CN110008864A - A kind of miniature manpower identification equipment and recognition methods - Google Patents
A kind of miniature manpower identification equipment and recognition methods Download PDFInfo
- Publication number
- CN110008864A CN110008864A CN201910224288.3A CN201910224288A CN110008864A CN 110008864 A CN110008864 A CN 110008864A CN 201910224288 A CN201910224288 A CN 201910224288A CN 110008864 A CN110008864 A CN 110008864A
- Authority
- CN
- China
- Prior art keywords
- manpower
- module
- image
- pen
- skin
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- 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
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/446—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering using Haar-like filters, e.g. using integral image techniques
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention discloses a kind of miniature manpower identification equipment and recognition methods, including optical imagery module, image capture module, data processing and memory module and communication interface module;Optical imagery module is used to the texture of skin on manpower imaging in described image acquisition module;Image capture module forms picture signal or image file for acquiring the optical imagery module imaging;Data processing and memory module are used to acquired image signal or image file carrying out Feature extraction and recognition, identify the texture of hand, the identity to authentication equipment grasping person;Communication interface module is used for transmission the identity information recognized;Wherein, which is pen shape, and optical imagery module is located at pen holding region.The present invention can pass through the identity of identification manpower texture recognition equipment grasping person in small space;It can be accurately corresponding by writing and/or content of signing and the identity of writer;It can be in the whole identity for stablizing constantly identification record equipment grasping person of writing or work.
Description
Technical field
The invention belongs to living things feature recognition field, it is related to a kind of novel ID authentication device and recognition methods, especially
A kind of miniature manpower identification device and method.
Background technique
With the development of electronic equipment manufacturing technology and imaging device, biometrics identification technology can be widely applied to give birth to
Every aspect in work.
But the existing most volume of living things feature recognition is larger, it is difficult to combine with practical experience of life and provide the knowledge of duration identity
Not.For example, existing palmmprint, fingerprint identification technology, need individual equipment, also it is difficult to directly accomplish lesser volume, is used to
Duration identification is carried out just not make very much.
On the other hand, in living things feature recognition field, lasting identification is always a urgent problem.
A kind of the case where common violation security protocol, be authorized user after carrying out identification authentication, gives other people on behalf of completing work
Make task, and the authentication of general identification system whole process relatively difficult to achieve.Alternatively, because of authentication behavior itself and writing, signature,
It physically, is separation, so being difficult to ensure that identity is unified with content.
In another aspect, the field for needing to combine text with penner's identity in law, finance, administration etc., also always
Lack a believable tool, authentication content that can be simple and convenient it is accurate.
Another aspect, existing person's handwriting identification, can identify the identity of writer by identification person's handwriting.It is existing to ask
Topic, is that recognition speed is slow, is easy to forge.Person's handwriting identification needs a certain amount of person's handwriting, writes the time ratio of these person's handwritings needs
It is longer, it is normally only used for signature recognition, it is difficult to the identity of continuous verification writer.By sufficiently practicing imitating, person's handwriting, handwriting
It is possible that being forged.
Summary of the invention
It is an object of the invention to propose a kind of miniature manpower identification device and method, providing for duration identification can
Energy.
For this purpose, miniature manpower identification equipment proposed by the present invention includes optical imagery module, image capture module, at data
Reason and memory module and communication interface module;The optical imagery module is used to the texture of skin on manpower imaging in the figure
As on acquisition module;Described image acquisition module for acquiring the optical imagery module imaging, formed picture signal or
Image file;The data processing and memory module be used to carry out acquired image signal or image file feature extraction with
Identification, identifies the texture of hand, the identity to authentication equipment grasping person;The communication interface module is used for transmission and recognizes
Identity information;Wherein, which is pen shape, and the optical imagery module is located at pen holding region.
In some embodiments of the invention, further include following technical characteristic:
The optical imagery module is unilateral catoptric imaging type, reflects unilateral light using the reflecting mirror of 45 degree of oblique placements
Road shoots the skin texture images that hold a pen of side.
The optical imagery module is panorama ring catoptric imaging type, uses the plane reflection being placed in parallel with ring cutting face
Mirror or to employ doubly curved reflecting mirror reflect the texture image for the skin annular region that holds a pen.
The data processing and memory module utilize multi-direction multiple dimensioned gabor texture feature extraction, then use study side
Method Classification and Identification.
It is described that unilateral reflect to reflecting mirror is that a side holds a pen the image of skin;On the outside of pen, positioning appropriate is added
Reinforcing post or the curved-surface structure that holds a pen, to auxiliary positioning.
When using plane mirror, reflection is skin image of the reflecting mirror to the region that holds a pen of lens group a distance;
When to employ doubly curved reflecting mirror, reflection is from hyperbolic mirror edge, to the region that holds a pen of a distance between lens group
Skin image.
Further include LED light source, for irradiating skin, provides illumination for imaging.
The optical imagery module and described image acquisition module are respectively the lens group and imaging sensor of optical fiber camera.
Further include pressure-induction handwriting pen tip, realizes while manpower identification, Writing contents and manpower are imaged and are deposited together
Storage.
The present invention also proposes a kind of manpower recognition methods, is identified using above-mentioned miniature manpower identification equipment, including
Following steps: S1, image preprocessing: adjusting the gray value of input picture, is first floating data, renormalization by grayvalue transition
To between 0,1.According to the grey level histogram of image, intensity profile is adjusted to more uniformly;S2, skin area positioning: in image
In, according to skin color and texture, position skin area position.Generate skin area exposure mask mask;S3, feature extraction: skin
It in regional scope, is filtered using the Gabor filter of multiple directions, on image after the filtering, counts LBP histogram feature;
S4, Classification and Identification: carrying out classification comparison to feature using SVM, chooses the corresponding threshold value of the error rates EER such as minimum and compares.
The beneficial effects of the present invention are: since the miniature manpower identification equipment is pen shape, optical imagery module position
In pen holding region, it can be achieved that: A, small space realize identification;B, writing, content of signing are accurate corresponding with identity;C, steady
Fixed constantly identification.
It using reflective imager part and optical fiber camera, may be implemented in micro volume, to (the 360 degree of rings of panorama around
Depending on) imaging, realize new living creature characteristic recognition system.
Detailed description of the invention
Fig. 1 is the hardware composition schematic diagram of the embodiment of the present invention.
Fig. 2A, 2B, 2C are the cross-sectional views of three embodiments of the invention.
Fig. 3 A, 3B, 3C are the light path schematic diagrams of three embodiments of the invention.
Fig. 4 A, 4B, 4C are the cross-sectional views of the other three embodiment of the present invention.
Fig. 5 A, 5B, 5C be Fig. 4 A, in 4B, 4C three embodiments light path schematic diagram.
Fig. 6 is the software flow pattern of the embodiment of the present invention.
Fig. 7 A-7D is the different image device of the embodiment of the present invention and application scheme schematic diagram.
Specific embodiment
The embodiment of the present invention is made with reference to the accompanying drawing and being further elaborated with.
1, hardware forms
The hardware of this embodiment scheme forms, have optical imagery, Image Acquisition, data processing and storage, communication interface this
Four module compositions, as shown in Figure 1.
Optical imagery: for the texture of skin on manpower to be imaged in image capture module, the mainly reflection of optical path
With convergence.In different embodiments of the invention, two schemes are respectively adopted: unilateral side reflection and the reflection of panorama ring.
Unilateral catoptric imaging is to reflect unilateral optical path using the reflecting mirror of 45 degree of oblique placements, shoots the skin that holds a pen of side
Skin texture image.
Panorama ring catoptric imaging, in different embodiments of the invention, also there are two types of schemes, or use and ring cutting face to put down
The plane mirror or to employ doubly curved reflecting mirror that row is placed reflect the texture image for the skin annular region that holds a pen.
Image Acquisition: optical imagery module imaging is acquired using the small camera mould group of volume, forms picture signal
Or image file.
Data processing and storage: camera acquired image is sent into embeded processor and carries out Feature extraction and recognition, knows
The texture of other hand, to identify the identity for the people that holds a pen.
What identification here utilized is the texture of skin on hand.Using multi-direction multiple dimensioned gabor texture feature extraction, so
Learning method Classification and Identification is used afterwards.
Gabor texture feature extraction is exactly filtered image using the gabor filter of multiple groups different parameters.Filter
It is after wave as a result, the feature of multidimensional can be presented, usually in the filtering of different directions because used multiple groups gabor filter
Maximum filter response, the grain direction feature as the Main way of current location, as the position are screened in device response kind.
And the response of the whole filter for different angular frequencies of image is image pair wherein responding the angular frequency of maximum filter
In the main angular frequency of texture.
This programme proposes that the feature for obtaining Gabor texture blending extracts N number of triple according to classification informationWhereinFor similar sample,ForBe not belonging to of a sort sample.Then learn
One forced coding device f (x) meets,
In this way, feature is encoded by f (x), ensure that similar distance is close, foreign peoples's distance is remote.Distance can directly be used
Classify different features.
As described above, being to carry out identification with dermatoglyph here, it is not limited to fingerprint, palmmprint, thus is not also needed
Palm is unfolded completely.Because the posture that holds a pen is typically all stable.As long as attitude stabilization, texture i.e. stable.Even
Fold also can be more stable as long as motor habit.
Communication interface: wired or wireless, the wireless home control network communication protocols such as optional bluetooth or 2.4GHz, transmission identification be can be
The identity information arrived.
2, specific structure
If Fig. 2A, 2B, 2C show the cross-sectional view of three embodiments, respectively correspond unilateral to reflecting mirror, plane to reflection
The case where mirror and hyperbolic reflecting mirror.Wherein reflecting mirror viewing area, pen body material be transparent material, high grade of transparency organic glass or
Glass (and various mix reinforcing glass).
Situation such as Fig. 2A from unilateral side to reflecting mirror, when using it is unilateral to reflecting mirror when, reflection is that a side holds a pen skin
Image.The program can only extract the image of a side, it is desirable that hold a pen direction and position will be fixed.It optionally, can be in pen
Positioning auxiliary column appropriate or the curved-surface structure that holds a pen are added, to auxiliary positioning in outside.
The situation of plane mirror such as Fig. 2 B, when using plane mirror, reflection be reflecting mirror to one section of lens group away from
From the region that holds a pen skin image.The program takes annular skin region, for the of less demanding of the direction that holds a pen, it is only necessary to hold a pen
Stablize position.
The situation of hyperbolic reflecting mirror such as Fig. 2 C, when to employ doubly curved reflecting mirror, reflection be from hyperbolic mirror edge,
To the skin image in the region that holds a pen of a distance between lens group.The region of hyperboloidal mirror reflection is bigger than plane mirror, but
Cost is very high, because bi-curved requirement on machining accuracy is high, Surface Parameters design comparison is many and diverse.Optical path in the case of three kinds is shown
It is intended to respectively as shown in Fig. 3 A, 3B, 3C.
As shown in Fig. 4 A, 4B, 4C, in three embodiments of another set, it is added with LED light source, light source irradiates skin, is
Imaging provides illumination.The position of light source, in lens group side.The monochromatic light LED, Huo Zhebai that can select in visible spectrum of light source
Color LED perhaps infrared LED or mixing visible light and infrared LED.
If Fig. 4 A, 4B, 4C show the cross-sectional view of three embodiments of addition light source, respectively correspond it is unilateral to reflecting mirror,
The case where plane is to reflecting mirror and hyperbolic reflecting mirror.
Structural schematic diagram with light source irradiation and imaging optical path is as shown in Fig. 5 A, 5B, 5C.
In further embodiments, reflective imager part is replaced using optical fiber camera, then lens group is in optical fiber side, figure
As sensor is in the optical fiber other side.It is that space row's step of imaging sensor and circuit is freer using the benefit of optical fiber camera.
Optical fiber can illuminate (multi-pass transmits simultaneously) while transmitting image.
Using reflective imager part and optical fiber camera, we be may be implemented in micro volume, to panorama (360 around
Degree is looked around) imaging, realize new living creature characteristic recognition system.
It should be understood that although optical fiber camera is once used in industrial endoscope field, for the optical imagery of front end, generally
There are two types of, it is directly observed with wide-angle lens, then have unilateral reflective.But the prior art utilize not yet endoscopic technique into
Row living things feature recognition.On the other hand, panorama panoramic imagery, although having application in robot field, to save camera, one
A camera claps 360 degree of panorama images.But because camera is cheap small in size low in energy consumption, around camera can be covered with, so
Panorama panoramic imagery is in fewer and fewer condition in robot field.The embodiment of the present invention merges two systems,
The technical effect that the prior art is unable to reach is reached.
But the embodiment of the present invention also terminates in this, and the system of the embodiment of the present invention has also incorporated the wound in terms of living things feature recognition
Newly, a kind of improved Gabor and study class algorithm are used.Gabor algorithm can extract texture, but gabor algorithm parameter is very
More, for gabor parameter optimizations are all debugged by expert manually for a long time all the time.The embodiment of the present invention uses depth
The study class algorithm of study makes full use of computing capability, scans Gabor parameter, and Optimized Coding Based device f (x) meets,
Recognition capability is improved, so that this system of the embodiment of the present invention just be enabled to be achieved.
Equipment is identified using the miniature manpower in above-described embodiment, it can be directly by the identity of penner and in being write
Hold correspond, it is ensured that writer's identity information of document it is authentic and valid, it is ensured that document writer's authentication
The range of content is accurate.In the prior art, due to person's handwriting identification be not it is instantaneous, need a certain amount of person's handwriting, centre has several
A word is distorted, and is difficult to differentiate.Unless meeting that several word just has special literary style as in film;And handwriting
It can learn to imitate.The present invention just identifies when then can accomplish to hold a pen.
Cooperate pressure-induction handwriting pen tip, can identify simultaneously people and record image.In this way can manpower identify while,
Writing contents and manpower are imaged and store together.It is such to be suitable in occasions such as bank counter signature, notarial office's signatures.
The above embodiment of the present invention using skin on hand texture carry out identification, not only for pen holding posture require compared with
Flexibly, it and may be implemented to minimize.The scheme of various embodiments of the present invention can also theoretically use fingerprint recognition also realize, but
For using the texture of skin on hand, there is following disadvantage: fingerprint recognition due to being contact identification, it there are commonly
Two kinds of sensors: scratch type and planar array type, wherein scratch type needs to rub, and planar array type needs biggish plane, is all directly embedded into
The Pen Association worked it out into handwriting is very flat very wide.Meanwhile fingerprint needs bigger connect to identify accurate stable really
Contacting surface product, and than the pendulum position of calibration.Fingerprint is easier to forge simultaneously.In the embodiment of the present invention using the texture of skin on hand into
The pen of row identification, diameter can accomplish about 1 centimetre now, and theoretically, laboratory discrimination is expected to can exceed that use
The discrimination of fingerprint recognition.
3, software flow
The software flow of this programme, after Image Acquisition input, identification process is divided into feature extraction and classifying device classification ratio
It is right.Here optional scheme is very more in fact.Basic procedure is as shown in Figure 6.
The scheme of one exemplary embodiments includes the following steps:
S1 image preprocessing: the gray value of input picture is adjusted, is indicated with floating number, normalizes to 0~1.According to image
Grey level histogram, adjustment intensity profile is to more uniform.
S2, skin area positioning: in the picture, according to skin color and texture, skin area position is positioned.Generate skin
Area mask mask.
S3, feature extraction: it in skin area range, is filtered using the Gabor filter in 6 directions, figure after the filtering
As upper, statistics LBP (local binary pattern) histogram feature.Or use 6-12 direction 3-4 different angular frequency
The Gabor filter of rate filters, then cooperates above-mentioned, satisfaction
Optimized Coding Based device f (x) is encoded.
S4, Classification and Identification: classification comparison is carried out to feature using SVM (support vector machine), is chosen most
The corresponding threshold value of the error rates EER (equal error rate) such as small compares.
4, application scheme
Different image devices and application scheme, as shown in figures 7 a-7d.Wherein, the general utility functions of pen are responsible in front end;Rear end
It is three kinds of different image device schemes.Front end scheme can combine in any permutation with rear end scheme.Rear end scheme is only imaged
Reflecting mirror is different, repeats no more.Front end scheme is designed for three kinds of concrete applications, is respectively as follows: manpower identification and is changed an ink
Pen, manpower identify pressure-induction handwriting pen, preformed identification signature pen.
Wherein, manpower identification change a pen by front can tape swapping ink cartridge nib and rear portion manpower identification part be grouped
At the part or traditional pen write leave ink marks on paper.Only manpower identification division, can be by identifying manpower
Texture, realize identification authentication.
Manpower identification pressure-induction handwriting pen is made of the pressure sensitivity nib of front with rear portion manpower identification division.The part write is
Pressure sensitivity contact realizes that need to arrange in pairs or groups handwriting pad or tablet computer are realized, and with manpower identification division share master control, data storage with
Communication.Manpower identification division can be cooperateed with pressure sensitivity nib, realize that the real time identity of content is write comments on a document, it is ensured that each content is write
Work/painter authentication, each pen can determine its creator.
Preformed identification signature pen is made of the signature pen nib of front with rear portion manpower identification division.It can merge comprising using
The person's handwritings such as the parameters such as pen shape state, speed, dynamics identify and the manpower based on dermatoglyph identifies two kinds of biological characteristics, and realization is more pacified
Full living things feature recognition.Wherein person's handwriting identification can use well-known technique.
The technical solution of the above embodiment of the present invention can bring it is following the utility model has the advantages that
A, identification is realized in small space.
B, writing, content of signing are accurate corresponding with identity.
C, stablize constantly identification.
Above-described embodiment is example of the invention, is not limited the invention, and those skilled in the art are not taking off
Under the premise of from present inventive concept, flexible modification can be made to the embodiment of the present invention, is all belonged to the scope of protection of the present invention.Than
Identified as that can also increase using the lasting shooting of camera, when writing, by a camera persistently shoot manpower and
The movement write, come the consistency of ensure to write people and write content.
For another example, the embodiment of the present invention can set the equipment such as smart phone with this so that on hardware configuration, there are interfaces
The result of signature and identification, is uploaded to APP by standby connection cooperation.Or bluetooth is used, relevant information is transferred to other equipment
On, including PC, mobile phone or tablet computer.
Using equipment of the invention, a signing system can also be done, connects multiple cell phone applications, is collected from cell phone application
The signature of biography and recognition result, and statistical report form is carried out automatically.
Claims (9)
1. a kind of miniature manpower identifies equipment, which is characterized in that including optical imagery module, image capture module, data processing
With memory module and communication interface module;
The optical imagery module is used to the texture of skin on manpower imaging in described image acquisition module;
Described image acquisition module forms picture signal or image file for acquiring the optical imagery module imaging;
The data processing and memory module are used to acquired image signal or image file carrying out Feature extraction and recognition,
Identify the texture of hand, the identity to authentication equipment grasping person;
The communication interface module is used for transmission the identity information recognized;
Wherein, which is pen shape, and the optical imagery module is located at pen holding region.
2. miniature manpower as described in claim 1 identifies equipment, which is characterized in that the optical imagery module is unilateral reflection
Imaging reflects the optical path of side using 45 degree of tilted-putted reflecting mirrors, shoots the image of side pen holding region dermatoglyph.
3. miniature manpower as described in claim 1 identifies equipment, which is characterized in that the optical imagery module is that panorama ring is anti-
Imaging-type is penetrated, is held a pen using the plane mirror or to employ doubly curved reflecting mirror, reflection that are placed in parallel with handwriting ring cutting face
The texture image of skin annular region;When wherein, using plane mirror, reflection be reflecting mirror to one section between lens group away from
From the region that holds a pen skin image;When to employ doubly curved reflecting mirror, reflection is to arrive lens group from hyperbolic mirror edge
Between a distance the region that holds a pen skin image.
4. miniature manpower as described in claim 1 identifies equipment, which is characterized in that the data processing and memory module store
Data, and image procossing and pattern-recognition are carried out, by identifying the texture of skin, identify the identity of the people of gripping device.
5. miniature manpower as claimed in claim 2 identifies equipment, which is characterized in that on the outside of pen, it is auxiliary to add positioning appropriate
Column is helped or the curved-surface structure that holds a pen, to auxiliary positioning.
6. miniature manpower as described in claim 1 identifies equipment, which is characterized in that further include LED light source, for irradiating skin
Skin provides illumination for imaging.
7. miniature manpower as described in claim 1 identifies equipment, which is characterized in that the optical imagery module and described image
Acquisition module is respectively the lens group and imaging sensor of optical fiber camera.
8. miniature manpower as described in claim 1 identifies equipment, which is characterized in that further include pressure-induction handwriting pen tip, realize
While manpower identifies, Writing contents and the identity information of people are stored together.
9. a kind of manpower recognition methods, which is characterized in that using micro- as described in any claim in claims 1 to 8
Type manpower identification equipment is identified, is included the following steps:
S1, image preprocessing: adjusting the gray value of input picture, is first floating data, renormalization to 0,1 by grayvalue transition
Between;According to the grey level histogram of image, intensity profile is adjusted to more uniformly;
S2, skin area positioning: in the picture, according to skin color and texture, skin area position is positioned;Generate skin area
Exposure mask mask;
S3, feature extraction: it in skin area range, is filtered using the Gabor filter of multiple directions, image after the filtering
On, count LBP histogram feature;
S4, Classification and Identification: carrying out classification comparison to feature using SVM, chooses the corresponding threshold value of the error rates EER such as minimum and compares.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910224288.3A CN110008864A (en) | 2019-03-22 | 2019-03-22 | A kind of miniature manpower identification equipment and recognition methods |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910224288.3A CN110008864A (en) | 2019-03-22 | 2019-03-22 | A kind of miniature manpower identification equipment and recognition methods |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110008864A true CN110008864A (en) | 2019-07-12 |
Family
ID=67167880
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910224288.3A Pending CN110008864A (en) | 2019-03-22 | 2019-03-22 | A kind of miniature manpower identification equipment and recognition methods |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110008864A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110598522A (en) * | 2019-07-17 | 2019-12-20 | 江西拓世智能科技有限公司 | Identity comparison method based on face and palm print palm vein recognition |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203786745U (en) * | 2014-04-08 | 2014-08-20 | 香港理工大学深圳研究院 | Door-handle-shaped holding posture human hand image acquisition device and holding posture human hand image identification system |
CN105183192A (en) * | 2015-09-08 | 2015-12-23 | 周兴剑 | Electronic identity pen based on intelligent touch screen interactive type input screen and electronic signing method |
CN105929985A (en) * | 2016-04-28 | 2016-09-07 | 深圳市华鼎星科技有限公司 | True chirography touch pen and touch device with radio frequency transmitting-receiving transmission function |
CN105976366A (en) * | 2016-04-29 | 2016-09-28 | 浙江大华技术股份有限公司 | Method and device for target loop positioning |
CN106370563A (en) * | 2016-08-26 | 2017-02-01 | 南京昊控软件技术有限公司 | Method and device for measuring sediment concentration of vertical fracture surface of model by means of optical method |
CN107633544A (en) * | 2016-07-14 | 2018-01-26 | 网易(杭州)网络有限公司 | The processing method and processing device of ambient light masking |
CN107644198A (en) * | 2017-08-18 | 2018-01-30 | 郑州云海信息技术有限公司 | It is a kind of based on Gabor filter and the palm vein recognition methods of LBP operators and system |
CN107845390A (en) * | 2017-09-21 | 2018-03-27 | 太原理工大学 | A kind of Emotional speech recognition system based on PCNN sound spectrograph Fusion Features |
-
2019
- 2019-03-22 CN CN201910224288.3A patent/CN110008864A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203786745U (en) * | 2014-04-08 | 2014-08-20 | 香港理工大学深圳研究院 | Door-handle-shaped holding posture human hand image acquisition device and holding posture human hand image identification system |
CN105183192A (en) * | 2015-09-08 | 2015-12-23 | 周兴剑 | Electronic identity pen based on intelligent touch screen interactive type input screen and electronic signing method |
CN105929985A (en) * | 2016-04-28 | 2016-09-07 | 深圳市华鼎星科技有限公司 | True chirography touch pen and touch device with radio frequency transmitting-receiving transmission function |
CN105976366A (en) * | 2016-04-29 | 2016-09-28 | 浙江大华技术股份有限公司 | Method and device for target loop positioning |
CN107633544A (en) * | 2016-07-14 | 2018-01-26 | 网易(杭州)网络有限公司 | The processing method and processing device of ambient light masking |
CN106370563A (en) * | 2016-08-26 | 2017-02-01 | 南京昊控软件技术有限公司 | Method and device for measuring sediment concentration of vertical fracture surface of model by means of optical method |
CN107644198A (en) * | 2017-08-18 | 2018-01-30 | 郑州云海信息技术有限公司 | It is a kind of based on Gabor filter and the palm vein recognition methods of LBP operators and system |
CN107845390A (en) * | 2017-09-21 | 2018-03-27 | 太原理工大学 | A kind of Emotional speech recognition system based on PCNN sound spectrograph Fusion Features |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110598522A (en) * | 2019-07-17 | 2019-12-20 | 江西拓世智能科技有限公司 | Identity comparison method based on face and palm print palm vein recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Vijayan et al. | Twins 3D face recognition challenge | |
CN111091075B (en) | Face recognition method and device, electronic equipment and storage medium | |
CN109948542A (en) | Gesture identification method, device, electronic equipment and storage medium | |
CN112232163B (en) | Fingerprint acquisition method and device, fingerprint comparison method and device, and equipment | |
CN113538574B (en) | Pose positioning method, device and equipment and computer readable storage medium | |
CN106980852A (en) | Based on Corner Detection and the medicine identifying system matched and its recognition methods | |
CN112101124B (en) | Sitting posture detection method and device | |
CN105335719A (en) | Living body detection method and device | |
CN112232155A (en) | Non-contact fingerprint identification method and device, terminal and storage medium | |
CN111860055B (en) | Face silence living body detection method, device, readable storage medium and equipment | |
CN108629272A (en) | A kind of embedded gestural control method and system based on monocular cam | |
CN112232159B (en) | Fingerprint identification method, device, terminal and storage medium | |
US20220148336A1 (en) | Face liveness detection method and related apparatus | |
CN109937434A (en) | Image processing method, device, terminal and storage medium | |
CN105335760A (en) | Image number character recognition method | |
CN109710788A (en) | Image pattern mark and management method and equipment | |
CN112419326A (en) | Image segmentation data processing method, device, equipment and storage medium | |
WO2022068931A1 (en) | Non-contact fingerprint recognition method and apparatus, terminal, and storage medium | |
Veluri et al. | Hand gesture mapping using MediaPipe algorithm | |
CN110008864A (en) | A kind of miniature manpower identification equipment and recognition methods | |
CN112232157A (en) | Fingerprint area detection method, device, equipment and storage medium | |
CN109460690A (en) | A kind of method and apparatus for pattern-recognition | |
Williams | Prototypes, exemplars, and object recognition | |
CN206363347U (en) | Based on Corner Detection and the medicine identifying system that matches | |
CN112232152B (en) | Non-contact fingerprint identification method and device, terminal and storage medium |
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: 20190712 |
|
RJ01 | Rejection of invention patent application after publication |