the prior art, the numeral that many use augmented realities are corresponding in traditional images information is converted into computer
Information draws single result, and is mostly based on the software application also the simplest conversion of augmented reality, i.e. one
Corresponding one of identification figure is easily recognized result;When scanning for multiple projects, the application of augmented reality does not provide pin
Combination to multiple recognition result produces corresponding result.
The Chinese phonetic alphabet is the important tool of learning Chinese characters, but the study of pure phonetic is abstract, uninteresting, in the face of just
Study phonetic, for the most active, attention is difficult to lasting child, the process of study phonetic is definitely one and chooses
War;Secondly, for abecedarian, initial consonant is also a big difficult point with difference and the collocation pronunciation of simple or compound vowel of a Chinese syllable.How to utilize enhancing
Reality technology realizes combining into syllables list is monosyllabic, also can realize combining the combination of two syllables into syllables simultaneously, be to merit our study
Problem.
Patent " a kind of learning system based on augmented reality and learning method thereof " (patent No.:
CN201110309866.7) providing one to utilize augmented reality to realize phonetic and know method for distinguishing, the method utilizes photographic head
Catch the phonetic marking pattern on reading matter carrier, then by a processor identification phonetic mark being provided with augmented reality software
Will, and judge the corresponding relation of phonetic mark and learning content, and then show on a display screen.Increase although this invention provides to utilize
Strong reality technology identification phonetic the method for the letter display relational learning video by identifying, but so simply identify tune
With not making up the interactive effect strengthened during pinyin learning, can not alphabetical profile based on card and character position,
Realize effective combination of reality syllable graph picture and virtual image.
Summary of the invention
The invention aims to overcome the weak point of above-mentioned background technology, answer based on to augmented reality
With, by an image acquisition equipment, the card with pinyin syllable can be carried out single pinyin syllable image or multiple phonetic sound
Joint combination image obtains, and utilizes the mode pattern Processing object of database retrieval, and provides single phonetic or pinyin combinations in real time
Voice, video and animation, fully combine the virtual object of phonetic figure in actual environment and generation.The present invention provides and contains institute
Reading recognized in the voice having the Chinese phonetic alphabet, is conducive in linguistic context environment repeatedly, forms the memory of unconscious phonetic, gives phonetic and begin to learn
The experience that person teaches through lively activities.
The present invention provides a kind of pinyin combinations based on augmented reality to recognize reading learning system and method, and its technical scheme is concrete
For:
The present invention, can be by an image acquisition equipment to pinyin syllable based on the application to augmented reality
Card carries out single pinyin syllable image or multiple pinyin syllable combination image obtains, place by the way of utilizing database retrieval
Reason pattern objects obtains card content information, provides single phonetic or the voice of pinyin combinations, video and animation in real time, by reality
Phonetic figure in environment is fully combined with the virtual object of generation.
The technical scheme is that, the Chinese phonetic alphabet based on augmented reality combination recognizes reading learning system, including with phonetic
The Pinyin card of reading recognized by picture, phonetic picture recognition module, pinyin combinations processing module, phonetic recognize read through model and multimedia mould
Block, wherein said phonetic picture recognition module can call described pinyin combinations processing module to obtaining in the case of many Pinyin cards
Getting phonetic data to process, the outfan of described phonetic picture recognition module and described phonetic recognize the input phase of read through model
Connect, to read Pinyin card obtains and identifies phonetic initial consonant and many matchmakers of simple or compound vowel of a Chinese syllable combination formation from recognizing of phonetic picture
Body unit indicates, and the input of outfan and described multi-media module that described phonetic recognizes read through model is connected, to export phonetic
Concrete pronunciation after combination and the multimedia image of this pronunciation relevant;
The described readable ard sheet with phonetic picture, is to be printed on phonetic initial consonant or the card of simple or compound vowel of a Chinese syllable image, and every card is all
It is printed on and possesses unique phonetic pattern identifying feature;
Initial consonant pattern and rhythm master pattern are independently printed, and each card is printed with phonetic alphabet pattern and sends out with this phonetic
The visualization pattern that sound is similar or font is similar, in card designs processes, monogram and visualization pattern are simultaneously as knowledge
Other foundation;
Described phonetic picture recognition module, i.e. can be used for realizing the identification module of augmented reality, and this identification module can be from print
Figuratum Pinyin card obtains relevant card content and the digital information of card position, the numeral of described relevant card content
Information is primarily with regard to the coding information of letter;The digital information of described relevant card position includes but is not limited to the row of many cards
Sequence, the space coordinates of card, the space coordinates (card position) of letter, card designs, card and the spacing of equipment;And other
Can be used for describing the information of Pinyin card content;
Described phonetic recognizes read through model, for receiving the digital information flow after data process, extracts the card in flow of information
Recognition coding, implements the retrieval of Pinyin information according to the coding got, and finds from multimedia database according to retrieval result
And call all coded multimedia informations of this pinyin combinations relevant;
Described multi-media module, for obtaining the many matchmakers recognizing the relevant card content that read through model sends from described phonetic
Body information encodes, and calls multimedia messages according to coding, many matchmakers such as including the relevant pronunciation of phonetic, video, threedimensional model, animation
Internal appearance, after multi-media module obtains coding, loads resource to internal memory according to coding, is eventually transferred to equipment from local or high in the clouds
End display screen.
Described pinyin combinations processing module, situation about combining for multiple Pinyin cards, putting position based on card and
The content of composite card performs contents processing, points out the card Realtime Alerts of anomaly association;For individual Pinyin card, according to
The content information of phonetic identification module transmission performs contents processing;
Described phonetic picture recognition module uses the mode of picture comparison, obtains the digital information about image content.
Situation about combining for multiple Pinyin cards, in image recognition processes, phonetic picture recognition module calls combination
Processing module, content based on the card putting position obtained and composite card performs combined arrangement and processes, to anomaly association
Card Realtime Alerts is pointed out.
