CN107330395B - A kind of iris image encryption method based on convolutional neural networks - Google Patents

A kind of iris image encryption method based on convolutional neural networks Download PDF

Info

Publication number
CN107330395B
CN107330395B CN201710498746.3A CN201710498746A CN107330395B CN 107330395 B CN107330395 B CN 107330395B CN 201710498746 A CN201710498746 A CN 201710498746A CN 107330395 B CN107330395 B CN 107330395B
Authority
CN
China
Prior art keywords
iris
image
iris image
carried out
cnn
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.)
Active
Application number
CN201710498746.3A
Other languages
Chinese (zh)
Other versions
CN107330395A (en
Inventor
王雪松
张庆
程玉虎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China University of Mining and Technology CUMT
Original Assignee
China University of Mining and Technology CUMT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China University of Mining and Technology CUMT filed Critical China University of Mining and Technology CUMT
Priority to CN201710498746.3A priority Critical patent/CN107330395B/en
Publication of CN107330395A publication Critical patent/CN107330395A/en
Application granted granted Critical
Publication of CN107330395B publication Critical patent/CN107330395B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06V40/18—Eye characteristics, e.g. of the iris
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/50—Maintenance of biometric data or enrolment thereof
    • G06V40/53—Measures to keep reference information secret, e.g. cancellable biometrics

Abstract

The iris image encryption method based on convolutional neural networks that the invention discloses a kind of proposing iris feature by CNN models, and then RS codes coding obtains encryption key, then carries out AES operations with image array corresponding grey scale value to be encrypted, that is, realizes ciphering process.Since iris sample is fewer in CNN training process, to ensure that encrypted high security, the generation of key must use whole iris, cannot iris be carried out to image block extraction to make up the problem of sample deficiency.The present invention carries out image block extraction to iris first, and training SAE models initialize CNN parameters using SAE, CNN model trainings are carried out using whole picture iris image.So design not only solves the few problem of iris sample, and has guarantee to the safety of image encryption.

