CN109635660A - The detection method of fingerprint sensing systems - Google Patents
The detection method of fingerprint sensing systems Download PDFInfo
- Publication number
- CN109635660A CN109635660A CN201811345858.6A CN201811345858A CN109635660A CN 109635660 A CN109635660 A CN 109635660A CN 201811345858 A CN201811345858 A CN 201811345858A CN 109635660 A CN109635660 A CN 109635660A
- Authority
- CN
- China
- Prior art keywords
- image
- fingerprint
- sensing systems
- fingerprint sensing
- detection method
- 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
- G06V40/12—Fingerprints or palmprints
- G06V40/13—Sensors therefor
- G06V40/1306—Sensors therefor non-optical, e.g. ultrasonic or capacitive sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06V40/1347—Preprocessing; Feature extraction
- G06V40/1359—Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop
-
- 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
- G06V40/1365—Matching; Classification
Abstract
The invention discloses a kind of detection methods of fingerprint sensing systems, comprising: obtains the image of the fingerprint sensing systems acquisition;Topography's information is obtained from the image of the acquisition;Fourier analysis is carried out to topography's information, to obtain assessment parameter;And fingerprint image and class fingerprint image are differentiated according to the assessment parameter.Fingerprint image and class fingerprint image can effectively be distinguished using the detection method of fingerprint sensing systems provided by the present invention, prevent attack of the class fingerprint image to fingerprint sensing systems.
Description
Technical field
The present invention relates to fingerprint sensing systems technical fields, and in particular to a kind of detection method of fingerprint sensing systems.
Background technique
Fingerprint is the texture of the uneven formation of finger surface skin.The texture features of fingerprint have uniqueness, stability,
Therefore it is usually used to the foundation as identification.Fingerprint sensing systems are exactly a kind of sensing that identity is identified by fingerprint
Device.Capacitance pen is to imitate human body (usually finger) using conductor material to complete a kind of auxiliary device of human-computer dialogue, and capacitance pen is pressed
Image can be obtained by being pressed on fingerprint sensing systems, and since the image that capacitance pen presses can be similar to fingerprint image, pass through
The shape of similar crestal line valley line can be obtained after enhancing, can carry out typing as fingerprint image.And due to capacitance pen contact head and
The lines that other conductors with lines press has randomness, can simulate fingerprint image minutiae point, and then may result in
Misrecognition threatens system safety.Make simultaneously when distinguishing the image of fingerprint image and capacitance pen and other conductors with lines
With some existing features such as: crestal line width, picture quality, gray scale square of attacking cities can not be distinguished effectively, because of the invention
A kind of fingerprint sensing systems detection method is to cope with fingerprint and capacitance pen and other conductors with lines on fingerprint sensing systems
It is effective resolution be just particularly important.
Summary of the invention
In order to solve the above-mentioned technical problems, the present invention provides a kind of detection methods of fingerprint sensing systems, can be effective
Differentiation fingerprint sensing systems on the image that receives be fingerprint image or class fingerprint image.
The detection method of a kind of fingerprint sensing systems provided according to the present invention characterized by comprising obtain the finger
The image of line sensor-based system acquisition;Topography's information is obtained from the image of the acquisition;To topography's information into
Row Fourier analysis, to obtain assessment parameter;And fingerprint image and class fingerprint image are differentiated according to the assessment parameter.
Preferably, the step of acquisition topography's information includes: to obtain image reform point according to the acquisition image;
Image radius is obtained by origin of described image focus point;Reference axis is established using described image focus point as coordinate origin;And
Pixel point sampling is carried out to described image according to the reference axis.
Preferably, the preparation method of described image focus point includes: for full image, with the geometric center point of its image
For image reform point;For half images, using the geometric center point of its effective image area as image reform point
Preferably, described image radius includes least radius R of the described image focus point to image border.
Preferably, the step of acquisition topography's information includes: the horizontal axis and the longitudinal axis for choosing the reference axis respectively
On pixel as topography's information.
Preferably, the step of acquisition topography's information further include: vertically carry out pixel point sampling.
Preferably, the sample range of the pixel is [- R, R], wherein the R is the least radius.
Preferably, the assessment parameter includes: after doing the Fourier transformation of N group specific frequency to topography's information
The N group coefficient arrived, wherein N is natural number greater than 1.
Preferably, the specific frequency includes fingerprint ridge line frequency.
Preferably, the resolving method of the fingerprint image and class fingerprint image includes: the method for discrimination using machine learning
It distinguishes.
Preferably, the method for discrimination includes: to be classified using support vector machines.
Preferably, the class fingerprint image includes capacitance pen image and other conductor pressing images with lines.
Preferably, the fingerprint sensing systems include capacitive sensing system and/optical profile type sensor-based system.
The beneficial effects of the present invention are: more efficiently solving fingerprint sensing system by the capacitance pen detection method
The resolution problems united to the image of fingerprint image and capacitance pen and other conductors with lines.
Detailed description of the invention
By referring to the drawings to the description of the embodiment of the present invention, above-mentioned and other purposes of the invention, feature and
Advantage will be apparent from.
Fig. 1 shows the method flow diagram using fingerprint typing or unlock in the prior art;
Fig. 2 shows the method flow diagrams that fingerprint typing or unlock are used in the embodiment of the present invention;
Fig. 3 shows the detection algorithm detection method flow chart of fingerprint sensing systems of the embodiment of the present invention;
Fig. 4 shows the step flow chart that topography's information is obtained in the embodiment of the present invention;
Fig. 5 shows the structure chart of fingerprint sensing systems.
Specific embodiment
To facilitate the understanding of the present invention, a more comprehensive description of the invention is given in the following sections with reference to the relevant attached drawings.In attached drawing
Give presently preferred embodiments of the present invention.But the present invention can realize in different forms, however it is not limited to described herein
Embodiment.Opposite, purpose of providing these embodiments is makes the disclosure of the present invention more thorough and comprehensive.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Used term is intended merely to description specifically in the description of the invention herein
Embodiment purpose, it is not intended that in limitation the present invention.
Fingerprint sensing systems include capacitive sensing system and/optical profile type sensor-based system, are sensed herein with capacitance type fingerprint
Illustrate problem of the present invention for system.Capacitance type fingerprint sensor-based system includes multiple capacitive sensing electrodes, and induction electrode is distributed in
In approximately the same plane, there is one layer of dielectric between sensing object (such as finger, capacitance pen or other conductors with lines),
Dielectric thickness is uniform.When measurement induction fingerprint, the peak of fingerprint lines contacts dielectric, contacts the fingerprint line of dielectric
The peak on road is defined in a constant distance value by dielectric in homogeneous thickness at a distance from induction electrode.Induction electrode is used for
Induction is at a distance from the peaks or valleys of fingerprint lines, since induction electrode is different at a distance from the peaks or valleys of fingerprint lines, induced electricity
The inductance capacitance that pole senses is also just different, and the inductance capacitance that induction electrode is sensed is converted to sensor output voltage letter
Number, sensor output voltage signal can be obtained by fingerprint image relevant to the peaks or valleys of fingerprint lines by subsequent processing
Signal.
In the following, referring to attached drawing, the present invention is described in detail.
Fig. 1 shows the method flow diagram in prior art fingerprint recognition system using fingerprint typing or unlock.
As shown in Figure 1, the fingerprint recognition system of capacitance type fingerprint sensor-based system carried out using fingerprint data input or
When carrying out equipment (such as mobile phone/tablet computer etc.) unlock using fingerprint, image is first typically acquired by fingerprint sensor,
Then image enhancement processing is carried out to institute's acquired image by fingerprint processor again, is finally believed using enhanced fingerprint image
Breath carries out fingerprint typing or unlock processing.But capacitance pen image or other conductors with lines are passing through information collection and letter
Also the effect of similar details in fingerprint can be obtained after number enhancing processing, the image of similar details in fingerprint is commonly referred to as class fingerprint image
Picture.Fingerprint recognition system will be unable to effectively distinguish fingerprint image and class fingerprint image.
Therefore, the present invention provides a kind of detection methods of fingerprint sensing systems, can be directed to existing in the prior art
The problem of fingerprint image and class fingerprint image cannot be distinguished carries out effective detection and differentiates.
Fig. 2 shows the processes for the method that the typing of fingerprint sensing systems fingerprint image or unlock are used in the embodiment of the present invention
Figure.
As shown in Fig. 2, compared with the existing technology, the embodiment of the present invention uses a kind of fingerprint sensing systems detection method,
It is added to the step of fingerprint image judges between acquisition fingerprint image and picture signal enhancing, can effectively distinguish fingerprint image
With class fingerprint image, to effectively prevent attack of the class fingerprint image to fingerprint sensing systems.
Specifically, carrying out image to fingerprint image when fingerprint sensing systems determine acquired image for fingerprint image
Enhancing processing, and then carry out fingerprint typing or unlock etc. using the collected fingerprint image of institute and operate;When fingerprint sensing systems are sentenced
Determine acquired image be non-fingerprint image when, fingerprint sensing systems will directly exit present image process flow, not execute
The operation such as picture signal enhancing and image typing or unlock, can effectively prevent class fingerprint image to fingerprint sensing systems in this way
Attack.
Fig. 3 shows the detection method flow chart of fingerprint sensing systems of the embodiment of the present invention.
As shown in figure 3, detection method includes the following steps for the fingerprint sensing systems of the embodiment of the present invention:
Step S1: the image of the fingerprint sensing systems acquisition is obtained.
Capacitance pen is to imitate human body (usually finger) using conductor material to complete a kind of interactive auxiliary device, that
By capacitance pen pressing, obtained image can be similar to fingerprint image on fingerprint sensing systems, can also obtain after enhancing
To the shape of similar crestal line/valley line.
In embodiments of the present invention, it needs to collect and record through the capacitance pen or fingerprint to the fingerprint sensing systems
Sample image obtained after pressing, in order to which subsequent further analysis is handled.
Step S2: topography's information is obtained from the image of the acquisition.
The step of specific method for obtaining topography's information can refer to acquisition topography's information shown in Fig. 4 stream
Cheng Tu is specifically included: the focus point of the image is found in fingerprint sensing systems institute acquired image;Then with institute
Stating image reform point is origin, tests and record distance of the origin away from image border each position, and minimum value therein is taken to make
For least radius R;And reference axis is established by coordinate origin of the focus point, while extracting the horizontal axis of the reference axis respectively
With the pixel on the longitudinal axis as detection sampled pixel point.
Further, the pixel method of sampling further includes being sampled along the vertical direction.
Further, for the searching of the focus point: fingerprint or class fingerprint image (i.e. fingerprint sensing system for full width
System gained image occupies entire picture frame), the focus point of described image is exactly the geometric center point of picture;For the finger of half range
Line or class fingerprint image (i.e. image obtained by fingerprint sensing systems only account for entire picture a part), the at this time center of gravity of described image
Point can slightly deviate, and the geometric center point that can choose effective coverage in the fingerprint or class fingerprint image of the half range is image reform
Point.
Further, the sample range of pixel is-R~R on the transverse and longitudinal axis.
Step S3: carrying out Fourier analysis to local image information, obtains assessment parameter.
The pixel that the sampling of two column has been obtained in the step S2, at this time respectively to Liang Lie topography information
The Fourier transformation of N group specific frequency is done, then takes its N group Fourier Transform Coefficients as the assessment parameter, wherein N is
Natural number greater than 1.
In embodiments of the present invention, it is only necessary to which the effect of needs can be reached by doing Fourier transformation to the pixel sampled
Fruit, it is relatively succinct quicker without carrying out Fourier analysis to whole image.
Further, the specific frequency refers to the wrinkle ridge line frequency of image in the present invention is implemented.
Step S4: fingerprint image and class fingerprint image are differentiated according to assessment parameter.
Further, the resolving method of the fingerprint image and class fingerprint image specifically includes: since capacitance pen is specific
Fluctuation in frequency is smaller, and amplitude is relatively low, thus can according to this characteristic as classification foundation to the assessment parameter (i.e. two
Group coefficient) classify, and then telling acquired image is to belong to fingerprint image to still fall within class fingerprint image.
Further, the class fingerprint image includes capacitance pen image and other conductor pressing images with lines.
Further, the classification method includes: the method for discrimination using machine learning, specially uses support vector machines
The method of (Support Vector Machine, SVM).It has perhaps in solution small sample, the identification of non-linear and high dimensional pattern
Mostly distinctive advantage, and in the other machines problem concerning study such as can promote the use of Function Fitting.The support vector machine method
The VC dimension (Vapnik-Chervonenkis Dimension) for being built upon Statistical Learning Theory it is theoretical (concept of VC dimension be for
The uniformly convergent speed of research learning process and generalization, by the one of the related collection of functions learning performance that statistical theory defines
A important indicator) and Structural risk minization basis on, according to limited sample information model complexity (i.e. to spy
Determine the study precision of training sample) and learning ability (i.e. without error identify arbitrary sample ability) between seek most preferably to roll over
In, to obtain optimal classifying quality.
For convenient for understanding the present invention, Fig. 5 shows the structural schematic diagram of fingerprint sensing systems of the present invention.
As shown in figure 5, the fingerprint sensing systems 100 include fingerprint sensor 110, for acquiring fingerprint image;Fingerprint
Processor 120, for handling fingerprint image, identification comparison fingerprint template, storage fingerprint template and control man-machine interface etc..Institute
It states finger prints processing system 100 to be connected with external device (ED), it is corresponding that fingerprint typing/unlock to the external device (ED) etc. may be implemented
Control.
It should be noted that herein, contained the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Finally, it should be noted that obviously, the above embodiment is merely an example for clearly illustrating the present invention, and simultaneously
The non-restriction to embodiment.For those of ordinary skill in the art, it can also do on the basis of the above description
Other various forms of variations or variation out.There is no necessity and possibility to exhaust all the enbodiments.And thus drawn
The obvious changes or variations that Shen goes out are still in the protection scope of this invention.
Claims (13)
1. a kind of detection method of fingerprint sensing systems characterized by comprising
Obtain the image of the fingerprint sensing systems acquisition;
Topography's information is obtained from the image of the acquisition;
Fourier analysis is carried out to topography's information, to obtain assessment parameter;And
Fingerprint image and class fingerprint image are differentiated according to the assessment parameter.
2. the detection method of fingerprint sensing systems according to claim 1, which is characterized in that the acquisition topography letter
The step of breath includes:
Image reform point is obtained according to the acquisition image;
Image radius is obtained by origin of described image focus point;
Reference axis is established using described image focus point as coordinate origin;And
Pixel point sampling is carried out to described image according to the reference axis.
3. the detection method of fingerprint sensing systems according to claim 2, which is characterized in that described image focus point obtains
Obtaining method includes:
For full image, using the geometric center point of its image as image reform point;
For half images, using the geometric center point of its effective image area as image reform point.
4. the detection method of fingerprint sensing systems according to claim 2, which is characterized in that described image radius includes institute
State image reform point to image border least radius R.
5. the detection method of fingerprint sensing systems according to claim 2, which is characterized in that the acquisition topography letter
The step of breath includes: to choose pixel on the horizontal axis and the longitudinal axis of the reference axis respectively as topography's information.
6. the detection method of fingerprint sensing systems according to claim 2, which is characterized in that the acquisition topography letter
The step of breath further include: vertically carry out pixel point sampling.
7. the detection method of fingerprint sensing systems according to claim 5, it is characterised in that: the sampling model of the pixel
It encloses for [- R, R], wherein the R is the least radius.
8. the detection method of fingerprint sensing systems according to claim 1, which is characterized in that the assessment parameter includes:
The N group coefficient obtained after the Fourier transformation of N group specific frequency is done to topography's information, wherein N is oneself greater than 1
So number.
9. the detection method of fingerprint sensing systems according to claim 8, it is characterised in that: the specific frequency includes referring to
Wrinkle ridge line frequency.
10. the detection method of fingerprint sensing systems according to claim 1, which is characterized in that the fingerprint image and class
The resolving method of fingerprint image includes: to be distinguished using the method for discrimination of machine learning.
11. the detection method of fingerprint sensing systems according to claim 10, which is characterized in that the method for discrimination packet
It includes: being classified using support vector machines.
12. according to claim 1 or the detection method of fingerprint sensing systems described in 10, it is characterised in that: the class fingerprint image
As including capacitance pen image and other conductor pressing images with lines.
13. the detection method of fingerprint sensing systems according to claim 1, it is characterised in that the fingerprint sensing systems packet
Include capacitive sensing system and/optical profile type sensor-based system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811345858.6A CN109635660A (en) | 2018-11-13 | 2018-11-13 | The detection method of fingerprint sensing systems |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811345858.6A CN109635660A (en) | 2018-11-13 | 2018-11-13 | The detection method of fingerprint sensing systems |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109635660A true CN109635660A (en) | 2019-04-16 |
Family
ID=66067908
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811345858.6A Pending CN109635660A (en) | 2018-11-13 | 2018-11-13 | The detection method of fingerprint sensing systems |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109635660A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109214160A (en) * | 2018-09-14 | 2019-01-15 | 温州科技职业学院 | A kind of computer network authentication system and method, computer program |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102395995A (en) * | 2009-04-13 | 2012-03-28 | 富士通株式会社 | Biometric information registration device, biometric information registration method, computer program for registering biometric information, biometric authentication device, biometric authentication method, and computer program for biometric authent |
CN103324944A (en) * | 2013-06-26 | 2013-09-25 | 电子科技大学 | Fake fingerprint detecting method based on SVM and sparse representation |
CN104463129A (en) * | 2014-12-17 | 2015-03-25 | 浙江维尔科技股份有限公司 | Fingerprint registration method and device |
WO2018090984A1 (en) * | 2016-11-18 | 2018-05-24 | 比亚迪股份有限公司 | Fingerprint recognition method and electronic apparatus |
CN108256415A (en) * | 2017-11-30 | 2018-07-06 | 北京集创北方科技股份有限公司 | Fingerprint identification method, device and system, electronic equipment |
CN108520225A (en) * | 2018-03-30 | 2018-09-11 | 南京信息工程大学 | A kind of fingerprint detection sorting technique based on spatial alternation convolutional neural networks |
-
2018
- 2018-11-13 CN CN201811345858.6A patent/CN109635660A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102395995A (en) * | 2009-04-13 | 2012-03-28 | 富士通株式会社 | Biometric information registration device, biometric information registration method, computer program for registering biometric information, biometric authentication device, biometric authentication method, and computer program for biometric authent |
CN103324944A (en) * | 2013-06-26 | 2013-09-25 | 电子科技大学 | Fake fingerprint detecting method based on SVM and sparse representation |
CN104463129A (en) * | 2014-12-17 | 2015-03-25 | 浙江维尔科技股份有限公司 | Fingerprint registration method and device |
WO2018090984A1 (en) * | 2016-11-18 | 2018-05-24 | 比亚迪股份有限公司 | Fingerprint recognition method and electronic apparatus |
CN108256415A (en) * | 2017-11-30 | 2018-07-06 | 北京集创北方科技股份有限公司 | Fingerprint identification method, device and system, electronic equipment |
CN108520225A (en) * | 2018-03-30 | 2018-09-11 | 南京信息工程大学 | A kind of fingerprint detection sorting technique based on spatial alternation convolutional neural networks |
Non-Patent Citations (3)
Title |
---|
张少乐: "基于子空间分析法的指纹特征提取", 中国优秀硕士学位论文全文数据库 信息科技辑, pages 175 - 178 * |
胡德文 等: "《生物特征识别技术与方法》", pages: 175 - 178 * |
陈若珠等: "一种基于重心的快速细化算法", 《兰州理工大学学报》, no. 02, 15 April 2009 (2009-04-15) * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109214160A (en) * | 2018-09-14 | 2019-01-15 | 温州科技职业学院 | A kind of computer network authentication system and method, computer program |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9754149B2 (en) | Fingerprint based smart phone user verification | |
Lin et al. | Palmprint verification using hierarchical decomposition | |
CN103324944B (en) | A kind of based on SVM with the false fingerprint detection method of rarefaction representation | |
CN107657241A (en) | A kind of signature true or false identification system towards signature pen | |
Lee et al. | A Gabor filter-based approach to fingerprint recognition | |
CN102446268A (en) | Fingerprint anti-counterfeit device and method thereof | |
Liu et al. | Finger vein recognition using optimal partitioning uniform rotation invariant LBP descriptor | |
Khalifa et al. | Wavelet, gabor filters and co-occurrence matrix for palmprint verification | |
Kekre et al. | Gabor filter based feature vector for dynamic signature recognition | |
Tiwari et al. | A review of advancements in biometric systems | |
Maltoni et al. | Fingerprint recognition | |
Raut et al. | Biometric palm prints feature matching for person identification | |
CN109635660A (en) | The detection method of fingerprint sensing systems | |
Xie et al. | Fingerprint quality analysis and estimation for fingerprint matching | |
Kaur et al. | Handwritten signature verification based on surf features using HMM | |
Hany et al. | Speeded-Up Robust Feature extraction and matching for fingerprint recognition | |
CN110222660B (en) | Signature authentication method and system based on dynamic and static feature fusion | |
Houtinezhad et al. | Off-line signature verification system using features linear mapping in the candidate points | |
Hong-Ying et al. | An iris recognition method based on multi-orientation features and Non-symmetrical SVM | |
CN109255318A (en) | Based on multiple dimensioned and multireel lamination Fusion Features fingerprint activity test methods | |
CN108345872A (en) | Fingerprint recognition harvester and system | |
Zaghloul et al. | Recognition of Hindi (Arabic) handwritten numerals | |
Haider et al. | Online recognition of single stroke handwritten Urdu characters | |
CN107067046B (en) | Hand-written digit recognition method based on mixed feature extraction | |
Liu et al. | Contactless fingerprint and palmprint fusion recognition based on quality assessment |
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 |