CN106295603A - Chinese sign language bidirectional translation system, method and apparatus - Google Patents
Chinese sign language bidirectional translation system, method and apparatus Download PDFInfo
- Publication number
- CN106295603A CN106295603A CN201610692422.9A CN201610692422A CN106295603A CN 106295603 A CN106295603 A CN 106295603A CN 201610692422 A CN201610692422 A CN 201610692422A CN 106295603 A CN106295603 A CN 106295603A
- Authority
- CN
- China
- Prior art keywords
- sign language
- module
- information
- translation system
- human body
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
-
- 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
- G09B21/009—Teaching or communicating with deaf persons
Abstract
The invention discloses a kind of Chinese sign language bidirectional translation system, method and apparatus.This Chinese sign language forward translation system includes sign language model library module, picture recognition module, sign language model matching module and forward output module, described sign language model library module is for storing the mathematical model of standard Chinese sign language, and the mathematical model of each sign language the most corresponding identifies information;Described picture recognition module, for identifying human body and the action message of described human body, forms a gesture model according to the action message of described human body and correspondence thereof;Described sign language model matching module is for obtaining the identification information that matching degree is corresponding higher than the mathematical model of a preset value;Described forward output module is for the forward output information corresponding according to the output of described identification information.The present invention, by identifying human body and the action message of described human body, forms a gesture model according to the action message of described human body and correspondence thereof, utilizes Data fusion technique, improves the recognition accuracy of gesture.
Description
Technical field
The present invention relates to a kind of sign language interpretation system and method, specifically, relate to a kind of Chinese sign language two-way translation system
System, method and apparatus.
Background technology
Generally deaf mute is to carry out linking up by sign language expressing, and this needs to link up the both sides expressed will understand hands
Language, and abled person learns sign language and needs to expend substantial amounts of energy and time.Study generally will not be specially gone due to abled person so that
Deaf mute is not smooth with the channel of communication of abled person, result in society both and seldom comes into contacts with.
Although prior art exists some sign language interpretation system, attempt by obtaining sign language action and being converted to word letter
Breath shows, but its major defect is that accuracy of identification is poor and output is the most true to nature understandable.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of Chinese sign language bidirectional translation system, method and apparatus, real
Existing deaf mute exchanges with the accessible of abled person.
In order to solve the problems referred to above, the invention provides a kind of Chinese sign language forward translation system, including sign language model storehouse
Module, picture recognition module, sign language model matching module and forward output module, wherein,
Described sign language model library module is for storing the mathematical model of standard Chinese sign language, and the mathematical model of each sign language is respectively
Corresponding one identifies information;
Described picture recognition module is for identifying human body and the action message of described human body, according to described human body
The action message of position and correspondence thereof forms a gesture model;
Described sign language model matching module is connected with described sign language model library module and picture recognition module respectively, and being used for will
The gesture model obtained is compared with the mathematical model in described sign language model library module, obtains matching degree higher than a preset value
Identification information corresponding to mathematical model;
Described forward output module is for the forward output information corresponding according to the output of described identification information.
Preferably, described forward output module includes that word output module, described identification information are Word message, described just
It is Word message to output information.
Preferably, described forward output module includes that voice output module, described identification information are Word message, institute's predicate
Sound output module for being converted to voice messaging by described Word message, and described forward output information is voice messaging;Described figure
As identification module includes multiple somatosensory recognition equipment for identifying hand exercise and other positions of human body.
Preferably, in described sign language model library module, the mathematical model of storage includes some eigenvalues, described eigenvalue with
Described human body and action message thereof are corresponding, and arrange according to preset order.
A kind of Chinese sign language forward interpretation method, is applied on an electronic equipment, and described electronic equipment has a memorizer,
In described memorizer, storage has the mathematical model of standard Chinese sign language, and the mathematical model of each sign language the most corresponding identifies information,
This sign language forward interpretation method comprises the following steps:
Identify human body and the action message of described human body, believe according to the action of described human body and correspondence thereof
Breath forms out a gesture model;
Compare with the mathematical model that described memorizer stores according to described gesture model, obtain matching degree pre-higher than one
If the identification information that the mathematical model of value is corresponding;
According to the forward output information that the output of described identification information is corresponding.
