CN107943449A - A kind of intelligent sound system based on human facial expression recognition - Google Patents
A kind of intelligent sound system based on human facial expression recognition Download PDFInfo
- Publication number
- CN107943449A CN107943449A CN201711411607.9A CN201711411607A CN107943449A CN 107943449 A CN107943449 A CN 107943449A CN 201711411607 A CN201711411607 A CN 201711411607A CN 107943449 A CN107943449 A CN 107943449A
- Authority
- CN
- China
- Prior art keywords
- user
- face
- control unit
- mobile phone
- expression 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
- 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
- G06F3/16—Sound input; Sound output
- G06F3/162—Interface to dedicated audio devices, e.g. audio drivers, interface to CODECs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
- G06F16/636—Filtering based on additional data, e.g. user or group profiles by using biological or physiological data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Physiology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of intelligent sound system based on human facial expression recognition,It is related to stereo set and intelligent man-machine interaction technical field,The present invention includes man face image acquiring unit,Storage unit,Operation processing unit,Wi Fi modules,User mobile phone client,Musical theme control unit and loudspeaker,Man face image acquiring unit photographs user facial photo simultaneously therefrom extracts face characteristic and expressive features,The trained different property data bases of expression and the registered face template of different user are stored in memory,Operation processing unit is to face characteristic and expressive features Classification and Identification,Record the psychology change of user and by the result of Expression Recognition,The psychology change of user and recommendation music are sent to user mobile phone client by Wi Fi modules,User mobile phone client controls musical theme control unit to play different genres of music by loudspeaker and dredges user emotion,The present invention changes with that can record user psychology,Dredge the advantages of user emotion promotes mental health.
Description
Technical field
Type of the present invention is related to stereo set and intelligent man-machine interaction technical field, and face is based on more particularly to one kind
The intelligent sound system of portion's Expression Recognition.
Background technology
At present, as the fast lifting of computer hardware performance, commercial face identification system rapidly enter market.It is real
Become with the face recognition technology of change and have become one of most important technology of domestic and international protection and monitor field, and it is domestic at present
Outer to have the matured product that identify human face expression to occur, human face expression reflects angry, glad, sad, surprised, detest and fear
Six kinds of main emotions, every kind of emotion reflect a kind of unique psychological activity of people with unique expression.
Existing sound technique mainly lifts the sound for the music that sound equipment plays out by the pendulum position of electronic technology and sound equipment
Matter and acoustic efficiency, and can only be selected by user oneself in the music to be played or random, loop play music list
Music, it is impossible to automatic identification user expression reflection psychological activity, it is impossible to record user within a period of time psychology change
The psychology change of change situation and the psychological activity reflected according to the expression of user and user recently recommends respective class from trend user
The music of type, to dredge user emotion.
The present invention in view of the foregoing drawbacks, realize with recognition of face and Expression Recognition technology come automatic identification user identity and
The corresponding psychological activity of user's expression, psychological situation of change of the counting user in setting time, and corresponded to according to user's expression
Psychology it is interactive and the automatic music type for recommending to be adapted to user to listen to of psychology change of user's nearest a period of time is to user, dredge
Lead user emotion and promote the mental health of user.
The content of the invention
It is an object of the invention to：The present invention provides one kind with recognition of face, Expression Recognition and recommends music work(automatically
The intelligent sound system based on human facial expression recognition of energy.
The present invention specifically uses following technical scheme to achieve these goals：
A kind of intelligent sound system based on human facial expression recognition, including loudspeaker, further include man face image acquiring unit,
Memory, operation processing unit, Wi-Fi module, musical theme control unit, user mobile phone client；The facial image is adopted
Collection unit is connected with the memory, and the memory is connected with the operation processing unit, the operation processing unit and institute
Wi-Fi module connection, the Wi-Fi module and the user mobile phone client network connection are stated, the musical theme control is single
Member is connected with the Wi-Fi module and the loudspeaker respectively；A kind of intelligent sound system based on human facial expression recognition
Recognition of face and human facial expression recognition are carried out to user, determine the identity and expression of user, the man face image acquiring unit, is used
The still image that face front still image in collection user and the man face image acquiring unit to input obtain carries out
Face datection, judges in the image of different illumination condition and background with the presence or absence of different directions posture, different expression and can
The method that artificial neural network can be used by the face of jewelry partial occlusion, the Face datection, with N × N pixels of sufficient amount
Face sample and the training sample that is inputted as artificial neural network of non-face sample, carry out the training of artificial neural network,
Constantly the number of plies of adjustment network and weights are realized using artificial neural network to the background comprising facial image in trained process
Image scans for, and distinguishes face and non-face, whole face recognition process knot if being not have face in image if judging result
Beam, if judging result be in image there are face if locating and tracking is carried out to face, first to face position in the picture into
Row is accurately positioned, and then facial image is pre-processed, and different illumination, head appearance are eliminated to a certain extent by pretreatment
Influence of the state to facial image, improves the accuracy rate of recognition of face, is influenced by the dark degree of optical illumination, original facial image is not by
The pixel composition of same gray value (0-255), according to the intensity profile situation of pixel in original facial image by original facial image
The grey level histogram of frequency that the pixel being converted into description original image occurs in different grey-scale, picture in original facial image
The intensity profile of element is often uneven, its intensity profile is often focused in narrow grey level range, causes image detail not
Enough clear and image contrasts are low, concentrated on original facial image from intensity profile using gray-level histogram equalization algorithm
It is transformed to that intensity profile scope is wider and the image of intensity profile evenly in narrow scope, i.e., to each in grey level histogram
Gray level is normalized, and improves the contrast of facial image；The process pre-processed to facial image is also wrapped
Include the angle and dimension normalization of end rotation in facial image by human eye positioning, to the face orientation in facial image into
The adjustment of professional etiquette generalized, improves the speed of recognition of face and reduces the complexity of face recognition algorithms, the mistake of the human eye positioning
Journey includes the central point of positioning human eye, estimation iris radius, detection upper eyelid curve, detection palpebra inferior curve, the positioning people
The method of the central point of eye is to describe facial image gray average and variance change in a certain direction using mixed projection function HPF
The synthesis of change situation, eyes region are compared with peripheral region, and color is dark, and gray value is low, and gray-value variation rate is higher, mixing
Projection function HPF can reflect the change of gray scale and reflect the change of rate of gray level, described after positioning eyes central point
Estimate that iris radius is realized by the circumference searched on the edge positioned at iris dark pixel and between sclera bright pixel, iris
It is approximate circle and iris is darker than background, the detection method of the upper palpebra inferior opens the detection of height, eyes including eyes
The detecting of marginal point, the removal of point not in the know, polynomial curve matching, the detection that the eyes open height pass through in vertical direction
The iris region of upper scanning facial image, and the red average value calculated per one-row pixels is realized, is opened in eyes known to height
On the premise of, the place reduced line by line since iris edge pixel brightness value in visible iris region is swept out, and is found
Brightness starts to dramatically increase and the point of local luminance values minimum, obtains a series of points positioned at eyes edge, realizes the eye
The detection of eyeball marginal point, the eyes marginal point detected may include the point not in the know and erroneous point for deviateing actual eye contour,
The straight line converted using hough removes the point not in the know for deviateing actual eye contour, realizes the point not in the know
Remove, in the eyes marginal point remained, the point of the leftmost side and the rightmost side is as canthus point, more than right and left eyes angle point line
The up contour point for the iris that eyes marginal point is detected as the point set in upper eyelid and addition, estimates eyelid curve, by canthus
Palpebra inferior is depicted with the conic section of iris circumference low spot, the man face image acquiring unit is completed human eye to facial image and determined
After position, head pose correction, greyscale transformation and histogram equalization, normalized, terminate image preprocessing process concurrency and send
Face recognition features' extraction is carried out to the operation processing unit；The man face image acquiring unit completes human eye to facial image
After positioning, head pose correction, greyscale transformation and histogram equalization, normalized, face-image is carried out to facial image
Identify sub-district regional partition, to the face of different expressions, the deformation that same position produces is different, it is necessary to which face is divided into
Different regions is carried out the extraction of geometric properties by the operation processing unit respectively；The operation processing unit is by the people of extraction
Face identification feature is contrasted with whole face templates in the registered face template library in the memory, carries out face knowledge
, do not determine recognition of face whether by with the identity information of user that identifies, if recognition of face is by determining the identity of user
Then face recognition process terminates information, carries out new user's registration not if if recognition of face and updates the registration in the reservoir
Face template storehouse, the process of face recognition features' extraction includes feature selecting and feature extraction, even if the feature extraction
The initial data of facial image is made choice and converted with operation time and computational complexity alap algorithm, is obtained anti-
The feature vector of face classification essence is reflected, primitive character quantity is very big, and the feature selecting is i.e. from one group of a large amount of primitive character
The validity feature of face can fully, effectively be represented by selecting a part, reduce the dimension of feature space；The Extraction of Geometrical Features
Series of features point, such as eyebrow, eye, nose, mouth, chin etc. are positioned to pretreated face face-image first, to the spy
The position and distance change for levying point are positioned and are measured, and determine the feature of its size, distance, shape and mutual ratio, from
And feature vector is obtained, by the Gabor wavelet coefficient of image convolution extraction feature point, made with the matching distance of Gabor characteristic
For the module of similarity, the process of the Extraction of Geometrical Features is completed；The operation processing unit is completed to by pre- place
After the Extraction of Geometrical Features of the facial image of reason, the facial expression feature database stored in the memory is read, passes through institute
State neural network classifier and discriminant classification is carried out to expression using multilayer neural network, and export Expression Recognition result；The Wi-
Fi modules provide Wi-Fi network and establish network connection with the user mobile phone client；The operation processing unit identifies user
Identity information and user's expression attribute and the psychological situation of change for counting registered user in period of setting, the calculation process
User psychology situation of change in user's expression attribute and set period of time is sent to user by unit by the Wi-Fi module
The user psychology situation of change of user's expression attribute and nearest two weeks is sent to institute by cell-phone customer terminal, the operation processing unit
Musical theme control unit is stated, the musical theme control unit receives user's expression attribute and the user psychology of nearest two weeks
Situation of change, according to pair between the nearest psychological situation of change of the attribute of user's Expression Recognition result, user and musical theme
It should be related to, the musical theme of recommendation is sent to by the user mobile phone client, the user mobile phone client by Wi-Fi module
Termination receives the musical theme of recommendation, sets the music list to be played, and is sent to the Wi-Fi module, the Wi-Fi moulds
The music list to be played of user setting is transmitted to the musical theme control unit, the musical theme control unit by block
The loudspeaker is controlled to play the music in the music playlist of user setting.
Further, the man face image acquiring unit is equipped with the camera for being used for shooting user's frontal face photo, shooting
Head automatic focus adjustable, primitive man's face face-image of shooting clear, is sent into the caching storage of the man face image acquiring unit,
Face datection, Face detection tracking and image are carried out to primitive man's face face-image for the man face image acquiring unit in advance to locate
Reason.
Further, the musical theme control unit is equipped with the SD card of storage music, and the musical theme control unit is embedding
Enter linux kernel and cut out operating system and music player application program after transplanting, the musical theme control unit is embedding
Embedded system, is embedded with the operating system based on linux kernel, manages the software and hardware resources of musical theme player and is appointed
The musical audio files for belonging to different musical themes are downloaded to the SD card by business scheduling, user, by described in SD card insertion
Musical theme control unit, the musical theme control unit read the music inside SD card, the corresponding different musical themes of generation
Music list, the musical theme control unit receive user's Expression Recognition result that the operation processing unit sends and
The nearest psychological situation of change of user, according to user's Expression Recognition result, the nearest psychological situation of change of user and different music
Correspondence between theme, by the Wi-Fi module by the musical theme of recommendation and the corresponding sound of musical theme recommended
Happy list is sent to the user mobile phone client, and it is anti-that the musical theme control unit receives the user mobile phone client
After the music list to be played of the user setting of feedback, start the music player application program of installation, broadcast by loudspeaker
Put the musical audio files in the music list to be played of user setting.
Further, the user mobile phone client is the application program for supporting IOS or the mobile phone of Android operation system,
The mobile phone-downloaded of user is simultaneously installed the Wi-Fi network that the Wi-Fi module provides is connected after the user mobile phone client, with institute
State the intelligent sound system based on human facial expression recognition and establish network connection, user mobile phone client connected Wi-Fi network receipts
User's recognition of face that the operation processing unit is sent is with Expression Recognition as a result, user mobile phone client connected Wi-Fi
Network receives the recommendation musical theme music list corresponding with musical theme is recommended that the musical theme control unit is sent, and uses
Family cell-phone customer terminal sends the music list to be played of user setting to the Wi-Fi module by Wi-Fi network.
Beneficial effects of the present invention are as follows：
1. using recognition of face and Expression Recognition, it can be achieved that automatic identification to user identity and to user's face expression
Automatic identification, and psychological situation of change of the counting user within the period of setting.
2. musical theme control unit changes according to the recognition result of user's expression and the user psychology of nearest two weeks, push
Musical theme music list corresponding with musical theme is recommended is recommended to select music to play for user, realization is dredged to user
User emotion, promotes user psychology health, and user experience is good.
Brief description of the drawings
Fig. 1 is a kind of operational process schematic diagram of the intelligent sound system based on human facial expression recognition.
Fig. 2 is a kind of structure diagram of the intelligent sound system based on human facial expression recognition.
Reference numeral：1- man face image acquiring units, 2- storage units, 3- operation processing units, 4-Wi-Fi modules, 5-
Musical theme control unit, 6- user mobile phone clients, 7- loudspeakers.
Embodiment
In order to which those skilled in the art are better understood from the present invention below in conjunction with the accompanying drawings with following embodiments to the present invention
It is described in further detail.
Embodiment 1
As shown in Fig. 1 to Fig. 2, the present invention provides a kind of intelligent sound system based on human facial expression recognition, including raises one's voice
Device 7, further includes man face image acquiring unit 1, memory 2, operation processing unit 3, Wi-Fi module 4, musical theme control unit
5th, user mobile phone client 6；The man face image acquiring unit 1 and the memory 2 connect, the memory 2 and the fortune
Calculate processing unit 3 to connect, the operation processing unit 3 and the Wi-Fi module 4 connect, the Wi-Fi module 4 and the use
6 network connection of family cell-phone customer terminal, the musical theme control unit 5 respectively with the Wi-Fi module 4 and the loudspeaker 7
Connection, the operation processing unit 3 by carrying out recognition of face and human facial expression recognition to user, come determine the identity of user and
Expression, and the recognition result and recommendation musical theme user's expression and identity are sent to user mobile phone with recommendation music list
Client 6, the music list to be played that 6 feedback user of user mobile phone client is set give the musical theme control unit 5,
5 controlling loudspeaker 7 of musical theme control unit plays the music in the music playlist of user setting to dredge user
Mood.The man face image acquiring unit 1, gathers the face front still image of user and carries out Face datection to it, judges
It whether there is different directions posture, different expressions in the image of different illumination condition and background and may be hidden by jewelry part
The face of gear, the man face image acquiring unit 1 distinguish face and non-face using the method for artificial neural network, realize face
Detection, whole face recognition process terminates if being not have face in image if judging result, if judging result is to exist in image
Face, the man face image acquiring unit 1 carry out locating and tracking to face, are accurately positioned the position of face in the picture, then
The man face image acquiring unit 1 pre-processes facial image inclined to eliminate different illumination, different head to greatest extent
Turn influence of the posture to facial image, improve the accuracy rate of recognition of face, influenced by the dark degree of optical illumination, the facial image
The intensity profile of pixel is often uneven in the original facial image that collecting unit 1 gathers, its intensity profile often focuses on narrow
In narrow grey level range, not clear and image enough the contrast of image detail is low, and the man face image acquiring unit 1 is to face
Original facial image is concentrated in narrow scope and is transformed to intensity profile by the process that image is pre-processed from intensity profile
Scope is wider and the image of intensity profile evenly, improves the contrast of facial image, the man face image acquiring unit 1 is to people
The process that face image is pre-processed is further included to be positioned the angle of end rotation in facial image and scale normalizing by human eye
Change, the adjustment to standardize to the face orientation in facial image, improve the speed of recognition of face, reduce face recognition algorithms