The Chinese phonetic alphabet based on augmented reality is recognized reading learning system and is configurable on any one and possesses image scanning function
On intelligent apparatus, such as android system mobile phone, IOS system mobile phone, panel computer PC computer etc.;
A kind of Chinese phonetic alphabet based on augmented reality combination recognize read learning system recognize reading method, concrete steps include:
Step 1: the single or combination of syllable graph picture identifies;Utilization scans with photographic head or other possess identical function
Equipment, photographic head is directed at the Pinyin card identified, phonetic picture recognition module is by Pinyin card in reading photographic head region
On phonetic alphabet pattern and to this visualization pattern that pinyin syllable pronunciation is similar or font is similar, obtain the card of this card
Recognition coding, obtains the positional information of card, card and the relative distance of equipment, the space coordinates of card, and other simultaneously
Card content and the information put can be indicated;
Described card recognition encodes, and is used for and the phonetic pattern comparison prestored in systems;If comparison success, it is thus achieved that this spelling
The coding information of sound pattern combines coding into syllables as card recognition;
The positional information of described card, in the case of combining at many cards, the arrangement of the Pinyin card identified
Position;
Described card and the relative distance of equipment, designation equipment and the spacing of the Pinyin card identified, surveyed in order to the later stage
Calculate the size of device screen display figure;
The space coordinates of described card, for designation equipment relative to the deflection of the Pinyin card identified and angle, fixed
The position later stage is about the display position at device screen of the animation of phonetic pronunciation;
Especially, for the acquisition of the pinyin combinations image information of multiple Pinyin cards, phonetic picture recognition module can be same
Time read the information of all Pinyin cards, and according to combining the letter of relevant syllable graph picture that custom will get the most successively into syllables
Breath is sequentially delivered to Chinese phonetic alphabet combination module and processes;
Step 2: the process of phonetic image coding information, phonetic recognizes the read through model Pinyin card identification code to being identified or group
The relative distance of the positional information of the Pinyin card combining coding into syllables, being identified, card and the equipment that close, between equipment and card
Carry out data process away from, the space coordinates of card and other information that can be used for indicating card content, obtain and include combining sound into syllables
Frequently, three-dimensional animation, the multimedia coding of displaying video;Concrete steps include:
Step 2-1: phonetic is recognized read through model and received image information stream, therefrom extracts identification code or the card combination of Pinyin card
Combine coding into syllables;
The identification code of Pinyin card be for scanning single letter in the case of Pinyin coding;What card combined combines coding into syllables
It is for the Pinyin coding scanned under multiple phonetic alphabet combined situation;
Step 2-2: according to identification code or the Pinyin coding of card combination of Pinyin card, retrieve in multimedia database
The multimedia coding corresponding with described Pinyin coding;
Step 2-3: phonetic is recognized read through model and extracted the information about card position from image information stream, including card with set
Standby relative distance, equipment and the spacing of card, the space coordinates of card;Based on the positional information got, pass through Three-dimensional Gravity
Position data is processed by the mode of structure, positions the display size and location coordinate of the three-dimensional animation about phonetic;
Step 3: transferring of multimedia messages;Multi-media module receives recognizes, via phonetic, the many matchmakers sent after read through model processes
Body encodes, and searches for and transfer the audio object of correspondence, object video, in real time based on coding from server end or local media library
The multimedia objects such as three-dimensional animation object, letter sequential write animation;
Especially, for the multiple multimedia objects got, multi-media module can be based on the Pinyin card identified
Spatial coordinated information, the multiple multimedia objects described in superposition, including three-dimensional animation, the audio frequency of pinyin pronunciation and video;
Step 4: the projection of multimedia messages;Multi-media module recognizes the card position obtained after read through model processes according to phonetic
Information, card content information and monogram and the relative position information of equipment, send content of multimedia after arrangement to equipment
End display;Use and recognize the user reading learning system, equipment end display screen is seen the phonetic relevant to identified Pinyin card
Dynamic image, phonetic pronunciation audio frequency and other multimedia objects prestored;
Especially, according to card position, card content, the relative position of monogram and equipment, it is ensured that screen shows
Multimedia animation fits like a glove with monogram.
In described step 1, situation about combining for multiple Pinyin cards, phonetic picture recognition module is identifying each
During phonetic alphabet on card, call correcting errors of pinyin combinations processing module automatic decision phonetic alphabet combination, specifically include: step
Phonetic alphabet that rapid 1-1: phonetic picture recognition module reads in screen in multiple Pinyin cards simultaneously and similar to letter pronunciation
Visualization pattern, obtain card recognition coding, simultaneously according to the positional information put before and after each identified Pinyin card,
By being identified that Pinyin card sorts;
Described card recognition coding is divided into consonant coding and simple or compound vowel of a Chinese syllable coding, encodes and compiles according to the alphabetical syllable of phonetic self
System, all code storage are in described Pinyin coding storehouse;
Step 1-2: sequence based on every Pinyin card and Pinyin card recognition coding, pinyin combinations processing module combines
Pinyin card recognition coding, whether obtain pinyin combinations combines coding into syllables, deposit according to combining into syllables to encode to inquire about in combinating Pinyin storehouse
At identical phonetic record, if it does, go to step 1-3;Otherwise go to step 1-4;
Described combinating Pinyin storehouse, combines identification code into syllables for deposit all combinating Pinyins;And only it is present in combinating Pinyin
Storehouse combines identification code into syllables, is just recognized Pinyin card combination correct;
Step 1-3: step 1-2 obtained combines coding, card combination positional information and the relative distance of equipment, sky into syllables
Between coordinate and other information that can be used for describing card sets co content and position, be sent to phonetic and recognize read through model;
Step 1-4: report to the police;Return " combining mistake into syllables " on the screen of equipment end, in card is changed in prompting, perhaps card is suitable
Sequence.
In the multimedia messages of described step 4 is shown, according to display position and the size of the multimedia object calculated,
At card three-dimensional animation present above, and three-dimensional animation keeps consistent with the visualization pattern in card, three-dimensional animation and reality
Pinyin card in environment fully combines.
In the multimedia messages of described step 4 is shown, according to the display space coordinate of the multimedia object calculated and
Size, according to the card character position presented in screen and size, along letter shapes, in the way of learning to write by tracing over characters printed in red, presents letter
The animation of sequential write.
