CN109382827A - A kind of robot system and its intelligent memory recognition methods - Google Patents
A kind of robot system and its intelligent memory recognition methods Download PDFInfo
- Publication number
- CN109382827A CN109382827A CN201811255264.6A CN201811255264A CN109382827A CN 109382827 A CN109382827 A CN 109382827A CN 201811255264 A CN201811255264 A CN 201811255264A CN 109382827 A CN109382827 A CN 109382827A
- Authority
- CN
- China
- Prior art keywords
- information
- unit
- user
- robot
- 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
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
- G06V40/10—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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/04—Viewing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
Abstract
The present invention relates to intelligent identification technology, disclosing a kind of robot system and its intelligent memory recognition methods, the robot system includes voice unit, auditory localization unit, behaviour control unit, visual sensor unit and information library unit.After the present invention detects voice by robot, user direction is positioned using sound source information, so that revolute is to the position of face user, and collected facial image is matched with information bank, output information is as a result, to realize machine man memory recognition methods；The recognition methods of robot is based on SITF algorithm, even if changing rotation angle, brightness of image or shooting visual angle, the detection effect still being able to.Robot memory recognition methods is able to achieve intelligent human-machine interaction, and optimum management user uses, and plays its intelligence, flexibility, moreover it is possible to improve the safety that user manages robot.
Description
Technical field
The present invention relates to intelligent identification technology field, specifically a kind of robot system and its intelligent memory recognition methods.
Background technique
Robotization is the key technology and important symbol in advanced field, as sensing technology is constantly broken through and the height of information
Speed development, robot the relevant technologies are widely furtherd investigate, and robot is changed into intelligent robot, intelligence from traditional robot
Energy robot has started to be applied in military, life and production.Currently, people have been no longer satisfied with status, research staff is
Make robot humanoid emphatically, machine man memory identification technology becomes more powerful.
In existing machine man memory identification, the recognition of face of robot is mainly based upon the images match of gray scale, utilizes
The gray value of images match, selects certain similarity measurements flow function, calculates this metric by pixel, realizes image according to result
Matching.
Images match based on gray scale, to illumination variation and noise more sensitive, this machine big to gray value of image dependence
Device people is based on Image Matching and obtains that face technology is computationally intensive, and effect is relatively low.
Summary of the invention
The purpose of the present invention is to provide a kind of robot system and its intelligent memory recognition methods, to solve above-mentioned background
The problem of being proposed in technology.
To achieve the above object, the invention provides the following technical scheme:
A kind of robot system, the robot system include voice unit, auditory localization unit, behaviour control unit,
Visual sensor unit and information library unit；
Institute's speech units, for detecting, acquiring and parsing the voice messaging of user, the voice messaging includes using
The voice at family, for use in the voice input for carrying out user name to the user for being not present in information bank；
The auditory localization unit, for carrying out location Calculation to the sound-source signal of acquisition, so as to robot system calling
Behaviour control unit；
The behaviour control unit, after user's discriminating direction, control robot, which executes, to be advanced and turns to, so as to
The position of robot steering face user；
The visual sensor unit identifies subscriber identity information for obtaining user's facial image；
Described information storehouse unit, for storing user information, for the information matches after recognition of face.
Auditory localization unit is divided into sound-source signal acquisition module, location Calculation module and result output module；Wherein sound source
For signal acquisition module in system starts, FPGA will start AD conversion according to the sample rate of 2KHz after completing initialization, arrive
After system starts, speech signal samples can be carried out by model EM6027 microphone using 20KHz frequency, that is, start
AD conversion, and AD conversion result is output to buffer and is buffered；Location Calculation module is empty using the sound source in quaternary cross town
Between location model, and calculate user's sound source position；As a result output module is by the direction for the target sound source being calculated and distance
It is exported by serial ports, serial ports uses 9600 baud rate, the transmission mode of custom protocol.
Face recognition technology is utilized in visual sensor unit, is broadly divided into Face datection, feature extraction and recognition of face
Three processes, i.e. 3D video camera acquire image, obtain facial image from acquisition image, characterize face by the feature of extraction
Information, and rapidly and accurately the extracted feature of face being compared with the face characteristic in information bank, according to similarity into
Row differentiates that the Euclidean distance of feature vector can measure the key point similitude in facial image and information bank image.Described
Recognition of face is based on SITF algorithm, and there are four steps for SITF algorithm: the first step detects scale spatial extrema point；Second step, essence
Determine extreme point position.Extreme point position and scale are accurately determined by fitting three-dimensional quadratic function；Third step is each pass
Key point assigned direction parameter；4th step, the generation of key point description.
The user information that storage has recorded in information library unit, including face information and user's name etc..
A kind of intelligent robot memory recognition methods, using above system, detailed process step are as follows:
Scanning circumstance acquires sound source information up to detecting voice messaging；
Judge Sounnd source direction, carries out band direction environmental scanning, detect ownership goal；
Obtain facial image to be identified；
The face information and information bank of acquisition are carried out information matches, export result by recognition of face.
Compared with prior art, the beneficial effects of the present invention are: utilizing sound after the present invention detects voice by robot
Source information positions user direction, so that revolute is to the position of face user, and by collected facial image
It is matched with information bank, output information result is to realize machine man memory recognition methods.
The recognition methods of robot is to rotate angle, brightness of image or shooting visual angle even if changing based on SITF algorithm,
The detection effect still being able to.Robot memory recognition methods is able to achieve intelligent human-machine interaction, and optimum management user
It uses, plays its intelligence, flexibility, moreover it is possible to improve the safety that user manages robot.
Detailed description of the invention
Fig. 1 is a kind of robot system system structure diagram of the invention.
Fig. 2 is that a kind of intelligent robot of the invention remembers recognition methods flow chart.
Fig. 3 is the structural schematic diagram of visual sensor unit of the invention.
Fig. 4 is the concrete application example flow diagram that a kind of intelligent robot of the invention remembers recognition methods.
Specific embodiment
The technical scheme in the embodiments of the invention will be clearly and completely described below, it is clear that described implementation
Example is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without making creative work belongs to the model that the present invention protects
It encloses.
In the description of the present invention, it should be noted that term " first ", " second ", " third " are used for description purposes only,
It is not understood to indicate or imply relative importance.
Referring to Fig. 1, a kind of robot system, the robot system includes voice unit, sound in the embodiment of the present invention
Source positioning unit, behaviour control unit, visual sensor unit and information library unit；
Institute's speech units, for detecting, acquiring and parsing the voice messaging of user, the voice messaging includes using
The voice at family, for use in the voice input for carrying out user name to the user for being not present in information bank；
The auditory localization unit, for carrying out location Calculation to the sound-source signal of acquisition, so as to robot system calling
Behaviour control unit；
The behaviour control unit, after user's discriminating direction, control robot, which executes, to be advanced and turns to, so as to
The position of robot steering face user；
The visual sensor unit identifies subscriber identity information for obtaining user's facial image；
Described information storehouse unit, for storing user information, for the information matches after recognition of face.
The auditory localization unit can be divided into sound-source signal acquisition module, location Calculation module and result output module.Its
In system starts, FPGA will turn middle sound-source signal acquisition module after completing initialization according to the sample rate of 2KHz starting AD
It changes, to after system starts, speech signal samples can be carried out by model EM6027 microphone using 20KHz frequency, also
It is starting AD conversion, and AD conversion result is output to buffer and is buffered；Location Calculation module is using quaternary cross town
Sound source space orient models, and calculate user's sound source position；As a result output module is by the direction for the target sound source being calculated
It is exported with distance by serial ports, serial ports uses 9600 baud rate, the transmission mode of custom protocol.
Visual sensor unit: face recognition technology is utilized in the unit, is broadly divided into Face datection, feature extraction and people
Face identifies that three processes, i.e. 3D video camera acquires image, facial image is obtained from acquisition image, by the feature of extraction come table
Face information is levied, and rapidly and accurately the extracted feature of face is compared with the face characteristic in information bank, according to phase
Differentiated like degree, the Euclidean distance of feature vector can measure the key point similitude in facial image and information bank image.
The recognition of face is based on SITF algorithm, and there are four steps for SITF algorithm: the first step detects scale space pole
Value point.The purpose of scale space is the Analysis On Multi-scale Features of simulated image data, and Gaussian convolution core is the unique of realization change of scale
Gaussian difference scale space is utilized in order to efficiently find stable key point in linear kernel:
D (x, y, σ)=(G (x, y, k σ)-G (x, y, σ)) * I (x, y)=L (x, y, k σ)-L (x, y, σ)
G (x, y, σ) is the Gaussian function of changeable scale, and (x, y) is space coordinate, and σ is scale coordinate, and L (x, y, σ) is one
A two-dimensional scale space,
WhereinL (x, y, σ)=G (x, y, σ) * I (x, y) detects scale space pole
Value point,
First have to find the extreme point of scale space, each sampled point is needed in Gaussian difference scale sky in facial image
Between compare with its image area with the consecutive points of scale domain, taking extreme point is key point.
Second step, it is accurate to determine extreme point position.Extreme point position and ruler are accurately determined by fitting three-dimensional quadratic function
Degree.
Third step is each key point assigned direction parameter.Modulus value and direction formula at (x, y):
4th step, the generation of key point description.The direction that reference axis is first rotated to be to key point, takes with key point and is
The region of 16 × 16 sizes of the heart, then gradient vector histogram of the key point in scale space on every 4 × 4 fritter is calculated,
The accumulated value for drawing each gradient direction forms a seed point, and a key point is described by 4 × 4 16 points, generates description
Description of son, SITF is feature vector.
Information library unit: the user information that storage has recorded in unit, including face information and user's name etc..Letter
Information in breath library can be used for face matching, calculate the similarity between the facial image in the facial image and information bank of acquisition
I.e. threshold value matches, and matched key point, may be from the different piece of facial image, key point portion to the minimum range provided
Point not identical classification that will will lead to is low, in response to this problem, has used the image of particular network overlapping subgraph, two images it
Between distance can be minimum average with them to the distance between all corresponding subgraphs with survey calculation.Assuming that characteristic point p and
Q, according to Euclidean distance formula:
Wherein n is dimension, DpAnd DqDescription of respectively p, q, using p as reference point, find characteristic point p Euclidean distance most
Close and secondary two close adjacent characteristic point q' and q·, then calculate (p, q') and (p, q·) d Euclidean distance than being image
Similarity, when similarity is greater than given threshold, robot will export corresponding user's name, similarity mode failure, robot
Voice output inquires that the facial image of acquisition and user's name are stored into information bank by user's name, system.
Behaviour control unit: the movement and steering of robot are finally realized by pid algorithm driving direct current generator.
Referring to Fig.2, a kind of intelligent robot remembers recognition methods, using above system, specific process step are as follows:
1. scanning circumstance acquires sound source information up to detecting voice messaging；
2. judging Sounnd source direction, direction environmental scanning is carried out, detects ownership goal；
3. obtaining facial image to be identified；
4. the face information and information bank of acquisition are carried out information matches, export result by recognition of face.
Among the above, obtain facial image to be identified using facial image obtain terminal realize, can be camera,
Obtain the equipment with camera shooting or camera function.
Information bank described above can be after carrying out shooting stroke picture to facial image to be identified, by the picture
It stores into information bank, is also possible to directly upload by administrative staff in equipment end.
Refering to Fig. 3, the structural schematic diagram of visual sensor unit is only shown and the embodiment of the present invention for ease of description
Relevant part.
In embodiments of the present invention, the visual sensor unit includes:
Information acquisition unit, for obtaining human face image information to be identified；
Information process unit, for handling the human face image information to be identified；
As a result output unit is extracted for exporting face characteristic as a result, so as to the information matches with information library unit.
Refering to Fig. 4, a kind of application example of intelligent robot memory recognition methods, using above system, detailed process
Step are as follows:
1. the title of user's calling robot.
2. robot has received the input of external voice data, and user's sound source is acquired and calculated to sound-source signal
Position.
3. auditory localization unit exports user location, in face of body kinematics to user.
4. carrying out recognition of face to user by 3D camera, robot adjusts itself pose face user and acquires image,
The information recognized is matched with robot information base information, judges whether there is the user information.
5. information extraction if robot information bank there are the user information, extracts the user's name, and replys language to user
Sound " * * * (user's name), why be me "；If the user information is not present in robot information bank, requry the users that " you are
Who? ", after user answers, robot voice: " hello, * * * (user's name) ", and extract user's name information and face letter
Breath, is stored in information bank, waits use next time.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (5)
1. a kind of robot system, which is characterized in that passed including voice unit, auditory localization unit, behaviour control unit, vision
Sensor cell and information library unit；
Institute's speech units are used to detect, acquire and parse the voice messaging of user, and voice messaging includes the voice of user,
For use in the voice input for carrying out user name to the user for being not present in information bank；
The auditory localization unit is used to carry out location Calculation to the sound-source signal of acquisition, so that robot system calls behavior control
Unit processed；
After the behaviour control unit is for realizing user's discriminating direction, control robot, which executes, to be advanced and turns to, so as to machine
The position of people steering face user；
The visual sensor unit identifies subscriber identity information for obtaining user's facial image；
Described information storehouse unit is for storing user information, for the information matches after recognition of face, the user information packet
Face information and user name are included.
2. a kind of robot system according to claim 1, which is characterized in that the auditory localization unit includes sound source letter
Number acquisition module, location Calculation module and result output module.
3. a kind of robot system according to claim 1, which is characterized in that the visual sensor unit includes information
Acquiring unit, information process unit and result output unit；
Information acquisition unit is used to obtain the human face image information with identification；
Information process unit is for handling the human face image information to be identified；
As a result output unit extracts result for exporting face characteristic.
4. a kind of robot system according to claim 3, which is characterized in that the visual sensor unit is used and is based on
Face recognition technology based on SITF algorithm.
5. a kind of intelligent robot remembers recognition methods, robot system as claimed in claim 4 is used, which is characterized in that packet
Include following steps:
Scanning circumstance acquires sound source information up to detecting voice messaging；
Judge Sounnd source direction, carries out band direction environmental scanning, detect ownership goal；
It obtains to identify facial image；
The face information and information bank of acquisition are carried out information matches, export result by recognition of face.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811255264.6A CN109382827A (en) | 2018-10-26 | 2018-10-26 | A kind of robot system and its intelligent memory recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811255264.6A CN109382827A (en) | 2018-10-26 | 2018-10-26 | A kind of robot system and its intelligent memory recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109382827A true CN109382827A (en) | 2019-02-26 |
Family
ID=65426855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811255264.6A Pending CN109382827A (en) | 2018-10-26 | 2018-10-26 | A kind of robot system and its intelligent memory recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109382827A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110000791A (en) * | 2019-04-24 | 2019-07-12 | 深圳市三宝创新智能有限公司 | A kind of motion control device and method of desktop machine people |
| CN111055288A (en) * | 2020-01-14 | 2020-04-24 | 弗徕威智能机器人科技（上海）有限公司 | On-call robot control method, storage medium and robot |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104985599A (en) * | 2015-07-20 | 2015-10-21 | 百度在线网络技术（北京）有限公司 | Intelligent robot control method and system based on artificial intelligence and intelligent robot |
| CN105058393A (en) * | 2015-08-17 | 2015-11-18 | 李泉生 | Guest greeting robot |
| CN105093986A (en) * | 2015-07-23 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Humanoid robot control method based on artificial intelligence, system and the humanoid robot |
| CN105701447A (en) * | 2015-12-30 | 2016-06-22 | 上海智臻智能网络科技股份有限公司 | Guest-greeting robot |
| CN106295662A (en) * | 2016-08-17 | 2017-01-04 | 广州中国科学院软件应用技术研究所 | A kind of automobile logo identification method and system |
| CN107065863A (en) * | 2017-03-13 | 2017-08-18 | 山东大学 | A kind of guide to visitors based on face recognition technology explains robot and method |
| CN108000529A (en) * | 2017-12-08 | 2018-05-08 | 子歌教育机器人（深圳）有限公司 | Intelligent robot |
| CN207606853U (en) * | 2017-12-04 | 2018-07-13 | 子歌教育机器人（深圳）有限公司 | The head control device and intelligent robot of robot |
-
2018
- 2018-10-26 CN CN201811255264.6A patent/CN109382827A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104985599A (en) * | 2015-07-20 | 2015-10-21 | 百度在线网络技术（北京）有限公司 | Intelligent robot control method and system based on artificial intelligence and intelligent robot |
| CN105093986A (en) * | 2015-07-23 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Humanoid robot control method based on artificial intelligence, system and the humanoid robot |
| CN105058393A (en) * | 2015-08-17 | 2015-11-18 | 李泉生 | Guest greeting robot |
| CN105701447A (en) * | 2015-12-30 | 2016-06-22 | 上海智臻智能网络科技股份有限公司 | Guest-greeting robot |
| CN106295662A (en) * | 2016-08-17 | 2017-01-04 | 广州中国科学院软件应用技术研究所 | A kind of automobile logo identification method and system |
| CN107065863A (en) * | 2017-03-13 | 2017-08-18 | 山东大学 | A kind of guide to visitors based on face recognition technology explains robot and method |
| CN207606853U (en) * | 2017-12-04 | 2018-07-13 | 子歌教育机器人（深圳）有限公司 | The head control device and intelligent robot of robot |
| CN108000529A (en) * | 2017-12-08 | 2018-05-08 | 子歌教育机器人（深圳）有限公司 | Intelligent robot |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110000791A (en) * | 2019-04-24 | 2019-07-12 | 深圳市三宝创新智能有限公司 | A kind of motion control device and method of desktop machine people |
| CN111055288A (en) * | 2020-01-14 | 2020-04-24 | 弗徕威智能机器人科技（上海）有限公司 | On-call robot control method, storage medium and robot |
| CN111055288B (en) * | 2020-01-14 | 2021-04-13 | 弗徕威智能机器人科技（上海）有限公司 | On-call robot control method, storage medium and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107748869B (en) | 3D face identity authentication method and device | |
| CN107609383B (en) | 3D face identity authentication method and device | |
| CN106104569B (en) | For establishing the method and apparatus of connection between electronic device | |
| WO2019128507A1 (en) | Image processing method and apparatus, storage medium and electronic device | |
| CN105740780B (en) | Method and device for detecting living human face | |
| CN109919977B (en) | Video motion person tracking and identity recognition method based on time characteristics | |
| CN108470169A (en) | Face identification system and method | |
| CN105740779B (en) | Method and device for detecting living human face | |
| CN107516127B (en) | Method and system for service robot to autonomously acquire attribution semantics of human-worn carried articles | |
| CN107045631A (en) | Facial feature points detection method, device and equipment | |
| CN110113116B (en) | Human behavior identification method based on WIFI channel information | |
| CN104731307B (en) | A kind of body-sensing action identification method and human-computer interaction device | |
| CN105989608B (en) | A kind of vision capture method and device towards intelligent robot | |
| CN107728482A (en) | Control system, control process method and device | |
| CN108198130B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| TW201201115A (en) | Facial expression recognition systems and methods and computer program products thereof | |
| CN109117753A (en) | Position recognition methods, device, terminal and storage medium | |
| CN108877787A (en) | Audio recognition method, device, server and storage medium | |
| CN108198159A (en) | A kind of image processing method, mobile terminal and computer readable storage medium | |
| CN109274883A (en) | Posture antidote, device, terminal and storage medium | |
| CN110796101A (en) | Face recognition method and system of embedded platform | |
| CN111046825A (en) | Human body posture recognition method, device and system and computer readable storage medium | |
| US20200210687A1 (en) | Face recognition device, face recognition method, and computer readable storage medium | |
| Manikandan et al. | Hand gesture detection and conversion to speech and text | |
| Maekawa et al. | WristSense: wrist-worn sensor device with camera for daily activity recognition |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190226 |