A kind of Chinese sign language forward translating equipment, including:
Forward identification module, for identifying human body and the action message of described human body, according to described people's body
The action message of position and correspondence thereof forms out a gesture model;
Forward acquisition module, for comparing with the mathematical model that described memorizer stores according to described gesture model,
Obtain the identification information that matching degree is corresponding higher than the mathematical model of a preset value;
Forward output module, for the forward output information corresponding according to the output of described identification information.
A kind of Chinese sign language bidirectional translation system, has above-mentioned sign language forward translation system and sign language reverse translation system
System;Described sign language reverse translation system, including sound identification module, sign language three-dimensional animation DBM, sign language data base
Join module and reverse output module;
Described sound identification module is for identifying the voice messaging of input and exporting the word corresponding with described voice messaging
Information;
Described sign language three-dimensional animation DBM is for storing the three-dimensional animation information of standard Chinese sign language, described three-dimensional
Animation information is corresponding with Word message;Described three-dimensional animation information is 3D hologram animation information, and described reverse output module is defeated
Go out 3D hologram animation information;
Described sign language database matching module connects described sound identification module and sign language three-dimensional animation data base's mould respectively
Block, in described sign language three-dimensional animation DBM by the retrieving text information that receives from described sound identification module with
The Word message of described three-dimensional animation information is compared, and obtains the three-dimensional that matching degree is corresponding higher than the Word message of a preset value
Holographic cartoon information;
Described reverse output module is connected with described sign language database matching module, is used for receiving described three-dimensional animation information
And pass through three-dimensional panoramic show.
Preferably, a startup module and a setting module are also included;Described startup module is turned over described sign language forward respectively
Translate system and described sign language reverse translation system connects, be used for starting described sign language forward translation system or described sign language is reversely turned over
Translate system;Described setting module is connected with described startup module, for setting the type of current goal, described startup module according to
Described type starts described sign language forward translation system or described sign language reverse translation system.
A kind of Chinese sign language two-way translation method, is applied on electronic equipment, including:
Set the type of current goal;
Type selecting sign language described above forward interpretation method according to current goal or such as sign language reverse translation method
Translate;Described sign language reverse translation method, is applied on an electronic equipment, and described electronic equipment has a memorizer, institute
Stating storage in memorizer and have the three-dimensional animation information of standard Chinese sign language, described three-dimensional animation information is corresponding with Word message, should
Sign language forward interpretation method comprises the following steps:
Identify the voice messaging of input and export the Word message corresponding with described voice messaging;
In which memory the retrieving text information received from described sound identification module is believed with described three-dimensional animation
The Word message of breath is compared, and obtains the three-dimensional animation information that matching degree is corresponding higher than the Word message of a preset value;Described
Three-dimensional animation information is 3D hologram animation information,
Receive described 3D hologram animation information, and export this 3D hologram animation information.
A kind of Chinese sign language two-way translation device, including:
Setup unit, for setting the type of current goal;
Select unit, anti-for type selecting sign language described above forward translating equipment or the sign language according to current goal
Translate to translating equipment;Described sign language reverse translation device includes:
Reversal of identification module, for identifying the voice messaging of input and exporting the word letter corresponding with described voice messaging
Breath;
Reversely acquisition module, for the retrieving text information that will receive from described sound identification module in which memory
Compare with the Word message of described three-dimensional animation information, obtain that matching degree is corresponding higher than the Word message of a preset value three
Dimension holographic cartoon information;
Reversely output module, is used for receiving described three-dimensional animation information and passing through three-dimensional panoramic show.
The invention has the beneficial effects as follows:
The sign language forward of present invention offer and bidirectional translation system and method are by identifying human body and described people's body
The action message of position, forms a gesture model according to the action message of described human body and correspondence thereof, utilizes data fusion skill
Art, improves the recognition accuracy of gesture.Additionally, the embodiment of the present invention is also by using holography display three-dimensional animation to show voice
Sign language animation after identification, the most true to nature understandable.
