CN108960004A - A kind of palm grain identification method - Google Patents
A kind of palm grain identification method Download PDFInfo
- Publication number
- CN108960004A CN108960004A CN201710354289.0A CN201710354289A CN108960004A CN 108960004 A CN108960004 A CN 108960004A CN 201710354289 A CN201710354289 A CN 201710354289A CN 108960004 A CN108960004 A CN 108960004A
- Authority
- CN
- China
- Prior art keywords
- mixed
- palmmprint
- phase
- feature
- phase feature
- 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
- G06V40/1347—Preprocessing; Feature extraction
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of palm grain identification methods based on two-dimensional filtering mixing.It carries out palmprint image extraction by two dimensional filter first;Then mixed-phase feature is extracted to filtered result;Then cryptographic operation is carried out to the palmmprint mixed-phase feature of extraction;Then it to the two encryption palmmprint mixed-phase features obtained after cryptographic operation, is matched with apart from matching algorithm, obtains matching result.This kind of recognition methods is influenced small by acquisition illumination condition, and computation complexity is low, and the advantages of in combination with identification and knowledge based password identification based on biological characteristic, accuracy of identification is high, and security of system is good.
Description
Technical field
The present invention relates to a kind of palm-print identifying arithmetics based on the encryption of two-dimensional filtering phase property.
Background technique
In today of advanced IT application, with the rapid development of computer technology and network technology, information security is shown
Unprecedented importance.In daily life and many occasions such as finance, the administration of justice, safety check, e-commerce require accurately
Identification.Today, there are mainly three types of the modes of the identification of the mankind: the first is Knowledge based engineering method, is such as used
Password, password etc.;Second is the method based on article, such as uses key, ID card;The third is that the biology based on human body is special
The method of sign, such as face, fingerprint, palmmprint, voice etc..First two method there is many flaws, take by the method based on article
Band is inconvenient and is easily lost, damages, is stolen or forges;Knowledge based engineering method is easy to pass into silence, crack.Therefore this two
Kind method is increasingly not suitable for modern development in science and technology and social progress.Personal identification method based on human body biological characteristics overcomes
Drawbacks described above is the feature intrinsic based on human body using biometric solution, will not lose or forget.Meanwhile the life of human body
Object feature is different, even twins, the information such as their fingerprint, iris are also different, so biological characteristic is difficult
Spoofed and duplication.Since human body biological characteristics not only have the characteristics that uniqueness and unchangeable property, and quantity also has very much
Limit, once these limited biological characteristics of people are compromised or are stolen, direct result is exactly these biological characteristics of people cannot
Identities match identification and the authentication being used further in security system.In addition, the human body biological characteristics as a people are not encrypted
When being just directly used in multiple independent security system identity identifying and authenticatings, the biological characteristic of a security system is broken or lets out
Dew, all these independent security systems are no longer safe, will cause various safety problems, can not protect privacy.Therefore
It is transferred to encrypted domain (encrypted biological characteristic) progress with regard to needing to be shifted matching and identification by direct biological characteristic and can substitute
Secure match and identification.In addition in incorporated business, it is added to new person or has labor turnover, these are required to these
The biological characteristic (privacy) of people is protected.After making encryption to these features, the registration of new characteristic and leaving office person
Can guarantee that adverse effect will not be generated to he or she after the deletion of work.
The personal recognition biological identification technology emerging as one, mainly has the advantage that compared with other biological feature
The area of palmmprint is larger, and much, therefore, palmmprint has more than fingerprint than one piece rich fingerprint of the information included in theory
Good ga s safety degree, the feature of extraction is not vulnerable to the interference of noise.Compared with iris feature, palm-print image capture equipment is simply easy
Row, cost are far below the acquisition equipment of iris image.It is compared with hand-type feature, palm print characteristics are stablized, and uniqueness is stronger, is not easy puppet
It makes, and accuracy of identification is higher.Palmmprint acquisition modes are associated with smaller with criminal and lawsuit, therefore consumers' acceptable degree is higher.
Currently, researcher has carried out compared with in-depth study the biological feather recognition method based on palmmprint, and take
Obtained certain achievement.But, the accuracy of identification of these methods is not only still to be improved, and lacks safety and secret protection.
Therefore, it is necessary to invent a kind of high precision palm print recognition method that can enhance safety and secret protection.
Summary of the invention
The purpose of the present invention is to provide a kind of safe palm-print identifying arithmetics based on the encryption of two-dimensional filtering phase property, should
Method is influenced smaller by acquisition illumination condition, and computation complexity is low, and the accuracy of identification of palmmprint is high, and security of system is good.
The present invention realizes its goal of the invention, the technical scheme adopted is that a kind of encrypted based on two-dimensional filtering phase property
Safe palm recognition method, the steps include:
The first step, the index finger and middle finger that people's palmprint image is obtained using border following algorithm, shape between the third finger and little finger of toe
At angle point, and palmprint image is corrected by the two angle points, be then cut into palm picture centre and size be 128 ×
The palmprint image block I of 128 pixels;
Second step constitutes two-dimentional compound filter with the two dimensional filter of 4 different directions;
Third step extracts the mixed-phase feature of palmprint image by the way of phase code;
4th step carries out exclusive or processing to palmmprint mixed-phase feature, obtains encryption palmmprint mixed-phase feature;
5th step carries out two palmprint images the operation of preceding four step respectively, obtains two encryption palmmprint mixed-phases
Feature, then encryption palmmprint mixed-phase feature is matched using apart from matching algorithm, obtain matching result.
Compared with prior art, the beneficial effects of the present invention are: method of the invention by acquisition illumination condition influenced it is small,
And computation complexity is low, and the advantages of in combination with identification and knowledge based password identification based on biological characteristic, accuracy of identification
Height, security of system are good..
Specific embodiment
A kind of specific embodiment of the invention is the safe palm recognition method based on mixed filtering, including following step
It is rapid:
The first step, the index finger and middle finger that people's palmprint image is obtained using border following algorithm, shape between the third finger and little finger of toe
At angle point, and palmprint image is corrected by the two angle points, then cutting palm picture centre size is 128 × 128 pictures
The rectangular image block I of element;
Second step constitutes two-dimentional compound filter with the two dimensional filter of 4 different directions, and two dimensional filter is sat in logarithm
Lower mark is Gaussian function.Compared with traditional two dimensional filter, two dimensional filter does not have DC component, and includes more height
Frequency ingredient.In terms of to natural image coded representation, the excessive low frequency for illustrating image of traditional two-dimensional function filter at
Point, and insufficient is indicated to the radio-frequency component of image.Therefore, there is two dimensional filter more preferable image to indicate effect.
Third step, the mixed-phase that palmprint image is extracted by the way of phase code to filtered palmprint image are special
Sign first uses decimation factor ρ (4 × 4) to carry out down-sampling obtained palmmprint mixed-phase feature, and obtaining size is 32 × 64
Simplify palmmprint mixed-phase feature PMPF (ρ).
4th step, with length PRBS pseudo-random bit sequence identical with the bit number of palmmprint mixed-phase feature is simplified to simplification
Palmmprint mixed-phase feature carries out exclusive or processing, obtains encrypting simplified palmmprint mixed-phase feature.
Claims (2)
1. a kind of palm grain identification method, the first step, extracts the index finger and middle finger of palmprint image, formed between the third finger and little finger of toe
Angle point, and palmprint image is corrected by the two angle points, it is then cut into palm picture centre and size is 128 × 128 pictures
The palmprint image block I of element;Second step constitutes two-dimentional compound filter with the filter of 4 different directions;Third step, using phase
The mode of position coding extracts the mixed-phase feature of palmprint image;4th step carries out exclusive or processing to palmmprint mixed-phase feature,
Obtain encryption palmmprint mixed-phase feature;5th step carries out two palmprint images the operation of preceding four step respectively, obtains two
Palmmprint mixed-phase feature is encrypted, then encryption palmmprint mixed-phase feature is matched using apart from matching algorithm, is obtained
With result.
2. safe palm recognition method according to claim 1, it is characterised in that: the palmmprint mixed-phase of the third step
When feature extraction, decimation factor ρ (4 × 4) are first used to carry out down-sampling obtained palmmprint mixed-phase feature, obtaining size is
32 × 64 simplification palmmprint mixed-phase feature, then to the 4th step, two step of the 5th step for simplifying the progress of palmmprint mixed-phase feature
Operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710354289.0A CN108960004A (en) | 2017-05-18 | 2017-05-18 | A kind of palm grain identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710354289.0A CN108960004A (en) | 2017-05-18 | 2017-05-18 | A kind of palm grain identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108960004A true CN108960004A (en) | 2018-12-07 |
Family
ID=64461515
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710354289.0A Pending CN108960004A (en) | 2017-05-18 | 2017-05-18 | A kind of palm grain identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108960004A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101286195A (en) * | 2008-06-03 | 2008-10-15 | 西南交通大学 | High precision palm print recognition method based on two-dimensional quadrature Log-Gabor filtering |
CN101308542A (en) * | 2008-06-26 | 2008-11-19 | 西南交通大学 | Highly precise safe palm recognition method encrypted based on phase characteristic of Log-Gabor mixed filtering |
-
2017
- 2017-05-18 CN CN201710354289.0A patent/CN108960004A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101286195A (en) * | 2008-06-03 | 2008-10-15 | 西南交通大学 | High precision palm print recognition method based on two-dimensional quadrature Log-Gabor filtering |
CN101308542A (en) * | 2008-06-26 | 2008-11-19 | 西南交通大学 | Highly precise safe palm recognition method encrypted based on phase characteristic of Log-Gabor mixed filtering |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100593790C (en) | Highly precise safe palm recognition method encrypted based on phase characteristic of Log-Gabor mixed filtering | |
CN102722696B (en) | Identity authentication method of identity card and holder based on multi-biological characteristics | |
CN103279697B (en) | Based on details in fingerprint Information hiding and the restoration methods of orthogonal matrix and modular arithmetic | |
Sudar et al. | Analysis of security threats and countermeasures for various biometric techniques | |
Abd Razak et al. | Data anonymization using pseudonym system to preserve data privacy | |
CN107124283A (en) | A kind of physical characteristics collecting system and physical characteristics collecting method | |
CN103607282A (en) | Identity fusion authentication method based on biological characteristics | |
CN102223233A (en) | Biological code authentication system and biological code authentication method | |
CN106372481A (en) | Fingerprint permutation and combination password | |
CN109635756A (en) | It merges fingerprint and refers to the two dimensional code identity identifying method of vein | |
Arunachalam et al. | AES Based Multimodal Biometric Authentication using Cryptographic Level Fusion with Fingerprint and Finger Knuckle Print. | |
CN104009973A (en) | Fingerprint detail information hiding and recovering method based on set polynomial conversion and harmonics | |
Brindha | Biometric template security using fuzzy vault | |
Saraswathi et al. | Retinal biometrics based authentication and key exchange system | |
Malik et al. | Accuracy improvement in palmprint authentication system | |
Meenakshi et al. | Securing revocable iris and retinal templates using combined user and soft biometric based password hardened multimodal fuzzy vault | |
Ashish et al. | Biometric template protection | |
Bala | Biometrics and information security | |
CN104462926A (en) | Intelligent card identity recognition method and system | |
Meenakshi et al. | Securing iris templates using combined user and soft biometric based password hardened fuzzy vault | |
Sowkarthika et al. | Securing iris and fingerprint templates using fuzzy vault and symmetric algorithm | |
CN108960004A (en) | A kind of palm grain identification method | |
Hajare et al. | Biometric template security using visual cryptography | |
Kaur | Multimodal based fuzzy vault using iris retina and fingervein | |
CN110391909A (en) | Terminal unlock method and system based on living things feature recognition |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181207 |
|
WD01 | Invention patent application deemed withdrawn after publication |