CN109063596A - A kind of face identification system and mobile terminal and recognition of face auxiliary device - Google Patents
A kind of face identification system and mobile terminal and recognition of face auxiliary device Download PDFInfo
- Publication number
- CN109063596A CN109063596A CN201810768754.XA CN201810768754A CN109063596A CN 109063596 A CN109063596 A CN 109063596A CN 201810768754 A CN201810768754 A CN 201810768754A CN 109063596 A CN109063596 A CN 109063596A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- face
- recognition
- noise
- 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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of face identification system and mobile terminals and recognition of face auxiliary device, face identification system includes mobile terminal and recognition of face auxiliary device, recognition of face auxiliary device includes high-definition camera, image noise reduction module, handle chip, memory module, display module and sending module, recognition of face auxiliary device connects central processing unit, central processing unit is separately connected database module and power module, central processing unit connects mobile terminal by wireless transport module, structure of the invention principle is simple, it can be realized the accurate identification to face, recognition efficiency is high.
Description
Technical field
The present invention relates to technical field of face recognition, specially a kind of face identification system and mobile terminal and recognition of face
Auxiliary device.
Background technique
Recognition of face is a popular computer technology research field, it belongs to biometrics identification technology, is to life
The biological characteristic of object (generally refering in particular to people) itself is individual to distinguish organism.The biology that biometrics identification technology is studied is special
Sign include face, fingerprint, palm line, iris, retina, sound (voice), the bodily form, personal habits (such as tap keyboard dynamics
With frequency, signature) etc., corresponding identification technology just has recognition of face, fingerprint recognition, personal recognition, iris recognition, retina to know
Not, speech recognition (can carry out identification with speech recognition, can also carry out the identification of voice content, only the former belongs to
Biometrics identification technology), the bodily form identification, keyboard tap identification, signature identification etc..Face identification system in the prior art is handed over
Mutually and complicated operation, and is unable to satisfy the demand of user.
Summary of the invention
The purpose of the present invention is to provide a kind of face identification system and mobile terminals and recognition of face auxiliary device, with solution
Certainly the problems mentioned above in the background art.
To achieve the above object, the invention provides the following technical scheme: a kind of face identification system, face identification system packet
Include mobile terminal and recognition of face auxiliary device, the recognition of face auxiliary device include high-definition camera, image noise reduction module,
Chip, memory module, display module and sending module are handled, the recognition of face auxiliary device connects central processing unit, described
Central processing unit is separately connected database module and power module, and the central processing unit is connected by wireless transport module and moved
Terminal.
Preferably, the high-definition camera is connected respectively by image noise reduction module connection processing chip, the processing chip
Connect memory module, display module and sending module.
Preferably, be equipped in the mobile terminal microprocessor, picture signal receiving module, picture signal sending module,
Identification module and image characteristics extraction module, the microprocessor are separately connected picture signal receiving module, identification module and figure
As characteristic extracting module, the microprocessor connects recognition of face auxiliary device by picture signal sending module.
Preferably, described image noise reduction module noise-reduction method is as follows:
A, input carries out noise estimation to noise-reduced image to described, obtains the noise level of image to noise-reduced image；
B, noise compression multiple k of the setting to noise-reduced image, and obtain target weight Wt；
C, it according to noise level σ, calculates in described image between each pixel and each interior pixel of its neighborhood
Similar weight wy；
D, total weight of the pixel is normalized to by the target weight according to similar weight wy and target weight Wt
Wt, obtaining weighted average is the pixel value after the pixel noise reduction.
Preferably, described image characteristic extracting module feature extracting method is as follows:
A, the location information and RGB color component of whole pixels in image are extracted；
B, the RGB color component of pixel each in image is transformed to hsv color component, and to three components of HSV
Non- homogenized quantization is carried out, obtains N kind color to get the colouring information of each pixel is arrived；
C, the processing that fringe region is extracted to image obtains the fringe region of image, and then it is every to obtain fringe region
The location information and colouring information of a pixel；
D, color autocorrelation characteristic is extracted to the fringe region of image, obtains the color auto-correlogram ERCAC of fringe region,
Obtain the feature vector of one group of A dimension；
E, edge direction autocorrelation characteristic is extracted to the whole region of image I, obtains global edge direction autocorrelogram
EOAC is to get the feature vector tieed up to one group of B；
F, to color autocorrelation characteristic is extracted in the whole region of image I, global color auto-correlogram CAC is obtained, i.e.,
Obtain the feature vector of one group of C dimension；
G, by the face of the color auto-correlogram ERCAC of fringe region, global edge direction autocorrelogram EOAC and the overall situation
Color autocorrelogram CAC is merged before carrying out feature, obtains the feature of image I to get the feature vector tieed up to one group (A+B+C), i.e.,
Realize the feature extraction to image.