Accompanying drawing explanation
Below in conjunction with the accompanying drawings the detailed description of the invention of the present invention is described in further detail, wherein:
Fig. 1 is the structural representation of a kind of sign language forward translation system one embodiment that the present invention provides;
Fig. 2 is the flow chart of a kind of sign language forward interpretation method one embodiment that the present invention provides;
Fig. 3 is the schematic diagram of a kind of sign language forward translating equipment one embodiment that the present invention provides;
Fig. 4 is the structural representation of a kind of sign language reverse translation system one embodiment that the present invention provides;
Fig. 5 is the flow chart of a kind of sign language reverse translation method one embodiment that the present invention provides;
Fig. 6 is the schematic diagram of a kind of sign language reverse translation device one embodiment that the present invention provides;
Fig. 7 is the schematic diagram of a kind of Chinese sign language bidirectional translation system one embodiment that the present invention provides;
Fig. 8 is the flow chart of a kind of Chinese sign language bidirectional translation system one embodiment that the present invention provides;
Fig. 9 is the flow chart of a kind of Chinese sign language two-way translation method one embodiment that the present invention provides;
Figure 10 is the schematic diagram of a kind of Chinese sign language two-way translation device one embodiment that the present invention provides.
100: sign language forward translation system 110: sign language model library module
120: sign language model matching module 130: forward output module
131: word output module 132: voice output module
140: picture recognition module 200: sign language reverse translation system
210: sign language three-dimensional animation DBM 220: sign language database matching module
230: reversely output module 240: sound identification module
250: reversal of identification module 260: reversely acquisition module
270: reversely acquisition module 300: start module
400: setting module 500: setup unit
600: select unit
Detailed description of the invention
Referring to shown in Fig. 1, Fig. 1 is that the structure of a kind of sign language forward translation system one embodiment that the present invention provides is shown
It is intended to.In the embodiment shown in Fig. 1, this sign language forward translation system 100 includes that sign language model library module 110, image are known
Other module 140, sign language model matching module 120 and forward output module 130.
Wherein, sign language model library module 110 is for storing the mathematical model of standard Chinese sign language, the mathematical model of each sign language
The most corresponding one identifies information.In the present embodiment, in sign language model library module 110, the mathematical model of storage includes some features
Value, eigenvalue for characterizing in sign language model library module 110 mathematical model of storage, and with human body and action message thereof
Correspondence, arranges the eigenvalue of storage according to a preset order.
Picture recognition module 140 for identifying the action message of human body and human body, according to human body and
Corresponding action message forms a gesture model.Specifically, for human body and the action message of human body, use number
Reduce the blind area of gesture model according to integration technology, improve the accuracy identified.In the present embodiment, picture recognition module 140
Can include multiple image unit and multiple motion capture module, image unit can catch target from multiple different angles
The action gesture that sign language is made when expressing.Motion capture module can use multiple can accurately identify hand exercise and human body its
The somatosensory recognition equipment at his position, the somatosensory recognition equipment of this identification hand exercise can be Leap Motion equipment, this identification
The somatosensory recognition equipment at other positions of human body can be Kinect device.Multiple different types of somatosensory recognition equipment take long benefit
Short, it is possible to comprehensive sign language gesture to be identified, utilize Data fusion technique, improve to greatest extent and identify accuracy and contracting
Little identification blind area, processes, through picture recognition module 140, the gesture model obtained and sends to sign language model matching module 120.
Sign language model matching module 120 is connected with sign language model library module 110 and picture recognition module 140 respectively, is used for
The gesture model of acquisition is compared with the mathematical model in sign language model library module 110, obtains matching degree and preset higher than one
The identification information corresponding to mathematical model of value, and identification information is sent to forward output module 130.
Forward output module 130 is for the forward output information corresponding according to the output of the information of identification.Forward output module 130
Can be multiple, such as, can include word output module 131, utilizing liquid crystal display display identification information be Word message,
Forward output information is Word message and/or pictorial information, the Word message that display sign language model matching module 120 sends.This
Outward, in some embodiments, forward output module 130 also includes that voice output module 132, identification information are Word message,
Voice output module 132 for being converted to voice messaging by Word message, and forward output information is voice messaging, utilizes speaker
Or the audible devices such as earphone send the corresponding voice messaging of output.
In an embodiment of the present invention, combined by multiple Leap Motion equipment and Kinect device, increase gesture
Identification region, and use Data fusion technique, improve the recognition accuracy of gesture.
See the flow chart that Fig. 2, Fig. 2 are a kind of sign language forward interpretation method one embodiments that the present invention provides.At Fig. 2
In the embodiment illustrated, this sign language forward interpretation method is applied on an electronic equipment, and electronic equipment has a memorizer, deposits
In reservoir, storage has the mathematical model of standard Chinese sign language, and the mathematical model of each sign language the most corresponding identifies information.
This sign language forward interpretation method includes step S201~step S203.
In step s 201, identify human body and the action message of human body, according to human body and correspondence thereof
Action message forms out a gesture model;
In step S202, compare with the mathematical model that memorizer stores according to gesture model, obtain matching degree high
In the identification information that the mathematical model of a preset value is corresponding;
In step S203, according to the forward output information that the output of the information of identification is corresponding.
It is corresponding with the sign language forward translation system 100 shown in Fig. 1 at sign language forward interpretation method of the present embodiment,
Technical information disclosed in sign language forward translation system 100 embodiment shown in Fig. 1 can also be applied in the present embodiment, because of
And the most no longer repeat.
See the schematic diagram that Fig. 3, Fig. 3 are a kind of sign language forward translating equipment one embodiments that the present invention provides.At Fig. 2
In the embodiment illustrated, this sign language forward translating equipment includes forward identification module 150, forward acquisition module 160 and forward
Output module 170.
Wherein, forward identification module 150 is for identifying human body and the action message of described human body, according to described
The action message of human body and correspondence thereof forms out a gesture model.Forward acquisition module 160 is for according to described gesture mould
The mathematical model that type stores with described memorizer is compared, and obtains the knowledge that matching degree is corresponding higher than the mathematical model of a preset value
Other information.Forward output module 170 is for the forward output information corresponding according to the output of described identification information.
See the structural representation that Fig. 4, Fig. 4 are a kind of sign language reverse translation system one embodiments that the present invention provides.
In the embodiment illustrated in fig. 4, this sign language reverse translation system 200 includes sound identification module 240, sign language three-dimensional animation number
According to library module 210, sign language database matching module 220 and reverse output module 230.
Wherein, sound identification module 240 is for identifying the voice messaging of input and exporting the word corresponding with voice messaging
Information.
Sign language three-dimensional animation DBM 210 is for storing the three-dimensional animation information of standard Chinese sign language, three-dimensional animation
Information is corresponding with Word message, and different Chinese are made up of different three-dimensional animations.
Sign language database matching module 220 connects sound identification module 240 and sign language three-dimensional animation DBM respectively
210, in sign language three-dimensional animation DBM 210 by the retrieving text information that receives from sound identification module 240 with
The Word message of three-dimensional animation information is compared, and obtains the three-dimensional animation that matching degree is corresponding higher than the Word message of a preset value
Information, such as, can be to find out the three-dimensional animation information that matching degree is the highest, and send it to reverse output module 230.
Reversely output module 230 is connected with sign language database matching module 220, is used for receiving three-dimensional animation information defeated
Go out.
In the present embodiment, this three-dimensional animation information is 3D hologram animation information, and reverse output module 230 can export
3D hologram animation information.It can be seen that in an embodiment, the sign language after using 3D hologram animation to show speech recognition is moved
Draw, the most true to nature understandable.
See the flow chart that Fig. 5, Fig. 5 are a kind of Chinese sign language reverse translation method one embodiments that the present invention provides.
In the embodiment illustrated in figure 5, this Chinese sign language reverse translation method is applied on an electronic equipment, and electronic equipment has one
Memorizer, in memorizer, storage has the three-dimensional animation information of standard Chinese sign language, and three-dimensional animation information is corresponding with Word message.Its
In, this sign language forward interpretation method includes step S501~step S503.
In step S501, identify the voice messaging of input, in conjunction with literary composition relation before and after voice, output and voice messaging pair
The Word message answered.
In step S502, in memory the retrieving text information received from sound identification module 240 is moved with three-dimensional
The Word message of picture information is compared, and obtains the three-dimensional animation information that matching degree is corresponding higher than the Word message of a preset value.
In step S503, receive three-dimensional animation information and export.
It is corresponding with the sign language reverse translation system 200 shown in Fig. 4 in sign language reverse translation method of the present embodiment,
Technical information disclosed in sign language forward translation system 100 embodiment shown in Fig. 4 can also be applied in the present embodiment, because of
And the most no longer repeat.
See the schematic diagram that Fig. 6, Fig. 6 are a kind of Chinese sign language reverse translation device one embodiments that the present invention provides.
In the embodiment that is shown in figure 6, this sign language reverse translation device includes reversal of identification module 250, reverse acquisition module 260 and
Reversely output module 270.
