CN101727567A - Fingerprint identification method and identification processing device thereof - Google Patents
Fingerprint identification method and identification processing device thereof Download PDFInfo
- Publication number
- CN101727567A CN101727567A CN200810155617A CN200810155617A CN101727567A CN 101727567 A CN101727567 A CN 101727567A CN 200810155617 A CN200810155617 A CN 200810155617A CN 200810155617 A CN200810155617 A CN 200810155617A CN 101727567 A CN101727567 A CN 101727567A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- module
- fingerprint image
- point
- vector
- 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
Images
Abstract
The invention relates to a fingerprint identification method and an identification processing device thereof. The method comprises the following steps: first, dividing collected fingerprint images into non-overlapping grid blocks, and then computing the gradient vectors along the X and Y directions of each pixel point in the grid blocks; estimating the gradient direction of the center point of each block as the local direction of each grid block, and then using even symmetrical Gabor filtering to acquire related characteristic points; and finally comparing and identifying the proportional values and angular dimensions among the characteristic points. The device comprises a storage module, a control module, a power supply module and a processing chip, wherein the peripheral interface modules of the storage module, the control module and the power supply module are respectively integrated on the processing chip; and the processing chip provides three optional interfaces of an SPI interface, a UART interface and a USB interface and forms a system-on-a-chip structure. The invention not only ensures quick and accurate collection and identification of the fingerprints, but also is favorable for combining the fingerprint identification technology with the current common mobile storage devices, thereby improving the safety of the mobile storage devices.
Description
Technical field
The present invention relates to a kind of living things feature recognition method and identification equipment thereof, relate in particular to a kind of recognition methods and recognition process unit thereof of fingerprint, belong to the calculating field.
Background technology
Along with the continuous development of infotech, safety problem causes people's attention day by day, the solution that growing field needs the applying biological recognition technology to provide, and information security market kept rapid growth in recent years at home.Biological identification technology is based on the unique physiology of individual and behavioural characteristic is carried out the technology that identity is differentiated, it is means based on biotechnology with the infotech, belongs to the research topic of pattern-recognition.Compare with traditional encipher-decipher method, biological identification technology is a recognition technology the most convenient at present and safety, and it does not need to remember complex password, does not need to carry the thing of key, smart card and so on yet.
Fingerprint identification technology becomes the optimal selection of field of biological recognition with its stability, ease for use, uniqueness, can be widely used in the systems such as evaluation, gate inhibition, financial security, entry and exit that commit a crime.
Yet the performance that how further to improve fingerprint recognition still has great importance, and especially technology and product combine, and need all be optimized existing algorithm and hardware circuit performance, could satisfy user's needs.Need a kind of method that many aspects such as Pre-process of Fingerprint Image, figure image intensifying, feature extraction and coupling are improved.
Summary of the invention
Purpose of the present invention is exactly in order to solve the above-mentioned problems in the prior art, and a kind of recognition methods and recognition process unit thereof of fingerprint is provided.
Purpose of the present invention is achieved through the following technical solutions:
The recognition methods of fingerprint, it may further comprise the steps:
1. step is divided into the fingerprint image of gathering the gridblock of non-overlapping copies;
Step 2., (i is j) along the gradient vector of its X, Y direction for each pixel in the computing grid piece;
3. step estimates that (i j) is the local direction of each gridblock of central point with pixel;
4. step adopts even symmetry Gabor filtering, and filtering noise also keeps ridge or the structure of paddy, obtains the correlated characteristic point of gathering fingerprint image;
5. step is relatively gathered on fingerprint image and the characteristic fingerprint image ratio value and the angular dimension between the unique point and is discerned.
The recognition methods of above-mentioned fingerprint, wherein: described being estimated as with pixel (i, the weighted mean of four central point piece gradient vectors the most contiguous j), as with i, j is the gradient vector of the gridblock of central point, is about to every and is divided into four fritters, calculates the gradient vector of each fritter central point, weighted mean is calculated the direction of this point again as the gradient vector of this piece X, Y direction.Certainly, directly estimate the direction of this fritter, be equivalent to divide carefully that then noise resisting ability will obviously weaken with every with the gradient vector of every fritter central point.
Further, the recognition methods of above-mentioned fingerprint, wherein: described identifying is to establish a certain unique point that a is an input picture; B1, b2, b3, b4 is its 4 the most contiguous unique points, c1, c2, c3, c4 is respectively b1, b2, b3, b4 is the most contiguous unique point except that a point, calculate triangle ab1c1 respectively, ab2c2, ab3c3, the area of ab4c4 ratio and corresponding angle ab1c1 between any two, ab2c2, ab3c3, ab4c4 charges in the input vector group, each member is made up of ratio and corresponding two angles in the Vector Groups, in the template vector group that the calculating equifinality deposits in, relatively whether all vectors in importation and the template part mate according to selected threshold decision two width of cloth images.
The fingerprint recognition treating apparatus, wherein: comprise memory module, control module, power module, process chip, memory module, control module, power module peripheral interface module separately all is integrated on the process chip, process chip provides SPI interface, UART interface, three kinds of optional interfaces of USB interface, constitutes chip structure on the sheet.
Above-mentioned fingerprint recognition treating apparatus, wherein: it is made up of described memory module RAM, ROM, EEPROM, and the ROM storage is in order to the program of identification fingerprint image, and EEPROM stores the fingerprint image template and the device configuration information in order to authentication of typing.
Further, above-mentioned fingerprint recognition treating apparatus, wherein: described control module, be used to gather fingerprint image after the notifier processes chip finish corresponding calculated, extract the characteristic fingerprint image and mate then with among the described EEPROM of memory module, and the result is exported.
Further, above-mentioned fingerprint recognition treating apparatus, wherein: the related data of described EEPROM stored is protected by 64 TDES cryptographic algorithm, and key is stored among the ROM.
Further, above-mentioned fingerprint recognition treating apparatus, wherein: the gridblock of described step in 1., getting minimum value is 16 * 16 pixels, maximal value is got 32 * 32 pixels.
The outstanding substantive distinguishing features and the obvious improvement of technical solution of the present invention is mainly reflected in: adopt method of the present invention, whole fingerprint collecting identification quick and precisely.Simultaneously, adopt and to help after this method the fingerprint identification technology use that combines with existing common movable storage device, the security of raising movable storage device.And guaranteeing accuracy and keeping under the situation of higher hard disc data transmission speed that it is nearly 2/3rds that the present invention adopts the chip area of encrypting module to reduce, and expanded the space for the technical progress of this area, implementation result is good.
Description of drawings
Purpose of the present invention, advantage and characteristics will illustrate by the non-limitative illustration of following preferred embodiment and explain.These embodiment only are the prominent examples of using technical solution of the present invention, and all technical schemes of taking to be equal to replacement or equivalent transformation and forming all drop within the scope of protection of present invention.In the middle of these accompanying drawings,
Fig. 1 is the synoptic diagram of executing of fingerprint collection identification;
Fig. 2 is the organigram of fingerprint unique point;
Fig. 3 is the organigram of fingerprint recognition process unit.
The implication of each Reference numeral is as follows among the figure:
1 USB interface, 2 UART interfaces
3 RAM 4 ROM
5 EEPROM, 6 chips
Embodiment
In common fingerprint recognition, the figure image intensifying is mainly used in the fingerprint image quality of improving unintelligible zone, for the fingerprint image enhancement algorithms, the general filtering algorithm that all is based on field of direction estimation, the fingerprint lines is divided into several direction calculating grey scale pixel values, mostly uses the parameter of ridge orientation as enhancement algorithms.Therefore, the present invention is at first doing corresponding improvement and research aspect the Flame Image Process of fingerprint and the coupling, in conjunction with Fig. 1～3, method is as follows: the W * W gridblock that at first fingerprint image of gathering is divided into non-overlapping copies, wherein to get minimum value be 16 * 16 pixels to W, maximal value is got 32 * 32 pixels, finishes fingerprint collecting, i.e. step S1.
Then, carry out image pre-service S2, specifically: (i, j) it is along the gradient vector of X, Y direction for each pixel in the computing grid piece.Estimate that subsequently (i j) is the local direction of each gridblock of central point, and promptly (as with i, j is the gradient vector of the gridblock of central point for i, the weighted mean of four central point piece gradient vectors the most contiguous j) with pixel with pixel.Then, adopt even symmetry Gabor filtering, filtering noise also keeps ridge or the structure of paddy, obtains the correlated characteristic point of gathering fingerprint image, i.e. step S3.The also fingerprint of completing steps S4 registration simultaneously when finishing above-mentioned work.Relatively gather on fingerprint image and the characteristic fingerprint image ratio value and the angular dimension between the unique point at last and discern, be i.e. step S5.After finishing, all working carries out the output of matching result, i.e. step S6.
Further, for finger print matching method, fingerprint feature point has uniqueness and stability, and most of fingerprint algorithms are based on unique point, and the extraction of unique point, the selection of type directly have influence on the accuracy of fingerprint matching.Owing in the process of calculated characteristics point, there is error unavoidably, produce false unique point, and have rotation, translation, non-linear deformation between the fingerprint image, influence matched accuracy.The present invention compares the ratio value and the angular relationship of two width of cloth image correspondences again at ratio value and the angular dimension between the calculated characteristics point on every width of cloth fingerprint image, can more effectively eliminate the influence of non-linear deformation.
Specifically, as shown in Figure 2: establishing a is a certain unique point of input picture, and b1, b2, b3, b4 are its 4 the most contiguous unique points, and c1, c2, c3, c4 are respectively b1, b2, b3, b4 the most contiguous unique point except that a point.The area that calculates triangle ab1c1, ab2c2, ab3c3, ab4c4 respectively ratio and corresponding angle ab1c1, ab2c2, ab3c3, ab4c4 between any two charges in the input vector group, each member is made up of ratio and corresponding two angles in the Vector Groups, calculate same result and deposit the template vector group in, compare all Vector Groups in importation and the template part, compare mutually again between the corresponding Vector Groups, determine according to selected threshold value whether two width of cloth images mate.
Realize at the circuit of reality, the present invention adopts the principle of chip 6 on the sheet, and with memory module, control module, power module, peripheral interface module all is integrated on the same chip 6, chip 6 provides the three kinds of interfaces that can select, is respectively SPI interface, UART interface 2, usb 1.
In conjunction with Fig. 3, memory module is made up of RAM3, ROM4, EEPROM5.ROM4 storage algorithm program and system program.EEPROM5 storage typing is in order to the fingerprint image template of authentication, device configuration information and to the renewal of hardware, and the data of the inside are protected by 64 TDES cryptographic algorithm, and its key leaves among the ROM4.Controller notifier processes chip 6 after having gathered a width of cloth fingerprint image acquisition is finished corresponding calculated, then with EEPROM5 in the characteristic fingerprint that extracts mate, and the result is outputed to peripheral hardware.Chip 6 will enter energy-saving mode automatically under the situation that does not have work, when the system of assurance fast and stable calculates, reduced line and chip 6 areas greatly, reduce the power consumption of total system
At present, common fingerprint recognition is mainly used in systems such as gate inhibition, notebook computer.The present invention can be applied in fingerprint identification module on the movable storage device.Fingerprint identification module is the optimal selection that mobile storage is encrypted because volume own is less and support usb communication.By combining of fingerprint identification module and hard disk, not only the encryption and decryption of data is accurate, and all reaches higher speed under various system testings.
By above-mentioned character express also in conjunction with the accompanying drawings as can be seen, adopt method of the present invention, whole fingerprint collecting identification quick and precisely.Simultaneously, adopt and to help after this method the fingerprint identification technology use that combines with existing common movable storage device, the security of raising movable storage device.And guaranteeing accuracy and keeping under the situation of higher hard disc data transmission speed that it is nearly 2/3rds that the present invention adopts the chip area of encrypting module to reduce, and good implementation prospect is arranged.
Claims (8)
1. the recognition methods of fingerprint (" collection " no feature! ), it is characterized in that may further comprise the steps:
1. step is divided into the fingerprint image of gathering the gridblock of non-overlapping copies;
Step 2., each pixel in the computing grid piece (i, j) it is along the gradient vector of X, Y direction;
3. step estimates that (i j) is the local direction of each gridblock of central point with pixel;
4. step adopts even symmetry Gabor filtering, and filtering noise also keeps ridge or the structure of paddy, obtains the correlated characteristic point of gathering fingerprint image;
5. step is relatively gathered on fingerprint image and the characteristic fingerprint image ratio value and the angular dimension between the unique point and is discerned.
2. the recognition methods of fingerprint according to claim 1, it is characterized in that: step is 3. described to be estimated as with pixel (i, the weighted mean of four central point piece gradient vectors the most contiguous j), as with i, j is the gradient vector of the gridblock of central point, is about to every and is divided into four fritters, calculates the gradient vector of each fritter central point, weighted mean is calculated the direction of this point again as the gradient vector of this piece X, Y direction.
3. the recognition methods of fingerprint according to claim 1 is characterized in that: described identifying is to establish a certain unique point that a is an input picture; B1, b2, b3, b4 is its 4 the most contiguous unique points, c1, c2, c3, c4 is respectively b1, b2, b3, b4 is the most contiguous unique point except that a point, calculate triangle ab1c1 respectively, ab2c2, ab3c3, the area of ab4c4 ratio and corresponding angle ab1c1 between any two, ab2c2, ab3c3, ab4c4 charges in the input vector group, each member is made up of ratio and corresponding two angles in the Vector Groups, calculate same template image result and deposit the template vector group in, relatively whether corresponding vector in input vector group and the template vector group mates according to selected threshold decision two width of cloth images.
4. fingerprint recognition treating apparatus, it is characterized in that: comprise memory module, control module, power module, process chip, memory module, control module, power module peripheral interface module separately all is integrated on the process chip, process chip provides SPI interface, UART interface, three kinds of optional interfaces of USB interface, constitutes chip structure on the sheet.
5. fingerprint recognition treating apparatus according to claim 4, it is characterized in that: it is made up of described memory module RAM, ROM, EEPROM, the ROM storage is in order to the program of identification fingerprint image, and EEPROM stores the fingerprint image template and the device configuration information in order to authentication of typing.
6. fingerprint recognition treating apparatus according to claim 4, it is characterized in that: described control module, the notifier processes chip is finished corresponding calculated after being used to gather fingerprint image, extracts the characteristic fingerprint image and mates then with among the described EEPROM of memory module, and the result is exported.
7. fingerprint recognition treating apparatus according to claim 4 is characterized in that: the related data of described EEPROM stored is protected by 64 TDES cryptographic algorithm, and key is stored among the ROM.
8. the recognition methods of fingerprint according to claim 1 is characterized in that: the gridblock of step in 1., and getting minimum value is 16 * 16 pixels, maximal value is got 32 * 32 pixels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810155617A CN101727567A (en) | 2008-10-28 | 2008-10-28 | Fingerprint identification method and identification processing device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810155617A CN101727567A (en) | 2008-10-28 | 2008-10-28 | Fingerprint identification method and identification processing device thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101727567A true CN101727567A (en) | 2010-06-09 |
Family
ID=42448445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810155617A Pending CN101727567A (en) | 2008-10-28 | 2008-10-28 | Fingerprint identification method and identification processing device thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101727567A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050458A (en) * | 2014-06-30 | 2014-09-17 | 洛阳企盟信息科技有限公司 | Fingerprint identification system |
| CN105354462A (en) * | 2015-09-30 | 2016-02-24 | 山东超越数控电子有限公司 | Protection method for mobile memory and mobile memory |
| WO2016054890A1 (en) * | 2014-10-11 | 2016-04-14 | 深圳市汇顶科技股份有限公司 | Fingerprint input information processing method, system and mobile terminal |
| CN106682470A (en) * | 2015-11-09 | 2017-05-17 | 南昌欧菲生物识别技术有限公司 | Fingerprint recognition system based on encrypted fingerprint information, terminal device and method |
| CN109035508A (en) * | 2018-07-11 | 2018-12-18 | 刘建 | Fingerprint Lock switching mode selects platform |
| CN109815780A (en) * | 2018-08-31 | 2019-05-28 | 武汉芯盈科技有限公司 | A kind of high-precision fingerprint identification method and system based on image procossing |
| CN109976500A (en) * | 2015-02-13 | 2019-07-05 | 比亚迪股份有限公司 | The awakening method of fingerprint identification device, mobile terminal and fingerprint identification device |
| CN110263754A (en) * | 2019-06-28 | 2019-09-20 | 北京迈格威科技有限公司 | Shield lower fingerprint and removes shading method, apparatus, computer equipment and storage medium |
| CN112039730A (en) * | 2020-08-31 | 2020-12-04 | 海南大学 | Performance evaluation method of encryption algorithm and storage medium |
-
2008
- 2008-10-28 CN CN200810155617A patent/CN101727567A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050458A (en) * | 2014-06-30 | 2014-09-17 | 洛阳企盟信息科技有限公司 | Fingerprint identification system |
| WO2016054890A1 (en) * | 2014-10-11 | 2016-04-14 | 深圳市汇顶科技股份有限公司 | Fingerprint input information processing method, system and mobile terminal |
| CN109976500A (en) * | 2015-02-13 | 2019-07-05 | 比亚迪股份有限公司 | The awakening method of fingerprint identification device, mobile terminal and fingerprint identification device |
| CN105354462A (en) * | 2015-09-30 | 2016-02-24 | 山东超越数控电子有限公司 | Protection method for mobile memory and mobile memory |
| CN105354462B (en) * | 2015-09-30 | 2018-05-18 | 山东超越数控电子有限公司 | A kind of guard method of mobile memory and mobile memory |
| CN106682470A (en) * | 2015-11-09 | 2017-05-17 | 南昌欧菲生物识别技术有限公司 | Fingerprint recognition system based on encrypted fingerprint information, terminal device and method |
| CN109035508B (en) * | 2018-07-11 | 2020-12-01 | 六安志成智能科技有限公司 | Fingerprint lock switch mode selection platform |
| CN109035508A (en) * | 2018-07-11 | 2018-12-18 | 刘建 | Fingerprint Lock switching mode selects platform |
| CN109815780A (en) * | 2018-08-31 | 2019-05-28 | 武汉芯盈科技有限公司 | A kind of high-precision fingerprint identification method and system based on image procossing |
| CN110263754A (en) * | 2019-06-28 | 2019-09-20 | 北京迈格威科技有限公司 | Shield lower fingerprint and removes shading method, apparatus, computer equipment and storage medium |
| CN110263754B (en) * | 2019-06-28 | 2021-08-06 | 北京迈格威科技有限公司 | Method and device for removing shading of off-screen fingerprint, computer equipment and storage medium |
| CN112039730A (en) * | 2020-08-31 | 2020-12-04 | 海南大学 | Performance evaluation method of encryption algorithm and storage medium |
| CN112039730B (en) * | 2020-08-31 | 2022-06-07 | 海南大学 | Performance evaluation method of encryption algorithm and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101727567A (en) | Fingerprint identification method and identification processing device thereof | |
| CN101558431B (en) | Face authentication device | |
| Yang et al. | Feature-level fusion of fingerprint and finger-vein for personal identification | |
| CN102722696B (en) | Identity authentication method of identity card and holder based on multi-biological characteristics | |
| Jagadeesan et al. | Cryptographic key generation from multiple biometric modalities: Fusing minutiae with iris feature | |
| Yue et al. | Orientation selection using modified FCM for competitive code-based palmprint recognition | |
| Hemalatha | A systematic review on Fingerprint based Biometric Authentication System | |
| CN101819629B (en) | Supervising tensor manifold learning-based palmprint identification system and method | |
| Abdullah et al. | Smart card with iris recognition for high security access environment | |
| CN107657161A (en) | Method of mobile payment and Related product based on recognition of face | |
| CN109815780A (en) | A kind of high-precision fingerprint identification method and system based on image procossing | |
| Kumar et al. | DWT Based Fingerprint Recognition using Non Minutiae Features | |
| CN109657657A (en) | A kind of mobile phone small area high-precision fingerprint identification method and system based on image procossing | |
| CN105184236A (en) | Robot-based face identification system | |
| Xue | Face Database Security Information Verification Based on Recognition Technology. | |
| CN108171900B (en) | ATM cash withdrawal system | |
| CN104915590A (en) | Human face recognition system and method applied to computer encryption | |
| Meraoumia et al. | Do multispectral palmprint images be reliable for person identification? | |
| WO2022000334A1 (en) | Biological feature recognition method and apparatus, and device and storage medium | |
| Desai et al. | Face anti-spoofing technique using CNN and SVM | |
| Shivabasappa et al. | A hybrid learning scheme towards authenticating hand-geometry using multi-modal features | |
| CN203299842U (en) | Thermal infrared image face recognition system adapted in underground coal mine | |
| CN105931320A (en) | Image control device with identity recognition function | |
| Zeng et al. | A novel approach to mugshot based arbitrary view face recognition | |
| Umer et al. | IoT-Enabled Multimodal Biometric Recognition System in Secure Environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Open date: 20100609 |