Description

A kind of iris image encryption method based on convolutional neural networks
Technical field
The invention belongs to area of pattern recognition, and in particular to a kind of iris image encryption side based on convolutional neural networks Method.
Background technology
Iris recognition technology is a kind of human biological's identification technology.Iris recognition technology is the knowledge in eyes based on iris Not, it is applied to the place of safety equipment (such as access control) and the confidentiality requirement of height.Human eyes structure is by sclera, rainbow The positions such as film, pupil, retina form.Iris is the annular section between black pupil and white sclera, is dissipated it includes many It layouts, the details such as filament, coronal, striped, crypts.And the entire life process iris after prenatal development stage forming will be kept It is constant.These characteristics determine the uniqueness of iris feature, and further define the uniqueness of identification.Therefore, the iris of eyes Characteristic can be applied to individual identity identification.
Iris is one of most robust feature in various biological identification technologies, special as identity characteristic and other biological Sign compares with superior property：Uniqueness, collects property, Noninvasive and safety at stability.In bio-identification In, Noninvasive is the inexorable trend of identity research and application development, with other non contact angle measurement methods (such as facial harmony Sound) it compares, iris recognition has higher accuracy.According to statistics, iris recognition is the minimum bio-identification of error rate, is based on rainbow The identity recognizing technology of film is gradually of interest by academia and business circles.
Iris can be widely applied for the numerous areas such as identification, encryption, have benefited from iris with some different from other biologies The specific characteristic of tissue includes mainly the following aspects：
(1) stability：In all one's life of people, iris information variation is very small, only encounters some special diseases Such as physical damnification, cataract, therefore iris has extremely strong stability；
(2) uniqueness：Iris is formed in embryonic development, and randomness is strong, is not influenced by gene.Development of fetus experience one A chaos morphogenetic process, this process causes the identical twinborn irises of DNA also to differ, to unique performance of iris It improves very big.So far, the iris that any two people does not occur is the same.As can be seen from Figure 2, iris is not smooth Curved surface, surface, which is dispersed with many recess, spot and shrinks details, these minutias such as ditch, determines iris information number According to composition Texture eigenvalue, is the external embodiment of iris uniqueness.
(3) non-infringement：Non- infringement property is also referred to as untouchable, refers to that need not be connect when carrying out information collection to iris It touches with regard to readable information.Iris is located on rear side of cornea, and protected situation is fine.During being acquired to iris, do not need Contact iris can be realized as iris capturing, it is therefore prevented that harmful effects, the user's acceptance such as transmission, iris damage compare It is high.Relative to biological characteristics such as palmmprint, fingerprints, iris need not contact acquisition, and sense of discomfort is lower, be more advantageous to the general of application Change.
(4) antifalsification：The change difficulty of iris feature is very big, in the case that vision without major injury be difficult change, The duplication and conversion for carrying out the iris of a people with special object are nearly impossible, due to the hair of In vivo detection technology Exhibition carries out iris processing come counterfeit live body using irises such as image, video recordings and is all likely to detected.
Biological identification technology optimal selection is iris, the reason is that relative to other biological feature, iris has highest unique Property, accuracy of identification is high, speed is fast, bioactivity is strong, antifalsification is strong and has many advantages, such as unchangeable stability.
The variable item up to 260 of iris is formed, internal structure is sufficiently complex, repeats possibility very little.Statistics shows two The probability of a human iris' striking resemblances is almost nil, and the left and right eye iris of same person is also not exactly the same.Iris is being developed It is constant to almost just stablizing when two or three years old, therefore the iris with labyrinth can be used as the unique mark of human body.
Iris encryption technology refers to using feature extraction algorithm, and carrying out feature extraction to iris image generates data flow, makees For the key of Encryption Algorithm, it is decrypted using same key during decryption, it is entire with decryption to complete encryption Process.Iris encryption technology is extracted using biological characteristic, to generate unique key, key be it is unique, can not be by other Bion carries out imitated generation.Iris encryption technology is fusion living things feature recognition and encryption technology, generates key and is added Close and decryption processing new technology.
Invention content
Goal of the invention：For the above-mentioned prior art, a kind of iris image encryption method based on convolutional neural networks is proposed, Under the premise of ensureing encrypted high security, solve the problems, such as in CNN training process since iris sample is than few.
Technical solution：A kind of iris image encryption method based on convolutional neural networks, ciphering process include the following steps：