The present invention compared with prior art, the method have the benefit that
(1) present invention is by by image acquisition equipment, based on the use to augmented reality, through capturing equipment
Card on phonetic pattern-information immediately process, call this locality or the multimedia resource in server high in the clouds, in real time by reality
Pinyin card image in environment is combined with virtual object, the multimedia object of generation, shows the voice about this pinyin syllable, regards
Frequency and animation, by the pronunciation of the Chinese phonetic alphabet, write, visual association image combines, and contributes in linguistic context environment, formed
Unconscious phonetic is remembered, and gives the experience that phonetic abecedarian teaches through lively activities;
(2) present invention provides initial consonant and the separate Pinyin card of simple or compound vowel of a Chinese syllable, utilizes monogram similar with letter pronunciation
Visualization pattern as identify letter foundation, reduce because letter profile similar and cause identification error;Reading is recognized at card
During, by combinatorial search and timely feedback mechanism, not only realize that single Pinyin card is recognized reading and also realize many phonetic card
What sheet combined recognizes reading, realizes many cards are combined the Instant alarming corrected errors simultaneously, breaks through the application of existing augmented reality and does not carries
Predicament for the combination of many recognition results.
Accompanying drawing explanation
Fig. 1 is that in the embodiment of the present invention, the module map reading learning system is recognized in the Chinese phonetic alphabet based on augmented reality combination;
In Fig. 2, A, B are printed on two kinds of readable ard sheets of unique syllable graph pattern identification in being the embodiment of the present invention;
Fig. 3 is that the phonetic that in the embodiment of the present invention, card mistake is placed recognizes reading schematic flow sheet;
Fig. 4 is the schematic diagram of card combination failure alarms in the embodiment of the present invention;
Fig. 5 is that in the embodiment of the present invention, pinyin combinations recognizes the schematic flow sheet reading learning method;
Fig. 6 is that in the embodiment of the present invention, pinyin combinations recognizes the schematic diagram reading study;
Fig. 7 is that in the embodiment of the present invention, the card figure of single phonetic alphabet has three-dimensional animation schematic diagram simultaneously (upper and lower two figures divide
Not Biao Shi);
Fig. 8 is the sequential write animation schematic diagram of single phonetic alphabet in the embodiment of the present invention.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Accompanying drawing, the present invention is described in more detail.
The present invention, can be by an image acquisition equipment to pinyin syllable based on the application to augmented reality
Card carries out single pinyin syllable image or multiple pinyin syllable combination image obtains, by the way of utilizing database retrieval
Pattern Processing object acquisition card content information, provides single phonetic or the voice of pinyin combinations, video and animation in real time, will be existing
Phonetic figure in real environment is fully combined with the virtual object of generation.
Similarity is there is in shape due to subalphbet, thus merely exist according to letter profile identification letter and know
Other error, technical solution of the present invention judges with the visualization pattern of this similar pronunciation of letter syllable according to letter profile simultaneously simultaneously
Letter, improves the degree of accuracy of Letter identification;
Described card recognition encodes, and is used for and the phonetic pattern comparison prestored in systems;If comparison success, it is thus achieved that this spelling
The coding information of sound pattern encodes as card recognition thing;
The positional information of described card, in the case of combining at many cards, the arrangement position of identification card;
Described card and the relative distance of equipment, designation equipment and the spacing of card, show in order to later stage measuring and calculating device screen
The size of diagram shape;
The space coordinates of described card, for designation equipment relative to the deflection of card and angle, the location later stage is relevant spells
The display position at device screen of the animation of pronunciation sound;
Especially, for the acquisition of the pinyin combinations image information of multiple Pinyin cards, phonetic picture recognition module can be same
Time read the information of all Pinyin cards, and according to combining the letter of relevant syllable graph picture that custom will get the most successively into syllables
Breath is sequentially delivered to Chinese phonetic alphabet combination module and processes;
Especially, situation about combining for multiple Pinyin cards, phonetic picture recognition module is identifying on each card
Phonetic alphabet time, pinyin combinations processing module energy automatic decision phonetic alphabet combination correct errors, specifically include:
Step 1-1: phonetic picture recognition module reads the phonetic alphabet in screen multiple Pinyin cards interior and and word simultaneously
The visualization pattern that female pronunciation is similar, obtains card recognition coding, simultaneously according to the positional information put before and after each card,
Sort for card;
Described card recognition coding is divided into consonant coding and simple or compound vowel of a Chinese syllable coding, encodes and compiles according to the alphabetical syllable of phonetic self
System, i.e. simple or compound vowel of a Chinese syllable (a, o, e, i, u, ü) is just encoded into (a, o, e, i, u, _ u), the establishment of initial consonant equivalent simple or compound vowel of a Chinese syllable;All code storage
In described Pinyin coding storehouse;
Step 1-2: sequence based on every card and card recognition coding, pinyin combinations processing module combinating Pinyin card
Recognition coding, obtain pinyin combinations combines coding into syllables, according to combine into syllables coding inquire about in combinating Pinyin storehouse whether exist identical
Phonetic record, if it does, go to step 1-3;Otherwise go to step 1-4;
Described combinating Pinyin storehouse, combines identification code into syllables for deposit all combinating Pinyins;And only it is present in combinating Pinyin
Storehouse combines identification code into syllables, is just recognized card combination correct;
Step 1-3: step 1-2 obtained combines coding, card combination positional information and the relative distance of equipment, sky into syllables
Between coordinate and other information that can be used for describing card sets co content and position, be sent to phonetic and recognize read through model;
Step 1-4: report to the police;Return " combining mistake into syllables " on the screen of equipment end, in card is changed in prompting, perhaps card is suitable
Sequence;
Step 2: the process of phonetic image information, mainly phonetic are recognized read through model and card identification code or combination are combined into syllables volume
The relative distance of code, the positional information of card, card and equipment, equipment and the spacing of card, the space coordinates of card, Yi Jiqi
He can be used for indicating the information of card content and carry out data process, obtains and includes combining into syllables audio frequency, three-dimensional animation, displaying video
Multimedia coding;Concrete steps include:
Step 2-1: phonetic is recognized read through model and received image information stream, therefrom extracts identification code or the card combination of Pinyin card
Combine coding into syllables;
Especially, the Pinyin coding in the case of the identification code of Pinyin card is for scanning single letter;Card combination
Combining coding into syllables is for the Pinyin coding scanned under multiple phonetic alphabet combined situation;
Step 2-2: combine coding into syllables according to the identification code of Pinyin card or card combination, retrieves in multimedia database
The multimedia coding corresponding with described Pinyin coding;
Step 2-3: phonetic is recognized read through model and extracted the information about card position from image information stream, including card with set
Standby relative distance, equipment and the spacing of card, the space coordinates of card;Based on the positional information got, pass through Three-dimensional Gravity
Position data is processed by the mode of structure, positions the display size and location coordinate of the three-dimensional animation about phonetic;
Step 3: transferring of multimedia messages;Multi-media module receives recognizes, via phonetic, the many matchmakers sent after read through model processes
Body encodes, and searches for and transfer the audio object of correspondence, object video, in real time based on coding from server end or local media library
The multimedia objects such as three-dimensional animation object, letter sequential write animation;
Especially, for the multiple multimedia objects got, multi-media module can spatial coordinated information based on card,
Multiple multimedia objects described in superposition;
Step 4: the projection of multimedia messages;Multi-media module recognizes the card position obtained after read through model processes according to phonetic
Information, card content information and monogram and the relative position information of equipment, send content of multimedia after arrangement to equipment
End display;Use the user recognizing reading learning system in the present invention, see relevant to Pinyin card in equipment end display screen
The Overlapping displays such as phonetic dynamic image, phonetic pronunciation audio frequency are in this current phonetic
Especially, according to card position, card content, the relative position of monogram and equipment, it is ensured that screen shows
The animation of phonetic alphabet sequential write fits like a glove with monogram;
Embodiment: refering to shown in Fig. 1, specifically include and be printed on the readable ard sheet 101 of phonetic picture, phonetic picture recognition module
102, pinyin combinations processing module 103, phonetic recognize read through model 104 and multi-media module 105, wherein said phonetic image recognition mould
Block 102 can call described pinyin combinations processing module 103 and process getting phonetic data in the case of many cards, institute
The input that the outfan stating phonetic picture recognition module 102 recognizes read through model 104 with described phonetic is connected, with from phonetic
The multimedia unit obtaining and identifying phonetic initial consonant and simple or compound vowel of a Chinese syllable combination formation in the readable ard sheet of picture indicates, and described phonetic is recognized
The outfan of read through model 104 is connected with the input of described multi-media module 105, to export the concrete pronunciation after pinyin combinations
And the multimedia image of this pronunciation of being correlated with;
The described readable ard sheet 101 with phonetic picture, is to be printed on phonetic initial consonant or the card of simple or compound vowel of a Chinese syllable image, every card
Have been imprinted with possessing unique phonetic pattern identifying feature;Referring particularly to shown in Fig. 2
Especially, initial consonant pattern and rhythm master pattern are independently printed on card, and each card is printed with phonetic alphabet figure
Case and similar to this pinyin pronunciation or that font is similar visualization pattern, in card designs processes, monogram and visualization
Pattern simultaneously as basis of characterization, such as phonetic alphabet " n " and " h ", letter " n " is furnished with the pattern of arched door, letter " h " according to
Pronunciation is furnished with the pattern of Flos Nelumbinis, forms well-defined figure after binary conversion treatment, and the lines of figure substantially protrude exterior view
Case and monogram, and Figure recognition result possesses the strongest uniqueness;
Described phonetic picture recognition module 102, i.e. can be used for realizing the identification module of augmented reality, and this identification module can be from
Print and figuratum Pinyin card obtains relevant card content and the digital information of card position, the number of described relevant card content
Word information is primarily with regard to the coding information of letter;The digital information of described relevant card position includes but is not limited to many cards
Sequence, the space coordinates of card, the space coordinates of letter, card and the spacing of equipment;
Especially, phonetic picture recognition module uses the mode of picture comparison, obtains the digital information about image content,
I.e. card recognition coding;
Described pinyin combinations processing module 103, situation about combining for multiple Pinyin cards, in image recognition processes,
Phonetic picture recognition module 102 calls combined treatment module 103, based on the card putting position obtained and the content of composite card
Execution combined arrangement processes, and points out the card Realtime Alerts of anomaly association;
Described phonetic recognizes read through model 104, for receiving the digital information flow after data process, extracts the card in flow of information
Sheet recognition coding, implements the retrieval of Pinyin information according to the coding got, and seeks from multimedia database according to retrieval result
Look for and call all coded multimedia informations of this pinyin combinations relevant;
Described multi-media module 105, recognizes, from described phonetic, relevant card content that read through model sends for obtaining
Coded multimedia information, calls multimedia messages according to coding, including the relevant pronunciation of phonetic, video, threedimensional model, animation etc.
Content of multimedia, after multi-media module obtains coding, loads resource to internal memory according to coding, is eventually transferred to from local or high in the clouds
Equipment end display screen;
Described Pinyin coding be divided into consonant coding and simple or compound vowel of a Chinese syllable coding, encode according to pinyin syllable work out, such as simple or compound vowel of a Chinese syllable (a, o,
E, i, u, ü) just it is encoded into (a, o, e, i, u, _ u), all code storage are in described Pinyin coding storehouse;
Recognize reading learning system based on the combination of a kind of Chinese phonetic alphabet based on augmented reality, the embodiment of the present invention utilizes described
Recognizing reading learning system study phonetic " zhang ", Fig. 3 is that the phonetic that in the embodiment of the present invention, card mistake is placed recognizes reading flow process signal
Figure, specifically includes:
Step 301: use android system mobile phone to log in Chinese phonetic alphabet group based on augmented reality in the embodiment of the present invention
Reading learning system is recognized in conjunction, utilizes mobile phone camera alignment Pinyin card " zh " and " ang ", and card placement order depends on from left to right
Secondary is " ang " and " zh ";
Step 302: the phonetic picture recognition module 102 recognizing read apparatus processes every card by the way of image binaryzation
On pattern, the card " zh " of process is using letter " zh " and background patterns " Aranea " as unique foundation of picture;The card processed
Sheet " ang " is using letter " ang " and background patterns " sheep " as the foundation of picture;The position of log sheet the most from left to right, i.e.
The position of card " ang " is 1, and the position of card " zh " is 2;
Step 303: treated card designs is compared with the local pattern that prestores, after comparison success, card " zh "
Obtain card identification code " zh ";Card " ang " obtains card identification code " ang ";
Step 304: call pinyin combinations processing module, according to the card position in step 402 and the card in step 403
Coding is combined, and obtain pinyin combinations combines coding " angzh " into syllables;
Step 305: find in combinating Pinyin data base and combine coding " angzh " into syllables;
Step 306: the pinyin combinations coding correct owing to only there being spelling in combinating Pinyin data base, and " angzh " deposits
At apparent error, device screen is reported to the police " cacography ", is seen Fig. 4;
Fig. 5 is that in the embodiment of the present invention, pinyin combinations recognizes the schematic flow sheet reading learning method, embodiment of the present invention middle school
The phonetic practised is
Step 501: use android system mobile phone to log in Chinese phonetic alphabet group based on augmented reality in the embodiment of the present invention
Reading learning system is recognized in conjunction, utilizes mobile phone camera alignment Pinyin card " zh " and " ang ", and card placement order depends on from left to right
Secondary is " zh " and " ang ";
Step 502: the phonetic picture recognition module 102 recognizing read apparatus processes every card by the way of image binaryzation
On pattern, the card " zh " after process is using letter " zh " and background patterns " Aranea " as unique foundation of picture;After process
Card " ang " using letter " ang " and background patterns " sheep " as the foundation of picture;The arrangement position of log sheet from left to right
Put, i.e. the position of card " zh " is 1, and the position of card " ang " is 2, and the space of the space coordinates of card, card letter is sat
The distance of mark, card and android system mobile phone;
Step 503: treated card designs is compared with the local pattern that prestores, after comparison success, card " zh "
Obtain card identification code " zh ";Card " ang " obtains card identification code " ang ";
Step 504: call pinyin combinations processing module 103, according in the card position in step 402 and step 403
Card code is combined, and obtain pinyin combinations combines coding " zhang " into syllables;
Step 505: search out in combinating Pinyin data base and combine coding " zhang " into syllables, confirms that card is put errorless;
Step 506: phonetic picture recognition module 102 will combine coding " zhang " and the positional information about card into syllables, including
The distance of space coordinates, card and the android system mobile phone of the space coordinates of card, card letter, with image data stream
Form is sent to phonetic and recognizes read through model 104;
Step 507: phonetic is recognized read through model 104 and extracted and combine coding " zhang " in flow of information into syllables, according to " zhang " many matchmakers
In body storehouse, search combines the multimedia coding of audio frequency into syllables;
Step 508: phonetic recognize read through model 104 extract the space coordinates of card in flow of information, card letter space coordinates,
Card and the distance of android system mobile phone, calculate position coordinates and display size that multimedia object shows;
Step 509: multi-media module 105, according to multimedia coding, loads audio object and red word from server high in the clouds
Body object;And red font object according to card space coordinates, card letter space coordinates, card and android system
The distance of mobile phone, fits completely with the card letter in device screen, marks the phonetic alphabet chosen in order to emphasis, sees Fig. 6;
The present invention also provides for recognizing reading learning method for the phonetic based on augmented reality of single phonetic alphabet, and the present invention implements
In example as a example by study single letter " zh ";The card that read through model 104 obtains is recognized based on phonetic picture recognition module 102 and phonetic
Identification code and card position information, confirm the letter on card and the space coordinates of card, the space coordinates of card letter, card
Sheet and the distance of android system mobile phone;
Further, multimedia coding is found according to card recognition code at multimedia gallery;Space coordinates according to card, card
The distance of space coordinates, card and the android system mobile phone of sheet letter, animation write in calculating three-dimensional animation object, letter
Position and size;
Further, multi-media module, according to multimedia coding, calls the audio frequency in service high in the clouds, calls multimedia money simultaneously
Source shows to mobile phone screen end, specifically includes:
(1) according to display position and the size of the multimedia object calculated, at card three-dimensional animation present above, and three
Dimension animation keeps consistent with the visualization pattern in card, sees upper and lower two figures of Fig. 7 (can be with screen);
(2) according to display space coordinate and the size of the multimedia object calculated, according to the card presented in screen
Character position and size, along letter shapes, in the way of learning to write by tracing over characters printed in red, present the animation of letter sequential write, see Fig. 8;
Those of ordinary skill in the field it is understood that the foregoing is only the specific embodiment of the present invention, and
Be not used in the restriction present invention, all within the spirit and principles in the present invention, any modification, equivalent substitution and improvement etc. done, all
Within protection scope of the present invention should being included in.
Claims (8)
1. the Chinese phonetic alphabet based on augmented reality combination recognize reading learning system, including recognize with phonetic picture reading Pinyin card,
Phonetic picture recognition module, pinyin combinations processing module, phonetic recognize read through model and multi-media module, and wherein said syllable graph picture is known
Other module can be called described pinyin combinations processing module and process getting phonetic data in the case of many Pinyin cards,
The input that the outfan of described phonetic picture recognition module recognizes read through model with described phonetic is connected, with from phonetic picture
Recognize and read Pinyin card obtains and identifies phonetic initial consonant and multimedia unit that simple or compound vowel of a Chinese syllable combination is formed indicates, described phonetic is recognized
The outfan of read through model is connected with the input of described multi-media module, to export the concrete pronunciation after pinyin combinations and relevant
The multimedia image of this pronunciation;
The described readable ard sheet with phonetic picture, is to be printed on phonetic initial consonant or the card of simple or compound vowel of a Chinese syllable image, and every card has been imprinted with
Possesses unique phonetic pattern identifying feature;
Initial consonant pattern and rhythm master pattern are independently printed, and each card be printed with phonetic alphabet pattern and with this pinyin pronunciation phase
Like or the similar visualization pattern of font, in card designs processes, monogram and visualization pattern depend on simultaneously as identification
According to;
Described phonetic picture recognition module, i.e. can be used for realizing the identification module of augmented reality, and this identification module can be from being printed on figure
The Pinyin card of case obtains relevant card content and the digital information of card position, the digital information of described relevant card content
Coding information primarily with regard to letter;The digital information of described relevant card position include but be not limited to many cards sequence,
The space coordinates of card, the space coordinates (card position) of letter, card designs, card and the spacing of equipment;And other can
For describing the information of Pinyin card content;
Described phonetic recognizes read through model, for receiving the digital information flow after data process, extracts the card recognition in flow of information
Coding, implements the retrieval of Pinyin information according to the coding got, and finds according to retrieval result and adjusts from multimedia database
All coded multimedia informations by this pinyin combinations relevant;
Described multi-media module, for obtaining the multimedia letter recognizing the relevant card content that read through model sends from described phonetic
Breath coding, calls multimedia messages according to coding, including the relevant pronunciation of phonetic, video, threedimensional model, in the multimedia such as animation
Hold, after multi-media module obtains coding, load resource from local or high in the clouds to internal memory according to coding, be eventually transferred to equipment end and show
Display screen;
Described pinyin combinations processing module, situation about combining for multiple Pinyin cards, putting position based on card and combination
The content of card performs contents processing, points out the card Realtime Alerts of anomaly association;For individual Pinyin card, according to phonetic
The content information of identification module transmission performs contents processing.
