CN108319912A - A kind of lip reading recognition methods, device, system and intelligent glasses - Google Patents
A kind of lip reading recognition methods, device, system and intelligent glasses Download PDFInfo
- Publication number
- CN108319912A CN108319912A CN201810090891.2A CN201810090891A CN108319912A CN 108319912 A CN108319912 A CN 108319912A CN 201810090891 A CN201810090891 A CN 201810090891A CN 108319912 A CN108319912 A CN 108319912A
- Authority
- CN
- China
- Prior art keywords
- information
- lip reading
- mouth
- lip
- voice messaging
- 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
- 239000011521 glass Substances 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004891 communication Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 34
- 230000008921 facial expression Effects 0.000 claims abstract description 20
- 210000003205 muscle Anatomy 0.000 claims abstract description 20
- 230000007704 transition Effects 0.000 claims abstract description 17
- 238000010606 normalization Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 238000012549 training Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 2
- 206010011878 Deafness Diseases 0.000 description 1
- 206010048865 Hypoacusis Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Telephone Function (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of lip reading recognition methods, device, system and intelligent glasses, this method to include：Lip reading information is obtained using camera, lip reading information includes the shape of the mouth as one speaks, oral area muscle transition information, lip color, mouth side Skin Color Information and facial expression information three classes；According to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory, lip reading information is identified, processing is converted into voice messaging；The voice messaging is reported using loud speaker or earphone.The technical solution can solve the communication problem of the hearing discrimination person of dispatching a person；Can solve remote communication problem, for example, there is part maritime personnel to have professional training lip reading in foreign countries to judge other ship or people on the bank, what is said or talked about；It can be used for working at height, military affairs etc., facilitate timely transmission and the feedback of information.
Description
Technical field
The present invention relates to intelligent wearable device field, more particularly to a kind of lip reading recognition methods, device, system and Brilliant Eyes
Mirror.
Background technology
Prior art spininess carries out speech recognition and Sign Language Recognition the design of intelligent glasses, for solving person hard of hearing
Or deaf-mute and normal person's communication problem, but these technologies are identified just for voice and gesture, are not identified to lip reading
Carry out relevant technical research.
Invention content
A kind of lip reading recognition methods, device, system and intelligent glasses provided by the invention, to solve or partly solve above-mentioned
The problem of.
According to an aspect of the present invention, the present invention provides a kind of lip reading recognition methods, this method includes：
Lip reading information is obtained using camera, the lip reading information includes the shape of the mouth as one speaks, oral area muscle transition information, lip color, mouth
Side Skin Color Information and facial expression information three classes；
According to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory, the lip reading information is carried out
Identification, processing are converted into voice messaging；
The voice messaging is reported using loud speaker or earphone.
Optionally, described according to the intelligent algorithm stored in memory, shape of the mouth as one speaks model and expression model information, to the lip
Language information is identified, and processing is converted into voice messaging：
The shape of the mouth as one speaks, oral area muscle transition information and the shape of the mouth as one speaks model information in memory are compared and analyzed, obtained
First lip reading information；
According to the lip color, the Magnifying chromoscopy of mouth colour of skin when Skin Color Information detects lip color and mouth, in memory
Intelligent algorithm carries out mouth movements feature judgement, and is compared and analyzed with the shape of the mouth as one speaks model information in memory, obtains second
Lip reading information；
Using image processing techniques to the facial expression information carry out Expression Recognition, and with the expression model in memory
Information compares and analyzes, and obtains third lip reading information；
Normalization is carried out to the first lip reading information, the second lip reading information and the third lip reading information, it will
Lip reading information after normalization is converted into voice messaging.
Optionally, the method further includes：It detects whether Connection Service device, when detecting Connection Service device, will obtain
The lip reading information be sent to the server, the lip reading information is identified by the server, processing is converted into
Voice messaging simultaneously passes the voice messaging back.
The invention also discloses a kind of lip reading identification device, the device include image collection module, memory, processor,
Voice broadcast module,
Described image acquisition module, be configured as using camera obtain lip reading information, the lip reading information include the shape of the mouth as one speaks,
Oral area muscle transition information, lip color, mouth side Skin Color Information and facial expression information three classes；
The memory is configured as storage intelligent algorithm, shape of the mouth as one speaks model and expression model information；
The processor is configured as according to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory,
The lip reading information is identified, processing is converted into voice messaging；
The voice broadcast module is configured as reporting the voice messaging using loud speaker or earphone.
Optionally, described device further includes：Wireless communication module；The wireless communication module, is configured as and server
And/or mobile terminal carries out wireless communication.
The invention also discloses a kind of lip reading identifying system, which includes camera, loud speaker or earphone, above-mentioned
Lip reading identification device；
The lip reading identification device obtains lip reading information using the camera, and the lip reading information includes the shape of the mouth as one speaks, oral area
Muscle transition information, lip color, mouth side Skin Color Information and facial expression information three classes；It is calculated according to the intelligence stored in memory
The lip reading information is identified in method, shape of the mouth as one speaks model and expression model information, and processing is converted into voice messaging, and utilizes
The loud speaker or earphone report the voice messaging.
Optionally, the system also includes：Server；
Module connects the server to the lip reading identification device by radio communication；
The lip reading identification device is detected whether to connect the server, when detecting the connection server, will be obtained
The lip reading information taken is sent to the server；
The lip reading information is identified in the server, and processing is converted into voice messaging and is identified to the lip reading and filled
It sets and passes the voice messaging back.
Optionally, the system also includes：Mobile terminal；Module connects institute to the lip reading identification device by radio communication
State mobile terminal；
The mobile terminal is configured as carrying out parameter setting to the lip reading identification device.
The invention also discloses a kind of intelligent glasses, camera, loud speaker or earphone, institute are provided on the intelligent glasses
It states and is provided with memory and processor in intelligent glasses,
The camera obtains lip reading information by style of shooting, and the lip reading information includes the shape of the mouth as one speaks, the variation of oral area muscle
Information, lip color, mouth side Skin Color Information and facial expression information three classes；
It is stored with intelligent algorithm, shape of the mouth as one speaks model and expression model information in the memory, and records the camera
The lip reading information of acquisition；
The processor is according to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory, to the lip
Language information is identified, and processing is converted into voice messaging；
The loud speaker or earphone report the voice messaging.
Optionally, it is additionally provided with wireless communication module in the intelligent glasses；The intelligent glasses pass through the channel radio
Letter module is carried out wireless communication with server and/or mobile terminal；
The processor detects the wireless communication module, and whether Connection Service device is incited somebody to action when detecting Connection Service device
The lip reading information that the camera obtains is sent to the server, is known to the lip reading information by the server
Not, processing is converted into voice messaging and passes the voice messaging back.
The advantageous effect of the embodiment of the present invention is：The shape of the mouth as one speaks, oral area muscle transition information, lip are obtained by using camera
Three category information of color, mouth side Skin Color Information and facial expression information；According to intelligent algorithm, shape of the mouth as one speaks model and the table stored in memory
Above-mentioned three category information is identified in feelings model information respectively, and processing is converted into voice messaging；It is broadcast using loud speaker or earphone
Voice messaging is reported, lip reading identification is completed.The technical solution can solve the communication problem of the hearing discrimination person of dispatching a person；It can solve
Remote communication problem, such as there is part maritime personnel to have professional training lip reading to judge other ship or people on the bank in foreign countries
What is said or talked about；It can be used for working at height, military affairs etc., facilitate timely transmission and the feedback of information.
Description of the drawings
Fig. 1 is a kind of lip reading recognition methods flow chart provided in an embodiment of the present invention；
Fig. 2 is another lip reading recognition methods flow chart provided in an embodiment of the present invention；
Fig. 3 is a kind of lip reading identification device figure provided in an embodiment of the present invention；
Fig. 4 is the analyzing processing figure of lip reading information；
Fig. 5 is a kind of lip reading identifying system figure provided in an embodiment of the present invention；
Fig. 6 is a kind of intelligent glasses schematic diagram provided in an embodiment of the present invention.