Wherein, reversal of identification module 250 is for identifying the voice messaging of input and exporting corresponding with described voice messaging
Word message.Reversely acquisition module 250 is for the Word message that will receive from described sound identification module in which memory
Retrieve the Word message with described three-dimensional animation information to compare, obtain matching degree corresponding higher than the Word message of a preset value
Three-dimensional animation information.Reversely output module 270 is used for receiving described three-dimensional animation information and exporting.
See the structural representation that Fig. 7, Fig. 7 are a kind of Chinese sign language bidirectional translation system one embodiments that the present invention provides
Figure.Chinese sign language bidirectional translation system shown in Fig. 7 has sign language forward translation system 100 and the hands that above-mentioned embodiment relates to
Language reverse translation system 200.
In the present embodiment, this Chinese sign language bidirectional translation system also includes a startup module 300, respectively with sign language forward
Translation system 100 and sign language reverse translation system 200 connect, and be used for starting sign language forward translation system 100 or sign language is reversely turned over
Translate system 200.Additionally, in the present embodiment, this Chinese sign language bidirectional translation system also includes a setting module 400, setting module
400 can pass through wired with starting module 300 or wirelessly be connected, such as, can be by bluetooth or USB interface
Connect.Setting module 400, for setting the type (being the most currently abled person or deaf mute) of current goal, starts module 300
Sign language forward translation system 100 or sign language reverse translation system 200 is started according to type.
See the flow chart that Fig. 8, Fig. 8 are a kind of Chinese sign language bidirectional translation system one embodiments that the present invention provides.
The Chinese sign language bidirectional translation system related at the embodiment shown in Fig. 7 after starting and initializing, including step S601~
603。
In step S801, setting module 400 is initially used for setting the type of current goal, it is judged that current goal is deaf and dumb
People or abled person, and will determine that result is sent to start module 300;
In step S802, startup module 300, according to the judged result of setting module 400, starts corresponding system: if
Judged result is deaf mute, then start sign language forward translation system 100;If it is judged that be abled person, then start sign language anti-
To translation system 200.
In step S803, it is judged that whether translation terminates, if translated, then terminate flow process, otherwise return and continue to turn over
Translate.
See the flow chart that Fig. 9, Fig. 9 are a kind of Chinese sign language two-way translation method one embodiments that the present invention provides.
In the embodiment shown in Fig. 9, this Chinese sign language two-way translation method, be applied on electronic equipment, including step S901 and
Step S902.
In step S901, set the type of current goal;
In step S902, the sign language forward interpretation method above-mentioned according to the type selecting of current goal or described above
Sign language reverse translation method is translated.
See the signal that Figure 10, Figure 10 are a kind of Chinese sign language two-way translation device one embodiments that the present invention provides
Figure.Chinese sign language two-way translation device shown in Figure 10 includes setup unit 500 and selects unit 600.
Wherein, setup unit 500 is for setting the type of current goal.Select unit 600 for according to current goal
Sign language forward translating equipment or sign language reverse translation method that type selecting is above-mentioned are translated.
Visible, the Chinese sign language bidirectional translation system that the present embodiment provides is capable of the accessible of deaf mute and abled person
Two-way exchange.On the one hand, Chinese sign language can be carried out identifying and be converted to word in high precision and voice messaging passes to abled person,
On the other hand, use sound identification module 240 to capture sign language three-dimensional animation that voice messaging obtains matching and picture pass to
Deaf mute.
Above in conjunction with accompanying drawing, embodiments of the present invention are explained in detail, but the present invention is not limited to above-mentioned enforcement
Mode, in the ken that one skilled in the relevant art is possessed, it is also possible in the premise without departing from present inventive concept
It is lower that various changes can be made.
Claims (10)
1. a Chinese sign language forward translation system, it is characterised in that include sign language model library module, picture recognition module, hands
Language model fitting module and forward output module, wherein,
Described sign language model library module is for storing the mathematical model of standard Chinese sign language, and the mathematical model of each sign language is the most corresponding
One identifies information;
Described picture recognition module is for identifying human body and the action message of described human body, according to described human body
And the action message of correspondence forms a gesture model;
Described sign language model matching module is connected with described sign language model library module and picture recognition module respectively, for obtaining
Gesture model compare with the mathematical model in described sign language model library module, obtain matching degree higher than the number of a preset value
Learn the identification information that model is corresponding;
Described forward output module is for the forward output information corresponding according to the output of described identification information.
2. Chinese sign language forward translation system as claimed in claim 1, it is characterised in that described forward output module includes literary composition
Word output module, described identification information is Word message, and described forward output information is Word message.
3. Chinese sign language forward translation system as claimed in claim 1, it is characterised in that described forward output module includes language
Sound output module, described identification information is Word message, and described voice output module is for being converted to language by described Word message
Message ceases, and described forward output information is voice messaging;Described picture recognition module include multiple for identify hand exercise and
The somatosensory recognition equipment at other positions of human body.
4. Chinese sign language forward translation system as claimed in claim 1, it is characterised in that deposit in described sign language model library module
The mathematical model of storage includes some eigenvalues, and described eigenvalue is corresponding with described human body and action message thereof, and according to
Preset order arranges.
5. a Chinese sign language forward interpretation method, is applied on an electronic equipment, it is characterised in that described electronic equipment has
One memorizer, in described memorizer, storage has the mathematical model of standard Chinese sign language, the mathematical model of each sign language the most corresponding
Identification information, this sign language forward interpretation method comprises the following steps:
Identify human body and the action message of described human body, according to the action message shape of described human body and correspondence thereof
Become out a gesture model;
Compare with the mathematical model that described memorizer stores according to described gesture model, obtain matching degree higher than a preset value
Identification information corresponding to mathematical model;
According to the forward output information that the output of described identification information is corresponding.
6. a Chinese sign language forward translating equipment, it is characterised in that including:
Forward identification module, for identifying human body and the action message of described human body, according to described human body and
The action message of its correspondence forms out a gesture model;
Forward acquisition module, for comparing with the mathematical model that described memorizer stores according to described gesture model, obtains
The identification information that matching degree is corresponding higher than the mathematical model of a preset value;
Forward output module, for the forward output information corresponding according to the output of described identification information.
7. a Chinese sign language bidirectional translation system, it is characterised in that there is the Chinese hands as described in any one of claim 1-4
Language forward translation system and Chinese sign language reverse translation system;Described sign language reverse translation system, including sound identification module, hands
Language three-dimensional animation DBM, sign language database matching module and reverse output module;
Described sound identification module is for identifying the voice messaging of input and exporting the Word message corresponding with described voice messaging;
Described sign language three-dimensional animation DBM is for storing the three-dimensional animation information of standard Chinese sign language, described three-dimensional animation
Information is corresponding with Word message;Described three-dimensional animation information is 3D hologram animation information, described reverse output module output three
Dimension holographic cartoon information;
Described sign language database matching module connects described sound identification module and sign language three-dimensional animation DBM respectively, uses
In in described sign language three-dimensional animation DBM by the retrieving text information that receives from described sound identification module with described
The Word message of three-dimensional animation information is compared, and obtains the three-dimensional animation that matching degree is corresponding higher than the Word message of a preset value
Information;
Described reverse output module is connected with described sign language database matching module, is used for receiving described three-dimensional animation information and leading to
Cross three-dimensional panoramic show.
8. Chinese sign language bidirectional translation system as claimed in claim 7, it is characterised in that: also include that a startup module and sets
Cover half block;Described startup module is connected with described sign language forward translation system and described sign language reverse translation system respectively, is used for
Start described sign language forward translation system or described sign language reverse translation system;Described setting module is with described startup module even
Connect, for setting the type of current goal, described startup module according to described type start described sign language forward translation system or
Described sign language reverse translation system.
9. a Chinese sign language two-way translation method, is applied on electronic equipment, it is characterised in that including:
Set the type of current goal;
Type selecting sign language as claimed in claim 5 forward interpretation method according to current goal or such as sign language reverse translation
Method is translated;Described sign language reverse translation method, is applied on an electronic equipment, and described electronic equipment has a storage
Device, in described memorizer, storage has the three-dimensional animation information of standard Chinese sign language, described three-dimensional animation information and Word message pair
Should, this sign language forward interpretation method comprises the following steps:
Identify the voice messaging of input and export the Word message corresponding with described voice messaging;
In which memory by the retrieving text information received from described sound identification module and described three-dimensional animation information
Word message is compared, and obtains the three-dimensional animation information that matching degree is corresponding higher than the Word message of a preset value;Described three-dimensional
Animation information is 3D hologram animation information;
Receive described 3D hologram animation information, and export this 3D hologram animation information.
10. a Chinese sign language two-way translation device, it is characterised in that including:
Setup unit, for setting the type of current goal;
Select unit, for according to the type selecting sign language as claimed in claim 6 forward translating equipment of current goal or
Sign language reverse translation device is translated;Described sign language reverse translation device includes:
Reversal of identification module, for identifying the voice messaging of input and exporting the Word message corresponding with described voice messaging;
Reversely acquisition module, in which memory by the retrieving text information received from described sound identification module and institute
The Word message stating three-dimensional animation information is compared, and the three-dimensional obtaining matching degree corresponding higher than the Word message of a preset value is moved
Picture information;
Reversely output module, is used for receiving described three-dimensional animation information and passing through three-dimensional panoramic show.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610692422.9A CN106295603A (en) | 2016-08-18 | 2016-08-18 | Chinese sign language bidirectional translation system, method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610692422.9A CN106295603A (en) | 2016-08-18 | 2016-08-18 | Chinese sign language bidirectional translation system, method and apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106295603A true CN106295603A (en) | 2017-01-04 |
Family
ID=57661605
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610692422.9A Pending CN106295603A (en) | 2016-08-18 | 2016-08-18 | Chinese sign language bidirectional translation system, method and apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106295603A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108074569A (en) * | 2017-12-06 | 2018-05-25 | 安徽省科普产品工程研究中心有限责任公司 | A kind of intelligence voice identifies in real time and methods of exhibiting |
CN108256458A (en) * | 2018-01-04 | 2018-07-06 | 东北大学 | A kind of two-way real-time translation system and method for deaf person's nature sign language |
CN108268835A (en) * | 2017-12-28 | 2018-07-10 | 努比亚技术有限公司 | sign language interpretation method, mobile terminal and computer readable storage medium |
CN108427910A (en) * | 2018-01-30 | 2018-08-21 | 浙江凡聚科技有限公司 | Deep-neural-network AR sign language interpreters learning method, client and server |
CN108629241A (en) * | 2017-03-23 | 2018-10-09 | 华为技术有限公司 | A kind of data processing method and data processing equipment |
CN108960158A (en) * | 2018-07-09 | 2018-12-07 | 珠海格力电器股份有限公司 | A kind of system and method for intelligent sign language translation |
CN109214295A (en) * | 2018-08-08 | 2019-01-15 | 长春理工大学 | The gesture identification method of data fusion based on Kinect v2 and Leap Motion |
CN109919127A (en) * | 2019-03-20 | 2019-06-21 | 邱洵 | A kind of sign language languages switching system |
CN112256827A (en) * | 2020-10-20 | 2021-01-22 | 平安科技(深圳)有限公司 | Sign language translation method and device, computer equipment and storage medium |
CN112669654A (en) * | 2021-01-05 | 2021-04-16 | 李京肽 | Foreign language learning bilingual broadcasting device and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101661330A (en) * | 2009-09-22 | 2010-03-03 | 深圳华为通信技术有限公司 | Method for converting sign language and terminal thereof |
CN101794528A (en) * | 2010-04-02 | 2010-08-04 | 北京大学软件与微电子学院无锡产学研合作教育基地 | Gesture language-voice bidirectional translation system |
CN102956132A (en) * | 2011-08-25 | 2013-03-06 | 鸿富锦精密工业(深圳)有限公司 | System, device and method for translating sign languages |
CN105489088A (en) * | 2016-01-13 | 2016-04-13 | 宋纪元 | Voice bionic sign language bidirectional translation system |
-
2016
- 2016-08-18 CN CN201610692422.9A patent/CN106295603A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101661330A (en) * | 2009-09-22 | 2010-03-03 | 深圳华为通信技术有限公司 | Method for converting sign language and terminal thereof |
CN101794528A (en) * | 2010-04-02 | 2010-08-04 | 北京大学软件与微电子学院无锡产学研合作教育基地 | Gesture language-voice bidirectional translation system |
CN102956132A (en) * | 2011-08-25 | 2013-03-06 | 鸿富锦精密工业(深圳)有限公司 | System, device and method for translating sign languages |
CN105489088A (en) * | 2016-01-13 | 2016-04-13 | 宋纪元 | Voice bionic sign language bidirectional translation system |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108629241A (en) * | 2017-03-23 | 2018-10-09 | 华为技术有限公司 | A kind of data processing method and data processing equipment |
CN108074569A (en) * | 2017-12-06 | 2018-05-25 | 安徽省科普产品工程研究中心有限责任公司 | A kind of intelligence voice identifies in real time and methods of exhibiting |
CN108268835A (en) * | 2017-12-28 | 2018-07-10 | 努比亚技术有限公司 | sign language interpretation method, mobile terminal and computer readable storage medium |
CN108256458B (en) * | 2018-01-04 | 2020-08-04 | 东北大学 | Bidirectional real-time translation system and method for deaf natural sign language |
CN108256458A (en) * | 2018-01-04 | 2018-07-06 | 东北大学 | A kind of two-way real-time translation system and method for deaf person's nature sign language |
CN108427910A (en) * | 2018-01-30 | 2018-08-21 | 浙江凡聚科技有限公司 | Deep-neural-network AR sign language interpreters learning method, client and server |
CN108960158A (en) * | 2018-07-09 | 2018-12-07 | 珠海格力电器股份有限公司 | A kind of system and method for intelligent sign language translation |
CN109214295A (en) * | 2018-08-08 | 2019-01-15 | 长春理工大学 | The gesture identification method of data fusion based on Kinect v2 and Leap Motion |
CN109214295B (en) * | 2018-08-08 | 2022-03-22 | 长春理工大学 | Gesture recognition method based on data fusion of Kinect v2 and Leap Motion |
CN109919127A (en) * | 2019-03-20 | 2019-06-21 | 邱洵 | A kind of sign language languages switching system |
CN109919127B (en) * | 2019-03-20 | 2021-12-17 | 胡海明 | Mute language conversion system |
CN112256827A (en) * | 2020-10-20 | 2021-01-22 | 平安科技(深圳)有限公司 | Sign language translation method and device, computer equipment and storage medium |
WO2021179703A1 (en) * | 2020-10-20 | 2021-09-16 | 平安科技(深圳)有限公司 | Sign language interpretation method and apparatus, computer device, and storage medium |
CN112669654A (en) * | 2021-01-05 | 2021-04-16 | 李京肽 | Foreign language learning bilingual broadcasting device and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106295603A (en) | Chinese sign language bidirectional translation system, method and apparatus | |
US11605193B2 (en) | Artificial intelligence-based animation character drive method and related apparatus | |
CN107728780B (en) | Human-computer interaction method and device based on virtual robot | |
JP7130057B2 (en) | Hand Keypoint Recognition Model Training Method and Device, Hand Keypoint Recognition Method and Device, and Computer Program | |
CN107203953B (en) | Teaching system based on internet, expression recognition and voice recognition and implementation method thereof | |
WO2021169431A1 (en) | Interaction method and apparatus, and electronic device and storage medium | |
US20200026764A1 (en) | Method of video call | |
CN109859096A (en) | Image Style Transfer method, apparatus, electronic equipment and storage medium | |
WO2020082566A1 (en) | Physiological sign recognition-based distance learning method, device, apparatus, and storage medium | |
WO2021083125A1 (en) | Call control method and related product | |
CN104572852B (en) | The recommended method and device of resource | |
CN109191940B (en) | Interaction method based on intelligent equipment and intelligent equipment | |
KR102193029B1 (en) | Display apparatus and method for performing videotelephony using the same | |
CN106296690A (en) | The method for evaluating quality of picture material and device | |
CN111459452B (en) | Driving method, device and equipment of interaction object and storage medium | |
CN110598576A (en) | Sign language interaction method and device and computer medium | |
US10326928B2 (en) | Image processing apparatus for determining whether section of target area matches section of person area and control method thereof | |
CN110688874A (en) | Facial expression recognition method and device, readable storage medium and electronic equipment | |
CN103745423B (en) | A kind of shape of the mouth as one speaks teaching system and teaching method | |
CN113835522A (en) | Sign language video generation, translation and customer service method, device and readable medium | |
CN105528080A (en) | Method and device for controlling mobile terminal | |
US20190164444A1 (en) | Assessing a level of comprehension of a virtual lecture | |
CN109300469A (en) | Simultaneous interpretation method and device based on machine learning | |
CN109920016A (en) | Image generating method and device, electronic equipment and storage medium | |
CN105096669A (en) | Method for training child daily communication capability by utilization of virtual technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination |