CN107563364A - The discriminating conduct of the fingerprint true and false and fingerprint identification method based on sweat gland - Google Patents
The discriminating conduct of the fingerprint true and false and fingerprint identification method based on sweat gland Download PDFInfo
- Publication number
- CN107563364A CN107563364A CN201710994412.5A CN201710994412A CN107563364A CN 107563364 A CN107563364 A CN 107563364A CN 201710994412 A CN201710994412 A CN 201710994412A CN 107563364 A CN107563364 A CN 107563364A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- sweat gland
- image
- finger print
- print layer
- 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.)
- Granted
Links
Abstract
The invention discloses the fingerprint true and false discriminating conduct based on sweat gland and fingerprint identification method, including：Obtain three-dimensional fingerprint image and extract outer fingerprint；According to fingerprint in outer fingerprint extraction；Sweat gland region is chosen according to inside and outside fingerprint；Tubulose is carried out to sweat gland region to filter to obtain tubular structure, and binary conversion treatment is carried out to tubular structure using default sweat gland threshold value, gone unless sweat duct shape structure, obtains sweat gland image；Sweat gland image is corrected according to the directional information of sweat gland and helical structure information；Judge whether current finger print is artificial fingerprint from sweat gland image.Fingerprint identification method based on sweat gland is after obtaining sweat gland image according to foregoing sweat gland extraction step to fingerprint to be identified, sweat gland in sweat gland image is compared with existing sweat gland in system, in combination with the comparison of inside and outside fingerprint, fingerprint recognition is carried out according to comparison result.
Description
Technical field
The present invention relates to human body biological characteristics to identify field, more particularly to a kind of fingerprint true and false discrimination side based on sweat gland
Method, and a kind of fingerprint identification method based on sweat gland.
Background technology
Fingerprint recognition plays an important role in the identification system based on biological characteristic.Existing fingerprint collecting
The two-dimensional imaging technique of contact mostly, wherein using it is more be based on total internal reflection, by the different reflecting effects of light
The optical fingerprint sensor being imaged to fingerprint surface.Fingerprint surface gathers, and its imaging effect requires higher to fingerprint condition,
When fingerprint surface has moist, fold or scar, image quality can decline, and cause fingerprint imaging distortion, influence to refer to
The success rate of line identification.
Connecting inner fingerprint has same feature with fingerprint surface, can pass through means of optical coherence tomography
(Optical Coherence Tomography, OCT) carries out three-dimensional imaging to fingerprint.Optical coherence tomography is a kind of non-
Contact, high-resolution, the imaging technique of chromatography, it can be used in miniorgan in observer's body, such as to being present under skin
Microcirculqtory system, microvessel structure, finger tip sweat gland etc. be imaged.High-resolution can be obtained by carrying out fingerprint imaging using OCT
The inside fingerprint image of rate, facilitates the extraction of fingerprint internal structure.
Fingerprint characteristic is from coarse to fine to be divided into three levels：Papillary flows to line, the center line and mastoid process of mastoid process line
The profile and pore of line, pore are exactly the opening of sweat gland pipeline.By carrying out sweat gland pipeline extraction, energy to OCT fingerprint images
The information of more identification is provided for fingerprint recognition, improves the performance of fingerprint recognition system.On the other hand, fingerprint surface can lead to
Cross multiple technologies and material is copied, artificial fingerprint has 68%~100% identification to existing Automated Fingerprint Identification System
Success rate, and OCT fingerprint imagings can then obtain the internal image of fingerprint, it is artificial distinguishing according to the internal structure of living body finger print
There is good effect in terms of fingerprint and actual fingerprint.
Can existing optical correlation tomography fingerprint image research be primarily upon the inside and outside fingerprint of fingerprint image, by detect
Realize that fingerprint is false proof with whether outer fingerprint matches to interior fingerprint or the interior fingerprint detected, utilize interior fingerprint to carry out fingerprint knowledge
Not.However, the situation that inside and outside fingerprint is copied also has occurred simultaneously, the imitation of interior fingerprint need to only replicate outer dactylotype, it is seen then that
Fingerprint imaging and identification technology based on OCT also gradually appear its defect, and the false proof problems demand of industry fingerprint solves.
The content of the invention
Have the characteristics that densely distributed, size is tiny and has helical structure based on sweat gland structure, the present invention utilizes fingerprint
The gradient information and structural information of image are accurately positioned and split the sweat gland structure of fingerprint, and are entered using the sweat gland structure extracted
The true and false of row fingerprint distinguishes, and then proposes a kind of fingerprint true and false discriminating conduct based on sweat gland, to solve existing fingerprint recognition
During existing can not effectively identify the problem of copying fingerprint.
The present invention provides following technical scheme to solve above-mentioned technical problem：
A kind of fingerprint true and false discriminating conduct based on sweat gland, comprises the following steps S1 to S6：
S1, the three-dimensional fingerprint image for obtaining current collection fingerprint；
S2, to the three-dimensional fingerprint image, outer fingerprint is detected using image gradient information, to extract outer finger print layer；
S3, in addition on the basis of finger print layer, the gray average of each tomographic image below outer finger print layer is calculated, it is equal based on gray scale
The variation tendency of value, fingerprint in detection；If interior fingerprint is not present, the current fingerprint that gathers is judged to forging fingerprint；If interior fingerprint
In the presence of then finger print layer in extraction, and perform step S4；
S4, sweat gland region is chosen, and tubulose filtering is carried out to sweat gland region, to extract tubular structure；Wherein, the sweat gland
Region of the region between outer finger print layer and interior finger print layer；
S5, using sweat gland threshold value, binary conversion treatment is carried out to step S4 filter result, obtains sweat gland image；Wherein, sweat
Gland threshold value is the one of grey scale pixel value chosen from the minimum tomographic image of gray average；
S6, judged according to sweat gland image to whether there is sweat gland in the three-dimensional fingerprint image, if in the presence of current collection refers to
Line is actual fingerprint；It is current to gather fingerprint to forge fingerprint if being not present.
During fingerprint is forged, the forgery of sweat gland is difficult that cost is very high in itself, therefore the fingerprint forged at present is basic
Not comprising sweat gland structure, i.e., sweat gland can not be extracted substantially.Above-mentioned fingerprint true and false discriminating conduct provided by the invention, by three
Tie up fingerprint image and carry out sweat gland extraction operation, whether the fingerprint to judge currently to gather can extract sweat gland structure, to judge
Whether it is to forge fingerprint, so as to solve the problems, such as the misrecognition of artificial fingerprint in the prior art.
The present invention separately additionally provides a kind of fingerprint identification method based on sweat gland, comprises the following steps S1 to S7：
S1, obtain three-dimensional fingerprint image；
S2, to the three-dimensional fingerprint image, outer fingerprint is detected using image gradient information, to extract outer finger print layer；
S3, in addition on the basis of finger print layer, the gray average of each tomographic image below outer finger print layer is calculated, it is equal based on gray scale
The variation tendency of value, fingerprint in detection；If interior fingerprint is not present, the current fingerprint that gathers is judged to forging fingerprint；If interior fingerprint
In the presence of then finger print layer in extraction, and perform step S4；
S4, sweat gland region is chosen, and tubulose filtering is carried out to sweat gland region, to extract tubular structure；Wherein, the sweat gland
Region of the region between outer finger print layer and interior finger print layer；
S5, using sweat gland threshold value, binary conversion treatment is carried out to step S4 filter result, obtains sweat gland image；Wherein, sweat
Gland threshold value is the one of grey scale pixel value chosen from the minimum tomographic image of gray average；
S6, the vertical relation based on sweat gland pipeline Yu outer fingerprint valley, the screening of sweat gland pipeline is carried out to sweat gland image, with
The position of sweat gland pipeline is determined, extracts sweat gland structure；
S7, by sweat gland structure, interior fingerprint and the outer fingerprint of current collection fingerprint respectively with it is existing in fingerprint recognition system
Sweat gland structure, interior fingerprint and outer fingerprint are matched, and identification is carried out according to matching result.
Above-mentioned fingerprint identification method provided by the invention, by carrying out the extraction of sweat gland to the fingerprint currently gathered, not only
Can be when sweat gland extracts according to whether sweat gland structure can be extracted to judge the true and false of fingerprint, moreover it is possible to be determined as actual fingerprint
When carrying out identification afterwards, using the sweat gland structure extracted, the identification of Fingerprint Identity is carried out with reference to inside and outside fingerprint, than list
Pure has higher accuracy rate by inside and outside fingerprint to identify.
Brief description of the drawings
Fig. 1 is the flow chart for the fingerprint true and false discriminating conduct based on sweat gland that the specific embodiment of the invention provides；
Fig. 2 is the flow chart for the fingerprint identification method based on sweat gland that the specific embodiment of the invention provides.
Embodiment
The invention will be further described with specific embodiment below in conjunction with the accompanying drawings.
The embodiment of the present invention provides a kind of fingerprint true and false discriminating conduct based on sweat gland, the process employs
A kind of brand-new sweat gland extraction algorithm come to the fingerprint collected carry out sweat gland extraction, according to whether sweat gland can be extracted to sentence
The true and false of severed finger line, relatively accurately the fingerprint of forgery can be distinguished.With reference to figure 1, the fingerprint true and false discriminating conduct bag
Include following steps S1 to S6：
S1, the three-dimensional fingerprint image for obtaining current finger print；
S2, to the three-dimensional fingerprint image, outer fingerprint is detected using image gradient information, to extract outer finger print layer；
S3, in addition on the basis of finger print layer, the gray average of each tomographic image below outer finger print layer is calculated, it is equal based on gray scale
The variation tendency of value, fingerprint in detection；If interior fingerprint is not present, the current fingerprint that gathers is judged to forging fingerprint；If interior fingerprint
In the presence of then finger print layer in extraction, and perform step S4；
S4, sweat gland region is chosen, and tubulose filtering is carried out to sweat gland region, to extract tubular structure；Wherein, the sweat gland
Region of the region between outer finger print layer and interior finger print layer；
S5, using sweat gland threshold value, binary conversion treatment is carried out to step S4 filter result, obtains sweat gland image；Wherein, sweat
Gland threshold value is the one of grey scale pixel value chosen from the minimum tomographic image of gray average；The layering of image herein be with
Pixel divides, in addition on the basis of finger print layer (glass surface that finger is placed when gathering fingerprint), along perpendicular to outer finger print layer
Direction it is downward, each pixel generally has on a tomographic image, then on a tomographic image is much in conplane pixel,
Each pixel has its corresponding gray value, in the gray value corresponding to pixel in that minimum tomographic image of gray average,
A suitable gray value is empirically chosen, is used for during as binary conversion treatment judging whether some tubular structure is sweat duct
The threshold value in road, when the gray value of some pipeline configuration is higher than the threshold value, then it is assumed that the pipeline configuration is sweat gland pipeline.
S6, judged according to sweat gland image to whether there is sweat gland in the three-dimensional fingerprint image, if in the presence of current collection refers to
Line is actual fingerprint；It is current to gather fingerprint to forge fingerprint if being not present.From the sweat gland figure obtained after binary conversion treatment
It as in, can interpolate that out with the presence or absence of sweat gland structure, in the sweat gland image for forging fingerprint, in the absence of sweat gland structure, can see
To be the non-sweat gland structure of interference information etc. as caused by outer fingerprint valley and strong reflection mostly, therefore by observing sweat gland image
It can determine whether the true and false of fingerprint.
In a kind of specific embodiment, using means of optical coherence tomography, finger scan is carried out；Scanning is obtained
One-dimensional signal carry out grey level compensation according to scan depths, export the two-dimentional tomoscan image of fingerprint image, and will two dimension it is disconnected
Layer scan image is redeveloped into three-dimensional fingerprint image.Using image gradient information, detected on the section of the three-dimensional fingerprint image
The glass surface of finger is placed during fingerprint collecting, outer finger print layer is extracted from the image layer of the glass surface detected, it is logical during due to collection
It is often that finger is close to glass surface, therefore detects the glass surface in three-dimensional fingerprint image, you can extracts the figure of outer finger print layer
Picture.Preferably, the detection of glass surface can be realized using Hough straight-line detection.The detection of interior fingerprint is to be based on outer fingerprint, due to
The reflection of outer fingerprint and interior fingerprint to light is better than sweat gland region, and therefore, below outer finger print layer, the gray value of image reduced before this
(entering sweat gland region), then rise can detect that (by sweat gland region to interior finger print layer) based on this gray-value variation trend
Interior finger print layer.
In the particular embodiment, tubular filter is carried out to the sweat gland region of selection using multiple dimensioned tubular structure wave filter
Ripple, strengthen the pipe section in image.Particular by the characteristic value for the Hessian matrix for calculating sweat gland region, pass through Hessian matrix
Characteristic value can be in response diagram picture sweat gland structural information.Suitable line size is set, tubulose enhancing is carried out to sweat gland image.
Binary conversion treatment is carried out to filtered piping drawing picture again, obtains sweat gland image, can determine whether it is to forge to refer to according to sweat gland image
Line or actual fingerprint.Preferably, can also following optimization processing be carried out to sweat gland image：Based on sweat gland pipeline and outer fingerprint valley
Vertical relation, to sweat gland image carry out sweat gland pipeline screening, to determine the position of sweat gland pipeline；Spiral knot based on sweat gland
Structure information pair determines that the sweat gland image after sweat gland pipeline location is corrected.
The method that fingerprint recognition is carried out based on sweat gland, then in fingerprint recognition system database in the finger print information of prior typing
Include inside and outside fingerprint and sweat gland structure.In fingerprint typing, the extraction of sweat gland structure generally comprises：To the fingerprint of typing
Three-dimensional fingerprint image carries out outer fingerprint extraction, interior fingerprint extraction and sweat gland extraction, specific extracting method successively to be used
The preparation method for inside and outside fingerprint extraction method and the sweat gland image mentioned in previous embodiment, obtaining sweat gland image can make
Sweat gland structural information for the fingerprint of typing is stored in database, for being compared during follow-up progress fingerprint recognition.When needing to carry out
During fingerprint individual verification based on sweat gland, for the fingerprint to be identified gathered in real time, then according to fingerprint recognition side as shown in Figure 2
Method carries out fingerprint recognition, specifically includes：Obtain three-dimensional fingerprint image；To the three-dimensional fingerprint image, believed using image gradient
Breath detects outer fingerprint, to extract outer finger print layer；In addition on the basis of finger print layer, the ash of each tomographic image below outer finger print layer is calculated
Spend average, the variation tendency based on gray average, fingerprint in detection；If interior fingerprint is not present, the current fingerprint that gathers is determined as
Forge fingerprint；If interior fingerprint is present, finger print layer in extraction；The region between outer finger print layer and interior finger print layer is chosen, is me
Sweat gland region interested, to the sweat gland region carry out tubulose filtering, to extract tubular structure；Using sweat gland threshold value, to entering
The tubular structure image extracted after row filtering carries out binary conversion treatment, obtains sweat gland image；Wherein, sweat gland threshold value is from gray scale
The one of grey scale pixel value chosen in the minimum tomographic image of average；Based on sweat gland pipeline pass vertical with outer fingerprint valley
System, the screening of sweat gland pipeline is carried out to sweat gland image, to determine the position of sweat gland pipeline, extract sweat gland structure；Current collection refers to
Sweat gland structure, interior fingerprint and the outer fingerprint of line respectively with existing sweat gland structure, interior fingerprint and outer fingerprint in fingerprint recognition system
Matched, identification is carried out according to matching result.
Preferably, by the way that with numerical quantization, matching result is obtained into a matching fraction, by matching fraction with setting in advance
The matching score threshold put is compared, if matching result is higher than the matching score threshold, fingerprint individual verification success；It is no
Then, then Fingerprint Identity None- identified.
Above content is to combine specific preferred embodiment further description made for the present invention, it is impossible to is assert
The specific implementation of the present invention is confined to these explanations.For those skilled in the art, do not taking off
On the premise of from present inventive concept, some equivalent substitutes or obvious modification can also be made, and performance or purposes are identical, all should
When being considered as belonging to protection scope of the present invention.
Claims (9)
1. a kind of fingerprint true and false discriminating conduct based on sweat gland, comprises the following steps S1 to S6：
S1, the three-dimensional fingerprint image for obtaining current collection fingerprint；
S2, to the three-dimensional fingerprint image, outer fingerprint is detected using image gradient information, to extract outer finger print layer；
S3, in addition on the basis of finger print layer, the gray average of each tomographic image below outer finger print layer is calculated, based on gray average
Variation tendency, fingerprint in detection；If interior fingerprint is not present, the current fingerprint that gathers is judged to forging fingerprint；If interior fingerprint is present,
Then finger print layer in extraction, and perform step S4；
S4, sweat gland region is chosen, and tubulose filtering is carried out to sweat gland region, to extract tubular structure；Wherein, the sweat gland region
For the region between outer finger print layer and interior finger print layer；
S5, using sweat gland threshold value, binary conversion treatment is carried out to step S4 filter result, obtains sweat gland image；Wherein, sweat gland threshold
Value is the one of grey scale pixel value chosen from the minimum tomographic image of gray average；
S6, judged according to sweat gland image to whether there is sweat gland in the three-dimensional fingerprint image, if in the presence of the current fingerprint that gathers is
Actual fingerprint；It is current to gather fingerprint to forge fingerprint if being not present.
2. fingerprint true and false discriminating conduct as claimed in claim 1, it is characterised in that step S1 is specifically included：
Using means of optical coherence tomography, finger scan is carried out；
Grey level compensation is carried out according to scan depths to the one-dimensional signal that scanning obtains, exports the two-dimentional faulted scanning pattern of fingerprint image
Picture, and two-dimentional tomoscan image is redeveloped into three-dimensional fingerprint image.
3. fingerprint true and false discriminating conduct as claimed in claim 1, it is characterised in that step S2 is specifically included：In the three-dimensional
The glass surface of fingerprint is inputted when fingerprint collecting is detected on the section of fingerprint image, the image layer extraction from the glass surface detected is outer
Finger print layer.
4. fingerprint true and false discriminating conduct as claimed in claim 3, it is characterised in that：The detection of glass surface is using suddenly in step S2
Husband straight-line detection is realized.
5. fingerprint true and false discriminating conduct as claimed in claim 1, it is characterised in that carried out in step S4 to the sweat gland region
Tubulose filtering specifically includes：Utilize multiple dimensioned tubular structure wave filter, the characteristic value of the Hessian matrix in calculating sweat gland region.
6. fingerprint true and false discriminating conduct as claimed in claim 1, it is characterised in that：Step S5 also includes to being obtained after binaryzation
Sweat gland image carry out following handle：Vertical relation based on sweat gland pipeline Yu outer fingerprint valley, sweat gland is carried out to sweat gland image
The screening of pipeline, to determine the position of sweat gland pipeline.
7. fingerprint true and false discriminating conduct as claimed in claim 6, it is characterised in that：Step S5 also includes the spiral based on sweat gland
Structural information pair determines that the sweat gland image after sweat gland pipeline location is corrected.
8. a kind of fingerprint identification method based on sweat gland, comprises the following steps S1 to S7：
S1, using means of optical coherence tomography gather fingerprint, obtain three-dimensional fingerprint image；
S2, to the three-dimensional fingerprint image, outer fingerprint is detected using image gradient information, to extract outer finger print layer；
S3, in addition on the basis of finger print layer, the gray average of each tomographic image below outer finger print layer is calculated, based on gray average
Variation tendency, fingerprint in detection；If interior fingerprint is not present, the current fingerprint that gathers is judged to forging fingerprint；If interior fingerprint is present,
Then finger print layer in extraction, and perform step S4；
S4, sweat gland region is chosen, and tubulose filtering is carried out to sweat gland region, to extract tubular structure；Wherein, the sweat gland region
For the region between outer finger print layer and interior finger print layer；
S5, using sweat gland threshold value, binary conversion treatment is carried out to step S4 filter result, obtains sweat gland image；Wherein, sweat gland threshold
Value is the one of grey scale pixel value chosen from the minimum tomographic image of gray average；
S6, the vertical relation based on sweat gland pipeline Yu outer fingerprint valley, the screening of sweat gland pipeline is carried out to sweat gland image, to determine
The position of sweat gland pipeline, extract sweat gland structure；
S7, by sweat gland structure, interior fingerprint and the outer fingerprint of current collection fingerprint respectively with existing sweat gland in fingerprint recognition system
Structure, interior fingerprint and outer fingerprint are matched, and identification is carried out according to matching result.
9. fingerprint identification method as claimed in claim 8, it is characterised in that：In step S7, by by matching result with numerical value
Quantify, by matching result compared with the matching score threshold pre-set, if matching result is higher than the matching fraction threshold
Value, then fingerprint individual verification success；Otherwise, then Fingerprint Identity None- identified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710994412.5A CN107563364B (en) | 2017-10-23 | 2017-10-23 | Sweat gland-based fingerprint authenticity identification method and fingerprint identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710994412.5A CN107563364B (en) | 2017-10-23 | 2017-10-23 | Sweat gland-based fingerprint authenticity identification method and fingerprint identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107563364A true CN107563364A (en) | 2018-01-09 |
| CN107563364B CN107563364B (en) | 2021-11-12 |
Family
ID=60985993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710994412.5A Active CN107563364B (en) | 2017-10-23 | 2017-10-23 | Sweat gland-based fingerprint authenticity identification method and fingerprint identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107563364B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446633A (en) * | 2018-03-20 | 2018-08-24 | 深圳大学 | A kind of method, system and device of novel finger print automatic anti-fake and In vivo detection |
| CN109074489A (en) * | 2018-07-20 | 2018-12-21 | 深圳市汇顶科技股份有限公司 | Method, fingerprint identification device and the electronic equipment of fingerprint recognition |
| CN109902569A (en) * | 2019-01-23 | 2019-06-18 | 上海思立微电子科技有限公司 | Conversion method, device and the fingerprint identification method of fingerprint image |
| CN110119699A (en) * | 2019-04-28 | 2019-08-13 | 清华大学深圳研究生院 | Interior fingerprint extraction method, device, system and storage medium and fingerprint identification method |
| CN110309699A (en) * | 2019-03-22 | 2019-10-08 | 浙江工业大学 | A kind of subcutaneous pore figure extraction method based on OCT |
| CN110334566A (en) * | 2019-03-22 | 2019-10-15 | 浙江工业大学 | Fingerprint extraction method inside and outside a kind of OCT based on three-dimensional full convolutional neural networks |
| CN111079626A (en) * | 2019-12-11 | 2020-04-28 | 深圳市迪安杰智能识别科技有限公司 | Live fingerprint identification method, electronic equipment and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101855650B (en) * | 2007-11-09 | 2012-12-12 | 富士通株式会社 | Biological information acquiring device, biological information accruing method, biological information acquiring program, and biometric authentication device |
| CN104751139A (en) * | 2015-03-31 | 2015-07-01 | 上海大学 | Fast fingerprint recognition method based on feature points of sweat glands and fingerprint images |
| CN105740750A (en) * | 2014-12-11 | 2016-07-06 | 深圳印象认知技术有限公司 | Fingerprint in-vivo detection and identification method and apparatus |
| CN106657056A (en) * | 2016-12-20 | 2017-05-10 | 深圳芯启航科技有限公司 | Biological feature information management method and system |
| CN107016326A (en) * | 2015-09-22 | 2017-08-04 | 赛峰身份与安全公司 | From the method for the sample extraction morphological feature of biomaterial |
| CN107146262A (en) * | 2017-04-18 | 2017-09-08 | 清华大学深圳研究生院 | The three-dimensional visualization method and system of a kind of OCT image |
-
2017
- 2017-10-23 CN CN201710994412.5A patent/CN107563364B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101855650B (en) * | 2007-11-09 | 2012-12-12 | 富士通株式会社 | Biological information acquiring device, biological information accruing method, biological information acquiring program, and biometric authentication device |
| CN105740750A (en) * | 2014-12-11 | 2016-07-06 | 深圳印象认知技术有限公司 | Fingerprint in-vivo detection and identification method and apparatus |
| CN104751139A (en) * | 2015-03-31 | 2015-07-01 | 上海大学 | Fast fingerprint recognition method based on feature points of sweat glands and fingerprint images |
| CN107016326A (en) * | 2015-09-22 | 2017-08-04 | 赛峰身份与安全公司 | From the method for the sample extraction morphological feature of biomaterial |
| CN106657056A (en) * | 2016-12-20 | 2017-05-10 | 深圳芯启航科技有限公司 | Biological feature information management method and system |
| CN107146262A (en) * | 2017-04-18 | 2017-09-08 | 清华大学深圳研究生院 | The three-dimensional visualization method and system of a kind of OCT image |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446633A (en) * | 2018-03-20 | 2018-08-24 | 深圳大学 | A kind of method, system and device of novel finger print automatic anti-fake and In vivo detection |
| CN109074489A (en) * | 2018-07-20 | 2018-12-21 | 深圳市汇顶科技股份有限公司 | Method, fingerprint identification device and the electronic equipment of fingerprint recognition |
| CN109074489B (en) * | 2018-07-20 | 2022-04-26 | 深圳市汇顶科技股份有限公司 | Fingerprint identification method, fingerprint identification device and electronic equipment |
| CN109902569A (en) * | 2019-01-23 | 2019-06-18 | 上海思立微电子科技有限公司 | Conversion method, device and the fingerprint identification method of fingerprint image |
| CN110309699A (en) * | 2019-03-22 | 2019-10-08 | 浙江工业大学 | A kind of subcutaneous pore figure extraction method based on OCT |
| CN110334566A (en) * | 2019-03-22 | 2019-10-15 | 浙江工业大学 | Fingerprint extraction method inside and outside a kind of OCT based on three-dimensional full convolutional neural networks |
| CN110309699B (en) * | 2019-03-22 | 2021-06-18 | 浙江工业大学 | Automatic extraction method of subcutaneous sweat pore map based on OCT |
| CN110119699A (en) * | 2019-04-28 | 2019-08-13 | 清华大学深圳研究生院 | Interior fingerprint extraction method, device, system and storage medium and fingerprint identification method |
| CN111079626A (en) * | 2019-12-11 | 2020-04-28 | 深圳市迪安杰智能识别科技有限公司 | Live fingerprint identification method, electronic equipment and computer readable storage medium |
| CN111079626B (en) * | 2019-12-11 | 2023-08-01 | 深圳市迪安杰智能识别科技有限公司 | Living body fingerprint identification method, electronic equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107563364B (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107563364A (en) | The discriminating conduct of the fingerprint true and false and fingerprint identification method based on sweat gland | |
| Wang et al. | Localizing microaneurysms in fundus images through singular spectrum analysis | |
| CN109543526B (en) | True and false facial paralysis recognition system based on depth difference characteristics | |
| Zhang et al. | A modified matched filter with double-sided thresholding for screening proliferative diabetic retinopathy | |
| Jitpakdee et al. | A survey on hemorrhage detection in diabetic retinopathy retinal images | |
| CN105005765B (en) | A kind of facial expression recognizing method based on Gabor wavelet and gray level co-occurrence matrixes | |
| CN108133476B (en) | Method and system for automatically detecting pulmonary nodules | |
| CN109858540B (en) | Medical image recognition system and method based on multi-mode fusion | |
| CN106815819B (en) | More strategy grain worm visible detection methods | |
| CN107610104A (en) | Crack detecting method at a kind of elevator compensation chain R based on machine vision | |
| CN112150442A (en) | New crown diagnosis system based on deep convolutional neural network and multi-instance learning | |
| CN111028206A (en) | Prostate cancer automatic detection and classification system based on deep learning | |
| Harangi et al. | Automatic detection of the optic disc using majority voting in a collection of optic disc detectors | |
| Jaafar et al. | Automated detection of red lesions from digital colour fundus photographs | |
| CN108511055A (en) | Ventricular premature beat identifying system and method based on Multiple Classifier Fusion and diagnostic rule | |
| CN109003275A (en) | The dividing method of weld defect image | |
| CN112465905A (en) | Characteristic brain region positioning method of magnetic resonance imaging data based on deep learning | |
| CN111598868B (en) | Lung ultrasonic image identification method and system | |
| CN113343755A (en) | System and method for classifying red blood cells in red blood cell image | |
| Malathi et al. | A survey on plant leaf disease detection using image processing techniques | |
| Bhatia et al. | Retinal vessel extraction via assisted multi-channel feature map and U-net. Front | |
| Orlando et al. | Learning to detect red lesions in fundus photographs: An ensemble approach based on deep learning | |
| CN101404062A (en) | Automatic screening method for digital galactophore image based on decision tree | |
| Noah Akande et al. | Implementation of a framework for healthy and diabetic retinopathy retinal image recognition | |
| CN116758336A (en) | Medical image intelligent analysis system based on artificial intelligence |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |