CN102663349A - Intelligent interaction method based on face identification and apparatus thereof - Google Patents
Intelligent interaction method based on face identification and apparatus thereof Download PDFInfo
- Publication number
- CN102663349A CN102663349A CN2012100780023A CN201210078002A CN102663349A CN 102663349 A CN102663349 A CN 102663349A CN 2012100780023 A CN2012100780023 A CN 2012100780023A CN 201210078002 A CN201210078002 A CN 201210078002A CN 102663349 A CN102663349 A CN 102663349A
- Authority
- CN
- China
- Prior art keywords
- visitor
- interactive device
- identity
- image
- face
- 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
Images
Landscapes
- Collating Specific Patterns (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides an intelligent interaction method based on face identification. The method comprises the following steps: using a camera to determine a visual area, and verifying a visitor identity through the face identification after a visitor enters into the visual area; after the visitor identity is determined, mechanically driving interaction equipment so that the interaction equipment is faced to the visitor; emitting an instruction to the interaction equipment by the visitor through man-machine interaction, wherein after the instruction is received, the interaction equipment processes the instruction and gives a feedback.
Description
Technical field
The present invention relates to image processing field, particularly area of facial recognition.
Background technology
Present interactive means is confined to mutual one to one more, and mostly interactive device is fixed.Not enough hommization and intellectuality also lack certain specific aim simultaneously.Especially the interactive mode to VIP client is also very single.
Summary of the invention
In view of this,, the invention provides a kind of intelligent interactive method and device, can realize portable many interactive modes to VIP client based on face recognition for addressing the above problem.
In order to achieve the above object, the present invention provides a kind of intelligent interactive method based on face recognition, and it may further comprise the steps: adopt camera to confirm the viewing area, after the visitor gets into the viewing area, verify visitor's identity through face recognition; After confirming visitor's identity, the Mechanical Driven interactive device makes it towards the visitor; The visitor sends instruction through man-machine interaction to said interactive device, and said interactive device receives instruction aftertreatment instruction and feeds back.
Further; Said after the visitor gets into the viewing area step through face recognition checking visitor identity further comprise: the face-image of input legitimate viewer in database in advance; And the image of importing is carried out rasterizing handle, the rgb value at the grid intersections place of acquisition input face image and the coordinate figure of relative profile; Eyes with the people in the viewing area are the focusing benchmark, adopt facial the detection in picture, to detect and isolate face-image; Facial figure to acquisition carries out the gridding processing, the rgb value at the place, grid point of crossing of acquisition collection in worksite face-image and the coordinate figure of relative profile; With the input face image of said collection in worksite face-image in the database coupling of comparing, after mating successfully, confirm observer's identity.
Further; Said visitor sends instruction through man-machine interaction to said interactive device; Said interactive device receives instruction aftertreatment instruction and gives feedback step and further comprises: the observer sends phonetic order to said interactive device, and said interactive device receives said phonetic order post analysis phonetic order and responds.
4. method according to claim 3 is characterized in that, when the phonetic order of analyzing the visitor when interactive device was the path searching instruction, the method through virtual reality showed the way for the visitor.
Further, when existing more than an observer who confirms identity in the said viewing area, after first observer sent phonetic order, the Mechanical Driven interactive device made it towards said first observer.
Further, after first observer sends phonetic order, after said interactive device receives phonetic order, confirm first observer's physical location through auditory localization, the said interactive device of Mechanical Driven makes it towards first observer.
Further, said method is after confirming visitor's identity, and the Mechanical Driven interactive device makes it after visitor's step, plays corresponding film according to said visitor's identity.
On the other hand; The present invention also provides a kind of intelligent interaction device based on face recognition, it is characterized in that, comprises with the lower part: camera; It is used to obtain the image in the viewing area, after the visitor gets into the viewing area, verifies visitor's identity through face recognition; Microphone array is used to receive visitor's phonetic order, and confirms said visitor's position; Mechanical arm, after perhaps microphone array was received phonetic order after confirming visitor's identity, mechanical arm drives interactive device made it towards the visitor.
Further, said camera also comprises the intensity of illumination sensor, is used for through the illuminance in the current viewing area of said intensity of illumination sensor, and is strong and weak according to illuminance, adjustment camera exposure.
Embodiment provided by the invention confirms mutual person's identity through face recognition, and reports corresponding contents according to mutual person's identity.Support multi-person speech interaction simultaneously, and can face mutual person directly, make alternately hommization more that emphasis point is more arranged.
