CN109165555A - Man-machine finger-guessing game method, apparatus and storage medium based on image recognition - Google Patents
Man-machine finger-guessing game method, apparatus and storage medium based on image recognition Download PDFInfo
- Publication number
- CN109165555A CN109165555A CN201810819742.5A CN201810819742A CN109165555A CN 109165555 A CN109165555 A CN 109165555A CN 201810819742 A CN201810819742 A CN 201810819742A CN 109165555 A CN109165555 A CN 109165555A
- Authority
- CN
- China
- Prior art keywords
- gesture
- finger
- guessing game
- images
- gestures
- 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
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F9/00—Games not otherwise provided for
- A63F9/24—Electric games; Games using electronic circuits not otherwise provided for
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F9/00—Games not otherwise provided for
- A63F9/24—Electric games; Games using electronic circuits not otherwise provided for
- A63F2009/2401—Detail of input, input devices
- A63F2009/243—Detail of input, input devices with other kinds of input
- A63F2009/2435—Detail of input, input devices with other kinds of input using a video camera
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F9/00—Games not otherwise provided for
- A63F9/24—Electric games; Games using electronic circuits not otherwise provided for
- A63F2009/2448—Output devices
- A63F2009/245—Output devices visual
- A63F2009/2457—Display screens, e.g. monitors, video displays
-
- 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
- G06V40/107—Static hand or arm
- G06V40/117—Biometrics derived from hands
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention provides a kind of man-machine finger-guessing game method, apparatus and storage medium based on image recognition construct gesture identification model this method comprises: being trained using convolutional neural networks algorithm to images of gestures gathered in advance；Wherein, the classification information in gesture identification model include: scissors, stone, cloth, other；The gesture information generated at random is sent to finger-guessing game equipment, corresponding gesture operation is carried out to control finger-guessing game equipment, and start camera simultaneously and capture to gesture detection zone, to obtain images to be recognized；Gesture identification is carried out to images to be recognized by gesture identification model, to obtain the user gesture information in gestures detection region；According to preset victory or defeat rule, judges the priority between user gesture information gesture information corresponding with finger-guessing game equipment, obtain finger-guessing game result.It can be improved gesture identification accuracy and efficiency by this method, while realizing the finger-guessing game of people Yu finger-guessing game equipment, improve the novel interest of human-computer interaction.
Description
Technical field
The present invention relates to human-computer interaction technique fields, and in particular to a kind of man-machine finger-guessing game method based on image recognition, dress
It sets and computer readable storage medium.
Background technique
The development process of human-computer interaction is exactly the process for adapting to computer from people and gradually adapting to people to computer, human-computer interaction
The development experience manual work stages of early stage, job control language and interactive command language stage, graphic user interface
(GUI) stage, network user interface stage, multichannel and multimedia intelligent human-computer interaction stage.Hand is as most flexible on body
Position, be to be used to carry out the tool of interpersonal limbs exchange earliest.Dynamic hand gesture recognition is in field of human-computer interaction
Important subject has important theoretical significance and broad application prospect.
Paper is a kind of finger-guessing game game.It is successively passed to originating from China with the continuous development of international trade
The ground such as Japan, Korea, Europe.Its game rule is simple and clear, can bore without loophole, and single playing method compares with fortune, and more bouts are played
Method compares with psychological game, deep to be liked by the people.
With the continuous development of science and technology, social change makes rapid progress, and finger-guessing game game is gradually developed by traditional manual guess
It fights to the finish at man-machine, participation number is also no longer limited to two people or more.The electronics finger-guessing game product of market, interactive media rely primarily on
Game terminal display screen, user and terminal punch, terminal recognition user gesture simultaneously, show that victory or defeat is flat as a result, completing once to guess
Fist.According to investigation, the said goods are generally existing following insufficient: 1) gesture identification is mainly measured according to the position sum number of finger
The contour feature of hand-type out, the technology recognition efficiency is low, computationally intensive, is not suitable for real-time gesture identification application.2) game go out
Fist and result all realized by terminal display screen, interactive virtual, stiff, lacks vivid, can not simulate traditional-handwork guess
Game-play enjoyment.
Summary of the invention
Based on this, the present invention provides a kind of man-machine finger-guessing game method, apparatus and storage medium based on image recognition can
Gesture identification accuracy and efficiency is improved, while improving the novel interest of human-computer interaction.
The man-machine finger-guessing game method based on image recognition that the embodiment of the invention provides a kind of, comprising:
Images of gestures gathered in advance is trained using convolutional neural networks algorithm, constructs gesture identification model；Its
In, the classification information in the gesture identification model include: scissors, stone, cloth, other；
The gesture information generated at random is sent to finger-guessing game equipment, carries out corresponding gesture behaviour to control the finger-guessing game equipment
Make, and start camera simultaneously and gesture detection zone is captured, to obtain images to be recognized；
Gesture identification is carried out to the images to be recognized by the gesture identification model, to obtain the gestures detection area
User gesture information in domain；
According to preset victory or defeat rule, judge user gesture information gesture information corresponding with the finger-guessing game equipment it
Between priority, obtain finger-guessing game result.
Preferably, the man-machine finger-guessing game method based on image recognition further include:
Corresponding video image carries out recognition of face in the target area captured to the camera, to judge the mesh
Mark region in whether someone；
When judging someone in the target area, the gestures detection region that detection is located in the target area is
It is no to put hand；If it is not, then voice messaging is sent to speech ciphering equipment, to play voice prompting to user；Guess if so, determining and entering
Fist game.
Preferably, described that images of gestures gathered in advance is trained using convolutional neural networks algorithm, construct gesture
Identification model specifically includes:
According to images of gestures gathered in advance, training image sample and test image sample are obtained；
The training image sample is trained using convolutional neural networks algorithm, constructs the gesture identification model；
The test image sample is input to the gesture identification model, obtains gesture test result；Wherein, the hand
Gesture test result is the result of loss function output in the gesture identification model；
According to the gesture test result, judge whether the recognition accuracy of the gesture identification model reaches default threshold
Value；If it is not, then adjusting training image sample described in the classification information in the gesture identification model and re -training；If so, really
The fixed gesture identification model construction is completed.
Preferably, described according to images of gestures gathered in advance, before obtaining training image sample and test image sample
Further include:
Several images of gestures are extracted from the gesture video captured in advance according to the frame number of setting；
Gray proces are carried out to the images of gestures using Weighted Average Algorithm.
Preferably, the preset threshold is 80%.
Preferably, the preset victory or defeat rule is cloth > stone > scissors > cloth.
Preferably, described that gesture identification is carried out to the images to be recognized by the gesture identification model, to obtain
After stating the user gesture information in gestures detection region further include:
When the user gesture information be other when, to display equipment send user gesture can not identification information so that
The display equipment shows that the user gesture can not identification information；
When the user gesture information is scissors, stone or cloth, determine to the user gesture and the finger-guessing game equipment
Corresponding gesture information carries out victory or defeat judgement.
Preferably, the man-machine finger-guessing game method based on image recognition further include:
When determining into after finger-guessing game game, when reaching the first setting time, random generate is sent to the finger-guessing game equipment
Gesture information, carry out corresponding gesture operation to control the finger-guessing game equipment.
The embodiment of the invention also provides a kind of man-machine finger-guessing game device based on image recognition, comprising:
Gesture identification model construction module, for being carried out using convolutional neural networks algorithm to images of gestures gathered in advance
Training constructs gesture identification model；Wherein, the classification information in the gesture identification model include: scissors, stone, cloth, its
He；
Gesture control module, for sending the gesture information generated at random to finger-guessing game equipment, to control the finger-guessing game equipment
Corresponding gesture operation is carried out, and starts camera simultaneously and gesture detection zone is captured, to obtain images to be recognized；
User gesture data obtaining module, user carry out gesture to the images to be recognized by the gesture identification model
Identification, to obtain the user gesture information in the gestures detection region；
Victory or defeat judgment module, for judging that the user gesture information is set with the finger-guessing game according to preset victory or defeat rule
Priority between standby corresponding gesture information, obtains finger-guessing game result.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer readable storage medium includes
The computer program of storage, wherein control in computer program operation and set where the computer readable storage medium
It is standby to execute such as the above-mentioned man-machine finger-guessing game method based on image recognition.
Compared with the existing technology, a kind of man-machine finger-guessing game method based on image recognition provided in an embodiment of the present invention is beneficial
Effect is: the man-machine finger-guessing game method based on image recognition includes: using convolutional neural networks algorithm to gathered in advance
Images of gestures is trained, and constructs gesture identification model；Wherein, the classification information in the gesture identification model include: scissors,
Stone, cloth, other；The gesture information generated at random is sent to finger-guessing game equipment, carries out corresponding hand to control the finger-guessing game equipment
Gesture operation, and start camera simultaneously and gesture detection zone is captured, to obtain images to be recognized；Known by the gesture
Other model carries out gesture identification to the images to be recognized, to obtain the user gesture information in the gestures detection region；Root
According to preset victory or defeat rule, judge preferential between user gesture information gesture information corresponding with the finger-guessing game equipment
Grade, obtains finger-guessing game result.By the above-mentioned man-machine finger-guessing game method based on image recognition, gesture identification accuracy and effect can be improved
Rate, while realizing the finger-guessing game of people Yu finger-guessing game equipment, improve the novel interest of human-computer interaction.
Detailed description of the invention
Fig. 1 is a kind of flow chart of man-machine finger-guessing game method based on image recognition provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of man-machine finger-guessing game device based on image recognition provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, it is a kind of process of man-machine finger-guessing game method based on image recognition provided in an embodiment of the present invention
Figure.
The man-machine finger-guessing game method based on image recognition, comprising:
S100: being trained images of gestures gathered in advance using convolutional neural networks algorithm, constructs gesture identification mould
Type；Wherein, the classification information in the gesture identification model include: scissors, stone, cloth, other；
Convolutional neural networks algorithm is that great amount of images sample, alternately convolution sum pondization are grasped in the database to storage
Make, gradually extract the high-level characteristic of image, classify to feature, completes identification function.The high-level characteristic is from large sample
Learn in data, a degree of offset, dimensional variation and deformation can be coped with, guarantee the stronger separability of feature, to feature
Classification has ideal detection effect, reduces the complexity of model.
According to the pre-set classification information of system, i.e., " scissors, stone, cloth, other " four classifications, images of gestures pair
Each classification is answered to classify.By convolutional neural networks algorithm, feature extraction, repeatedly recognition training are carried out to images of gestures,
The feature vector of extraction is corresponded to each classification to store, thus complete to correspond to the gesture identification model of aforementioned four classification
Building.
S200: sending the gesture information generated at random to finger-guessing game equipment, carries out corresponding hand to control the finger-guessing game equipment
Gesture operation, and start camera simultaneously and gesture detection zone is captured, to obtain images to be recognized；
S300: gesture identification is carried out to the images to be recognized by the gesture identification model, to obtain the gesture
User gesture information in detection zone；
S400: according to preset victory or defeat rule, judge user gesture information gesture corresponding with the finger-guessing game equipment
Priority between information obtains finger-guessing game result.
The finger-guessing game result by show equipment shown, wherein be horizontal angle show equipment refer to liquid crystal display,
The material object hardware such as touch screen.The display of finger-guessing game result is considered as a game over.After game over, examined again by camera
Survey whether current gestures detection area puts hand.If gestures detection area without hand, continue to test target area whether someone；If gesture is examined
Surveying area has hand, and the finger-guessing game equipment continues to carry out finger-guessing game game with user.
The above-mentioned man-machine finger-guessing game method based on image recognition carries out face and gesture identification using convolutional neural networks algorithm,
Compared with traditional technology, accomplish that data are more acurrate, identifies more time saving, raising gesture identification accuracy and efficiency.In addition, of the invention
Finger-guessing game equipment, using the hardware in kind such as mechanical arm, finger-guessing game gesture device, interactive media is no longer limited to terminal display screen, raw
Dynamic image, simulation traditional-handwork guess mode, increases novel interesting property for human-computer interaction.
In an alternative embodiment, the man-machine finger-guessing game method based on image recognition further include:
Corresponding video image carries out recognition of face in the target area captured to the camera, to judge the mesh
Mark region in whether someone；
When judging someone in the target area, the gestures detection region that detection is located in the target area is
It is no to put hand；If it is not, then voice messaging is sent to speech ciphering equipment, to play voice prompting to user；Guess if so, determining and entering
Fist game.
In the present embodiment, pass through camera, real-time grasp shoot on-site target region scene；It is right by people face identification technology
Video image carry out the identification of people face, detection target area whether someone.The scene refers to the public field such as exhibition room, multi-purpose market
Institute.The target area refers to when the recognizable region of preceding camera, it is 3 meters of camera position specially current within the scope of periphery
Space.
If the target area nobody, system is not dealt with, not enter finger-guessing game game.
If described target area someone, by camera, detect whether presently described gestures detection region puts hand.It is described
Gestures detection region refers to manual identification's frame in target area.If the gestures detection region is set without hand, system control voice
Preparation goes out voice, and user is attracted to come finger-guessing game.If there is hand in the gestures detection region, the finger-guessing game equipment continues to swim with user
Play.The finger-guessing game equipment refers to the hardware in kind such as mechanical arm, finger-guessing game gesture device, and punch gesture is generated at random according to system
Gesture information definition, the benchmark in conjunction with the punch gesture of user, as finger-guessing game victory or defeat.
It determines before entering finger-guessing game game, by camera, whether the continuous current gestures detection region of 5 seconds real-time detections is put
Hand.If gestures detection region controls speech ciphering equipment and issues voice, prompt user that hand is placed on gestures detection region without hand.If hand
Gesture detection zone has hand, and control speech ciphering equipment issues voice, user is prompted to start punch.
In an alternative embodiment, S100: using convolutional neural networks algorithm to images of gestures gathered in advance into
Row training, constructs gesture identification model, specifically includes:
According to images of gestures gathered in advance, training image sample and test image sample are obtained；
The training image sample is trained using convolutional neural networks algorithm, constructs the gesture identification model；
The test image sample is input to the gesture identification model, obtains gesture test result；Wherein, the hand
Gesture test result is the result of loss function output in the gesture identification model；
According to the gesture test result, judge whether the recognition accuracy of the gesture identification model reaches default threshold
Value；If it is not, then adjusting training image sample described in the classification information in the gesture identification model and re -training；If so, really
The fixed gesture identification model construction is completed.
In the present embodiment, based on the total quantity of images of gestures, images of gestures is divided into two classes, one kind is training image sample
This, one kind is test image sample.The training image sample is the 90% of the images of gestures, when being used for model recognition training
It uses；The test image sample is the 10% of the images of gestures, after user model recognition training, when trial operation is tested
It uses.The training image sample is stored in the training image database of local server, the test image sample storage
In the test image database of local server.
When the number of the training image sample repetition training in the training image database reaches default numerical value, mould
Type training stops, and obtains the gesture identification model.Further, the numerical value that sets is 200,000 time,
According to the output of loss function as a result, judging the accuracy of the gesture identification model identification.If accuracy reaches
Systemic presupposition threshold values, model are considered as ideal, can carry out trial operation test with the test image sample of test image database；It is no
Then, model is considered as undesirable, need to readjust parameter, continues to instruct repeatedly with the training image sample of the training image database
Practice.The parameter refers to the classification information of the gesture identification model, it may be assumed that " scissors, stone, cloth, other " four classifications.Into one
Step ground, the preset threshold are 80%.
In an alternative embodiment, described according to images of gestures gathered in advance, obtain training image sample and survey
Before examination image pattern further include:
Several images of gestures are extracted from the gesture video captured in advance according to the frame number of setting；
By camera, a large amount of gesture videos captured about user's punch.System extracts gesture video, and according to setting
Frame number, video is split into multiple images.Above-mentioned acquisition mode can collect the punch gesture of user from different perspectives, be
Next punch gesture identification provides more accurate guarantee.Further, the frame number set is 30 frame.
Gray proces are carried out to the images of gestures using Weighted Average Algorithm.
Since the images of gestures extracted from gesture video is color image, specifically it is made of multiple pixels,
And each pixel is indicated by tri- values of RGB；Gray proces are carried out to the images of gestures, will not influence images of gestures
Texture feature information, and each pixel only needs a gray value that can indicate, substantially increases images of gestures treatment effeciency.
Specifically, gray proces are carried out to the images of gestures by following gray proces Weighted Average Algorithm formula:
F (i, j)=0.30R (i, j)+0.59G (i, j)+0.11B (i, j)
Wherein, i, j represent a pixel in the position of two-dimensional space vector, it may be assumed that the i-th row, jth column.
According to above-mentioned formula, the gray value of each pixel in the images of gestures is calculated, value range is 0-255, is made
Black-white-gray state is presented in the images of gestures.
In this way, acquiring images of gestures from continuous gesture video, to establish the gesture identification model, not only
Irregular or transformation gesture finger-guessing game movement is efficiently identified, but also can predict that user connects based on the punch gesture of user
The punching action got off.
In an alternative embodiment, the preset threshold is 80%.
In an alternative embodiment, the preset victory or defeat rule is cloth > stone > scissors > cloth.
In an alternative embodiment, described that gesture is carried out to the images to be recognized by the gesture identification model
Identification, after obtaining the user gesture information in the gestures detection region further include:
When the user gesture information be other when, to display equipment send user gesture can not identification information so that
The display equipment shows that the user gesture can not identification information；
When the user gesture information is scissors, stone or cloth, determine to the user gesture and the finger-guessing game equipment
Corresponding gesture information carries out victory or defeat judgement.
In an alternative embodiment, the man-machine finger-guessing game method based on image recognition further include:
When determining into after finger-guessing game game, when reaching the first setting time, random generate is sent to the finger-guessing game equipment
Gesture information, carry out corresponding gesture operation to control the finger-guessing game equipment.
Further, when the corresponding user gesture information of the images to be recognized identified is other, the camera shooting
Head is captured the gestures detection region, and re-start gesture identification again after reaching the second setting time.
For example, finger-guessing game equipment is not dealt with if detecting user earlier than the finger-guessing game equipment punch, and reaching described first
Setting time just carries out punch；If detecting user and the finger-guessing game equipment punch simultaneously, camera captures user's punch gesture；
If in the finger-guessing game equipment punch after detecting user, the camera is captured again after reaching the second setting time
User's punch gesture.Wherein, first setting time is 3 seconds, and second setting time is 2 seconds.
The present invention uses method identical with the gesture identification model, constructs people according to the video image that camera is captured
Then face identification model carries out recognition of face by candid photograph image of the human face recognition model to target area, here, not existing
The building process of human face recognition model is illustrated.
Referring to Fig. 2, it is that the embodiment of the invention also provides a kind of man-machine finger-guessing game device based on image recognition shows
It is intended to, the man-machine finger-guessing game device based on image recognition includes:
Gesture identification model construction module 1, for using convolutional neural networks algorithm to images of gestures gathered in advance into
Row training, constructs gesture identification model；Wherein, the classification information in the gesture identification model include: scissors, stone, cloth, its
He；
Convolutional neural networks algorithm is that great amount of images sample, alternately convolution sum pondization are grasped in the database to storage
Make, gradually extract the high-level characteristic of image, classify to feature, completes identification function.The high-level characteristic is from large sample
Learn in data, a degree of offset, dimensional variation and deformation can be coped with, guarantee the stronger separability of feature, to feature
Classification has ideal detection effect, reduces the complexity of model.
According to the pre-set classification information of system, i.e., " scissors, stone, cloth, other " four classifications, images of gestures pair
Each classification is answered to classify.By convolutional neural networks algorithm, feature extraction, repeatedly recognition training are carried out to images of gestures,
The feature vector of extraction is corresponded to each classification to store, thus complete to correspond to the gesture identification model of aforementioned four classification
Building.
Gesture control module 2 is set for sending the gesture information generated at random to finger-guessing game equipment 5 with controlling the finger-guessing game
It is standby to carry out corresponding gesture operation, and start camera 6 simultaneously and gesture detection zone is captured, to obtain figure to be identified
Picture；
User gesture data obtaining module 3, user carry out hand to the images to be recognized by the gesture identification model
Gesture identification, to obtain the user gesture information in the gestures detection region；
Victory or defeat judgment module 4, for judging that the user gesture information is set with the finger-guessing game according to preset victory or defeat rule
Priority between standby corresponding gesture information, obtains finger-guessing game result.
The finger-guessing game result is by showing that equipment 7 is shown, wherein is that horizontal angle shows that equipment refers to liquid crystal display
The material object hardware such as screen, touch screen.The display of finger-guessing game result is considered as a game over.After game over, again by camera shooting
Head detects whether current gestures detection area puts hand.If gestures detection area without hand, continue to test target area whether someone；If hand
Gesture detection zone has hand, and the finger-guessing game equipment continues to carry out finger-guessing game game with user.
The above-mentioned man-machine finger-guessing game device based on image recognition carries out face and gesture identification using convolutional neural networks algorithm,
Compared with traditional technology, accomplish that data are more acurrate, identifies more time saving, raising gesture identification accuracy and efficiency.In addition, of the invention
Finger-guessing game equipment, using the hardware in kind such as mechanical arm, finger-guessing game gesture device, interactive media is no longer limited to terminal display screen, raw
Dynamic image, simulation traditional-handwork guess mode, increases novel interesting property for human-computer interaction.
In an alternative embodiment, the man-machine finger-guessing game device based on image recognition further include:
Face recognition module, corresponding video image carries out face in the target area for capturing to the camera
Identification, with judge in the target area whether someone；
Hand detection module, for when judging someone in the target area, detection to be located in the target area
Whether hand is put in the gestures detection region；If it is not, then sending voice messaging to speech ciphering equipment, mentioned with playing voice to user
Show；Enter finger-guessing game game if so, determining.
In the present embodiment, pass through camera, real-time grasp shoot on-site target region scene；It is right by people face identification technology
Video image carry out the identification of people face, detection target area whether someone.The scene refers to the public field such as exhibition room, multi-purpose market
Institute.The target area refers to when the recognizable region of preceding camera, it is 3 meters of camera position specially current within the scope of periphery
Space.
If the target area nobody, system is not dealt with, not enter finger-guessing game game.
If described target area someone, by camera, detect whether presently described gestures detection region puts hand.It is described
Gestures detection region refers to manual identification's frame in target area.If the gestures detection region is set without hand, system control voice
Preparation goes out voice, and user is attracted to come finger-guessing game.If there is hand in the gestures detection region, the finger-guessing game equipment continues to swim with user
Play.The finger-guessing game equipment refers to the hardware in kind such as mechanical arm, finger-guessing game gesture device, and punch gesture is generated at random according to system
Gesture information definition, the benchmark in conjunction with the punch gesture of user, as finger-guessing game victory or defeat.
It determines before entering finger-guessing game game, by camera, whether the continuous current gestures detection region of 5 seconds real-time detections is put
Hand.If gestures detection region controls speech ciphering equipment and issues voice, prompt user that hand is placed on gestures detection region without hand.If hand
Gesture detection zone has hand, and control speech ciphering equipment issues voice, user is prompted to start punch.
In an alternative embodiment, gesture identification model construction module 1 includes:
Image division unit, for obtaining training image sample and test chart being decent according to images of gestures gathered in advance
This；
Model training unit is constructed for being trained using convolutional neural networks algorithm to the training image sample
The gesture identification model；
Model measurement unit obtains gesture survey for the test image sample to be input to the gesture identification model
Test result；Wherein, the gesture test result is the result of loss function output in the gesture identification model；
Model judging unit, for judging that the identification of the gesture identification model is accurate according to the gesture test result
Whether rate reaches preset threshold；If it is not, then adjusting training described in the classification information in the gesture identification model and re -training
Image pattern；If so, determining that the gesture identification model construction is completed.
In the present embodiment, based on the total quantity of images of gestures, images of gestures is divided into two classes, one kind is training image sample
This, one kind is test image sample.The training image sample is the 90% of the images of gestures, when being used for model recognition training
It uses；The test image sample is the 10% of the images of gestures, after user model recognition training, when trial operation is tested
It uses.The training image sample is stored in the training image database of local server, the test image sample storage
In the test image database of local server.
When the number of the training image sample repetition training in the training image database reaches default numerical value, mould
Type training stops, and obtains the gesture identification model.Further, the numerical value that sets is 200,000 time,
According to the output of loss function as a result, judging the accuracy of the gesture identification model identification.If accuracy reaches
Systemic presupposition threshold values, model are considered as ideal, can carry out trial operation test with the test image sample of test image database；It is no
Then, model is considered as undesirable, need to readjust parameter, continues to instruct repeatedly with the training image sample of the training image database
Practice.The parameter refers to the classification information of the gesture identification model, it may be assumed that " scissors, stone, cloth, other " four classifications.Into one
Step ground, the preset threshold are 80%.
In an alternative embodiment, the gesture identification model construction module 1 further include:
Images of gestures acquisition unit extracts several hands from the gesture video captured in advance for the frame number according to setting
Gesture image；
By camera, a large amount of gesture videos captured about user's punch.System extracts gesture video, and according to setting
Frame number, video is split into multiple images.Above-mentioned acquisition mode can collect the punch gesture of user from different perspectives, be
Next punch gesture identification provides more accurate guarantee.Further, the frame number set is 30 frame.
Gray scale processing unit, for carrying out gray proces to the images of gestures using Weighted Average Algorithm.
Since the images of gestures extracted from gesture video is color image, specifically it is made of multiple pixels,
And each pixel is indicated by tri- values of RGB；Gray proces are carried out to the images of gestures, will not influence images of gestures
Texture feature information, and each pixel only needs a gray value that can indicate, substantially increases images of gestures treatment effeciency.
Specifically, gray proces are carried out to the images of gestures by following gray proces Weighted Average Algorithm formula:
F (i, j)=0.30R (i, j)+0.59G (i, j)+0.11B (i, j)
Wherein, i, j represent a pixel in the position of two-dimensional space vector, it may be assumed that the i-th row, jth column.
According to above-mentioned formula, the gray value of each pixel in the images of gestures is calculated, value range is 0-255, is made
Black-white-gray state is presented in the images of gestures.
Images of gestures is acquired from continuous gesture video, to establish the gesture identification model, is not only efficiently identified
Irregular or transformation gesture finger-guessing game movement, but also the next punch of user can be predicted based on the punch gesture of user
Movement.
In an alternative embodiment, the preset threshold is 80%.
In an alternative embodiment, the preset victory or defeat rule is cloth > stone > scissors > cloth.
In an alternative embodiment, the man-machine finger-guessing game device based on image recognition further include:
Information sending module, for when the user gesture information be other when, to display equipment send user gesture without
Method identification information, so that the display equipment shows that the user gesture can not identification information；
Victory or defeat judges starting module, for determining to the use when the user gesture information is scissors, stone or cloth
Family gesture and the corresponding gesture information of the finger-guessing game equipment carry out victory or defeat judgement.
In an alternative embodiment, the gesture control module 2 is specifically used for after determination enters finger-guessing game game,
When reaching the first setting time, the gesture information generated at random is sent, to the finger-guessing game equipment to control the finger-guessing game equipment
Carry out corresponding gesture operation.
Further, when the corresponding user gesture information of the images to be recognized identified is other, the camera shooting
Head is captured the gestures detection region, and re-start gesture identification again after reaching the second setting time.
Such as: if detecting user earlier than the finger-guessing game equipment punch, finger-guessing game equipment is not dealt with, and is reaching described first
Setting time just carries out punch；If detecting user and the finger-guessing game equipment punch simultaneously, camera captures user's punch gesture；
If in the finger-guessing game equipment punch after detecting user, the camera is captured again after reaching the second setting time
User's punch gesture.Wherein, first setting time is 3 seconds, and second setting time is 2 seconds.
The present invention uses method identical with the gesture identification model, constructs people according to the video image that camera is captured
Then face identification model carries out recognition of face by candid photograph image of the human face recognition model to target area, here, not existing
The building process of human face recognition model is illustrated.
The embodiment of the invention also provides a kind of man-machine finger-guessing game device based on image recognition, including processor, memory
And the computer program executed by the processor is stored in the memory and is configured as, the processor executes institute
Such as the above-mentioned man-machine finger-guessing game method based on image recognition is realized when stating computer program.
Illustratively, the computer program can be divided into one or more module/units, one or more
A module/unit is stored in the memory, and is executed by the processor, to complete the present invention.It is one or more
A module/unit can be the series of computation machine program instruction section that can complete specific function, and the instruction segment is for describing institute
State implementation procedure of the computer program in the man-machine finger-guessing game device based on image recognition.For example, the computer program
The module of the man-machine finger-guessing game device as shown in Figure 2 based on image recognition can be divided into.
The man-machine finger-guessing game device based on image recognition can be desktop PC, notebook, palm PC and cloud
Server etc. is held to calculate equipment.The man-machine finger-guessing game device based on image recognition may include, but be not limited only to, and processor is deposited
Reservoir.It will be understood by those skilled in the art that the schematic diagram is only based on the example of the man-machine finger-guessing game device of image recognition,
The restriction to the man-machine finger-guessing game device based on image recognition is not constituted, may include components more more or fewer than diagram, or
Person combines certain components or different components, such as the man-machine finger-guessing game device based on image recognition can also include defeated
Enter output equipment, network access equipment, bus etc..
Alleged processor can be central processing unit (Central Processing Unit, CPU), can also be it
His general processor, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng the processor is the control centre of the man-machine finger-guessing game device based on image recognition, and various interfaces and route is utilized to connect
Connect the various pieces of the entirely man-machine finger-guessing game device based on image recognition.
The memory can be used for storing the computer program and/or module, and the processor is by operation or executes
Computer program in the memory and/or module are stored, and calls the data being stored in memory, described in realization
The various functions of man-machine finger-guessing game device based on image recognition.The memory can mainly include storing program area and storing data
Area, wherein storing program area can application program needed for storage program area, at least one function (such as sound-playing function,
Image player function etc.) etc.；Storage data area, which can be stored, uses created data (such as audio data, electricity according to mobile phone
Script for story-telling etc.) etc..In addition, memory may include high-speed random access memory, it can also include nonvolatile memory, such as
Hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other volatibility are solid
State memory device.
Wherein, if the integrated module/unit of the man-machine finger-guessing game device based on image recognition is with SFU software functional unit
Form realize and when sold or used as an independent product, can store in a computer readable storage medium.
Based on this understanding, the present invention realizes all or part of the process in above-described embodiment method, can also pass through computer journey
Sequence is completed to instruct relevant hardware, and the computer program can be stored in a computer readable storage medium, the meter
Calculation machine program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program packet
Include computer program code, the computer program code can for source code form, object identification code form, executable file or
Certain intermediate forms etc..The computer-readable medium may include: any reality that can carry the computer program code
Body or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and
Software distribution medium etc..It should be noted that the content that the computer-readable medium includes can be according in jurisdiction
Legislation and the requirement of patent practice carry out increase and decrease appropriate, such as in certain jurisdictions, according to legislation and patent practice, meter
Calculation machine readable medium does not include electric carrier signal and telecommunication signal.
It should be noted that the apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.In addition, device provided by the invention
In embodiment attached drawing, the connection relationship between module indicate between them have communication connection, specifically can be implemented as one or
A plurality of communication bus or signal wire.Those of ordinary skill in the art are without creative efforts, it can understand
And implement.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer readable storage medium includes
The computer program of storage, wherein control in computer program operation and set where the computer readable storage medium
It is standby to execute such as the above-mentioned man-machine finger-guessing game method based on image recognition.
Compared with the existing technology, a kind of man-machine finger-guessing game method based on image recognition provided in an embodiment of the present invention is beneficial
Effect is: the man-machine finger-guessing game method based on image recognition includes: using convolutional neural networks algorithm to gathered in advance
Images of gestures is trained, and constructs gesture identification model；Wherein, the classification information in the gesture identification model include: scissors,
Stone, cloth, other；The gesture information generated at random is sent to finger-guessing game equipment, carries out corresponding hand to control the finger-guessing game equipment
Gesture operation, and start camera simultaneously and gesture detection zone is captured, to obtain images to be recognized；Known by the gesture
Other model carries out gesture identification to the images to be recognized, to obtain the user gesture information in the gestures detection region；Root
According to preset victory or defeat rule, judge preferential between user gesture information gesture information corresponding with the finger-guessing game equipment
Grade, obtains finger-guessing game result.By the above-mentioned man-machine finger-guessing game method based on image recognition, gesture identification accuracy and effect can be improved
Rate, while realizing the finger-guessing game of people Yu finger-guessing game equipment, improve the novel interest of human-computer interaction.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (10)
1. a kind of man-machine finger-guessing game method based on image recognition characterized by comprising
Images of gestures gathered in advance is trained using convolutional neural networks algorithm, constructs gesture identification model；Wherein, institute
State the classification information in gesture identification model include: scissors, stone, cloth, other；
The gesture information generated at random is sent to finger-guessing game equipment, carries out corresponding gesture operation to control the finger-guessing game equipment, and
Start camera simultaneously to capture gesture detection zone, to obtain images to be recognized；
Gesture identification is carried out to the images to be recognized by the gesture identification model, to obtain in the gestures detection region
User gesture information；
According to preset victory or defeat rule, judge between user gesture information gesture information corresponding with the finger-guessing game equipment
Priority obtains finger-guessing game result.
2. the man-machine finger-guessing game method based on image recognition as described in claim 1, which is characterized in that described to be based on image recognition
Man-machine finger-guessing game method further include:
Corresponding video image carries out recognition of face in the target area captured to the camera, to judge the target area
In domain whether someone；
When judging someone in the target area, whether the gestures detection region that detection is located in the target area is put
It lets go；If it is not, then voice messaging is sent to speech ciphering equipment, to play voice prompting to user；It is swum if so, determining and entering finger-guessing game
Play.
3. the man-machine finger-guessing game method based on image recognition as described in claim 1, which is characterized in that described to use convolutional Neural
Network algorithm is trained images of gestures gathered in advance, constructs gesture identification model, specifically includes:
According to images of gestures gathered in advance, training image sample and test image sample are obtained；
The training image sample is trained using convolutional neural networks algorithm, constructs the gesture identification model；
The test image sample is input to the gesture identification model, obtains gesture test result；Wherein, the gesture is surveyed
Test result is the result of loss function output in the gesture identification model；
According to the gesture test result, judge whether the recognition accuracy of the gesture identification model reaches preset threshold；If
It is no, then adjust training image sample described in the classification information in the gesture identification model and re -training；If so, described in determining
Gesture identification model construction is completed.
4. the man-machine finger-guessing game method based on image recognition as claimed in claim 3, which is characterized in that the basis acquires in advance
Images of gestures, before obtaining training image sample and test image sample further include:
Several images of gestures are extracted from the gesture video captured in advance according to the frame number of setting；
Gray proces are carried out to the images of gestures using Weighted Average Algorithm.
5. the man-machine finger-guessing game method based on image recognition as claimed in claim 3, which is characterized in that the preset threshold is
80%.
6. the man-machine finger-guessing game method based on image recognition as described in claim 1, which is characterized in that the preset victory or defeat rule
It is then cloth > stone > scissors > cloth.
7. the man-machine finger-guessing game method based on image recognition as described in claim 1, which is characterized in that described to pass through the gesture
Identification model to the images to be recognized carry out gesture identification, with obtain the user gesture information in the gestures detection region it
Afterwards further include:
When the user gesture information be other when, to display equipment send user gesture can not identification information so that described
Display equipment shows that the user gesture can not identification information；
When the user gesture information is scissors, stone or cloth, determine corresponding to the user gesture and the finger-guessing game equipment
Gesture information carry out victory or defeat judgement.
8. the man-machine finger-guessing game method based on image recognition as claimed in claim 2, which is characterized in that described to be based on image recognition
Man-machine finger-guessing game method further include:
When determining into after finger-guessing game game, when reaching the first setting time, the hand generated at random is sent to the finger-guessing game equipment
Gesture information carries out corresponding gesture operation to control the finger-guessing game equipment.
9. a kind of man-machine finger-guessing game device based on image recognition characterized by comprising
Gesture identification model construction module, for being instructed using convolutional neural networks algorithm to images of gestures gathered in advance
Practice, constructs gesture identification model；Wherein, the classification information in the gesture identification model include: scissors, stone, cloth, other；
Gesture control module is carried out for sending the gesture information generated at random to finger-guessing game equipment with controlling the finger-guessing game equipment
Corresponding gesture operation, and start camera simultaneously and gesture detection zone is captured, to obtain images to be recognized；
User gesture data obtaining module, user carry out gesture knowledge to the images to be recognized by the gesture identification model
Not, to obtain the user gesture information in the gestures detection region；
Victory or defeat judgment module, for judging the user gesture information and the finger-guessing game equipment pair according to preset victory or defeat rule
The priority between gesture information answered, obtains finger-guessing game result.
10. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage
Machine program, wherein equipment where controlling the computer readable storage medium in computer program operation is executed as weighed
Benefit require any one of 1 to 8 described in the man-machine finger-guessing game method based on image recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810819742.5A CN109165555A (en) | 2018-07-24 | 2018-07-24 | Man-machine finger-guessing game method, apparatus and storage medium based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810819742.5A CN109165555A (en) | 2018-07-24 | 2018-07-24 | Man-machine finger-guessing game method, apparatus and storage medium based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109165555A true CN109165555A (en) | 2019-01-08 |
Family
ID=64898216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810819742.5A Pending CN109165555A (en) | 2018-07-24 | 2018-07-24 | Man-machine finger-guessing game method, apparatus and storage medium based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109165555A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947257A (en) * | 2019-03-30 | 2019-06-28 | 哈尔滨理工大学 | A kind of images of gestures recognition methods |
| CN111001154A (en) * | 2020-01-10 | 2020-04-14 | 北京铭客教育科技有限公司 | Intelligent finger-guessing entertainment system with voice broadcasting function |
| CN111126279A (en) * | 2019-12-24 | 2020-05-08 | 深圳市优必选科技股份有限公司 | Gesture interaction method and gesture interaction device |
| CN112034981A (en) * | 2020-08-20 | 2020-12-04 | 深圳创维－Rgb电子有限公司 | Display terminal control method, display terminal, and computer-readable storage medium |
| CN112070987A (en) * | 2020-08-28 | 2020-12-11 | 哈尔滨拓博科技有限公司 | Game gift device control method based on gesture recognition, storage medium and device |
| CN112506342A (en) * | 2020-12-04 | 2021-03-16 | 郑州中业科技股份有限公司 | Man-machine interaction method and system based on dynamic gesture recognition |
| CN113190108A (en) * | 2021-03-26 | 2021-07-30 | 特斯联科技集团有限公司 | Museum exhibition non-inductive touch and sound linkage method and system |
| CN113453032A (en) * | 2021-06-28 | 2021-09-28 | 广州虎牙科技有限公司 | Gesture interaction method, device, system, server and storage medium |
| CN113515974A (en) * | 2020-04-10 | 2021-10-19 | 初速度（苏州）科技有限公司 | Gesture label calibration system, method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150235079A1 (en) * | 2011-05-23 | 2015-08-20 | Sony Corporation | Learning device, learning method, and program |
| CN107329564A (en) * | 2017-06-09 | 2017-11-07 | 济南大学 | Man-machine finger-guessing game method based on gesture Intellisense and Mechanism of Human-Computer Cooperation |
| CN107808143A (en) * | 2017-11-10 | 2018-03-16 | 西安电子科技大学 | Dynamic gesture identification method based on computer vision |
-
2018
- 2018-07-24 CN CN201810819742.5A patent/CN109165555A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150235079A1 (en) * | 2011-05-23 | 2015-08-20 | Sony Corporation | Learning device, learning method, and program |
| CN107329564A (en) * | 2017-06-09 | 2017-11-07 | 济南大学 | Man-machine finger-guessing game method based on gesture Intellisense and Mechanism of Human-Computer Cooperation |
| CN107808143A (en) * | 2017-11-10 | 2018-03-16 | 西安电子科技大学 | Dynamic gesture identification method based on computer vision |
Non-Patent Citations (8)
| Title |
|---|
| 丁刚毅 等: "《数字媒体技术》", 31 August 2015 * |
| 北方工业大学教务处主编: "《创青春 大学生科学研究与创业行动计划优秀研究报告论文集 2016》", 31 December 2017 * |
| 王作冰: "《人工智能时代的教育革命》", 31 May 2017, 北京联合出版公司 * |
| 王命延 等: ""机器人跟踪手势姿态图像运动准确性仿真"", 《计算机仿真》 * |
| 王廷信: "《艺术学界 第17辑》", 30 June 2017 * |
| 蒋先刚: "《数字图像模式识别工程项目研究》", 31 March 2014 * |
| 谭昶 等: ""基于改进RCE和RBF神经网络的静态手势识别"", 《计算机工程与应用》 * |
| 韦康博: "《国家大战略 从德国工业4.0到中国制造2025》", 31 August 2016, 北京：现代出版社 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947257A (en) * | 2019-03-30 | 2019-06-28 | 哈尔滨理工大学 | A kind of images of gestures recognition methods |
| CN111126279A (en) * | 2019-12-24 | 2020-05-08 | 深圳市优必选科技股份有限公司 | Gesture interaction method and gesture interaction device |
| CN111126279B (en) * | 2019-12-24 | 2024-04-16 | 深圳市优必选科技股份有限公司 | Gesture interaction method and gesture interaction device |
| CN111001154A (en) * | 2020-01-10 | 2020-04-14 | 北京铭客教育科技有限公司 | Intelligent finger-guessing entertainment system with voice broadcasting function |
| CN113515974A (en) * | 2020-04-10 | 2021-10-19 | 初速度（苏州）科技有限公司 | Gesture label calibration system, method and device |
| CN112034981A (en) * | 2020-08-20 | 2020-12-04 | 深圳创维－Rgb电子有限公司 | Display terminal control method, display terminal, and computer-readable storage medium |
| CN112070987A (en) * | 2020-08-28 | 2020-12-11 | 哈尔滨拓博科技有限公司 | Game gift device control method based on gesture recognition, storage medium and device |
| CN112506342A (en) * | 2020-12-04 | 2021-03-16 | 郑州中业科技股份有限公司 | Man-machine interaction method and system based on dynamic gesture recognition |
| CN112506342B (en) * | 2020-12-04 | 2022-01-28 | 郑州中业科技股份有限公司 | Man-machine interaction method and system based on dynamic gesture recognition |
| CN113190108A (en) * | 2021-03-26 | 2021-07-30 | 特斯联科技集团有限公司 | Museum exhibition non-inductive touch and sound linkage method and system |
| CN113453032A (en) * | 2021-06-28 | 2021-09-28 | 广州虎牙科技有限公司 | Gesture interaction method, device, system, server and storage medium |
| CN113453032B (en) * | 2021-06-28 | 2022-09-30 | 广州虎牙科技有限公司 | Gesture interaction method, device, system, server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109165555A (en) | Man-machine finger-guessing game method, apparatus and storage medium based on image recognition | |
| CN108234870A (en) | Image processing method, device, terminal and storage medium | |
| CN106469302B (en) | A kind of face skin quality detection method based on artificial neural network | |
| CN104346816B (en) | Depth determining method and device and electronic equipment | |
| CN110119815A (en) | Model training method, device, storage medium and equipment | |
| CN109558832A (en) | A kind of human body attitude detection method, device, equipment and storage medium | |
| CN109657554A (en) | A kind of image-recognizing method based on micro- expression, device and relevant device | |
| CN103020885B (en) | Depth image compression | |
| CN108734557A (en) | Methods, devices and systems for generating dress ornament recommendation information | |
| CN108198130B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| KR101872635B1 (en) | Automatic make-up evaluation system and operating method thereof | |
| CN108875452A (en) | Face identification method, device, system and computer-readable medium | |
| CN106062673A (en) | Controlling a computing-based device using gestures | |
| CN107111746A (en) | According to the models fitting of original time-of-flight images | |
| CN112232258B (en) | Information processing method, device and computer readable storage medium | |
| CN108197618A (en) | For generating the method and apparatus of Face datection model | |
| CN109978975A (en) | A kind of moving method and device, computer equipment of movement | |
| CN105139450B (en) | A kind of three-dimensional personage construction method and system based on face simulation | |
| CN109559362B (en) | Image subject face replacing method and device | |
| CN109815776A (en) | Action prompt method and apparatus, storage medium and electronic device | |
| CN109145871A (en) | Psychology and behavior recognition methods, device and storage medium | |
| CN107066081B (en) | Interactive control method and device of virtual reality system and virtual reality equipment | |
| CN114360018B (en) | Rendering method and device of three-dimensional facial expression, storage medium and electronic device | |
| CN109409199A (en) | Micro- expression training method, device, storage medium and electronic equipment | |
| JP2023103335A (en) | Computer program, server device, terminal device, and display method |
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 |
Application publication date: 20190108 |
|
| RJ01 | Rejection of invention patent application after publication |