Complexity, the man face image acquiring unit 1 to facial image complete human eye positioning, head pose correction, gradation of image it is equal
After weighing apparatusization, normalized, terminate image preprocessing process concurrency and give the progress of operation processing unit 3 face recognition features
Extraction；The man face image acquiring unit 1 completes facial image human eye positioning, head pose correction, greyscale transformation and Nogata
After figure equalization, normalized, face-image identification sub-district regional partition is carried out to facial image, face is divided into different
Region is carried out the extraction of geometric properties by the operation processing unit 3 respectively；The operation processing unit 3 knows the face of extraction
Other feature is contrasted with whole face templates in the registered face template library in the memory 2, carries out recognition of face, really
Determine recognition of face whether by with the identity information of user that identifies, recognition of face is by successfully determining the identity letter of user
Breath, face recognition process terminate, and the operation processing unit 3 completes the Extraction of Geometrical Features to the facial image by pretreatment
Afterwards, the facial expression feature database stored in the memory 2 is read, expression is carried out by the neural network classifier
Discriminant classification, identifies the expression and mood of user, and exports Expression Recognition result；The Wi-Fi module 4 provides Wi-Fi network,
User mobile phone client 6 connects the Wi-Fi module 4 and provides Wi-Fi network；The operation processing unit 3 identifies user identity
Information and user's expression attribute and the psychological situation of change for counting registered user in period of setting, the operation processing unit
User psychology situation of change in user's expression attribute and set period of time is sent to the use by 3 by the Wi-Fi module 4
Family cell-phone customer terminal 6, the operation processing unit is by user's Expression Recognition result and the user psychology situation of change of nearest two weeks
It is sent to the musical theme control unit 5, the musical theme control unit 5 receives user's expression attribute and two weeks nearest
User psychology situation of change, according to nearest psychological situation of change and the music master of the attribute of user's Expression Recognition result, user
Correspondence between topic, the user mobile phone client 6 is sent to by Wi-Fi module 4 by the musical theme of recommendation, described
User mobile phone client 6 receives the musical theme of recommendation, sets the music list to be played, and be sent to the Wi-Fi moulds
The music list to be played of user setting is transmitted to the musical theme control unit 5, institute by block 4, the Wi-Fi module 4
Stating musical theme control unit 5 controls the loudspeaker 7 to play the music in the music playlist of user setting.
The man face image acquiring unit 1 is equipped with the camera for being used for shooting user's frontal face photo, uses the base
When the intelligent sound system of human facial expression recognition, the head of user is placed in the front of the camera, and camera is adjusted automatically
Whole focal length, shoots the picture rich in detail of user's face, and the original face image data photographed is sent into the facial image and is adopted
Collect the caching storage of unit 1, the man face image acquiring unit 1 carries out Face datection, Face detection to primitive man's face face-image
Tracking and image preprocessing, and pretreated facial image is sent into the operation processing unit 3 and carries out recognition of face and table
Feelings identify, determine the identity and expression attribute of user.
Embodiment 2
As shown in Fig. 1 to Fig. 2, the present invention provides a kind of intelligent sound system based on human facial expression recognition, including raises one's voice
Device 7, further includes man face image acquiring unit 1, memory 2, operation processing unit 3, Wi-Fi module 4, musical theme control unit
5th, user mobile phone client 6；The man face image acquiring unit 1 and the memory 2 connect, the memory 2 and the fortune
Calculate processing unit 3 to connect, the operation processing unit 3 and the Wi-Fi module 4 connect, the Wi-Fi module 4 and the use
6 network connection of family cell-phone customer terminal, the musical theme control unit 5 respectively with the Wi-Fi module 4 and the loudspeaker 7
Connection, the man face image acquiring unit 1 gathers the face direct picture of user, and the image to collecting carries out face inspection
Survey, Face detection tracking and image preprocessing, and pretreated primitive man's face face-image is sent into the calculation process list
Member 3, the operation processing unit 3 extract pretreated face direct picture face recognition features, and with the memory 2
The face template storehouse of middle storage is contrasted, and completes face recognition process, determines the identity information of user, and new user makes for the first time
With the intelligent sound system based on human facial expression recognition, the recognition of face is not by the face mould stored in the memory 2
It can not find in plate storehouse and the matched face template data of pretreated face direct picture, the operation processing unit 3
New user's registration is carried out, classification is registered to the pretreated face direct picture for completing extraction face recognition features, is added
It is added in face template storehouse.
The musical theme control unit 5 is equipped with the SD card of storage music, and the musical theme control unit 5 is embedded in
Linux kernel cuts out the operating system and music player application program after transplanting, and the musical theme control unit 5 is insertion
There is the operating system based on linux kernel, the software and hardware resources of musical theme player can be managed and carry out task scheduling
Embedded system, the audio file that user's download belongs to different musical themes are inserted into the music to the SD card, the SD card
Theme control unit 5, the musical theme control unit 5 read the music inside SD card, the corresponding different musical themes of generation
Music list, the musical theme control unit 5 receive user's Expression Recognition result that the operation processing unit 3 sends and
The nearest psychological situation of change of user, according to user's Expression Recognition result, the nearest psychological situation of change of user and different music
Correspondence between theme, by the Wi-Fi module 4 by the musical theme of recommendation and the corresponding sound of musical theme recommended
Happy list is sent to the user mobile phone client 6, the music list to be played that the user mobile phone client 6 is set, and
The Wi-Fi module 4 is sent to, the music to be played that the Wi-Fi module 4 sets the user mobile phone client 6 arranges
Table is transmitted to the musical theme control unit 5, and the musical theme control unit 5 starts the music player application journey of installation
Sequence, controls the loudspeaker 7 to play the music VF text in the music list to be played that the user mobile phone client 6 is set
Part.
The user mobile phone client 6 is the application program for supporting IOS or the mobile phone of Android operation system, user's
Mobile phone-downloaded is simultaneously installed the Wi-Fi network that the Wi-Fi module 4 provides is connected after the user mobile phone client 6, with the base
Network connection is established in the intelligent sound system of human facial expression recognition, user mobile phone client 6 was connected described in Wi-Fi network receipts
User's recognition of face that operation processing unit 3 is sent is with Expression Recognition as a result, user mobile phone client 6 connected Wi-Fi nets
Network receives the recommendation musical theme music list corresponding with musical theme is recommended that the musical theme control unit 5 is sent, and uses
Family cell-phone customer terminal 6 sends the music list to be played of user setting to the Wi-Fi module by Wi-Fi network,.
The above, is only presently preferred embodiments of the present invention, is not intended to limit the invention, patent protection model of the invention
Enclose and be subject to claims, the equivalent structure change that every specification and accompanying drawing content with the present invention is made, similarly
It should include within the scope of the present invention.
Claims (4)
1. a kind of intelligent sound system based on human facial expression recognition, including loudspeaker (7), it is characterised in that：Further include face
Image acquisition units (1), memory (2), operation processing unit (3), Wi-Fi module (4), musical theme control unit (5), use
Family cell-phone customer terminal (6)；The man face image acquiring unit (1) and the memory (2) connection, the memory (2) and institute
State operation processing unit (3) connection, the operation processing unit (3) and the Wi-Fi module (4) connection, the Wi-Fi module
(4) and the user mobile phone client (6) network connection, the musical theme control unit (5) respectively with the Wi-Fi module
(4) connected with the loudspeaker (7).
A kind of 2. intelligent sound system based on human facial expression recognition according to claim 1, it is characterised in that：The people
Face image acquiring unit (1) is equipped with the camera for being used for shooting user's frontal face photo.
A kind of 3. intelligent sound system based on human facial expression recognition according to claim 1, it is characterised in that：The sound
Happy theme control unit (5) is equipped with the SD card of storage music, and the embedded linux kernel of the musical theme control unit (5) is cut out
Operating system and music player application program after transplanting.
A kind of 4. intelligent sound system based on human facial expression recognition according to claim 1, it is characterised in that：The use
Family cell-phone customer terminal (6) is the application program for supporting IOS or the mobile phone of Android operation system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711411607.9A CN107943449A (en) | 2017-12-23 | 2017-12-23 | A kind of intelligent sound system based on human facial expression recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711411607.9A CN107943449A (en) | 2017-12-23 | 2017-12-23 | A kind of intelligent sound system based on human facial expression recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107943449A true CN107943449A (en) | 2018-04-20 |
Family
ID=61938717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711411607.9A Pending CN107943449A (en) | 2017-12-23 | 2017-12-23 | A kind of intelligent sound system based on human facial expression recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107943449A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846049A (en) * | 2018-05-30 | 2018-11-20 | 郑州易通众联电子科技有限公司 | Stereo set control method and stereo set control device |
| CN109411090A (en) * | 2018-09-26 | 2019-03-01 | 长沙师范学院 | A kind of infantile psychology status assessing system based on fuzzy evaluation |
| CN109542216A (en) * | 2018-10-11 | 2019-03-29 | 平安科技（深圳）有限公司 | Man-machine interaction method, system, computer equipment and storage medium |
| CN109660918A (en) * | 2018-12-27 | 2019-04-19 | 腾讯科技（深圳）有限公司 | Sound collection assembly array and sound collection equipment |
| CN109839828A (en) * | 2019-01-03 | 2019-06-04 | 深圳壹账通智能科技有限公司 | Intelligent home furnishing control method and device, storage medium and electronic equipment |
| CN109886084A (en) * | 2019-01-03 | 2019-06-14 | 广东数相智能科技有限公司 | Face authentication method, electronic equipment and storage medium based on gyroscope |
| CN109885277A (en) * | 2019-02-26 | 2019-06-14 | 百度在线网络技术（北京）有限公司 | Human-computer interaction device, mthods, systems and devices |
| CN109919102A (en) * | 2019-03-11 | 2019-06-21 | 重庆科技学院 | A kind of self-closing disease based on Expression Recognition embraces body and tests evaluation method and system |
| CN110363154A (en) * | 2019-07-17 | 2019-10-22 | 安徽航天信息有限公司 | A kind of service quality examining method and system based on Emotion identification |
| CN110755091A (en) * | 2018-07-26 | 2020-02-07 | 杨万友 | Personal mental health monitoring system and method |
| CN111667063A (en) * | 2020-06-30 | 2020-09-15 | 腾讯科技（深圳）有限公司 | Data processing method and device based on FPGA |
| CN112101293A (en) * | 2020-09-27 | 2020-12-18 | 深圳市灼华网络科技有限公司 | Facial expression recognition method, device, equipment and storage medium |
| CN112382015A (en) * | 2020-11-11 | 2021-02-19 | 华南麟睿科技(衡阳)有限公司 | Intelligent article storing and taking method based on face recognition technology |
| CN112446730A (en) * | 2019-08-28 | 2021-03-05 | 富士施乐株式会社 | Information processing apparatus and recording medium |
| CN112488888A (en) * | 2020-12-08 | 2021-03-12 | 福建小电科技有限公司 | Wisdom campus safety early warning system based on thing networking and big data technology |
| CN113533392A (en) * | 2021-07-12 | 2021-10-22 | 重庆大学 | Combined scanning CL imaging method |
-
2017
- 2017-12-23 CN CN201711411607.9A patent/CN107943449A/en active Pending
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846049A (en) * | 2018-05-30 | 2018-11-20 | 郑州易通众联电子科技有限公司 | Stereo set control method and stereo set control device |
| CN110755091A (en) * | 2018-07-26 | 2020-02-07 | 杨万友 | Personal mental health monitoring system and method |
| CN109411090A (en) * | 2018-09-26 | 2019-03-01 | 长沙师范学院 | A kind of infantile psychology status assessing system based on fuzzy evaluation |
| CN109542216A (en) * | 2018-10-11 | 2019-03-29 | 平安科技（深圳）有限公司 | Man-machine interaction method, system, computer equipment and storage medium |
| CN109542216B (en) * | 2018-10-11 | 2022-11-22 | 平安科技（深圳）有限公司 | Man-machine interaction method, system, computer equipment and storage medium |
| CN109660918A (en) * | 2018-12-27 | 2019-04-19 | 腾讯科技（深圳）有限公司 | Sound collection assembly array and sound collection equipment |
| US11856376B2 (en) | 2018-12-27 | 2023-12-26 | Tencent Technology (Shenzhen) Company Limited | Sound acquisition component array and sound acquisition device |
| CN109660918B (en) * | 2018-12-27 | 2021-11-09 | 腾讯科技（深圳）有限公司 | Sound collection assembly array and sound collection equipment |
| CN109886084A (en) * | 2019-01-03 | 2019-06-14 | 广东数相智能科技有限公司 | Face authentication method, electronic equipment and storage medium based on gyroscope |
| CN109839828A (en) * | 2019-01-03 | 2019-06-04 | 深圳壹账通智能科技有限公司 | Intelligent home furnishing control method and device, storage medium and electronic equipment |
| CN109885277A (en) * | 2019-02-26 | 2019-06-14 | 百度在线网络技术（北京）有限公司 | Human-computer interaction device, mthods, systems and devices |
| CN109919102A (en) * | 2019-03-11 | 2019-06-21 | 重庆科技学院 | A kind of self-closing disease based on Expression Recognition embraces body and tests evaluation method and system |
| CN110363154A (en) * | 2019-07-17 | 2019-10-22 | 安徽航天信息有限公司 | A kind of service quality examining method and system based on Emotion identification |
| CN112446730A (en) * | 2019-08-28 | 2021-03-05 | 富士施乐株式会社 | Information processing apparatus and recording medium |
| CN111667063A (en) * | 2020-06-30 | 2020-09-15 | 腾讯科技（深圳）有限公司 | Data processing method and device based on FPGA |
| CN111667063B (en) * | 2020-06-30 | 2021-09-10 | 腾讯科技（深圳）有限公司 | Data processing method and device based on FPGA |
| CN112101293A (en) * | 2020-09-27 | 2020-12-18 | 深圳市灼华网络科技有限公司 | Facial expression recognition method, device, equipment and storage medium |
| CN112382015A (en) * | 2020-11-11 | 2021-02-19 | 华南麟睿科技(衡阳)有限公司 | Intelligent article storing and taking method based on face recognition technology |
| CN112488888A (en) * | 2020-12-08 | 2021-03-12 | 福建小电科技有限公司 | Wisdom campus safety early warning system based on thing networking and big data technology |
| CN113533392A (en) * | 2021-07-12 | 2021-10-22 | 重庆大学 | Combined scanning CL imaging method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107943449A (en) | A kind of intelligent sound system based on human facial expression recognition | |
| CN103902961B (en) | Face recognition method and device | |
| Akyol et al. | Automatic detection of optic disc in retinal image by using keypoint detection, texture analysis, and visual dictionary techniques | |
| He et al. | Toward accurate and fast iris segmentation for iris biometrics | |
| EP1093633B1 (en) | Iris identification system and method of identifying a person through iris recognition | |
| CN105426695B (en) | A kind of health status detecting system based on iris | |
| CN107239772B (en) | Palm print and palm vein image collecting device and clearance gate | |
| CN109033942A (en) | Authentication device and authentication method | |
| KR20160012902A (en) | Method and device for playing advertisements based on associated information between audiences | |
| CN106446753A (en) | Negative expression identifying and encouraging system | |
| CN108133055A (en) | Intelligent dress ornament storage device and based on its storage, recommend method and apparatus | |
| CN101976332A (en) | Finger vein collection and identification method by means of multi-features | |
| CN109215763A (en) | A kind of emotional health monitoring method and system based on facial image | |
| KR102593624B1 (en) | Online Test System using face contour recognition AI to prevent the cheating behaviour and method thereof | |
| CN107423703A (en) | Based on face, fingerprint and the multimodal recognition device and method for referring to vein pattern | |
| CN109325462A (en) | Recognition of face biopsy method and device based on iris | |
| KR20200012355A (en) | Online lecture monitoring method using constrained local model and Gabor wavelets-based face verification process | |
| CN108615296A (en) | unmanned vending method and unmanned vending machine | |
| CN208351494U (en) | Face identification system | |
| CN108090517A (en) | A kind of cereal recognition methods, device and computer storage media | |
| CN107368817A (en) | Face identification method and device | |
| Czajka | Iris liveness detection by modeling dynamic pupil features | |
| CN108734518A (en) | A method of counting advertising results using image recognition technology | |
| CN109480775A (en) | A kind of icterus neonatorum identification device based on artificial intelligence, equipment, system | |
| Rafik et al. | Application of metaheuristic for optimization of iris Image segmentation by using evaluation Hough Transform and methods Daugman |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180420 |
|
| WD01 | Invention patent application deemed withdrawn after publication |