Description of drawings
Fig. 1 is based on the intelligent interactive method process flow diagram of face recognition in specific embodiment of the present invention.
Fig. 2 carries out the effect synoptic diagram after rasterizing is handled to face-image in specific embodiment of the present invention.
Fig. 3 carries out the synoptic diagram that mate the key area to face-image in specific embodiment of the present invention.
Fig. 4 utilizes microphone array to obtain the method synoptic diagram of sound source in specific embodiment of the present invention.
Fig. 5 is the intelligent interaction device synoptic diagram that gives face recognition in specific embodiment of the present invention.
Embodiment
The invention provides a kind of intelligent interactive method based on face recognition, specifically as shown in Figure 1, it may further comprise the steps.
Eyes with the people in the viewing area are the focusing benchmark, adopt facial the detection in picture, to detect and isolate face-image.
Facial figure to acquisition carries out the gridding processing, the rgb value at the place, grid point of crossing of acquisition collection in worksite face-image and the coordinate figure of relative profile.
With the input face image of said collection in worksite face-image in the database coupling of comparing, after mating successfully, confirm observer's identity.
In a concrete embodiment, as shown in Figure 3, the Delta Region and the face profile of main scanning contrast people face are like positions such as eyes, nose, face, chin, cheekbone, place between the eyebrows, foreheads.In order to make matching detection more accurate, the present invention has adopted edge sharpening to handle the combination Fourier algorithm in a concrete embodiment and has repeatedly handled image, up to the profile that can describe people's face clearly and key parameter point.Simultaneously, detect the illuminance in the current viewing area through camera, strong and weak according to illuminance, adjustment camera exposure.Find a view at random through camera, through with the comparison of chances of losing games portion image, adjustment collection in worksite face-image quality is revised the rgb value of collection in worksite face-image corresponding point.
In a concrete embodiment, the visitor sends phonetic order to said interactive device, and said interactive device receives said phonetic order post analysis phonetic order and responds.How ask weather like the visitor, systematic analysis is also circulated a notice of weather on the same day.In a specific embodiment, when the phonetic order of analyzing the visitor when interactive device was the path searching instruction, the method through virtual reality showed the way for the visitor, and overview and analogue navigation promptly show paths on interactive device.
When existing more than an observer who confirms identity in the said viewing area, after first observer sent phonetic order, the Mechanical Driven interactive device made it towards said first observer.
In a specific embodiment, after first observer sent phonetic order, said interactive device received phonetic order, confirmed first observer's physical location through auditory localization, and the said interactive device of Mechanical Driven makes it towards first observer.Concrete grammar is as shown in Figure 4, and the frequency stabilization because human body is spoken does not have very strong variation, can adopt one group of microphone array to receive that the difference of identical voice calculates the sound source position of different voice according to different microphones.The vector that target A, B, C pass to microphone Mic C has nothing in common with each other, so the intensity of sound of the target A that obtains of Mic C, B, C is different.In like manner the intensity of sound of the target A that obtains of microphone Mic A, microphone Mic B, B, C is also different.The intensity of sound that system obtains according to MicA, MicB, MicC, and combine the physical location difference of 3 microphones to calculate sequencing of speaking and the orientation of target A, B, C.
The present invention also provide a kind of based on face recognition can only interactive device, as shown in Figure 5, it comprises with the lower part.
Camera 1, it is used to obtain the image in the viewing area, after the visitor gets into the viewing area, verifies visitor's identity through face recognition.In a concrete embodiment, in database, import the face-image of legitimate viewer in advance, and the image of input is carried out the rasterizing processing, the rgb value at the grid intersections place of acquisition input face image and the coordinate figure of relative profile.Facial image after rasterizing is handled is as shown in Figure 2, and the data of each grid intersection comprise the rgb value and this position with respect to face mask of this point.
Eyes with the people in the viewing area are the focusing benchmark, adopt facial the detection in picture, to detect and isolate face-image.
Facial figure to acquisition carries out the gridding processing, the rgb value at the place, grid point of crossing of acquisition collection in worksite face-image and the coordinate figure of relative profile.
With the input face image of said collection in worksite face-image in the database coupling of comparing, after mating successfully, confirm observer's identity.