Compared with prior art, the beneficial effects of the present invention are:
(1) structure of the invention principle is simple, can be realized the accurate identification to face, and recognition efficiency is high.
(2) in the present invention, image noise reduction module noise-reduction method can guarantee the uniformity of full figure noise reduction and in different images
The stability of noise reduction, and noise reduction effect can be determined intuitively by user's expectation, and image recognition precision is improved.
(3) in the present invention, the image characteristic extracting method of use reduces calculation amount and improves performance；Melted by feature
It closes, realizes the more comprehensively content description based on picture structure, further improve recognition of face efficiency.
Detailed description of the invention
Fig. 1 is present system functional block diagram；
Fig. 2 is image noise reduction module noise-reduction method flow chart of the present invention；
Fig. 3 is image characteristics extraction modular character extracting method flow chart 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, the present invention provides a kind of technical solution: a kind of face identification system, face identification system include moving
Dynamic terminal 1 and recognition of face auxiliary device 2, the recognition of face auxiliary device 2 include high-definition camera 3, image noise reduction module
4, chip 5, memory module 6, display module 7 and sending module 8 are handled, the recognition of face auxiliary device 2 connects central processing
Device 9, the central processing unit 9 are separately connected database module 10 and power module 11, and the central processing unit 9 is by wirelessly passing
Defeated module 12 connects mobile terminal 1；High-definition camera 3 passes through the connection processing chip 5 of image noise reduction module 4, the processing chip 5
It is separately connected memory module 6, display module 7 and sending module 8.
It is equipped with microprocessor 12, picture signal receiving module 13, picture signal in the present invention, in mobile terminal 1 and sends mould
Block 14, identification module 15 and image characteristics extraction module 16, the microprocessor 12 be separately connected picture signal receiving module 13,
Identification module 15 and image characteristics extraction module 16, the microprocessor 12, which connects face by picture signal sending module 14, to be known
Other auxiliary device 2.
As shown in Fig. 2, image noise reduction module noise-reduction method is as follows:
A, input carries out noise estimation to noise-reduced image to described, obtains the noise level of image to noise-reduced image；
B, noise compression multiple k of the setting to noise-reduced image, and obtain target weight Wt；
C, it according to noise level σ, calculates in described image between each pixel and each interior pixel of its neighborhood
Similar weight wy；
D, total weight of the pixel is normalized to by the target weight according to similar weight wy and target weight Wt
Wt, obtaining weighted average is the pixel value after the pixel noise reduction.
In the present invention, image noise reduction module noise-reduction method can guarantee the uniformity of full figure noise reduction and to noise reduction in different images
Stability, and noise reduction effect can intuitively by user expectation be determined, improve image recognition precision.
As shown in figure 3, image characteristics extraction modular character extracting method is as follows:
A, the location information and RGB color component of whole pixels in image are extracted；
B, the RGB color component of pixel each in image is transformed to hsv color component, and to three components of HSV
Non- homogenized quantization is carried out, obtains N kind color to get the colouring information of each pixel is arrived；
C, the processing that fringe region is extracted to image obtains the fringe region of image, and then it is every to obtain fringe region
The location information and colouring information of a pixel；
D, color autocorrelation characteristic is extracted to the fringe region of image, obtains the color auto-correlogram ERCAC of fringe region,
Obtain the feature vector of one group of A dimension；
E, edge direction autocorrelation characteristic is extracted to the whole region of image I, obtains global edge direction autocorrelogram
EOAC is to get the feature vector tieed up to one group of B；
F, to color autocorrelation characteristic is extracted in the whole region of image I, global color auto-correlogram CAC is obtained, i.e.,
Obtain the feature vector of one group of C dimension；
G, by the face of the color auto-correlogram ERCAC of fringe region, global edge direction autocorrelogram EOAC and the overall situation
Color autocorrelogram CAC is merged before carrying out feature, obtains the feature of image I to get the feature vector tieed up to one group (A+B+C), i.e.,
Realize the feature extraction to image.In the present invention, the image characteristic extracting method of use reduces calculation amount and improves performance；
By Fusion Features, the more comprehensively content description based on picture structure is realized, recognition of face efficiency is further improved.
Working principle: noise reduction process is carried out after recognition of face auxiliary device acquisition face characteristic image, image noise reduction is increased
Central processing unit processing is sent to after strong, picture signal is transmitted to mobile terminal by central processing unit, the image in mobile terminal
Characteristic extracting module extracts characteristics of image, and to identifying, recognition result is sent on recognition of face auxiliary device and shows.
In conclusion structure of the invention principle is simple, the accurate identification to face can be realized, recognition efficiency is high.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (5)
1. a kind of face identification system, face identification system includes mobile terminal (1) and recognition of face auxiliary device (2), spy
Sign is: the recognition of face auxiliary device (2) include high-definition camera (3), image noise reduction module (4), processing chip (5),
Memory module (6), display module (7) and sending module (8), the recognition of face auxiliary device (2) connect central processing unit
(9), the central processing unit (9) is separately connected database module (10) and power module (11), and the central processing unit (9) is logical
Cross wireless transport module (12) connection mobile terminal (1).
2. a kind of face identification system according to claim 1, it is characterised in that: the high-definition camera (3) passes through figure
As noise reduction module (4) connection processing chip (5), the processing chip (5) be separately connected memory module (6), display module (7) and
Sending module (8).
3. a kind of face identification system according to claim 1, it is characterised in that: be equipped in the mobile terminal (1) micro-
Processor (12), picture signal receiving module (13), picture signal sending module (14), identification module (15) and characteristics of image mention
Modulus block (16), it is special that the microprocessor (12) is separately connected picture signal receiving module (13), identification module (15) and image
It levies extraction module (16), the microprocessor (12) connects recognition of face auxiliary device by picture signal sending module (14)
(2)。
4. a kind of face identification system according to claim 1, it is characterised in that: described image noise reduction module noise-reduction method
It is as follows:
A, input carries out noise estimation to noise-reduced image to described, obtains the noise level of image to noise-reduced image；
B, noise compression multiple k of the setting to noise-reduced image, and obtain target weight Wt；
C, it according to noise level σ, calculates similar between each pixel and each pixel in its neighborhood in described image
Weight wy；
D, total weight of the pixel is normalized to by the target weight Wt according to similar weight wy and target weight Wt, obtained
Pixel value after being the pixel noise reduction to weighted average.
5. a kind of face identification system according to claim 3, it is characterised in that: described image characteristic extracting module feature
Extracting method is as follows:
A, the location information and RGB color component of whole pixels in image are extracted；
B, the RGB color component of pixel each in image is transformed to hsv color component, and three components of HSV is carried out
Non- homogenized quantization obtains N kind color to get the colouring information of each pixel is arrived；
C, the processing that fringe region is extracted to image obtains the fringe region of image, and then obtains each picture of fringe region
The location information and colouring information of vegetarian refreshments；
D, color autocorrelation characteristic is extracted to the fringe region of image, obtain the color auto-correlogram ERCAC of fringe region to get
The feature vector tieed up to one group of A；
E, edge direction autocorrelation characteristic is extracted to the whole region of image I, obtains global edge direction autocorrelogram EOAC,
Obtain the feature vector of one group of B dimension；
F, to color autocorrelation characteristic is extracted in the whole region of image I, global color auto-correlogram CAC is obtained to get arriving
The feature vector of one group of C dimension；
G, certainly by the color of the color auto-correlogram ERCAC of fringe region, global edge direction autocorrelogram EOAC and the overall situation
Correlation figure CAC is merged before carrying out feature, is obtained the feature of image I to get the feature vector tieed up to one group (A+B+C), that is, is realized
Feature extraction to image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810768754.XA CN109063596A (en) | 2018-07-13 | 2018-07-13 | A kind of face identification system and mobile terminal and recognition of face auxiliary device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810768754.XA CN109063596A (en) | 2018-07-13 | 2018-07-13 | A kind of face identification system and mobile terminal and recognition of face auxiliary device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063596A true CN109063596A (en) | 2018-12-21 |
Family
ID=64816470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810768754.XA Pending CN109063596A (en) | 2018-07-13 | 2018-07-13 | A kind of face identification system and mobile terminal and recognition of face auxiliary device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063596A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113177491A (en) * | 2021-05-08 | 2021-07-27 | 重庆第二师范学院 | Self-adaptive light source face recognition system and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021899A (en) * | 2007-03-16 | 2007-08-22 | 南京搜拍信息技术有限公司 | Interactive human face identificiating system and method of comprehensive utilizing human face and humanbody auxiliary information |
| CN101770578A (en) * | 2010-03-24 | 2010-07-07 | 上海交通大学 | Image characteristic extraction method |
| CN102610015A (en) * | 2012-03-13 | 2012-07-25 | 浙江万里学院 | Multimedia visual entrance guard system |
| CN104036457A (en) * | 2013-09-02 | 2014-09-10 | 上海联影医疗科技有限公司 | Image noise reduction method |
| CN104346602A (en) * | 2013-08-07 | 2015-02-11 | 上海贯城信息科技有限公司 | Face recognition method and device based on feature vectors |
| CN206209760U (en) * | 2016-08-09 | 2017-05-31 | 北京文安智能技术股份有限公司 | A kind of face identification system and mobile terminal and recognition of face servicing unit |
| CN107180234A (en) * | 2017-06-01 | 2017-09-19 | 四川新网银行股份有限公司 | The credit risk forecast method extracted based on expression recognition and face characteristic |
-
2018
- 2018-07-13 CN CN201810768754.XA patent/CN109063596A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021899A (en) * | 2007-03-16 | 2007-08-22 | 南京搜拍信息技术有限公司 | Interactive human face identificiating system and method of comprehensive utilizing human face and humanbody auxiliary information |
| CN101770578A (en) * | 2010-03-24 | 2010-07-07 | 上海交通大学 | Image characteristic extraction method |
| CN102610015A (en) * | 2012-03-13 | 2012-07-25 | 浙江万里学院 | Multimedia visual entrance guard system |
| CN104346602A (en) * | 2013-08-07 | 2015-02-11 | 上海贯城信息科技有限公司 | Face recognition method and device based on feature vectors |
| CN104036457A (en) * | 2013-09-02 | 2014-09-10 | 上海联影医疗科技有限公司 | Image noise reduction method |
| CN206209760U (en) * | 2016-08-09 | 2017-05-31 | 北京文安智能技术股份有限公司 | A kind of face identification system and mobile terminal and recognition of face servicing unit |
| CN107180234A (en) * | 2017-06-01 | 2017-09-19 | 四川新网银行股份有限公司 | The credit risk forecast method extracted based on expression recognition and face characteristic |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113177491A (en) * | 2021-05-08 | 2021-07-27 | 重庆第二师范学院 | Self-adaptive light source face recognition system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108234591B (en) | Content data recommendation method and device based on identity authentication device and storage medium | |
| CN105160318B (en) | Lie detecting method based on facial expression and system | |
| KR101141643B1 (en) | Apparatus and Method for caricature function in mobile terminal using basis of detection feature-point | |
| CN105426850B (en) | Associated information pushing device and method based on face recognition | |
| WO2020125631A1 (en) | Video compression method and apparatus, and computer-readable storage medium | |
| CN112037162B (en) | Facial acne detection method and equipment | |
| US20110299774A1 (en) | Method and system for detecting and tracking hands in an image | |
| WO2020140726A1 (en) | Photographing method and electronic device | |
| WO2021036853A1 (en) | Image processing method and electronic apparatus | |
| CN110287771B (en) | Image palm region extraction method and device | |
| CN111209812B (en) | Target face picture extraction method and device and terminal equipment | |
| CN111857334B (en) | Human gesture letter recognition method and device, computer equipment and storage medium | |
| CN108259758B (en) | Image processing method, image processing apparatus, storage medium, and electronic device | |
| CN106920256B (en) | Effective missing child searching system | |
| CN110796100B (en) | Gait recognition method and device, terminal and storage device | |
| WO2019153860A1 (en) | Information exchange method, device, storage medium, and electronic device | |
| CN112036284B (en) | Image processing method, device, equipment and storage medium | |
| CN113507558B (en) | Method, device, terminal equipment and storage medium for removing image glare | |
| WO2022135574A1 (en) | Skin color detection method and apparatus, and mobile terminal and storage medium | |
| CN113902785B (en) | Depth image processing method, system, device and computer storage medium | |
| CN114283473A (en) | Face detection method and device, computer equipment and storage medium | |
| CN109063596A (en) | A kind of face identification system and mobile terminal and recognition of face auxiliary device | |
| CN112036277B (en) | Face recognition method, electronic equipment and computer readable storage medium | |
| WO2021078037A1 (en) | Facial skin detection method and apparatus | |
| CN109829388A (en) | Video data handling procedure, device and computer equipment based on micro- expression |
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: 20181221 |
|
| RJ01 | Rejection of invention patent application after publication |