Method for dynamic biometric personal authentication based on handwriting features
SUBSTANCE: database of users allowed to access a system is formed from sampled and quantised readings of handwriting samples of a matrix of two-dimensional discrete Haar transform coefficients. When allowing a new user into the system, a matrix of two-dimensional discrete Haar transform coefficients similar to the reference sample is formed from the sampled and quantised readings of handwriting samples of that user. Comparison is carried out and a decision is made to associate the obtained record to one of the reference records.
EFFECT: high reliability of authorised access in systems requiring use of personal identification means.
2 cl, 4 dwg
The invention relates to computing, methods of data processing for biometric measurement, in particular to methods of digital processing of handwritten text. The invention can be used in systems restrict access to protected information by means of biometric identification on the individual characteristics of handwriting in addition to existing means of identification or replacement of these facilities.
The progress made in the field of computer data processing , has removed many of the technical problems on the implementation of systems identification and monitoring by the motor (motor) mechanisms of man, manifested most fully in the process of writing and speech. Engine dynamic characteristics of the individual shall remain in full individuality in the process of functioning of a living organism, which is what makes them the most informative source of human individuality.
There is a method of identification by the peculiarities of the signature (RU # 2148274 from 27.04.2000, G06K 9/22, 9/62, G06F 15/18), namely, that enter in the computer is converted into digital form fluctuations pen reproducing handwriting identifiable person and its pressure on the tablet, calculate differential and integral parameters of the text, cu is IU, additionally calculates the correlation coefficients of these calculated parameters, and compute the estimates of the correlation coefficients, decide on personal identification by comparing the mentioned parameters calculated from their reference values. The main disadvantage of this technical solution is incomplete use of the received information in the form of the dynamic characteristics of vibration of stylus and pressure, which reduces the reliability of the decision.
The prototype of the claimed invention is a method of biometric authentication according to the handwriting in the computerized access control system (RU # 2469397 C1 from 10.12.2012, G06K 9/00) consists in the fact that multi-component analog signal is converted into digital form, forming the matrix of quantized samples, the values of its elements is calculated using two-dimensional discrete cosine transform matrix coefficients, the elements of which are used as identification parameters of the user, any user that logs access control, offer to perform in a similar way the pattern writing handwriting handwriting received multi-channel analog signal is converted into digital form, calculated using two-dimensional discrete cosine transform Mat the Itza coefficients, elements which are compared with the corresponding elements of the matrices of coefficients of two-dimensional discrete cosine transform of registered users in the database, which is recognized by the user is considered incidental reference recording, if the difference is minimal.
The main disadvantage of this method is that the Fourier transform, in particular two-dimensional discrete cosine transform is ill-suited to work with functions defined on a short interval argument, and functions whose value dramatically and significantly changed.
The analysis of the level of technology has allowed to establish that the analogues, characterized by a set of characteristics that are identical to all features of the claimed technical solution is available, which indicates compliance of the claimed method the condition of patentability "novelty".
The aim of the invention is to develop a method of dynamic biometric identity authentication on the peculiarities of the handwriting handwriting, allowing to increase the reliability of the verification of the user.
This objective is achieved in that the determination of the individual characteristics of handwriting produced by the identity matrix, obtained by two-dimensional discrete Haar transformation, this creates a base et the h-parameters of the samples of the handwriting of the user, made in the computerized system, in the form of interval changes each identification parameter, newly introduced to the system user identity is an identity matrix, obtained by two-dimensional discrete Haar transformation, thus calculate the maximum and minimum values of the identifiable parameters, and the decision on the admission of any user in the system is accepted, if the Hamming distance is minimum, which determine the total number of depositions of the identification parameters for the intervals of admissible values of the reference parameters of the samples of the handwriting of users admitted in the computerised system, otherwise form the message about unauthorized attempt logon, the intervals of admissible values of the reference parameters of the samples of the handwriting of users admitted in the computerised system, artificially increased by 20-40% compared with calculated values.
This set of essential features allows you to create a computerized system for the decision support using user authentication on the features of the handwritten text.
The implementation of the method is illustrated by drawings, where Fig.1 presents a conceptual model of the proposed method, Fig.2 - p is intitially scheme of processing of multidimensional analog signal, in Fig.3 shows an example of forming a matrix of two-dimensional discrete Haar transformation, Fig.4 - forming vector quantized samples from a single channel measurements.
The proposed method consists of three consecutive stages: the stage of creating a database of reference parameters of the handwriting of the users who have access to the computerized system, stage recording and processing parameters handwriting handwriting of any user included in the computerised system, and the stage of the decision on admission. These stages are shown in Fig.1.
The first stage envisages the creation of a database of the identification parameters of the samples of the handwriting of users admitted in the computerised system, this involves the following steps. Using a device for measuring motion parameters of stylus, such a device is described in patent RU №2475699 C2 from 20.02.2013, G01B 7/00), issued in the name of the applicant, it is recorded handwriting sample (Fig.2). This patent uses the maximum amount of initial information, analyzing the dynamics of writing handwriting (the trajectory of the writing unit for writing text - curves fluctuations writing site for axis Y(t), X(t), varying the pressure of writing unit for writing text - pressure curve P(t).
The multichannel processing the tax signal is carried out in accordance with patent No. 2469397, G06K 9/00 from 10.12.2012, issued in the name of the applicant. On the basis of a set of quantized discrete samples multichannel signal form the matrix of quantized samples (Fig.3, 4), bearing original information about the features of the writing of the text. For the formation of an identity matrix with the allocation of identification parameters spend two-dimensional discrete Haar transform, described, for example, in the book . Thanks to a more complete representation of the local features of multidimensional signal, missing the Fourier series, wavelets, in particular, the Haar transform, have found practical application for analysis of subtle features of multidimensional signals. Two-dimensional discrete Haar transform includes the processing of the matrix is N×N values, where the first operations are performed with each row of the matrix, and then the same operation is performed for each column of the result. The conversion is performed according to the following method. For example, consider the matrix 4×4:
The first step of the two-dimensional discrete Haar transformation consists of a one-dimensional transform of each row by multiplying the matrix PW. Here we use the matrix W is orthonormal function Haar fourth order :
The next step consists in performing a one-dimensional transform of each column. To do this, the transformation matrix columns transposed, then multiplied by the transform matrix, then the result is again transposed. With the same success it is possible to transpose convert matrix and multiply it by the matrix of the transformed columns:
Here the sign (...)Tmeans transpose. Thus, two-dimensional discrete transformation of the original matrix P will be:
The transformed matrix T contains the average of all elements of the original matrix in the upper left corner (8), and the remaining elements correspond to the differences. Elements, spaced further from the upper left corner correspond to more accurate level of detail, i.e. the higher frequency of elementary waves. The resulting transformations are matrix coefficients of two-dimensional discrete Haar transformation (DDP), which is used as the identification parameters for authentication. When you create a database of registered users in creation mode the master records the handwriting sample is introduced into the system access consistently specified number of times. Each of the entered tolerance handwriting analyze and memorize individually, the calculation parameter identification is carried out with the statistical eskay by validating that the received parameters in one sample. Once generated database scripts users admitted to the system - "Their", it is possible to implement authentication procedures. In the second phase, to verify the identity of any user that logs access control offer by using the above-mentioned device for measuring motion parameters of writing unit (RU # 2475699 C2 from 20.02.2013, G01B 7/00), to capture handwriting sample. Write handwriting sample is carried out repeatedly. The received multi-channel analog signal is converted into digital form. Then form the matrix of quantized samples, which is subjected to two-dimensional discrete Haar transform (detail as was shown above). The resulting matrix is used as the identity matrix and compare with identity verification with the reference matrix database users admitted to the system.
At the stage of decision on admission into the system, when performing authentication procedures as a decision rule we will use a measure of Hamming  the proximity of the identification parameters of the user who logs to the master database settings. The thing is that allowed in user - "My" rarely makes a mistake and, accordingly, a measure of Hamming is small. This is not the case is when trying to authenticate users, not contained in the database - "Other users". For "Stranger", unauthorized included in the system, errors are much more frequent. This allows you to decide on the admission of the audited entity in a computerized system.
After analyzing the current implementation of the vectors of the identification parameters, you can find typical user interval changes each specific identification parameter [min(xj), max(xj)]. Now if by ingestion parameter xjin the interval [min(xj),max(xj)] to assign ej=0, and on a roll of xjfrom the interval [min(xj), max(xj)] to assign ej=1, then we get a vector of Hamming . For a user that is allowed into the system, this vector must be from almost all zeros. When an unauthorized entry into the system by the claimant other identification parameters, the vector of Hamming will have a lot of mismatches (many units). For this method of dynamic biometric authentication pattern recorded during multiple (more than 5-6 times) the verification procedure are the values of the minima and maxima of the measured identification parameters . Then the absolute value of the Hamming distance-Ex to biometric reference user in the database, ledue is defined as the total number of deposition measurements at intervals of admissible values of the biometric pattern. It should be noted that the artificial narrowing of the intervals of admissible values leads to an increase in the probability of error of the first kind with an average size of 0.01 to 0.1, when admitted into the system the user is "Your" rejected the rule of tolerance . It is also shown that the optimum is stretching the field "Your", so that it took from 20 to 40% of the region of possible values of the measure of Hamming. This ratio, on the one hand, allows to have a distribution of values of "Their" close to normal, and on the other hand, to correctly collect information security audit by observing the behavior of "us" and "them" users.
The main advantage of the proposed method in comparison with the known biometric authentication methods is as follows:
- authentication method signature is the usual way the motor manifestations of the dynamic characteristics of the individual;
the handwriting is not alienated from the person, since each person, as each character inherent in private individual features in terms of the peculiarities of handwriting;
- for authentication signature is not required expensive scanner biometric information;
- the possibility of application of a new class of devices dynamic Biomet the practical identity authentication, suitable for use in all areas where it is necessary to identify the person by his signature and retrieve information related to the physiological condition of the person.
In addition, the possibility of improving information security to protect information resources from unauthorized access in existing and new information systems.
The proposed signs are essential as they ensure the achievement of a new technical result, namely provide the opportunity to make the procedure of authenticating identity more credible, independent of the conditions of writing and exclude subjectivity upon admission to the system.
1. S. M. Rusakova, A. S. Komarov. Intelligent system to solve the identification problem in graphology. Artificial intelligence and decision making, No. 4/2010, S. 49-54.
2. SMOLENTSEV, N. To. Fundamentals of theory of wavelets. Wavelets in Matlab. - M.: LVR Press, 2005. 304 S.
3. Computer-aided medical diagnosis http://dvo.sut.ru/libr/biomed/i 132maka/3.htm.
4. Measurement of the proximity of the image to a biometric reference measure Hamming, publ. 30.04.2010, http://razvedka.ru/catalog/582/609/15637.htm.
1. The way dynamic biometric identity authentication according to the features of handwriting, which consists in sampling the polynomial analogue of the first signal, reproducing the dynamics of reproduction of handwritten text, the quantization of discrete samples, the formation of the matrix of quantized samples, converting it to a digital mind, according to the values of its elements calculations identity matrix, characterized in that the determination of the individual characteristics of handwriting produced by the identity matrix, obtained by two-dimensional discrete Haar transformation, this creates a base reference parameters handwriting samples of users allowed in the computerized system, in the form of interval changes each identification parameter, newly introduced to the system user identity is an identity matrix, obtained by two-dimensional discrete Haar transformation, thus calculate the maximum and minimum values of the identifiable parameters, and the decision on the admission of any user in the system is accepted, if the Hamming distance is minimum, which determine the total number of depositions of the identification parameters for the intervals of admissible values of the reference parameters of the samples of the handwriting of users admitted in the computerised system, otherwise form the message about unauthorized attempt login.
2. The method according to p. 1, characterized in that the intervals on the permissible values of the reference parameters of the samples of the handwriting of the user, made in the computerised system, artificially increased by 20-40% compared with calculated values.
FIELD: information technology.
SUBSTANCE: device comprises the pretreatment units of first and second images, the recording units of first and second images, the conversion units of first and second images into a color space YIQ, the enhancing units of the real component of first and second images, the image forming units as a result of rotation of the first and second image, the units of image forming in changing the angle of inclination of the first and second images, the units of storage of simulated images for the first and second images, the unit of application of the method SIFT, the calculation unit of quantity of equal descriptors, the unit of storage of the found pair of duplicates.
EFFECT: ensuring the ability to compare the descriptors applied to the task of searching image duplicates.
SUBSTANCE: device additionally includes a register of criteria codes, a unit of memory of criteria codes, a decoder of criteria codes and a unit of result memory.
EFFECT: increased efficiency of a device due to reduced quantity of requested criteria of recognition for instances, when the result becomes available in advance by the current situation of recognition.
5 dwg, 2 tbl
FIELD: radio engineering, communication.
SUBSTANCE: image recognition device contains a multichannel switch, an ADC, a marker associativity coefficient memory unit, a logical AND unit, a shift register unit, a control unit, a logical OR element, an address register, an address selection memory unit, a buffer register.
EFFECT: device performance improvement.
4 dwg, 4 tbl
FIELD: textiles, paper.
SUBSTANCE: invention relates to a paper sheet processing device. A paper sheet processing device in accordance with the present invention comprises: a unit of image formation, made with the ability to capture an image of a paper sheet and to generate an image of a paper sheet; an identification unit made with the ability to identify symbol of each digital position included in the serial number from the serial number area of the image of the paper sheet; an output unit made with the ability to output an image of the part corresponding to the serial number part of the paper sheet image, when there is a digital position which symbol can not be identified by the identification unit; a display unit made with the ability to display each symbol identified by the identification unit, and the image output from the output unit; and the input unit made with the ability to receive input of each symbol corresponding to the digital position which symbol can not be identified by the identification unit.
EFFECT: improving performance in identification of the symbol.
13 cl, 12 dwg
SUBSTANCE: method includes: estimating a statistical model of positions of anatomical points; training an anatomical point detector; obtaining a three-dimensional image of the region of interest; detecting a plurality of anatomical point candidates; searching for the best configuration of anatomical points among the candidates; constructing view planes based on the found configuration of anatomical points; estimation of parameters of said statistical model is carried out using an annotated plurality of three-dimensional images; the anatomical point detector is trained using energy of said statistical model as parts of a loss function; detection of the plurality of anatomical point candidates is carried out with an anatomical point detector which is trained using said algorithm; the search for the best configuration of anatomical points is carried out using a greedy iterative search of a configuration which minimises said energy of the statistical model. System realises method's actions.
EFFECT: high efficiency of automatic planning of two-dimensional views in three-dimensional medical images.
11 cl, 5 dwg
SUBSTANCE: method for comprehensive inspection of people at checkpoints includes identification based on hand shape and an access code and gas analytical detection of trace amounts of hazardous substances, wherein the beginning of inspection includes personal identification based on a digital code, performing biometric verification of the identity based on hand shape while simultaneously inspecting the hand position on a sampling plate, which includes reading hand parameters and comparing hand parameters obtained from scanning with reference values stored in the database of an inspection and access control system; after removing the hand from the sampling plate, before the beginning of gas analysis, the region where the hand was located is insulated with a protective cover; a gas analyser then automatically moves towards the sampling plate, after which the sampling plate is heated to a certain temperature, and the vapour of the left traces enters the gas analyser; the comprehensive inspection result is sent to the inspection and access control system.
EFFECT: automation and high efficiency of detecting trace amounts of controlled substances on hands, high sensitivity and reliability of detecting trace amounts of substances coupled with biometric verification of a person from hand shape.
FIELD: information technology.
SUBSTANCE: method of authenticating a bank account holder during a remote banking service using biometric properties of the face of the bank account holder is characterised by that when opening a bank account and/or issuing a bank card, a photograph of the account holder is taken and then stored in electronic form in the database of the bank and the bank card memory, and when conducting account transactions using a computer, a mobile telephone, an ATM, a point-of-sale terminal an image of the face of the person conducting a transaction via a web camera, an optical scanner, installed on the used hardware, is transmitted to the database of the bank, wherein the computer of the bank compares the obtained image with the image stored in the database of the bank, and authorises the transaction if the images are identical, or bars the transaction if the images do not match, and the card is blocked by the ATM at the instruction of the card issuer.
EFFECT: high reliability of authenticating a bank account holder.
SUBSTANCE: invention relates to classification of biomolecular data. For this, classification system (100) is used. System input receives multiple attributes (102) of the sample to be classified and multiple appropriate error estimates (104). Statistical module (106) associates probability distribution density functions (108) with said attributes. Note here that appropriate probability distribution density functions depend upon error estimates. Replication module (110) generates multiple disturbed dummy treatments (112). Note here that attributes are arbitrarily disturbed in compliance with apt probability distribution density functions. Classifier (114) classifies disturbed dummy treatments on the basis of disturbed attributes. Analyser (118) classifies the sample to be classified proceeding from the analysis of classified dummy treatments (116) to produce classification (120) of samples.
EFFECT: higher reliability.
13 cl, 6 dwg
FIELD: information technology.
SUBSTANCE: method of searching for copyright infringements on an image, executed on a computer system, involves calculating a descriptor for an image N1, situated in a memory unit N1; calculating a descriptor for an image N2, situated in a memory unit N2; comparing the values of the descriptors of images N1 and N2; if said values are equal, images N1 and N2 are compared, after which the comparison results are displayed on an information display device.
EFFECT: high accuracy, quality and speed of searching for identical or confusingly similar images.
13 cl, 5 dwg
FIELD: physics, computer engineering.
SUBSTANCE: invention relates to classification of image data and more specifically to classification of image data based on a model for adapting to an object in the image data. The system comprises a segmentation unit (110) for segmenting the image data by adapting the model to the object in the image data and a classification unit (120) for assigning a class to the image data based on the model adapted to the object in the image data, thereby classifying the image data, wherein the classification unit (120) comprises an attribute unit (122) for computing a value of an attribute of the model based on the model adapted to the object in the image data, and wherein the assigned class is based on the computed value of the attribute. Thus, the system (100) of the invention is capable of classifying image data without any user input. All inputs required for classifying the image data 10 constitute a model for adapting to an object in the image data. However, a person skilled in the art will understand that in some versions of the system (100), a limited number of user inputs may be enabled to let the user influence and control the system and the classification process.
EFFECT: enabling classification of image data without any data input by the user.
13 cl, 8 dwg
FIELD: automated recognition of symbols.
SUBSTANCE: method includes following stages: tuning, forming symbols models, recognition, recording background model together with background of read image, separating model of registered background from elementary image of background, combining for each position of symbol of model of letters and/or digits with elementary displaying of appropriate background, forming of combined models, comparison of unknown symbols to combined models, recognition of each unknown symbol as appropriate symbol, combined model of which is combined with it best in accordance to "template comparison" technology.
EFFECT: higher efficiency.
10 cl, 10 dwg
FIELD: optical recognition of symbols.
SUBSTANCE: method includes dividing image on areas, finding areas with hand-written symbols, using structural and sign classifiers for recognition of symbols, use of structure classifier as main recognition tool, selecting best suiting symbol of several variants.. recognition of symbol includes recognition of symbol by at least one additional sign classifier of crossed symbols, performing concurrent comparison to crossed symbol and at least one common symbol like the latter, and identification of symbol as crossed one in case of better compliance to signs of crossed symbols.
EFFECT: higher efficiency.
FIELD: identification devices.
SUBSTANCE: device has photographic image of a person and microprocessor, which has processor, memory, connected to processor and containing authentication data, and interface means, connected to said processor to organize communication with external device. Said photographic image has specially concealed information, contents of which when combined with said authentication data provides for authentication of said photographic image, and said microprocessor is made with possible realization of at least a portion of said authentication.
EFFECT: higher efficiency.
5 cl, 4 dwg
FIELD: identity recognition devices.
SUBSTANCE: device has in case in form of small suitcase, a computer, which is compatible to operation systems meant for using programs of scientific identification. Computer is connected to display and keyboard, it can be connected to printer external relatively to case, and presumes presence of remote connection to processing center, responsible for identification. Device additionally has fingerprint reader connected to computer and digital camera connected to computer.
EFFECT: higher speed of operation, higher reliability, broader functional capabilities.
5 cl, 3 dwg
SUBSTANCE: method includes conversion of recognized and standard images to digital form, their digital processing by determining coordinates, comparison and determining of match of recognized and standard contours. Determining of coordinates of line of characteristic contour of recognized image of symbol is performed using appropriate standard graphic image by finding value of coordinates X, Y, angle β of position of optical center of text symbols by superposition along area of printed area of digital images - in straight contrast of standard on appropriate recognized in reversed contrast.
EFFECT: higher reliability.
2 cl, 1 dwg
FIELD: coherent optics, Fourier optics.
SUBSTANCE: method for recognition of images in optical-digital correlators includes procedures for input of amplitude distributions of standard and compared objects into correlator, transformation of these distributions to synthesized phase distributions, receiving correlation between them, registration of received recognition signal and estimation of recognition result, distributions of standard and compared objects, related to arbitrary type objects, are unambiguously matched with phase random distributions Ψst(x,y), Ψ(x,y), synthesized from distributions of standard and compared objects and starting phase distribution Ψo(x,y), utilized further during recognition in optical-digital correlator instead of real objects.
EFFECT: increased trustworthiness of recognition of images of arbitrary class objects.
FIELD: technology for encoding and recognition of papillary patterns, possible utilization in automated biometric informational systems for identification of personality.
SUBSTANCE: method includes generation of three passports, including an additional statistical one and determinate one. Successive execution of comparison procedures of given papillary patterns received from papillary pattern indicator with passports makes it possible to shorten total duration of recognition procedure due to taking a decision about recognition of papillary patter at early stages while satisfying recognition clarity criterions.
EFFECT: increased trustworthiness and speed of recognition of papillary pattern images due to prevented influence of rotation and shifting of compared papillary patterns, automatic consideration of systematic and random errors, decreased duration of recognition procedure.
FIELD: technologies for encoding and recognizing papillary patterns, possible utilization in automated biometrical information systems for identification of personality.
SUBSTANCE: method includes stage of generation of papillary pattern passport with further placement of the latter into computer memory, and stage of comparison of given papillary pattern to passport of papillary patterns, which utilization procedure for comparing two sets of values of electric parameters with arbitrary number of characteristic points, which is performed by full search of sets of characteristic parameters of all characteristic points. In process of full search of sets of coordinates and characteristic parameters, values of electric parameters are selected, matching in two sets, on basis of numbers of coincidences a signal is generated about match of compared sets of electric parameter values.
EFFECT: shorter time and increased trustworthiness of recognition of papillary patterns; prevented influence from rotation and shifting of papillary patterns, increased stability of characteristics and decreased length of papillary pattern passport.
FIELD: engineering of equipment, limiting access to system being protected, possible use for preventing unsanctioned access to system by random individuals.
SUBSTANCE: method includes determining coordinates of certain specifics of papillary pattern of user and on basis of difference of coordinates of produced image of print and one stored in database, positive or negative decision is produced about access of user to system.
EFFECT: increased level of protection of system.
FIELD: method for monitoring marks, made on printed documents.
SUBSTANCE: method includes making a digital image of front side of document by determining content of one-color and multi-color components of image pixels, content of color component of each pixel is compared to range from upper to lower thresholds for appropriate pixel of acceptable unmarked document and appropriate abnormal pixel is generated, if value of pixel is outside interval between upper and lower thresholds, then presence of mark different from dirt is detected, if abnormal pixels produced as a result satisfy previously set conditions.
EFFECT: provision of possible determining of some or other forms of distortion of document.
3 cl, 6 dwg