Specific implementation mode
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.Embodiment described in following exemplary embodiment does not represent consistent with the application
All embodiments.On the contrary, they are only and some aspects phase one as detailed in the attached claim, the application
The example of the device and method of cause.
It is the purpose only merely for description specific embodiment in term used in this application, is not intended to be limiting the application.
It is also intended to including majority in the application and "an" of singulative used in the attached claims, " described " and "the"
Form, unless context clearly shows that other meanings.
Fig. 1 be a kind of lip reading recognition methods flow chart provided in an embodiment of the present invention, as shown in Figure 1, this method include with
Lower step：
Step S11：Lip reading information is obtained using camera, lip reading information includes the shape of the mouth as one speaks, oral area muscle transition information, lip
Color, mouth side Skin Color Information and facial expression information three classes；
Step S12：According to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory, to lip reading information
It is identified, processing is converted into voice messaging；Specially：By the shape of the mouth as one speaks, oral area muscle transition information and the mouth mould in memory
Type information compares and analyzes, and obtains the first lip reading information；According to lip color, mouth lip color and colour of skin when mouth are detected in Skin Color Information
Magnifying chromoscopy carries out mouth movements feature judgement with the intelligent algorithm in memory, and believes with the shape of the mouth as one speaks model in memory
Breath compares and analyzes, and obtains the second lip reading information；Expression Recognition is carried out to facial expression information using image processing techniques, and
It is compared and analyzed with the expression model information in memory, obtains third lip reading information；To the first lip reading information, the second lip reading
Information and third lip reading information carry out normalization, convert the lip reading information after normalization to voice messaging.
Step S13：Utilize loud speaker or earphone broadcast voice information.
Method shown in Fig. 1 further includes：Connection Service device is detected whether, when detecting Connection Service device, by the lip of acquisition
Language information is sent to server, and lip reading information is identified by server, and processing is converted into voice messaging and passes voice letter back
Breath.
Fig. 2 is another lip reading recognition methods flow chart provided in an embodiment of the present invention, which mainly answers
With in intelligent wearable device, by taking intelligent glasses as an example, camera, loud speaker or earphone, intelligence are set on intelligent glasses
Memory, processor and wireless communication module are provided in glasses.As shown in Fig. 2, this approach includes the following steps：
Step S21：Camera obtains lip reading information；The mug shot of people is shot by camera to obtain lip reading letter
Breath, including the shape of the mouth as one speaks, oral area muscle transition information, lip color, mouth side Skin Color Information and facial expression information three classes；
Step S22：Judge whether to be connected with server；Camera by the lip reading information got be sent to server it
Before, intelligent glasses first detect whether itself is connected with server, if detecting that intelligent glasses are not attached to server, transport
Row step S23, if detecting that intelligent glasses are connected to server, operating procedure S24；
Step S23：Processor is handled to obtain voice messaging to lip reading information；The lip reading information that camera will be got
It is sent to processor, analyzing processing is carried out to the lip reading information got according to the method described in step S12 in Fig. 1 by processor
Obtain voice messaging；
Step S24：Server is handled to obtain voice messaging to lip reading information；If detecting intelligent glasses and service
Device is connected, then preferentially by lip reading information, module is sent to server to camera by radio communication, is also accordingly deposited in server
Intelligent algorithm, shape of the mouth as one speaks model and expression model information are contained, to the processing side of the analysis and processing method and processor of lip reading information
Method is identical, and details are not described herein；
Step S25：Voice messaging is sent to intelligent glasses；
Step S26：Voice messaging is subjected to voice broadcast by loud speaker or earphone；Wherein earphone can be bluetooth ear
Voice messaging can be transmitted directly to bluetooth headset by bluetooth and carry out voice broadcast by machine, server.
Wireless communication module can be bluetooth or WIFI, for being wirelessly communicated with server and mobile terminal；In addition, intelligence
Glasses module can also be connected with mobile terminal by radio communication, and parameter setting is carried out to intelligent glasses by mobile terminal,
Such as the size of volume parameters can be set.