Reading learning system recognized in the Chinese phonetic alphabet based on augmented reality the most according to claim 1, it is characterised in that described spelling
Sound picture recognition module uses the mode of picture comparison, obtains the digital information about image content.
Reading learning system recognized in the Chinese phonetic alphabet based on augmented reality the most according to claim 1, it is characterised in that for many
Opening the situation of Pinyin card combination, in image recognition processes, phonetic picture recognition module calls combined treatment module, based on obtaining
The card putting position taken and the content of composite card perform combined arrangement and process, and carry the card Realtime Alerts of anomaly association
Show.
Reading learning system recognized in the Chinese phonetic alphabet based on augmented reality the most according to claim 1, it is characterised in that the present invention
In the Chinese phonetic alphabet based on augmented reality recognize reading learning system be configurable on any one intelligence possessing image scanning function
On device, such as android system mobile phone, IOS system mobile phone, panel computer etc..
5. the Chinese phonetic alphabet based on augmented reality combination recognize read learning system recognize a reading method, it is characterized in that step includes:
Step 1: the single or combination of syllable graph picture identifies;Utilization scans with photographic head or other possess setting of identical function
Standby, photographic head is directed at the Pinyin card identified, phonetic picture recognition module is by Pinyin card in reading photographic head region
Phonetic alphabet pattern and to this visualization pattern that pinyin syllable pronunciation is similar or font is similar, obtain this card card know
Do not encode, obtain the positional information of card, card and the relative distance of equipment, the space coordinates of card, and other energy simultaneously
Mark card content and the information put;
Described card recognition encodes, and is used for and the phonetic pattern comparison prestored in systems;If comparison success, it is thus achieved that this syllable graph
The coding information of case combines coding into syllables as card recognition;
The positional information of described card, in the case of combining at many cards, the arrangement position of the Pinyin card identified;
Described card and the relative distance of equipment, designation equipment and the spacing of the Pinyin card identified, set in order to later stage measuring and calculating
The size of standby screen display figure;
The space coordinates of described card, for designation equipment relative to the deflection of the Pinyin card identified and angle, behind location
Phase is about the display position at device screen of the animation of phonetic pronunciation;
Especially, for the acquisition of the pinyin combinations image information of multiple Pinyin cards, phonetic picture recognition module can be read simultaneously
Take the information of all Pinyin cards, and the most successively the information of the relevant syllable graph picture got is depended on according to combining custom into syllables
The secondary Chinese phonetic alphabet combination module that is sent to processes;
Step 2: the process of phonetic image coding information, phonetic recognizes the read through model Pinyin card identification code to being identified or combination
The positional information of the Pinyin card combine coding into syllables, being identified, card and the relative distance of equipment, equipment and the spacing of card, card
The space coordinates of sheet and other information that can be used for indicating card content carry out data process, obtain include combining into syllables audio frequency, three
Dimension animation, the multimedia coding of displaying video;Concrete steps include:
Step 2-1: phonetic is recognized read through model and received image information stream, therefrom extracts identification code or the spelling of card combination of Pinyin card
Read coding;
The identification code of Pinyin card be for scanning single letter in the case of Pinyin coding;The coding that combines into syllables of card combination is pin
To the Pinyin coding scanned under multiple phonetic alphabet combined situation;
Step 2-2: according to identification code or the Pinyin coding of card combination of Pinyin card, retrieval and institute in multimedia database
State the multimedia coding that Pinyin coding is corresponding;
Step 2-3: phonetic is recognized read through model and extracted the information about card position from image information stream, including card and equipment
Relative distance, equipment and the spacing of card, the space coordinates of card;Based on the positional information got, by three-dimensionalreconstruction
Position data is processed by mode, positions the display size and location coordinate of the three-dimensional animation about phonetic;
Step 3: transferring of multimedia messages;Multi-media module receives recognizes the multimedia volume sent after read through model processes via phonetic
Code, searches for and transfers the audio object of correspondence, object video, real-time three-dimensional based on coding from server end or local media library
The multimedia objects such as animation object, letter sequential write animation;
Especially, for the multiple multimedia objects got, multi-media module can be based on the space of the Pinyin card identified
Coordinate information, the multiple multimedia objects described in superposition, including three-dimensional animation, the audio frequency of pinyin pronunciation and video;
Step 4: the projection of multimedia messages;Multi-media module recognizes the card position letter obtained after read through model processes according to phonetic
Breath, card content information and monogram and the relative position information of equipment, send content of multimedia after arrangement to equipment end
Display;Use and recognize the user reading learning system, in equipment end display screen, see that the phonetic relevant to identified Pinyin card moves
State image, phonetic pronunciation audio frequency and other multimedia objects prestored;
Especially, according to card position, card content, the relative position of monogram and equipment, it is ensured that many matchmakers that screen shows
Body animation fits like a glove with monogram.
The most according to claim 5 recognize reading method, it is characterized in that, in described step 1, combining for multiple Pinyin cards
Situation, phonetic picture recognition module, when identifying the phonetic alphabet on each card, is called
Correcting errors of pinyin combinations processing module automatic decision phonetic alphabet combination, specifically includes: step 1-1: phonetic image recognition
Module reads the phonetic alphabet in screen multiple Pinyin cards interior and the visualization pattern similar to letter pronunciation simultaneously, obtains card
Sheet recognition coding, simultaneously according to the positional information put before and after each identified Pinyin card, by being identified that Pinyin card is arranged
Sequence;
Described card recognition coding is divided into consonant coding and simple or compound vowel of a Chinese syllable coding, encodes and works out according to the alphabetical syllable of phonetic self, institute
There is code storage in described Pinyin coding storehouse;
Step 1-2: sequence based on every Pinyin card and Pinyin card recognition coding, pinyin combinations processing module combinating Pinyin
Card recognition encodes, and obtain pinyin combinations combines coding into syllables, according to combining coding inquires about whether there is phase in combinating Pinyin storehouse into syllables
Same phonetic record, if it does, go to step 1-3;Otherwise go to step 1-4;
Described combinating Pinyin storehouse, combines identification code into syllables for deposit all combinating Pinyins;And be only present in combinating Pinyin storehouse
Combine identification code into syllables, be just recognized Pinyin card combination correct;
Step 1-3: combine into syllables coding, card combination positional information and the relative distance of equipment, the space that step 1-2 are obtained are sat
It is marked with and other information that can be used for describing card sets co content and position, is sent to phonetic and recognizes read through model;
Step 1-4: report to the police;Return " combining mistake into syllables " on the screen of equipment end, perhaps card order is changed in card in prompting.
The most according to claim 5 recognize reading method, it is characterized in that in the multimedia messages of described step 4 is shown, according to
The display position of the multimedia object calculated and size, at card three-dimensional animation present above, and in three-dimensional animation and card
Visualization pattern keep consistent, three-dimensional animation Pinyin card in actual environment is fully combined.
The most according to claim 5 recognize reading method, it is characterized in that in the multimedia messages of described step 4 is shown, according to
The display space coordinate of the multimedia object calculated and size, according to the card character position presented in screen and size,
Along letter shapes, in the way of learning to write by tracing over characters printed in red, present the animation of letter sequential write.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610596888.9A CN106097794A (en) | 2016-07-25 | 2016-07-25 | The Chinese phonetic alphabet based on augmented reality combination is recognized reading learning system and recognizes reading method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610596888.9A CN106097794A (en) | 2016-07-25 | 2016-07-25 | The Chinese phonetic alphabet based on augmented reality combination is recognized reading learning system and recognizes reading method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106097794A true CN106097794A (en) | 2016-11-09 |
Family
ID=57450575
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610596888.9A Pending CN106097794A (en) | 2016-07-25 | 2016-07-25 | The Chinese phonetic alphabet based on augmented reality combination is recognized reading learning system and recognizes reading method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106097794A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106658173A (en) * | 2017-02-16 | 2017-05-10 | 成都市极米科技有限公司 | Video display method, device and system |
CN106710372A (en) * | 2017-01-11 | 2017-05-24 | 成都市极米科技有限公司 | Pinyin card identification method, device and terminal device |
CN107610236A (en) * | 2017-08-21 | 2018-01-19 | 武汉秀宝软件有限公司 | A kind of exchange method and system based on figure identification |
CN108170817A (en) * | 2017-12-29 | 2018-06-15 | 努比亚技术有限公司 | Differentiation video acquiring method, device and the readable storage medium storing program for executing of photo main body |
CN108595531A (en) * | 2018-03-30 | 2018-09-28 | 孙博 | Spell training method, system, computer equipment and storage medium |
CN108986569A (en) * | 2018-08-24 | 2018-12-11 | 深圳市玩瞳科技有限公司 | A kind of desktop AR interactive learning method and device |
CN109215411A (en) * | 2018-08-24 | 2019-01-15 | 深圳市博悦生活用品有限公司 | A kind of mutual education method and system |
CN109754644A (en) * | 2017-11-06 | 2019-05-14 | 彼乐智慧科技(北京)有限公司 | A kind of teaching method and system based on augmented reality |
CN110379227A (en) * | 2019-07-19 | 2019-10-25 | 中原工学院 | A kind of students' Chinese voice on-line study system |
CN111681467A (en) * | 2020-06-01 | 2020-09-18 | 广东小天才科技有限公司 | Vocabulary learning method, electronic equipment and storage medium |
CN112927571A (en) * | 2021-03-03 | 2021-06-08 | 广东富利时实业有限公司 | Teaching system based on AR recognition |
CN112926586A (en) * | 2021-02-19 | 2021-06-08 | 北京大米未来科技有限公司 | Text recognition method and device, readable storage medium and electronic equipment |
CN113393719A (en) * | 2021-06-30 | 2021-09-14 | 张家口智趣学科技有限公司 | Pinyin learning method and device |
CN114220301A (en) * | 2021-12-20 | 2022-03-22 | 深圳市卓俊文化科技有限公司 | Chinese character spelling and reading terminal and method for teaching |
CN113611173B (en) * | 2021-09-07 | 2023-11-14 | 福建铭塔玩具股份有限公司 | Chinese character spelling machine and its realizing method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20100058843A (en) * | 2008-11-25 | 2010-06-04 | 세종대학교산학협력단 | Method and system for teaching hangeul using augmented reality |
CN101923791A (en) * | 2010-05-31 | 2010-12-22 | 华中师范大学 | Method for learning Chinese by combining reality enhancing technique and plane reading material |
CN102509484A (en) * | 2011-10-13 | 2012-06-20 | 苏州梦想人软件科技有限公司 | Learning system based on augmented reality technology and learning method thereof |
CN103310099A (en) * | 2013-05-30 | 2013-09-18 | 佛山电视台南海分台 | Method and system for realizing augmented reality by adopting image capture and recognition technology |
CN103544724A (en) * | 2013-05-27 | 2014-01-29 | 华夏动漫集团有限公司 | System and method for realizing fictional cartoon character on mobile intelligent terminal by augmented reality and card recognition technology |
CN103745214A (en) * | 2014-01-08 | 2014-04-23 | 广东小天才科技有限公司 | Character recognition method and recognition equipment |
-
2016
- 2016-07-25 CN CN201610596888.9A patent/CN106097794A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20100058843A (en) * | 2008-11-25 | 2010-06-04 | 세종대학교산학협력단 | Method and system for teaching hangeul using augmented reality |
CN101923791A (en) * | 2010-05-31 | 2010-12-22 | 华中师范大学 | Method for learning Chinese by combining reality enhancing technique and plane reading material |
CN102509484A (en) * | 2011-10-13 | 2012-06-20 | 苏州梦想人软件科技有限公司 | Learning system based on augmented reality technology and learning method thereof |
CN103544724A (en) * | 2013-05-27 | 2014-01-29 | 华夏动漫集团有限公司 | System and method for realizing fictional cartoon character on mobile intelligent terminal by augmented reality and card recognition technology |
CN103310099A (en) * | 2013-05-30 | 2013-09-18 | 佛山电视台南海分台 | Method and system for realizing augmented reality by adopting image capture and recognition technology |
CN103745214A (en) * | 2014-01-08 | 2014-04-23 | 广东小天才科技有限公司 | Character recognition method and recognition equipment |
Non-Patent Citations (2)
Title |
---|
李铁萌等: "基于增强现实的学前儿童识字教育系统及实验研究", 《软件》 * |
王清 等: "基于增强现实的安卓英语单词识记软件的设计与实现", 《计算机教学与教育信息化》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106710372A (en) * | 2017-01-11 | 2017-05-24 | 成都市极米科技有限公司 | Pinyin card identification method, device and terminal device |
CN106658173A (en) * | 2017-02-16 | 2017-05-10 | 成都市极米科技有限公司 | Video display method, device and system |
CN107610236B (en) * | 2017-08-21 | 2021-05-11 | 武汉秀宝软件有限公司 | Interaction method and system based on graph recognition |
CN107610236A (en) * | 2017-08-21 | 2018-01-19 | 武汉秀宝软件有限公司 | A kind of exchange method and system based on figure identification |
CN109754644A (en) * | 2017-11-06 | 2019-05-14 | 彼乐智慧科技(北京)有限公司 | A kind of teaching method and system based on augmented reality |
CN108170817A (en) * | 2017-12-29 | 2018-06-15 | 努比亚技术有限公司 | Differentiation video acquiring method, device and the readable storage medium storing program for executing of photo main body |
CN108595531A (en) * | 2018-03-30 | 2018-09-28 | 孙博 | Spell training method, system, computer equipment and storage medium |
CN108986569A (en) * | 2018-08-24 | 2018-12-11 | 深圳市玩瞳科技有限公司 | A kind of desktop AR interactive learning method and device |
CN109215411A (en) * | 2018-08-24 | 2019-01-15 | 深圳市博悦生活用品有限公司 | A kind of mutual education method and system |
CN110379227A (en) * | 2019-07-19 | 2019-10-25 | 中原工学院 | A kind of students' Chinese voice on-line study system |
CN111681467A (en) * | 2020-06-01 | 2020-09-18 | 广东小天才科技有限公司 | Vocabulary learning method, electronic equipment and storage medium |
CN112926586A (en) * | 2021-02-19 | 2021-06-08 | 北京大米未来科技有限公司 | Text recognition method and device, readable storage medium and electronic equipment |
CN112927571A (en) * | 2021-03-03 | 2021-06-08 | 广东富利时实业有限公司 | Teaching system based on AR recognition |
CN113393719A (en) * | 2021-06-30 | 2021-09-14 | 张家口智趣学科技有限公司 | Pinyin learning method and device |
CN113611173B (en) * | 2021-09-07 | 2023-11-14 | 福建铭塔玩具股份有限公司 | Chinese character spelling machine and its realizing method |
CN114220301A (en) * | 2021-12-20 | 2022-03-22 | 深圳市卓俊文化科技有限公司 | Chinese character spelling and reading terminal and method for teaching |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106097794A (en) | The Chinese phonetic alphabet based on augmented reality combination is recognized reading learning system and recognizes reading method | |
CN106033435B (en) | Item identification method and device, indoor map generation method and device | |
Xu et al. | Human re-identification by matching compositional template with cluster sampling | |
Nelson et al. | A cubist approach to object recognition | |
KR102124466B1 (en) | Apparatus and method for generating conti for webtoon | |
CN110446063A (en) | Generation method, device and the electronic equipment of video cover | |
CN109448453A (en) | Point based on image recognition tracer technique reads answering method and system | |
CN110516554A (en) | A kind of more scene multi-font Chinese text detection recognition methods | |
US20100299134A1 (en) | Contextual commentary of textual images | |
CN109191940A (en) | Interaction method based on intelligent equipment and intelligent equipment | |
CN106503756A (en) | Based on the method that image outline sets up Chinese character handwriting model | |
US20220207266A1 (en) | Methods, devices, electronic apparatuses and storage media of image processing | |
CN106846438A (en) | A kind of jewellery try-in method, apparatus and system based on augmented reality | |
CN107018254A (en) | Information processing system, the information processing terminal and information processing method | |
CN112257513A (en) | Training method, translation method and system for sign language video translation model | |
CN115393872A (en) | Method, device and equipment for training text classification model and storage medium | |
CN104881641A (en) | Mobile device based digital recognition method and system for questionnaires and tables | |
KR20170039953A (en) | Learning apparatus using augmented reality | |
Nakjai et al. | Thai finger spelling localization and classification under complex background using a YOLO-based deep learning | |
Ouali et al. | Real-time application for recognition and visualization of arabic words with vowels based dl and ar | |
CN106484118A (en) | A kind of augmented reality exchange method based on fixing trigger source and system | |
CN111738177A (en) | Student classroom behavior identification method based on attitude information extraction | |
Margetis et al. | A smart environment for augmented learning through physical books | |
CN116205723A (en) | Artificial intelligence-based face tag risk detection method and related equipment | |
Beglov | Object information based on marker recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20171214 Address after: Huidalu Nanjing high tech Development Zone of Jiangsu province 210000 City No. 6 Building 2 floor room 207 Beidou Applicant after: Nanjing Fangcun focus information technology Co. Ltd. Address before: A software building Spark Road 210003 in Jiangsu province high tech Industrial Development Zone of Nanjing city 8-12F Applicant before: Focus Technology Co., Ltd. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |
|
RJ01 | Rejection of invention patent application after publication |