In a concrete embodiment, as shown in Figure 3, the Delta Region and the face profile of main scanning contrast people face are like positions such as eyes, nose, face, chin, cheekbone, place between the eyebrows, foreheads.In order to make matching detection more accurate, the present invention has adopted the edge sharpening processing in a concrete embodiment, repeatedly handle image in conjunction with Fourier algorithm, up to the profile that can describe people's face clearly and key parameter point.Simultaneously, said camera 1 also comprises the intensity of illumination sensor.Through the illuminance in the current viewing area of said intensity of illumination sensor, strong and weak according to illuminance, adjustment camera exposure.Find a view at random through camera, through with the comparison of chances of losing games portion image, adjustment collection in worksite face-image quality is revised the rgb value of collection in worksite face-image corresponding point.
Microphone array 2 is used to receive visitor's phonetic order, and confirms said visitor's position.In a concrete embodiment, microphone array 2 can receive that the difference of identical voice calculates the sound source position of different voice according to different microphones.The vector that target A, B, C pass to microphone Mic C has nothing in common with each other, so the intensity of sound of the target A that obtains of Mic C, B, C is different.In like manner the intensity of sound of the target A that obtains of microphone Mic A, microphone Mic B, B, C is also different.The intensity of sound that system obtains according to MicA, MicB, MicC, and combine the physical location difference of 3 microphones to calculate sequencing of speaking and the orientation of target A, B, C.
Mechanical arm 4, after perhaps microphone array was received phonetic order after confirming visitor's identity, mechanical arm drives interactive device 3 made it towards the visitor.In a concrete embodiment, the Mechanical Driven interactive device is play corresponding video according to visitor's identity behind the visitor, like welcome's video.
The above is merely preferred embodiment of the present invention, and is in order to restriction the present invention, not all within spirit of the present invention and principle, any modification of being done, is equal to replacement etc., all should be included within protection scope of the present invention.
Claims (9)
1. intelligent interactive method based on face recognition, it may further comprise the steps:
Adopt camera to confirm the viewing area, after the visitor gets into the viewing area, verify visitor's identity through face recognition;
After confirming visitor's identity, the Mechanical Driven interactive device makes it towards the visitor;
The visitor sends instruction through man-machine interaction to said interactive device, and said interactive device receives instruction aftertreatment instruction and feeds back.
2. method according to claim 1 is characterized in that, said after the visitor gets into the viewing area step through face recognition checking visitor identity further comprise:
In database, import the face-image of legitimate viewer in advance, and the image of input is carried out the rasterizing processing, the rgb value at the grid intersections place of acquisition input face image and the coordinate figure of relative profile;
Eyes with the people in the viewing area are the focusing benchmark, adopt facial the detection in picture, to detect and isolate face-image;
Facial figure to acquisition carries out the gridding processing, the rgb value at the place, grid point of crossing of acquisition collection in worksite face-image and the coordinate figure of relative profile;
With the input face image of said collection in worksite face-image in the database coupling of comparing, after mating successfully, confirm observer's identity.
3. method according to claim 1; It is characterized in that; Said visitor sends instruction through man-machine interaction to said interactive device; Said interactive device receives instruction aftertreatment instruction and gives feedback step and further comprises: the observer sends phonetic order to said interactive device, and said interactive device receives said phonetic order post analysis phonetic order and responds.
4. method according to claim 3 is characterized in that, when the phonetic order of analyzing the visitor when interactive device was the path searching instruction, the method through virtual reality showed the way for the visitor.
5. method according to claim 3 is characterized in that, when existing more than an observer who confirms identity in the said viewing area, after first observer sent phonetic order, the Mechanical Driven interactive device made it towards said first observer.
6. method according to claim 5; It is characterized in that, after first observer sends phonetic order, after said interactive device receives phonetic order; Confirm first observer's physical location through auditory localization, the said interactive device of Mechanical Driven makes it towards first observer.
7. method according to claim 1 is characterized in that, said method is after confirming visitor's identity, and the Mechanical Driven interactive device makes it after visitor's step, plays corresponding film according to said visitor's identity.
8. the intelligent interaction device based on face recognition is characterized in that, comprises with the lower part: camera, and it is used to obtain the image in the viewing area, after the visitor gets into the viewing area, verifies visitor's identity through face recognition; Microphone array is used to receive visitor's phonetic order, and confirms said visitor's position; Mechanical arm, after perhaps microphone array was received phonetic order after confirming visitor's identity, mechanical arm drives interactive device made it towards the visitor.
