CN108197611A - A kind of humanoid robot pattern recognition system - Google Patents
A kind of humanoid robot pattern recognition system Download PDFInfo
- Publication number
- CN108197611A CN108197611A CN201810109445.1A CN201810109445A CN108197611A CN 108197611 A CN108197611 A CN 108197611A CN 201810109445 A CN201810109445 A CN 201810109445A CN 108197611 A CN108197611 A CN 108197611A
- Authority
- CN
- China
- Prior art keywords
- module
- face
- image
- fingerprint
- recognition system
- 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
-
- 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
- G06V40/12—Fingerprints or palmprints
- G06V40/13—Sensors therefor
-
- 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
- G06V40/12—Fingerprints or palmprints
- G06V40/13—Sensors therefor
- G06V40/1324—Sensors therefor by using geometrical optics, e.g. using prisms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Optics & Photonics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of humanoid robot pattern recognition system of robotic technology field, including face identification system and fingerprint recognition system, uniformly the data acquisition module is electrically connected for the face identification system and fingerprint recognition system, the data acquisition module is connect with the data preprocessing module, the data preprocessing module is electrically connected with the characteristic extracting module, the characteristic extracting module is connect with the classification processing module, the classification processing module is electrically connected with the result output module, the present invention is by acquiring the face and finger print information of human body, it and will be in face and finger print information unified fusion to pattern recognition system, the unification for realizing a variety of recognition modes integrates, this system is easy to operate, the accuracy rate of pattern-recognition is high.
Description
Technical field
The invention discloses a kind of humanoid robot pattern recognition system, specially robotic technology field.
Background technology
With society and industrialization structure variation, the mankind for science and technology-oriented product since it is increasingly severe, and because doctor
It is quick to learn scientific and technological progress, astogeny society is quickly formed.Therefore, the development potentiality in service humanoid robot future should not be underestimated.
Epoch at scientific and technological tip, robot become the defender of people, especially in the service of the old and the weak women and children, with science and technology now not
Without possible.So service humanoid robot future, by as the indispensable life partner of society, and humanoid robot is in comparison
More it is more than general wheel-type or multi-foot robot, reason more allows people to connect without him under the class humanoid robot appearance similar with the mankind
Closely, while the human-like movement of class has the handling capacity of hypsography or narrow space and advantageous overcomes ability.Usually
Described machine recognition, computer identification belong to pattern-recognition, things are compared by some way, according to certain
Decision rule identifies things.But pattern-recognition so far develop into not yet it is unified, effectively can be applied to all patterns
The scope of identification.It to come into operation for this purpose, we have proposed a kind of humanoid robot pattern recognition system, to solve the above problems.
Invention content
The purpose of the present invention is to provide a kind of humanoid robot pattern recognition system, to solve to carry in above-mentioned background technology
The problem of going out.
To achieve the above object, the present invention provides following technical solution:A kind of humanoid robot pattern recognition system, including
The uniform data acquisition module of face identification system and fingerprint recognition system, the face identification system and fingerprint recognition system
It is electrically connected, the data acquisition module is connect with the data preprocessing module, the data preprocessing module and the spy
Levy extraction module be electrically connected, the characteristic extracting module with it is described classification processing module connect, it is described classify processing module and
The result output module is electrically connected;
The data acquisition module is used to obtain the electric signal of fixed form, for non-electrical information, need to be turned by various sensors
Change electric signal into;
The data preprocessing module be used for the data information original obtained to the data acquisition module degenerate or interfere, redundancy
Data information carries out dry, increases its signal-to-noise ratio, useful frequency domain information is extracted after recovery;
Original metric data is converted into the information of effective means expression by the characteristic extracting module, to acquired information from amount
Survey conversion of the space to feature space;
The classification processing module carries out feature choosing according in fixed feature space to the metric data as training sample
It selects and extracts, obtain its distribution in feature space, and categorised decision is carried out to classification samples;
The result output module is used to export classification results in time, and communicated by RS485 buses with host computer.
Preferably, the data type that the data acquisition module obtains has two dimensional image, one-dimensional waveform and physical parameter
Logical value.
Preferably, the face identification system includes image collection module, and described image acquisition module is clapped for camera
It according to rear acquisition face picture, and is uploaded in described image preprocessing module, described image preprocessing module is used for face figure
Piece information carries out image light compensation, Gaussian smoothing and Equalization Histogram processing, make its improve the contrast of facial image and
Binaryzation converts, and image information after treatment is transmitted in the Face detection module, and the Face detection module is used for
Pretreated face picture is positioned, to carry out feature extraction, is then transmitted the facial image after localization process
Into the face characteristic extraction module, the face characteristic extraction module puies forward the face characteristic value in facial image
It takes, and the characteristic value in the characteristic value and background data base of image zooming-out is completed to the knowledge of face more afterwards by face recognition module
Not.
Preferably, the fingerprint recognition system includes fingerprint image acquisition module, and the fingerprint image acquisition module is used for
Somatic fingerprint image is acquired, and the fingerprint pretreatment module is transferred to be handled, the fingerprint pretreatment module is for one by one
Take the fingerprint the characteristic points such as endpoint, crosspoint, central point and triangulation point of line, is then uploaded to the Finger print characteristic abstract mould
In block, the Finger print characteristic abstract module is used to carry out according to centered on central point or triangulation point or the global feature of field of direction point
Minutiae matches are at that the fingerprint image matching module is transferred to handle after under same coordinate, the fingerprint image
As matching module is for comparison branching characteristic point under same coordinate, fingerprint matching knot is obtained according to the similarity of comparison
Fruit.
Preferably, the acquisition of the fingerprint image acquisition mould fingerprint image in the block is led to by CMOS camera and Mitsubishi's mirror
The refraction of light is crossed to complete, wherein CMOS camera pixel is 800W, and Mitsubishi's mirror is isosceles right angle Mitsubishi mirror.
Compared with prior art, the beneficial effects of the invention are as follows:The present invention by acquiring the face and finger print information of human body,
And by face and finger print information unified fusion to pattern recognition system, the unification for realizing a variety of recognition modes integrates, this is
It unites easy to operate, the accuracy rate of pattern-recognition is high.
Description of the drawings
Fig. 1 is present system functional block diagram;
Fig. 2 is face identification system block diagram of the present invention;
Fig. 3 is fingerprint recognition system block diagram of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment shall fall within the protection scope of the present invention.
- 3 are please referred to Fig.1, the present invention provides a kind of technical solution:A kind of humanoid robot pattern recognition system, including people
Uniformly the data acquisition module is electric for face identifying system and fingerprint recognition system, the face identification system and fingerprint recognition system
Property connection, the data acquisition module connect with the data preprocessing module, the data preprocessing module and the feature
Extraction module is electrically connected, and the characteristic extracting module is connect with the classification processing module, the classification processing module and institute
State the electric connection of result output module;
The face identification system includes image collection module, and described image acquisition module obtains face after taking pictures for camera
Picture, and be uploaded in described image preprocessing module, described image preprocessing module is used to carry out figure to face picture information
As light compensation, Gaussian smoothing and Equalization Histogram processing, it is made to improve the contrast of facial image and binaryzation transformation, warp
Crossing treated, image information is transmitted in the Face detection module, and the Face detection module is used for pretreated people
Face picture is positioned, and to carry out feature extraction, the facial image after localization process then is transmitted to the face characteristic
In extraction module, the face characteristic extraction module extracts the face characteristic value in facial image, and by recognition of face
Characteristic value in the characteristic value and background data base of image zooming-out is completed the identification of face by module more afterwards;
The fingerprint recognition system includes fingerprint image acquisition module, and the fingerprint image acquisition module is used to acquire somatic fingerprint
Image, and the fingerprint pretreatment module is transferred to be handled, the fingerprint pretreatment module is for the line that takes the fingerprint one by one
The characteristic points such as endpoint, crosspoint, central point and triangulation point are then uploaded in the Finger print characteristic abstract module, the finger
Line characteristic extracting module is used to carry out fingerprint feature point according to centered on central point or triangulation point or the global feature of field of direction point
Matching is at that the fingerprint image matching module is transferred to handle after under same coordinate, the fingerprint image matching module
For the comparison branching characteristic point under same coordinate, fingerprint matching is obtained according to the similarity of comparison as a result, the fingerprint
The acquisition of fingerprint image in image capture module is completed by CMOS camera and Mitsubishi's mirror by the refraction of light, wherein
CMOS camera pixel is 800W, and Mitsubishi's mirror is isosceles right angle Mitsubishi mirror;
The data acquisition module is used to obtain the electric signal of fixed form, for non-electrical information, need to be turned by various sensors
Change electric signal into, the data type that the data acquisition module obtains has patrolling for two dimensional image, one-dimensional waveform and physical parameter
Collect value;
The data preprocessing module be used for the data information original obtained to the data acquisition module degenerate or interfere, redundancy
Data information carries out dry, increases its signal-to-noise ratio, useful frequency domain information is extracted after recovery;
Original metric data is converted into the information of effective means expression by the characteristic extracting module, to acquired information from amount
Survey conversion of the space to feature space;
The classification processing module carries out feature choosing according in fixed feature space to the metric data as training sample
It selects and extracts, obtain its distribution in feature space, and categorised decision is carried out to classification samples;
The result output module is used to export classification results in time, and communicated by RS485 buses with host computer.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understanding without departing from the principles and spirit of the present invention can carry out these embodiments a variety of variations, modification, replace
And modification, the scope of the present invention is defined by the appended.
Claims (5)
1. a kind of humanoid robot pattern recognition system, it is characterised in that:Including face identification system and fingerprint recognition system, institute
Stating face identification system and fingerprint recognition system, uniformly the data acquisition module is electrically connected, the data acquisition module and institute
Data preprocessing module connection is stated, the data preprocessing module is electrically connected with the characteristic extracting module, and the feature carries
Modulus block is connect with the classification processing module, and the classification processing module is electrically connected with the result output module;
The data acquisition module is used to obtain the electric signal of fixed form, for non-electrical information, need to be turned by various sensors
Change electric signal into;
The data preprocessing module be used for the data information original obtained to the data acquisition module degenerate or interfere, redundancy
Data information carries out dry, increases its signal-to-noise ratio, useful frequency domain information is extracted after recovery;
Original metric data is converted into the information of effective means expression by the characteristic extracting module, to acquired information from amount
Survey conversion of the space to feature space;
The classification processing module carries out feature choosing according in fixed feature space to the metric data as training sample
It selects and extracts, obtain its distribution in feature space, and categorised decision is carried out to classification samples;
The result output module is used to export classification results in time, and communicated by RS485 buses with host computer.
2. a kind of humanoid robot pattern recognition system according to claim 1, it is characterised in that:The data acquisition mould
The data type that block obtains has the logical value of two dimensional image, one-dimensional waveform and physical parameter.
3. a kind of humanoid robot pattern recognition system according to claim 1, it is characterised in that:The recognition of face system
System includes image collection module, and described image acquisition module obtains face picture after taking pictures for camera, and is uploaded to described
In image pre-processing module, described image preprocessing module is used to carry out image light compensation, Gao Siping to face picture information
The processing of sliding and Equalization Histogram makes it improve the contrast of facial image and binaryzation transformation, image letter after treatment
Breath is transmitted in the Face detection module, and the Face detection module is used to position pretreated face picture,
To carry out feature extraction, then the facial image after localization process is transmitted in the face characteristic extraction module, it is described
Face characteristic extraction module extracts the face characteristic value in facial image, and by face recognition module by image zooming-out
Characteristic value completes the identification of face with the characteristic value in background data base more afterwards.
4. a kind of humanoid robot pattern recognition system according to claim 1, it is characterised in that:The fingerprint recognition system
System includes fingerprint image acquisition module, and the fingerprint image acquisition module is used to acquire somatic fingerprint image, and transfer to the finger
Line preprocessing module is handled, and the fingerprint pretreatment module is used for take the fingerprint one by one endpoint, crosspoint, the central point of line
And the characteristic points such as triangulation point, it is then uploaded in the Finger print characteristic abstract module, the Finger print characteristic abstract module is used for
According to minutiae matches are carried out centered on central point or triangulation point or the global feature of field of direction point, it is at same
The fingerprint image matching module is transferred to handle after under coordinate, the fingerprint image matching module is used under same coordinate
Branching characteristic point is compared, fingerprint matching result is obtained according to the similarity of comparison.
5. a kind of humanoid robot pattern recognition system according to claim 4, it is characterised in that:The fingerprint image is adopted
The acquisition of collection mould fingerprint image in the block is completed by CMOS camera and Mitsubishi's mirror by the refraction of light, wherein CMOS camera shootings
Head portrait element is 800W, and Mitsubishi's mirror is isosceles right angle Mitsubishi mirror.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810109445.1A CN108197611A (en) | 2018-02-05 | 2018-02-05 | A kind of humanoid robot pattern recognition system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810109445.1A CN108197611A (en) | 2018-02-05 | 2018-02-05 | A kind of humanoid robot pattern recognition system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108197611A true CN108197611A (en) | 2018-06-22 |
Family
ID=62592378
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810109445.1A Pending CN108197611A (en) | 2018-02-05 | 2018-02-05 | A kind of humanoid robot pattern recognition system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108197611A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1801181A (en) * | 2006-01-06 | 2006-07-12 | 华南理工大学 | Robot capable of automatically recognizing face and vehicle license plate |
CN101414351A (en) * | 2008-11-03 | 2009-04-22 | 章毅 | Fingerprint recognition system and control method |
CN103279744A (en) * | 2013-05-28 | 2013-09-04 | 中国科学院自动化研究所 | Multi-scale tri-mode texture feature-based method and system for detecting counterfeit fingerprints |
CN106529501A (en) * | 2016-11-29 | 2017-03-22 | 黑龙江大学 | Fingerprint and finger vein image fusion method based on weighted fusion and layered serial structure |
-
2018
- 2018-02-05 CN CN201810109445.1A patent/CN108197611A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1801181A (en) * | 2006-01-06 | 2006-07-12 | 华南理工大学 | Robot capable of automatically recognizing face and vehicle license plate |
CN101414351A (en) * | 2008-11-03 | 2009-04-22 | 章毅 | Fingerprint recognition system and control method |
CN103279744A (en) * | 2013-05-28 | 2013-09-04 | 中国科学院自动化研究所 | Multi-scale tri-mode texture feature-based method and system for detecting counterfeit fingerprints |
CN106529501A (en) * | 2016-11-29 | 2017-03-22 | 黑龙江大学 | Fingerprint and finger vein image fusion method based on weighted fusion and layered serial structure |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Hand posture recognition using finger geometric feature | |
Nagi et al. | Max-pooling convolutional neural networks for vision-based hand gesture recognition | |
Singha et al. | Hand gesture recognition based on Karhunen-Loeve transform | |
Ahuja et al. | Static vision based Hand Gesture recognition using principal component analysis | |
CN107992881A (en) | A kind of Robotic Dynamic grasping means and system | |
Yang et al. | Hand gesture recognition: An overview | |
CN109766782B (en) | SVM-based real-time limb action recognition method | |
Labati et al. | A neural-based minutiae pair identification method for touch-less fingerprint images | |
Pandey et al. | Hand gesture recognition for sign language recognition: A review | |
Gupta et al. | FPGA based real time human hand gesture recognition system | |
CN105760828B (en) | A kind of static gesture identification method of view-based access control model | |
Li et al. | A novel hand gesture recognition based on high-level features | |
Ma et al. | Binocular vision object positioning method for robots based on coarse-fine stereo matching | |
CN207752527U (en) | A kind of Robotic Dynamic grasping system | |
Li et al. | First-person hand action recognition using multimodal data | |
CN108197611A (en) | A kind of humanoid robot pattern recognition system | |
Yang et al. | Target position and posture recognition based on RGB-D images for autonomous grasping robot arm manipulation | |
Ghadi et al. | An intelligent healthcare monitoring framework for daily assistant living | |
Benhamida et al. | Human Action Recognition and Coding based on Skeleton Data for Visually Impaired and Blind People Aid System | |
Singh et al. | Computer vision based hand gesture recognition: A survey | |
Li et al. | Tactile Sensing, Skill Learning, and Robotic Dexterous Manipulation | |
Samoil et al. | Multispectral hand recognition using the Kinect v2 sensor | |
Naveenkumar et al. | Vector quantization based pairwise joint distance maps (VQ-PJDM) for 3D action recognition | |
Yin et al. | Finger identification in hand gesture based human-robot interaction | |
Veluchamy et al. | Vision based gesturally controllable human computer interaction system |
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: 20180622 |
|
RJ01 | Rejection of invention patent application after publication |