Fig. 3 is a kind of lip reading identification device figure provided in an embodiment of the present invention, as shown in figure 3, the device 30 includes image
Acquisition module 301, memory 302, processor 303, voice broadcast module 304,
Image collection module 301 is configured as obtaining lip reading information using camera, and lip reading information includes the shape of the mouth as one speaks, oral area
Muscle transition information, lip color, mouth side Skin Color Information and facial expression information three classes；
Memory 302 is configured as storage intelligent algorithm, shape of the mouth as one speaks model and expression model information, and record image obtains
The lip reading information that modulus block obtains；
Processor 303 is configured as according to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory,
Lip reading information is identified, processing is converted into voice messaging；
Fig. 4 is the analyzing processing figure of lip reading information, as shown in figure 4, by the shape of the mouth as one speaks, oral area muscle transition information and memory
Shape of the mouth as one speaks model information compare and analyze, obtain the first lip reading information；According to lip color, mouth side Skin Color Information detection lip color and mouth
The Magnifying chromoscopy of the side colour of skin, in memory intelligent algorithm carry out mouth movements feature judgement, and with the mouth in memory
Type model information compares and analyzes, and obtains the second lip reading information；Table is carried out to facial expression information using image processing techniques
Feelings identify, and are compared and analyzed with the expression model information in memory, obtain third lip reading information；First lip reading is believed
Breath, the second lip reading information and third lip reading information carry out normalization, convert the lip reading information after normalization to voice letter
Breath.
Voice broadcast module 304 is configured as utilizing loud speaker or earphone broadcast voice information.
Fig. 3 shown devices further include：Wireless communication module is configured as carrying out with server and/or mobile terminal wireless
Communication.Wireless communication module may be bluetooth or WIFI.
Fig. 5 is a kind of lip reading identifying system figure provided in an embodiment of the present invention, as shown in figure 5, the system 50 includes camera shooting
First 501, loud speaker 502 or earphone 502, above-mentioned lip reading identification device 30；
Lip reading identification device 30 obtains lip reading information using camera, and lip reading information includes the shape of the mouth as one speaks, oral area muscle variation letter
Breath, lip color, mouth side Skin Color Information and facial expression information three classes；According to stored in memory intelligent algorithm, mouth mould
Type and expression model information, are identified lip reading information, and processing is converted into voice messaging, and utilizes loud speaker or earphone
Broadcast voice information.
System shown in Figure 5 further includes：Server 503；The module Connection Service device by radio communication of lip reading identification device 30
503；Lip reading identification device 20 detects whether Connection Service device 503, when detecting Connection Service device 503, by the lip reading of acquisition
Information is sent to server 503；Lip reading information is identified in server 503, and processing is converted into voice messaging and knows to lip reading
Other device 30 passes voice messaging back.
System shown in Figure 3 further includes：Mobile terminal 504；The module connection movement by radio communication of lip reading identification device 30
Terminal 504；Mobile terminal 504 is configured as carrying out parameter setting to lip reading identification device 30.
Lip reading identification device and camera, loud speaker or earphone in system shown in Figure 5 can be wired connection, also may be used
Think wireless connection, so that lip reading identification device is received the lip reading information of camera acquisition by wired or wireless mode, to raising
Sound device or earphone send voice messaging and carry out voice broadcast,
The embodiment of the present invention additionally provides a kind of intelligent glasses, be provided on the intelligent glasses camera, loud speaker or
Earphone, memory and processor are provided in intelligent glasses, and Fig. 6 is a kind of intelligent glasses principle provided in an embodiment of the present invention
Figure, as shown in fig. 6, camera obtains lip reading information by style of shooting, lip reading information includes the shape of the mouth as one speaks, oral area muscle variation letter
Breath, lip color, mouth side Skin Color Information and facial expression information three classes；Intelligent algorithm, shape of the mouth as one speaks model and expression are stored in memory
The lip reading information that model information and recording camera obtain；Processor according to stored in memory intelligent algorithm, mouth mould
Type and expression model information, are identified lip reading information, and processing is converted into voice messaging；Loud speaker or earphone report voice
Information, loud speaker and earphone herein belong to a part for intelligent glasses, intelligence are not belonging to different from loud speaker above-mentioned and earphone
Energy glasses, only wirelessly or non-wirelessly connect with intelligent glasses.It is additionally provided with wireless communication module in the intelligent glasses；Intelligent glasses
Module is carried out wireless communication with server and/or mobile terminal by radio communication；Whether processor detects wireless communication module
The lip reading information that camera obtains is sent to server, by server pair by Connection Service device when detecting Connection Service device
Lip reading information is identified, and processing is converted into voice messaging and passes voice messaging back.
For device embodiments, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, can select according to the actual needs
Some or all of module therein is selected to achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying wound
In the case that the property made is worked, you can to understand and implement.
In conclusion by using camera obtain the shape of the mouth as one speaks, oral area muscle transition information, lip color, mouth side Skin Color Information and
Three category information of facial expression information；According to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory, to above-mentioned
Three category informations are identified respectively, and processing is converted into voice messaging；Using loud speaker or earphone broadcast voice information, lip is completed
Language identifies.The present invention can solve the communication problem of the hearing discrimination person of dispatching a person；It can solve remote communication problem, such as
Foreign countries have part maritime personnel to have professional training lip reading, and to judge other ship or people on the bank, what is said or talked about；It can be used for high-altitude
Operation, military affairs etc. facilitate timely transmission and the feedback of information.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (10)
1. a kind of lip reading recognition methods, which is characterized in that the method includes：
Lip reading information is obtained using camera, the lip reading information includes the shape of the mouth as one speaks, oral area muscle transition information, lip color, mouth side skin
Color information and facial expression information three classes；
According to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory, the lip reading information is identified,
Processing is converted into voice messaging；
The voice messaging is reported using loud speaker or earphone.
2. according to the method described in claim 1, it is characterized in that, described according to the intelligent algorithm stored in memory, the shape of the mouth as one speaks
The lip reading information is identified in model and expression model information, and processing is converted into voice messaging：
The shape of the mouth as one speaks, oral area muscle transition information and the shape of the mouth as one speaks model information in memory are compared and analyzed, obtain first
Lip reading information；
According to the lip color, the Magnifying chromoscopy of mouth colour of skin when Skin Color Information detects lip color and mouth, with the intelligence in memory
Algorithm carries out mouth movements feature judgement, and is compared and analyzed with the shape of the mouth as one speaks model information in memory, obtains the second lip reading
Information；
Using image processing techniques to the facial expression information carry out Expression Recognition, and with the expression model information in memory
It compares and analyzes, obtains third lip reading information；
Normalization is carried out to the first lip reading information, the second lip reading information and the third lip reading information, by normalizing
Treated, and lip reading information is converted into voice messaging.
3. according to the method described in claim 1, it is characterized in that, the method further includes：
It detects whether Connection Service device, when detecting Connection Service device, the lip reading information of acquisition is sent to the clothes
Business device, is identified the lip reading information by the server, and processing is converted into voice messaging and passes the voice messaging back.
4. a kind of lip reading identification device, which is characterized in that described device includes image collection module, memory, processor, voice
Broadcasting module,
Described image acquisition module is configured as obtaining lip reading information using camera, and the lip reading information includes the shape of the mouth as one speaks, oral area
Muscle transition information, lip color, mouth side Skin Color Information and facial expression information three classes；
The memory is configured as storage intelligent algorithm, shape of the mouth as one speaks model and expression model information；
The processor is configured as according to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory, to institute
It states lip reading information to be identified, processing is converted into voice messaging；
The voice broadcast module is configured as reporting the voice messaging using loud speaker or earphone.
5. device according to claim 4, which is characterized in that described device further includes：Wireless communication module；
The wireless communication module is configured as carrying out wireless communication with server and/or mobile terminal.