9. device according to claim 8 is characterized in that said camera also comprises the intensity of illumination sensor, is used for through the illuminance in the current viewing area of said intensity of illumination sensor, and is strong and weak according to illuminance, adjustment camera exposure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100780023A CN102663349A (en) | 2012-03-22 | 2012-03-22 | Intelligent interaction method based on face identification and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100780023A CN102663349A (en) | 2012-03-22 | 2012-03-22 | Intelligent interaction method based on face identification and apparatus thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102663349A true CN102663349A (en) | 2012-09-12 |
Family
ID=46772833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012100780023A Pending CN102663349A (en) | 2012-03-22 | 2012-03-22 | Intelligent interaction method based on face identification and apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102663349A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103019388A (en) * | 2013-01-09 | 2013-04-03 | 苏州云都网络技术有限公司 | Screen unlocking method, screen locking method and terminal |
| WO2015131712A1 (en) * | 2014-09-19 | 2015-09-11 | 中兴通讯股份有限公司 | Face recognition method, device and computer readable storage medium |
| CN105513304A (en) * | 2016-01-13 | 2016-04-20 | 华侨大学 | Audio and video identifying alarm using APP (application) of mobile phone to operate rolling shutter door |
| CN106446873A (en) * | 2016-11-03 | 2017-02-22 | 北京旷视科技有限公司 | Face detection method and device |
| CN110720762A (en) * | 2019-09-26 | 2020-01-24 | 广州视觉风科技有限公司 | Intelligent interaction method and device based on facial recognition |
-
2012
- 2012-03-22 CN CN2012100780023A patent/CN102663349A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103019388A (en) * | 2013-01-09 | 2013-04-03 | 苏州云都网络技术有限公司 | Screen unlocking method, screen locking method and terminal |
| WO2015131712A1 (en) * | 2014-09-19 | 2015-09-11 | 中兴通讯股份有限公司 | Face recognition method, device and computer readable storage medium |
| US10311291B2 (en) | 2014-09-19 | 2019-06-04 | Zte Corporation | Face recognition method, device and computer readable storage medium |
| CN105513304A (en) * | 2016-01-13 | 2016-04-20 | 华侨大学 | Audio and video identifying alarm using APP (application) of mobile phone to operate rolling shutter door |
| CN105513304B (en) * | 2016-01-13 | 2020-07-17 | 华侨大学 | But cell-phone APP controls voice and video recognition alarm of rolling slats door |
| CN106446873A (en) * | 2016-11-03 | 2017-02-22 | 北京旷视科技有限公司 | Face detection method and device |
| CN110720762A (en) * | 2019-09-26 | 2020-01-24 | 广州视觉风科技有限公司 | Intelligent interaction method and device based on facial recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11031012B2 (en) | System and method of correlating mouth images to input commands | |
| US10853677B2 (en) | Verification method and system | |
| CN102663349A (en) | Intelligent interaction method based on face identification and apparatus thereof | |
| US9007473B1 (en) | Architecture for augmented reality environment | |
| US10638251B2 (en) | Customizing head-related transfer functions based on monitored responses to audio content | |
| US11234096B2 (en) | Individualization of head related transfer functions for presentation of audio content | |
| CN107894836B (en) | Human-computer interaction method for processing and displaying remote sensing image based on gesture and voice recognition | |
| TW201923759A (en) | Sound processing method and interactive device | |
| TWI620098B (en) | Head mounted device and guiding method | |
| CN107945625A (en) | A kind of pronunciation of English test and evaluation system | |
| US9591229B2 (en) | Image tracking control method, control device, and control equipment | |
| CN106926252A (en) | A kind of hotel's intelligent robot method of servicing | |
| US11526589B2 (en) | Wearer identification based on personalized acoustic transfer functions | |
| US11218831B2 (en) | Determination of an acoustic filter for incorporating local effects of room modes | |
| KR20140125183A (en) | Eye-glasses which attaches projector and method of controlling thereof | |
| US10987198B2 (en) | Image simulation method for orthodontics and image simulation device thereof | |
| CN107293236A (en) | The intelligent display device of adaptive different user | |
| CN114365510A (en) | Selecting spatial positioning for audio personalization | |
| KR20220044489A (en) | Image processing apparatus, image processing method, and program | |
| CN207373180U (en) | A kind of hotel's intelligent robot service system | |
| US11871198B1 (en) | Social network based voice enhancement system | |
| CN102194110B (en) | Eye positioning method in human face image based on K-L (Karhunen-Loeve) transform and nuclear correlation coefficient | |
| CN204215356U (en) | Contactless health interactive system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120912 |