Step 1, the iris image in iris database is pre-processed respectively, iris image collection X is obtained, to X Image block extraction is carried out, obtains iris image block data set X'；
Step 2, the iris image block data set X' is for training four layers of SAE models, by learning per layer parameter W={ W(1),W(2),W(3), W(4), for initializing CNN model convolution layer parameter K={ K(1),K(2)And full connection layer parameter W '={ W ′(3),W′(4), CNN model trainings are then carried out using the iris image collection X；
Step 3, encryption side acquires iris image, and trained CNN models are inputted after pretreatment, realizes to feature vector V1 Extraction, feature vector V1Dimension according to use resume image be adjusted；
Step 4, using RS codes to feature vector V1It is encoded, obtains encryption key Vk1With RS error correcting codes；
Step 5, encryption key V is utilizedk1AES operations are carried out with image array corresponding pixel points gray value to be encrypted, are obtained Encrypted image then completes entire ciphering process；
Decrypting process includes the following steps：
Step 1, iris image acquiring is carried out to decryption side, trained CNN models is input to after pretreatment, realize extraction Iris feature vector V2；
Step 2, using RS error correcting codes to feature vector V2Error correction is carried out, decruption key V is obtainedk2；
Step 3, decruption key V is utilizedk2AES inverse operations are carried out with the encrypted image matrix corresponding pixel points gray value, It obtains decrypted image, then completes entire decrypting process.
Further, in the step 2, in CNN models, section restrictive condition is increased to initiation parameter：SAE is trained The parameter W gone out is limited inIn section, then convolution kernel K={ K in CNN(1),K(2)And full connection Layer weights W '={ W '(3),W′(4)Computational methods be：
nkRepresent kth layer SAE number of nodes, nk+1Represent+1 node layer number of kth.
Further, iris preprocessing is included the following steps：
(1) iris image I0Edge detection carries out Iris Location, realizes iris segmentation I1；
(2) the iris image I extracted1I is normalized2；
(3) by I2Carry out ZCA whitening processings I3。
Advantageous effect：The present invention is based on the iris image Encryption Algorithm of convolutional neural networks, first to the iris figure of acquisition As data are pre-processed, characteristic vector pickup is then carried out to iris image using trained CNN models.The feature of extraction Vector is used for the generation of encryption key, finally uses encryption key and original image array corresponding pixel points gray value to be encrypted AES operations, then can be obtained encrypted image.
Entire encryption is used with the training for first carrying out deep learning model, deep learning model before decrypting process, is needed CNN needs to carry out CNN parameter initializations due to the problem that iris image acquiring difficulty causes greatly sample less.It is trained in CNN It, cannot to ensure that encrypted high security, the generation of key must use whole iris in the process since iris sample is fewer Iris is subjected to image block extraction to make up the problem of sample deficiency.It is carried in view of the above-mentioned problems, carrying out image block to iris first It takes, training SAE models initialize CNN parameters using SAE, and CNN model trainings are carried out using whole picture iris image.So design The few problem of iris sample is not only solved, and has guarantee to the safety of image encryption.
Description of the drawings
Iris image encryptions of the Fig. 1 based on convolutional Neural net network and decryption flow；
Fig. 2 CASIA iris database image patterns；
Fig. 3 iris images standardize；
Fig. 4 iris image ZCA albefactions；
Fig. 5 iris image RS codes encode；
Fig. 6 is trained and test set accuracy.
Specific implementation mode
Further explanation is done to the present invention below in conjunction with the accompanying drawings.
A kind of iris image encryption method based on convolutional neural networks, ciphering process include the following steps：
Step 1, the iris image in iris database is pre-processed respectively, iris image collection X is obtained, to X Image block extraction is carried out, obtains iris image block data set X'.Iris preprocessing is included the following steps：
(1) iris image edge detection carries out Iris Location, realizes iris segmentation；
(2) iris image extracted is normalized；
(3) image after normalized is subjected to ZCA whitening processings.
Step 2, iris image block data set X' is for training four layers of SAE models (Stacked Autoencoder, stack Own coding model), obtain trained parameter matrix W={ W(1),W(2),W(3), W(4), for initializing CNN models (Convolutional Neural Network, convolutional neural networks) convolution layer parameter K={ K(1),K(2)And full articulamentum ginseng Number W '={ W '(3),W′(4), then iris image collection X is used to carry out CNN model trainings.
In CNN models, if initiation parameter can cause there is no limit condition, gradient disappears or what amplitude was spread shows As, therefore section restrictive condition is increased to initiation parameter.CNN convolutional layer propagated forward linearization calculations are：
In formula, z indicates the output of network layer node, ωiIndicate that ith feature figure corresponds to weight matrix, xiIndicate i-th of spy Sign figure, m indicate characteristic pattern number.Assuming that it is being uniformly distributed for σ that meet mean value, which be 0 standard deviation, then every layer of variance formula is：
In formula, n represents the nodal point number of each layer of network, nk-1Indicate -1 node layer number of kth,Indicate -1 layer of input of kth Expectation,Indicate the expectation of -1 layer of weight matrix of kth,Indicate the expectation of -2 layers of input of kth,Indicate the 1st layer of input Expectation,Indicate the expectation of i-th layer of weight matrix, niIndicate that the i-th node layer number, k indicate kth layer network structure sheaf.
It can be seen that from formula, with the increase of the neural network number of plies, ifThen variance can be increasing, production Raw parameter diffusion；IfThen variance can be smaller and smaller, generates gradient and disappears.Therefore, it is also desirable toAt this timeIt can then obtain
In back-propagation process, have：
It can similarly obtain：
In formula, Loss indicates object function,Indicate kth i-th of input feature vector figure of layer,Indicate the 1st layer of j-th of input Characteristic pattern,Indicate that+1 layer of j-th of input feature vector figure of kth corresponds to weight matrix,Indicate that+1 layer of weight matrix of kth corresponds to It is expected thatIndicate+1 layer of ith feature figure of kth.
Parameter is overflowed in order to prevent and gradient disappears, and needs to meet：
Comparing can find that variance at this time produces contradiction, in order to solve this case, calculate variance and use formula：
The modulus value of data x, variance formula, which are, to be indicated for Uniform-distributed Data x ∈ [- a, a], a：
By can be calculated：
Therefore, the parameter that SAE is trained is limited inIn section, nkRepresent kth layer SAE Number of nodes, nk+1+ 1 node layer number of kth is represented, so as to avoid the generation of the above problem.
By trained parameter matrix W={ W(1),W(2),W(3),W(4)Section normalization is carried out, as convolution kernel K in CNN ={ K(1),K(2)And full articulamentum weights W '={ W '(3),W′(4), computational methods are：
nkRepresent kth layer SAE number of nodes, nk+1Represent+1 node layer number of kth.
Step 3, encryption side acquires iris image, and trained CNN models are inputted after pretreatment, realizes to feature vector V1 Extraction, feature vector V1Dimension according to use resume image be adjusted.
Step 4, using RS codes (Reed-solomon codes, RS code) to feature vector V1It is encoded, obtains encryption Key Vk1With RS error correcting codes；
Step 5, encryption key V is utilizedk1AES encryption operation is carried out with image array corresponding pixel points gray value to be encrypted (Advanced Encryption Standard, Advanced Encryption Standard) show that encrypted image, encrypted image, that is, ciphertext are then complete At entire ciphering process.
Decryption is to restore original image information, and decrypting process in general is the inverse operation of ciphering process, but this The algorithm that invention proposes not is complete inverse transformation.Decrypting process includes the following steps：
Step 1, iris image acquiring is carried out to decryption side, trained CNN models is input to after pretreatment, realize extraction Iris feature vector V2。
Step 2, due to V2And V1The difference that there may be numerical value in certain dimensions, using RS error correcting codes to feature vector V2Error correction is carried out, decruption key V is obtainedk2。
Step 3, decruption key V is utilizedk2AES inverse operations are carried out with encrypted image matrix corresponding pixel points gray value, are obtained Decrypted image then completes entire decrypting process.
In order to improve the confidence level and predictability of algorithm, experiment iris data collection uses the public version of CASIA iris databases, Data set is divided into training set and test set, original iris image sample is as shown in Figure 2.The iris image of acquired original includes The unrelated interruptions factor such as face, eyelashes first carries out it Iris Location, segmentation, normalization and ZCA whitening pretreatments, iris Image preprocessing process is as shown in Figure 1.
Pretreated iris image eliminates the disturbing factors such as part face, eyelashes, eyelid, includes only iris portion, Feature identification degree is improved in order to reduce image redundancy, using to iris image ZCA whitening processings, such as Fig. 4.Then RS is carried out Code coding, the purpose that RS codes coding is carried out to iris image are extractions when preventing from carrying out characteristic vector pickup in decrypting process Iris feature vector and the iris feature vector that extracts when encryption it is inconsistent, be so conducive to encryption key and decruption key Successful match improves the probability of successful decryption, reduces operation complexity.
The deep learning model that feature learning is carried out to iris uses CNN, data set to be opened altogether comprising iris image 400, altogether 10 classes, per 40 images of one kind, wherein 300 are used as training sample, 100 are used as test sample.SAE structures use five layers of net Network, it is 5 × 5 that CNN structures, which use five layer network layers, convolution kernel size, and down-sampled step-length is 2 × 2, and the first convolutional layer generates feature Figure number is 6, and it is 12 that the second convolutional layer, which generates characteristic pattern number,.Feature extraction result is shown and setting feature vector comparison, net After network training, training accuracy and testing precision are as shown in Figure 6.
During encrypted, complete to CNN after training, to acquire an eye image, the life of key is encrypted At by encryption key and image to be encrypted progress AES operations, realization ciphering process.It is completed above based on convolutional neural networks Iris image ciphering process.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered It is considered as protection scope of the present invention.

Claims (3)

1. a kind of iris image encryption method based on convolutional neural networks, it is characterised in that：Ciphering process includes the following steps：
Step 1, the iris image in iris database is pre-processed respectively, obtains iris image collection X, X is carried out Image block extracts, and obtains iris image block data set X'；
Step 2, the iris image block data set X' is for training four layers of SAE models, by learning per layer parameter W={ W(1),W(2),W(3), W(4), for initializing CNN model convolution layer parameter K={ K(1),K(2)And full connection layer parameter W '={ W '(3),W ′(4), CNN model trainings are then carried out using the iris image collection X；
Step 3, encryption side acquires iris image, and trained CNN models are inputted after pretreatment, realizes to feature vector V1Carry It takes, feature vector V1Dimension according to use resume image be adjusted；
Step 4, using RS codes to feature vector V1It is encoded, obtains encryption key Vk1With RS error correcting codes；
Step 5, encryption key V is utilizedk1AES operations are carried out with image array corresponding pixel points gray value to be encrypted, obtain encryption Image then completes entire ciphering process；
Decrypting process includes the following steps：
Step 1, iris image acquiring is carried out to decryption side, trained CNN models is input to after pretreatment, realize extraction iris Feature vector V2；
Step 2, using RS error correcting codes to feature vector V2Error correction is carried out, decruption key V is obtainedk2；
Step 3, decruption key V is utilizedk2AES inverse operations are carried out with encrypted image matrix corresponding pixel points gray value, obtain decryption Image then completes entire decrypting process.
2. the iris image encryption method according to claim 1 based on convolutional neural networks, it is characterised in that：It is described to add In the step 2 of close process, in CNN models, section restrictive condition is increased to initiation parameter：The parameter W limits that SAE is trained System existsIn section, then convolution kernel K={ K in CNN(1),K(2)And full articulamentum weights W '= {W′(3),W′(4)Computational methods be：
nkRepresent kth layer SAE number of nodes, nk+1Represent+1 node layer number of kth.
3. the iris image encryption method according to claim 1 or 2 based on convolutional neural networks, it is characterised in that：It is right Iris preprocessing includes the following steps：
(1) to iris image I0Edge detection carries out Iris Location, realizes iris segmentation I1；
(2) to the iris image I of extraction1It is normalized, obtains I2；
(3) by I2ZCA whitening processings are carried out, I is obtained3。
CN201710498746.3A 2017-06-27 2017-06-27 A kind of iris image encryption method based on convolutional neural networks Active CN107330395B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710498746.3A CN107330395B (en) 2017-06-27 2017-06-27 A kind of iris image encryption method based on convolutional neural networks

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710498746.3A CN107330395B (en) 2017-06-27 2017-06-27 A kind of iris image encryption method based on convolutional neural networks

Publications (2)

Publication Number Publication Date
CN107330395A CN107330395A (en) 2017-11-07
CN107330395B true CN107330395B (en) 2018-11-09

Family

ID=60197495

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710498746.3A Active CN107330395B (en) 2017-06-27 2017-06-27 A kind of iris image encryption method based on convolutional neural networks

Country Status (1)

Country Link
CN (1) CN107330395B (en)

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108011712A (en) * 2017-11-13 2018-05-08 佛山科学技术学院 A kind of Mobile medical system private data communication means
CN110211016B (en) * 2018-02-28 2022-11-01 佛山科学技术学院 Watermark embedding method based on convolution characteristic
US11032251B2 (en) * 2018-06-29 2021-06-08 International Business Machines Corporation AI-powered cyber data concealment and targeted mission execution
CN109190453A (en) * 2018-07-09 2019-01-11 奇酷互联网络科技（深圳）有限公司 The method and apparatus for preventing iris information from revealing
CN109389094B (en) * 2018-10-23 2021-04-16 北京无线电计量测试研究所 Stable iris feature extraction and matching method
CN111464304B (en) * 2019-01-18 2021-04-20 江苏实达迪美数据处理有限公司 Hybrid encryption method and system for controlling system network security
CN109995520A (en) * 2019-03-06 2019-07-09 西北大学 Cipher key transmission methods, image processing platform based on depth convolutional neural networks
CN110059589B (en) * 2019-03-21 2020-12-29 昆山杜克大学 Iris region segmentation method in iris image based on Mask R-CNN neural network
CN110427804B (en) * 2019-06-18 2022-12-09 中山大学 Iris identity verification method based on secondary transfer learning
CN110378138A (en) * 2019-07-22 2019-10-25 上海鹰瞳医疗科技有限公司 Data encryption, decryption method and neural network training method and equipment
CN110505047B (en) * 2019-08-14 2022-08-23 江苏海洋大学 Double encryption method for iris feature protection
CN111401145B (en) * 2020-02-26 2022-05-03 三峡大学 Visible light iris recognition method based on deep learning and DS evidence theory
CN111382455B (en) * 2020-03-18 2023-05-26 北京丁牛科技有限公司 File protection method and device
CN111538969A (en) * 2020-03-30 2020-08-14 北京万里红科技股份有限公司 Document encryption method, document decryption device, electronic equipment and medium
CN111639351B (en) * 2020-05-20 2022-03-15 燕山大学 Battery tracing management coding encryption and decryption method based on self-encoder and Henon mapping
CN111654368B (en) * 2020-06-03 2021-10-08 电子科技大学 Key generation method for generating countermeasure network based on deep learning
CN112037211B (en) * 2020-09-04 2022-03-25 中国空气动力研究与发展中心超高速空气动力研究所 Damage characteristic identification method for dynamically monitoring small space debris impact event
CN112668472B (en) * 2020-12-28 2021-08-31 中国科学院自动化研究所 Iris image feature extraction method, system and device based on federal learning
CN112749663B (en) * 2021-01-15 2023-07-07 金陵科技学院 Agricultural fruit maturity detection system based on Internet of things and CCNN model
CN112395635B (en) * 2021-01-18 2021-05-04 北京灵汐科技有限公司 Image processing method, device, secret key generating method, device, training method and device, and computer readable medium
CN112395636B (en) * 2021-01-19 2021-07-30 国网江西省电力有限公司信息通信分公司 Power grid data encryption model training method, system, storage medium and equipment

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006025129A1 (en) * 2004-08-30 2006-03-09 Toyama-Prefecture Personal authentication system
CN1996378A (en) * 2005-12-31 2007-07-11 北京华旗数码影像技术研究院有限责任公司 Embedded device for detecting iris watermark information
CN103917727A (en) * 2011-11-08 2014-07-09 虹膜技术公司 Locking apparatus with enhanced security using iris image
CN104239815A (en) * 2014-09-19 2014-12-24 西安凯虹电子科技有限公司 Electronic document encryption and decryption method and method based on iris identification
CN104992100A (en) * 2015-07-15 2015-10-21 西安凯虹电子科技有限公司 Iris dynamic encryption and decryption system and method for electronic document flowing
CN105354501A (en) * 2015-10-28 2016-02-24 广东欧珀移动通信有限公司 Photo processing method and processing system
CN106095144A (en) * 2016-07-29 2016-11-09 石家庄蜗牛科技有限公司 The mouse of a kind of multi-enciphering and authentication method thereof

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI519994B (en) * 2014-04-29 2016-02-01 華晶科技股份有限公司 Image encryption and decryption method for using physiological features and device for capturing images thereof
CN106096526B (en) * 2016-06-06 2019-03-29 联想(北京)有限公司 A kind of iris identification method and iris authentication system
CN106559424B (en) * 2016-11-16 2019-11-12 北京释码大华科技有限公司 A kind of iris image encryption method, equipment and system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006025129A1 (en) * 2004-08-30 2006-03-09 Toyama-Prefecture Personal authentication system
CN1996378A (en) * 2005-12-31 2007-07-11 北京华旗数码影像技术研究院有限责任公司 Embedded device for detecting iris watermark information
CN103917727A (en) * 2011-11-08 2014-07-09 虹膜技术公司 Locking apparatus with enhanced security using iris image
CN104239815A (en) * 2014-09-19 2014-12-24 西安凯虹电子科技有限公司 Electronic document encryption and decryption method and method based on iris identification
CN104992100A (en) * 2015-07-15 2015-10-21 西安凯虹电子科技有限公司 Iris dynamic encryption and decryption system and method for electronic document flowing
CN105354501A (en) * 2015-10-28 2016-02-24 广东欧珀移动通信有限公司 Photo processing method and processing system
CN106095144A (en) * 2016-07-29 2016-11-09 石家庄蜗牛科技有限公司 The mouse of a kind of multi-enciphering and authentication method thereof

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
An efficient image encryption algorithm based on blocks permutation and Rubik"s cube principle for iris images;Khaled Loukhaoukha 等;《2013 8th International on System,Signal Processing and their Application》;20130919;全文 *
基于虹膜特征的密钥生成和AES算法的图像加密;解瑞云 等;《河南师范大学学报(自然科学版)》;20160907;第44卷(第5期);全文 *
基于虹膜生物特征信息的图像加密方法;柴晓冬;《计算机应用》;20080615;第28卷(第S1期);全文 *

Also Published As

Publication number Publication date
CN107330395A (en) 2017-11-07

Similar Documents

Publication Publication Date Title
CN107330395B (en) A kind of iris image encryption method based on convolutional neural networks
Yuan et al. Fingerprint liveness detection using an improved CNN with image scale equalization
Daugman The importance of being random: statistical principles of iris recognition
KR20220136510A (en) Deep neural network for iris identification
US10922399B2 (en) Authentication verification using soft biometric traits
CN113570684A (en) Image processing method, image processing device, computer equipment and storage medium
CN112101087B (en) Facial image identity identification method and device and electronic equipment
CN114511705A (en) Biological feature extraction method and device for multi-party secure computing system
Wright et al. One-shot-learning for visual lip-based biometric authentication
Cimmino et al. M2FRED: Mobile masked face REcognition through periocular dynamics analysis
Sujana et al. An effective CNN based feature extraction approach for iris recognition system
KR100749380B1 (en) A method for generating invariant biometric code in biometric cryptosystem
Algashaam et al. Hierarchical fusion network for periocular and iris by neural network approximation and sparse autoencoder
Sangve et al. Lip recognition for authentication and security
CN115294638A (en) Iris identification system deployment method based on FPGA, iris identification method and system
Arora et al. Cryptography and Tay-Grey wolf optimization based multimodal biometrics for effective security
Chirchi et al. Modified circular fuzzy segmentor and local circular encoder to iris segmentation and recognition
Rot et al. Deep periocular recognition: A case study
Khalil et al. Personal identification with iris patterns
Sujana et al. Multi-modal Biometric System for Face and Fingerprint using Convolutional Neural Network
KR102651718B1 (en) Device and method for a finger vein recognize based on modified deblurgan
Parvathy et al. FRMSDNET Classifier for Multimodal Feature Fusion Biometric Authentication
US20230274830A1 (en) Method for perceptive traits based semantic face image manipulation and aesthetic treatment recommendation
Vidhya et al. Iris Recognition-A Multilayer Algorithm based: CNN and Transfer Learning
Shashidhar et al. An Efficient method for Recognition of Occluded Faces from Images

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