6. a kind of lip reading identifying system, which is characterized in that the system comprises camera, loud speaker or earphone, claims 4
Or the lip reading identification device described in 5；
The lip reading identification device obtains lip reading information using the camera, and the lip reading information includes the shape of the mouth as one speaks, oral area muscle
Transition information, lip color, mouth side Skin Color Information and facial expression information three classes；According to the intelligent algorithm stored in memory,
The lip reading information is identified in shape of the mouth as one speaks model and expression model information, and processing is converted into voice messaging, and described in utilization
Loud speaker or earphone report the voice messaging.
7. system according to claim 6, which is characterized in that the system also includes：Server；
Module connects the server to the lip reading identification device by radio communication；
The lip reading identification device detects whether to connect the server, when detecting the connection server, by acquisition
The lip reading information is sent to the server；
The lip reading information is identified in the server, and processing is converted into voice messaging and is passed to the lip reading identification device
Return the voice messaging.
8. system according to claim 6, which is characterized in that the system also includes：Mobile terminal；The lip reading identification
Module connects the mobile terminal to device by radio communication；
The mobile terminal is configured as carrying out parameter setting to the lip reading identification device.
9. a kind of intelligent glasses, which is characterized in that camera, loud speaker or earphone are provided on the intelligent glasses, it is described
Memory and processor are provided in intelligent glasses,
The camera obtains lip reading information by style of shooting, and the lip reading information includes the shape of the mouth as one speaks, oral area muscle transition information,
Lip color, mouth side Skin Color Information and facial expression information three classes；
It is stored with intelligent algorithm, shape of the mouth as one speaks model and expression model information in the memory, and records the camera and obtains
Lip reading information；
The processor believes the lip reading according to intelligent algorithm, shape of the mouth as one speaks model and the expression model information stored in memory
Breath is identified, and processing is converted into voice messaging；
The loud speaker or earphone report the voice messaging.
10. intelligent glasses according to claim 9, which is characterized in that be additionally provided with wireless communication in the intelligent glasses
Module；The intelligent glasses are carried out wireless communication by the wireless communication module with server and/or mobile terminal；
The processor detect the wireless communication module whether Connection Service device will be described when detecting Connection Service device
The lip reading information that camera obtains is sent to the server, and the lip reading information is identified by the server,
Processing is converted into voice messaging and passes the voice messaging back.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810090891.2A CN108319912A (en) | 2018-01-30 | 2018-01-30 | A kind of lip reading recognition methods, device, system and intelligent glasses |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810090891.2A CN108319912A (en) | 2018-01-30 | 2018-01-30 | A kind of lip reading recognition methods, device, system and intelligent glasses |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108319912A true CN108319912A (en) | 2018-07-24 |
Family
ID=62890093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810090891.2A Pending CN108319912A (en) | 2018-01-30 | 2018-01-30 | A kind of lip reading recognition methods, device, system and intelligent glasses |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108319912A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110351631A (en) * | 2019-07-11 | 2019-10-18 | 京东方科技集团股份有限公司 | Deaf-mute's alternating current equipment and its application method |
| WO2020192231A1 (en) * | 2019-03-25 | 2020-10-01 | 中国科学院深圳先进技术研究院 | Auxiliary communication system based on surface electromyography lip reading recognition |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1323435A (en) * | 1998-10-02 | 2001-11-21 | 国际商业机器公司 | System and method for providing network coordinated conversational services |
| CN101101752A (en) * | 2007-07-19 | 2008-01-09 | 华中科技大学 | Monosyllabic language lip-reading recognition system based on vision character |
| CN101674363A (en) * | 2009-09-23 | 2010-03-17 | 中兴通讯股份有限公司 | Mobile equipment and talking method |
| CN103092329A (en) * | 2011-10-31 | 2013-05-08 | 南开大学 | Lip reading technology based lip language input method |
| CN103295575A (en) * | 2012-02-27 | 2013-09-11 | 北京三星通信技术研究有限公司 | Speech recognition method and client |
| WO2015154419A1 (en) * | 2014-09-03 | 2015-10-15 | 中兴通讯股份有限公司 | Human-machine interaction device and method |
| JP2015220684A (en) * | 2014-05-20 | 2015-12-07 | 株式会社ニコン | Portable terminal equipment and lip reading processing program |
| CN105488524A (en) * | 2015-11-26 | 2016-04-13 | 中山大学 | Wearable device based lip language identification method and system |
-
2018
- 2018-01-30 CN CN201810090891.2A patent/CN108319912A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1323435A (en) * | 1998-10-02 | 2001-11-21 | 国际商业机器公司 | System and method for providing network coordinated conversational services |
| CN101101752A (en) * | 2007-07-19 | 2008-01-09 | 华中科技大学 | Monosyllabic language lip-reading recognition system based on vision character |
| CN101674363A (en) * | 2009-09-23 | 2010-03-17 | 中兴通讯股份有限公司 | Mobile equipment and talking method |
| CN103092329A (en) * | 2011-10-31 | 2013-05-08 | 南开大学 | Lip reading technology based lip language input method |
| CN103295575A (en) * | 2012-02-27 | 2013-09-11 | 北京三星通信技术研究有限公司 | Speech recognition method and client |
| JP2015220684A (en) * | 2014-05-20 | 2015-12-07 | 株式会社ニコン | Portable terminal equipment and lip reading processing program |
| WO2015154419A1 (en) * | 2014-09-03 | 2015-10-15 | 中兴通讯股份有限公司 | Human-machine interaction device and method |
| CN105488524A (en) * | 2015-11-26 | 2016-04-13 | 中山大学 | Wearable device based lip language identification method and system |
Non-Patent Citations (1)
| Title |
|---|
| 杨冬涛等,: "基于唇色信息的唇部检测方法研究", vol. 28, no. 11, pages 3 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020192231A1 (en) * | 2019-03-25 | 2020-10-01 | 中国科学院深圳先进技术研究院 | Auxiliary communication system based on surface electromyography lip reading recognition |
| CN110351631A (en) * | 2019-07-11 | 2019-10-18 | 京东方科技集团股份有限公司 | Deaf-mute's alternating current equipment and its application method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108470169A (en) | Face identification system and method | |
| CN106104569B (en) | For establishing the method and apparatus of connection between electronic device | |
| US11727952B2 (en) | Glasses with closed captioning, voice recognition, volume of speech detection, and translation capabilities | |
| CN103888581B (en) | A kind of communication terminal and its method for recording call-information | |
| CN104360736B (en) | terminal control method and system based on gesture | |
| CN103902046B (en) | Intelligent prompt method and terminal | |
| CN104820495B (en) | A kind of micro- Expression Recognition of exception and based reminding method and device | |
| CN107480622A (en) | Micro- expression recognition method, device and storage medium | |
| CN108009521A (en) | Humanface image matching method, device, terminal and storage medium | |
| CN107606512A (en) | A kind of intelligent desk lamp, the method and device based on intelligent desk lamp prompting user's sitting posture | |
| WO2021036318A1 (en) | Video image processing method, and device | |
| CN208351494U (en) | Face identification system | |
| JP2021532461A (en) | Skin detection method and electronic device | |
| CN208875459U (en) | A kind of intelligent safety helmet | |
| CN112016367A (en) | Emotion recognition system and method and electronic equipment | |
| US20210350823A1 (en) | Systems and methods for processing audio and video using a voice print | |
| CN109829691B (en) | C/S card punching method and device based on position and deep learning multiple biological features | |
| CN109104209A (en) | A kind of intelligent wearable device | |
| CN108198265A (en) | Attendance checking system based on voice and face composite identification | |
| CN108319912A (en) | A kind of lip reading recognition methods, device, system and intelligent glasses | |
| CN108206892A (en) | Guard method, device, mobile terminal and the storage medium of contact person's privacy | |
| KR102263154B1 (en) | Smart mirror system and realization method for training facial sensibility expression | |
| CN105989328A (en) | Method and device for detecting use of handheld device by person | |
| KR20160011302A (en) | System and method for digital image processing by wearable glass device | |
| CN204790850U (en) | Unusual little expression discernment and reminding device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |