CN106446836A - Sign language recognition and interpretation device - Google Patents
Sign language recognition and interpretation device Download PDFInfo
- Publication number
- CN106446836A CN106446836A CN201610859052.3A CN201610859052A CN106446836A CN 106446836 A CN106446836 A CN 106446836A CN 201610859052 A CN201610859052 A CN 201610859052A CN 106446836 A CN106446836 A CN 106446836A
- Authority
- CN
- China
- Prior art keywords
- module
- sign language
- translating equipment
- electric conductor
- language recognition
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/033—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor
- G06F3/0346—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Abstract
The invention discloses a sign language recognition and interpretation device comprising an interpretation device body. The side wall of the interpretation device body is provided with a camera. The interpretation device body is connected with a gesture recognition device through an electric conductor. The body is internally provided with a single-chip microcomputer module, and the single-chip microcomputer module is connected with the camera and the gesture recognition device through the electric conductor. The single-chip microcomputer module is connected with a video analysis module, a voice chip module, a power supply module and a sign language learning module through the electric conductor. The gestures made by communicators are photographed by the camera, the photographed images are decoded and analyzed through the video analysis module, the gestures of the communicators are analyzed through the gesture recognition device and the two analysis results are combined so that sign language recognition and interpretation can be more accurately performed and broadcasted, and communication with the deaf people is further facilitated.
Description
Technical field
The present invention relates to sign language translation device technical field, specially a kind of Sign Language Recognition translating equipment.
Background technology
Need when generally normal person is linked up with deaf and dumb personage to learn a set of sign language, the Learning demands cost of sign language is sizable
Energy and considerable time.In addition, the expression way of most of sign languages is different because of the difference in nationality or area, therefore different states
The deaf and dumb personage in nationality or area mutually carries out exchanging the problem that there is also communication, but existing sign language translation device is often recognized
Effect be not very accurate, for the problems referred to above, special propose a kind of Sign Language Recognition translating equipment.
Content of the invention
It is an object of the invention to provide a kind of Sign Language Recognition translating equipment, with asking for solving to propose in above-mentioned background technology
Topic.
For achieving the above object, the present invention provides following technical scheme:A kind of Sign Language Recognition translating equipment, including translation dress
Body is put, on the side wall of the translating equipment body, photographic head is installed, the translating equipment body is connected with by electric conductor
Action recognition device, the inside of the body is provided with one-chip computer module, and one-chip computer module by electric conductor and photographic head and is moved
Make identifying device connection, the one-chip computer module is connected with analysis module, speech chip module, power supply mould by electric conductor
Block and sign language study module.
Preferably, the analysis module includes to be sequentially connected electrically video reception module, signal conversion module, at a high speed
DSP module, Video decoding module, data acquisition module, characteristic extracting module and identification module, the characteristic extracting module passes through
Electric conductor is connected with training module, and training module is electrically connected with identification module by electric conductor.
Preferably, the sign language study module include sign language library module, gesture database management module and User logs in and
Management module.
Preferably, the gesture database management module includes that gesture increases module, gesture library replacement module and gesture library and deletes
Module.
Preferably, action sensing module and acceleration sensing module is provided with inside the action recognition device, and action is passed
Sense module and acceleration sensing module are electrically connected with one-chip computer module by electric conductor.
Preferably, the supply module is connected with voltage detection module, and supply module and voltage detecting by electric conductor
The electric connection mode of intermodule is two-way electrical connection.
Preferably, the one-chip computer module is connected with wireless communication module by electric conductor.
Preferably, the communication modes that the wireless communication module is adopted are transmitted for WIFI.
Preferably, the communication modes that the wireless communication module is adopted are transmitted for Zigbee.
Compared with prior art, the invention has the beneficial effects as follows:A kind of Sign Language Recognition translating equipment, is clapped by photographic head
The gesture that Communicator makes is taken the photograph, the image for photographing is decoded, and is analyzed by analysis module, and lead to
Action recognition device is crossed, the gesture of Communicator is analyzed, then both are combined, can more accurately carry out sign language knowledge
Do not translate, and reported, convenient exchanged with deaf and dumb personage.
Description of the drawings
Fig. 1 is the structural representation of the present invention;
Fig. 2 is the structured flowchart of the present invention;
Fig. 3 is the structured flowchart of analysis module in the present invention;
Fig. 4 is the structured flowchart of gesture database management module in the present invention;
Fig. 5 is the structured flowchart of action sensing module in the present invention;
Fig. 6 is the structured flowchart of speech chip module in the present invention.
In figure:1st, translating equipment body, 2, photographic head, 3, action recognition device.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Fig. 1-6 are referred to, the first technical scheme that the present invention is provided:A kind of Sign Language Recognition translating equipment, including translation
Device body 1, is provided with photographic head 2 on the side wall of the translating equipment body 1, the translating equipment body 1 passes through electric conductor
Action recognition device 3 is connected with, the inside of the body 1 is provided with one-chip computer module, and one-chip computer module passes through electric conductor and takes the photograph
As 2 and action recognition device 3 connect, the one-chip computer module is connected with analysis module, speech chip by electric conductor
Module, supply module and sign language study module, the analysis module includes video reception module, the signal being sequentially connected electrically
Modular converter, high-speed dsp module, Video decoding module, data acquisition module, characteristic extracting module and identification module, the spy
Levy extraction module and training module is connected with by electric conductor, and training module is electrically connected with identification module by electric conductor, described
Sign language study module includes sign language library module, gesture database management module and User logs in and management module, the gesture library
Management module includes that gesture increases module, gesture library replacement module and gesture library removing module, inside the action recognition device 3
Action sensing module and acceleration sensing module is provided with, and action sensing module and acceleration sensing module are by electric conductor and list
Piece machine module is electrically connected, and is shot the gesture that Communicator makes by photographic head 2, and is passed through action recognition device 3, to exchange
The gesture of person is analyzed, then both are combined, and can more accurately carry out Sign Language Recognition translation, and be reported,
Convenient exchanged with deaf and dumb personage, the supply module is connected with voltage detection module by electric conductor, and mould of powering
Electric connection mode between block and voltage detection module is electrically connected for two-way, and the real-time voltage of supply module can be detected,
Overvoltage abnormal work is prevented, the one-chip computer module is connected with wireless communication module by electric conductor, the wireless telecommunications mould
The communication modes that block is adopted are transmitted for WIFI, can be carried out data transmission with extraneous mobile device.
The operation principle of the first embodiment of the present invention:The gesture that Communicator makes is shot by photographic head 2, and will
The image for photographing is transported in analysis module, is carried out turning by image by the signal conversion module in analysis module
Change, processed by high-speed dsp module after conversion, using Video decoding module, video is decoded, collection apparatus module
Necessary feature is extracted, is processed by training module, training module is used semi-continuous HMM model, choosing
Take and remove from Chinese dictionary and expression, the relevant word of the shape of the mouth as one speaks and " gesture synonym " remaining more than 4000 sign language vocabularies afterwards
The subset of collection, is initialized to model first, after model library is built up, starts identification by identification module, by handss to be identified
Words and phrases are calculated with each sign words model in model library, calculate sign language number to be identified using forward-backward algorithm algorithm
According to the matching degree with model, and judge whether finger bends by action sensing module in action recognition device 3, and
The mobile status of handss is judged by acceleration sensing module, and the gesture of Communicator is analyzed, then the judgement phase by both
In conjunction with can more accurately carry out Sign Language Recognition translation, and be reported by speech chip module, it is also possible to use
WIFI communication mode, makes mobile device be reported, convenient exchanged with deaf and dumb personage, by sign language study module
User logs in and management module logged in, store sign language action using sign language library module, be easy to user learn,
And using gesture database management module, the gesture for storing can be increased, replaced and be deleted.
Fig. 1-6 are referred to, second technical scheme that the present invention is provided:A kind of Sign Language Recognition translating equipment, including translation
Device body 1, is provided with photographic head 2 on the side wall of the translating equipment body 1, the translating equipment body 1 passes through electric conductor
Action recognition device 3 is connected with, the inside of the body 1 is provided with one-chip computer module, and one-chip computer module passes through electric conductor and takes the photograph
As 2 and action recognition device 3 connect, the one-chip computer module is connected with analysis module, speech chip by electric conductor
Module, supply module and sign language study module, the analysis module includes video reception module, the signal being sequentially connected electrically
Modular converter, high-speed dsp module, Video decoding module, data acquisition module, characteristic extracting module and identification module, the spy
Levy extraction module and training module is connected with by electric conductor, and training module is electrically connected with identification module by electric conductor, described
Sign language study module includes sign language library module, gesture database management module and User logs in and management module, the gesture library
Management module includes that gesture increases module, gesture library replacement module and gesture library removing module, inside the action recognition device 3
Action sensing module and acceleration sensing module is provided with, and action sensing module and acceleration sensing module are by electric conductor and list
Piece machine module is electrically connected, and is shot the gesture that Communicator makes by photographic head 2, and is passed through action recognition device 3, to exchange
The gesture of person is analyzed, then both are combined, and can more accurately carry out Sign Language Recognition translation, and be reported,
Convenient exchanged with deaf and dumb personage, the supply module is connected with voltage detection module by electric conductor, and mould of powering
Electric connection mode between block and voltage detection module is electrically connected for two-way, and the real-time voltage of supply module can be detected,
Overvoltage abnormal work is prevented, the one-chip computer module is connected with wireless communication module by electric conductor, the wireless telecommunications mould
The communication modes that block is adopted are transmitted for WIFI, can be carried out data transmission with extraneous mobile device.
The operation principle of second embodiment of the present invention:The gesture that Communicator makes is shot by photographic head 2, and will
The image for photographing is transported in analysis module, is carried out turning by image by the signal conversion module in analysis module
Change, processed by high-speed dsp module after conversion, using Video decoding module, video is decoded, collection apparatus module
Necessary feature is extracted, is processed by training module, training module is used semi-continuous HMM model, choosing
Take and remove from Chinese dictionary and expression, the relevant word of the shape of the mouth as one speaks and " gesture synonym " remaining more than 4000 sign language vocabularies afterwards
The subset of collection, is initialized to model first, after model library is built up, starts identification by identification module, by handss to be identified
Words and phrases are calculated with each sign words model in model library, calculate sign language number to be identified using forward-backward algorithm algorithm
According to the matching degree with model, and judge whether finger bends by action sensing module in action recognition device 3, and
The mobile status of handss is judged by acceleration sensing module, and the gesture of Communicator is analyzed, then the judgement phase by both
In conjunction with can more accurately carry out Sign Language Recognition translation, and be reported by speech chip module, it is also possible to use
Zigbee communication modes, make mobile device be reported, convenient exchanged with deaf and dumb personage, by sign language study module
In User logs in and management module logged in, store sign language action using sign language library module, be easy to user
Practise, and using gesture database management module, the gesture for storing can be increased, replaced and be deleted.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, permissible
Understanding can carry out multiple changes, modification, replacement to these embodiments without departing from the principles and spirit of the present invention
And modification, the scope of the present invention be defined by the appended.
Claims (9)
1. a kind of Sign Language Recognition translating equipment, including translating equipment body(1), it is characterised in that:The translating equipment body(1)
Side wall on photographic head is installed(2), the translating equipment body(1)Action recognition device is connected with by electric conductor(3), institute
State body(1)Inside be provided with one-chip computer module, and one-chip computer module is by electric conductor and photographic head(2)With action recognition device
(3)Connection, the one-chip computer module is connected with analysis module, speech chip module, supply module and handss by electric conductor
Language study module.
2. a kind of Sign Language Recognition translating equipment according to claim 1, it is characterised in that:The analysis module includes
The video reception module that is sequentially connected electrically, signal conversion module, high-speed dsp module, Video decoding module, data acquisition module,
Characteristic extracting module and identification module, the characteristic extracting module is connected with training module by electric conductor, and training module is logical
Cross electric conductor to electrically connect with identification module.
3. a kind of Sign Language Recognition translating equipment according to claim 1, it is characterised in that:The sign language study module includes
Sign language library module, gesture database management module and User logs in and management module.
4. a kind of Sign Language Recognition translating equipment according to claim 3, it is characterised in that:The gesture database management module bag
Include gesture and increase module, gesture library replacement module and gesture library removing module.
5. a kind of Sign Language Recognition translating equipment according to claim 1, it is characterised in that:The action recognition device(3)
Inside is provided with action sensing module and acceleration sensing module, and action sensing module and acceleration sensing module pass through electric conductor
Electrically connect with one-chip computer module.
6. a kind of Sign Language Recognition translating equipment according to claim 1, it is characterised in that:The supply module passes through conductance
The electric connection mode that body is connected between voltage detection module, and supply module and voltage detection module is electrically connected for two-way.
7. a kind of Sign Language Recognition translating equipment according to claim 1, it is characterised in that:The one-chip computer module is by electricity
Conductor is connected with wireless communication module.
8. a kind of Sign Language Recognition translating equipment according to claim 7, it is characterised in that:The wireless communication module is adopted
Communication modes be WIFI transmission.
9. a kind of Sign Language Recognition translating equipment according to claim 7, it is characterised in that:The wireless communication module is adopted
Communication modes be Zigbee transmission.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610859052.3A CN106446836A (en) | 2016-09-28 | 2016-09-28 | Sign language recognition and interpretation device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610859052.3A CN106446836A (en) | 2016-09-28 | 2016-09-28 | Sign language recognition and interpretation device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106446836A true CN106446836A (en) | 2017-02-22 |
Family
ID=58170828
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610859052.3A Pending CN106446836A (en) | 2016-09-28 | 2016-09-28 | Sign language recognition and interpretation device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106446836A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110032740A (en) * | 2019-04-20 | 2019-07-19 | 卢劲松 | It customizes individual character semanteme and learns application method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101354609A (en) * | 2008-09-18 | 2009-01-28 | 北京理工大学 | Novel data gloves based on CCD sensor |
CN101819635A (en) * | 2010-04-02 | 2010-09-01 | 北京大学软件与微电子学院无锡产学研合作教育基地 | Micro-inertial navigation signal and mode recognition-based sign language interpretation method |
KR20110041757A (en) * | 2009-10-16 | 2011-04-22 | 에스케이텔레콤 주식회사 | Apparatus and method for providing user interface by gesture |
US20110306471A1 (en) * | 2010-06-12 | 2011-12-15 | Ming-Shih Huang | Interactive Exercise System For Reducing The Risk Of Developing And Relieving The Symptoms Of Carpal Tunnel Syndrome. |
CN103049761A (en) * | 2013-01-21 | 2013-04-17 | 中国地质大学(武汉) | Sign language recognition method and system based on sign language gloves |
CN105100482A (en) * | 2015-07-30 | 2015-11-25 | 努比亚技术有限公司 | Mobile terminal and system for realizing sign language identification, and conversation realization method of the mobile terminal |
-
2016
- 2016-09-28 CN CN201610859052.3A patent/CN106446836A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101354609A (en) * | 2008-09-18 | 2009-01-28 | 北京理工大学 | Novel data gloves based on CCD sensor |
KR20110041757A (en) * | 2009-10-16 | 2011-04-22 | 에스케이텔레콤 주식회사 | Apparatus and method for providing user interface by gesture |
CN101819635A (en) * | 2010-04-02 | 2010-09-01 | 北京大学软件与微电子学院无锡产学研合作教育基地 | Micro-inertial navigation signal and mode recognition-based sign language interpretation method |
US20110306471A1 (en) * | 2010-06-12 | 2011-12-15 | Ming-Shih Huang | Interactive Exercise System For Reducing The Risk Of Developing And Relieving The Symptoms Of Carpal Tunnel Syndrome. |
CN103049761A (en) * | 2013-01-21 | 2013-04-17 | 中国地质大学(武汉) | Sign language recognition method and system based on sign language gloves |
CN105100482A (en) * | 2015-07-30 | 2015-11-25 | 努比亚技术有限公司 | Mobile terminal and system for realizing sign language identification, and conversation realization method of the mobile terminal |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110032740A (en) * | 2019-04-20 | 2019-07-19 | 卢劲松 | It customizes individual character semanteme and learns application method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109033307A (en) | Word polyarch vector based on CRP cluster indicates and Word sense disambiguation method | |
CN108108340A (en) | For the dialogue exchange method and system of intelligent robot | |
CN107944441A (en) | A kind of scanning-type translation pen | |
WO2018128238A1 (en) | Virtual consultation system and method using display device | |
CN106097835B (en) | Deaf-mute communication intelligent auxiliary system and communication method | |
CN109005382A (en) | A kind of video acquisition management method and server | |
CN108320738A (en) | Voice data processing method and device, storage medium, electronic equipment | |
CN103279734A (en) | Novel intelligent sign language translation and man-machine interaction system and use method thereof | |
CN105787442A (en) | Visual interaction based wearable auxiliary system for people with visual impairment, and application method thereof | |
CN101674363A (en) | Mobile equipment and talking method | |
Fang et al. | Dynamic gesture recognition using inertial sensors-based data gloves | |
CN105975557A (en) | Topic searching method and device applied to electric equipment | |
CN206003392U (en) | A kind of deaf-mute's social activity gloves | |
CN108510988A (en) | A kind of speech recognition system and method for deaf-mute | |
CN112214605A (en) | Text classification method and related device | |
CN113963304A (en) | Cross-modal video time sequence action positioning method and system based on time sequence-space diagram | |
CN105869622B (en) | Chinese hot word detection method and device | |
CN111429924A (en) | Voice interaction method and device, robot and computer readable storage medium | |
CN104361787A (en) | System and method for converting signals | |
CN107025617A (en) | A kind of intelligent tutoring learning system based on artificial intelligence | |
CN106446836A (en) | Sign language recognition and interpretation device | |
Loeding et al. | Progress in automated computer recognition of sign language | |
CN210516214U (en) | Service equipment based on video and voice interaction | |
CN107643908A (en) | Voice application trigger control method, device and terminal | |
CN114510942A (en) | Method for acquiring entity words, and method, device and equipment for training model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |