Method of labelling and identifying signals. RU patent 2510624.
 Associative recognition device / 2504837Associative recognition device comprises P units for calculating an activation function and P groups of units for generating membership function values, wherein each of the P groups of units for generating membership function values includes K units for generating membership function values, inputs of each of which are connected to inputs of like units of membership function values of each of the other groups from the P groups of units for generating membership function values and are inputs of the associative recognition device, wherein the device also includes P groups of multipliers by weight coefficients, each having K units of multipliers by weight coefficients, inputs of each of which are connected to outputs of corresponding units for generating membership function values from P groups of units for generating membership function values, and the outputs are connected to corresponding inputs of P units for selecting the maximum signal, and outputs of each of the P units for selecting the maximum signal are connected to the input of the corresponding unit for calculating the activation function from the P units for calculating the activation function. |
 Method and apparatus for performing user video authentication / 2504004Disclosed is a method of performing video authentication of a user, which comprises steps of: receiving a user-provided authentication photograph; capturing a continuous video image of the user in real time over a certain period of time using a video capturing device at a user client; performing real-time decomposition of the video image and obtaining a series of video data frames; selecting from the series of video data frames a specific number of video data frames and generating at least one contrast image for video authentication of the user based on the specific number of video data frames; comparing the authentication photograph with the contrast image and making a decision on the user video authentication result according to the comparison result. |
 Pattern recognition method, pattern recognition device and computer program / 2487408Method of recognising a pattern in an image comprises the following steps: starting search for a pattern in received images, thereby subjecting the received image to: dividing the image into regions (A1-An), calculating region-specific reference values from region image information, wherein samples are taken only from a part of pixels in a region and reference values are calculated for said region based on the samples taken, comparing the calculated reference values (REF) with stored reference values (REF), and displaying the recognised pattern if a part consisting of adjacent regions (A1-An) is found in the received image, where reference values (REF) of regions correspond to the stored reference values (REF) with sufficient accuracy. |
 Method of identifying signals / 2485586Method of identifying signals is realised by applying essentially different transformations of digital sequences in form of loops to obtain unique shortcut characteristics of said sequences, use as addresses of which allows to cut the number of successive comparisons with references. Reducing operations for comparing the identified signal segment with a reference will drop, in the extreme case, from j operations for comparison on the number of reference signals to two operations: calculating the binary address Bi and determining the identifier Cj of the value of belonging to the reference class. |
 Method of identifying mobile device user from unique signature thereof / 2483355Method of identifying a mobile device user from a signature thereof involves booting the device, launching an application, opening an input window, entering user signature data, digitising said data, determining the beginning and the end of fragments of the entered signature, comparing with a decision threshold, making a decision on personal identification, and unlocking the device in case of a positive decision, wherein the digitised data are broken into an identical number of sections, the signature time is analysed, the obtained time is compared with the time of input of the signature of the true owner stored in the device memory, and the device is unlocked in case of a positive decision on signature identification. |
 Generator of number of financial operation and financial operations carried out with its help / 2479032Generator of a number of a financial operation comprises an electronic processing device, a memory unit, a device for data input and a display. It is arranged as capable of generation of a unique number of a financial operation, which models a number of the main account of a regular credit or a debit card of a financial institution, and which includes an actual number of a subscriber account in a coded form. An issuing bank extracts the inbuilt number of the account and the amount, verifies compliance of the inbuilt and the provided amount (and also performs other standard inspections) and in case of their compliance authorizes the operation. |
 System and method of controlling electronic financial operations / 2479030System includes a means of determining designation of an identifier for determining designation of an identifier provided by a potential subscriber in accordance with circumstances thereof, as well as a response means for issuing a predetermined response in accordance with designation of the identifier. The designation can either be "normal" or "forced". If a "normal" identifier is provided, the subscriber is allowed a normal set of operations. If a "forced" identifier is provided, operations are not allowed, the account of the subscriber is frozen and personnel is alerted on the need to assist the subscriber. As an alternative, a limited number of operations can be allowed and personnel can be alerted. |
 Subscriber id verification / 2479029System for performance of a financial operation between a potential subscriber and a receiving side includes a facility for ID and account verification, including the following: a storage facility, where a biometric identifier of a potential subscriber is stored, and account details, a receiving facility for getting the biometric identifier and account details of the potential subscriber from the receiving side; in which the received biometric identifier is verified by comparison with the appropriate biometric identifier stored against account details, a facility of communication with a financial institution, and a facility for response to the receiving side in response to the request on verification of the biometric identifier and account details of the potential subscriber. |
 Method of classifying fingerprint pictures during personal authentication / 2473125During training, a random number N with length of n bits is obtained; n artificial neurons are created; neuron inputs are randomly connected to memory cells with data on inclination of dermal ridges of fragments of examples of the classified fingerprint picture; further, the neurons are trained to output a random number N when presenting examples of the classified picture; the random number N is the hashed and the reference hash value is stored, as well as the connection of the neural network and its training parameters; and during authentication, there is repeated breaking up of the scanned picture into fragments, calculation of the average inclination on the fragment and the calculated value is transmitted to inputs of the neural network; the hash result is calculated at the output of the neural network and then compared with the reference value; in case of a match, personal authentication is continued, otherwise the authentication procedure is stopped once the time allocated for an authentication session runs out. |
 Method of detecting pornography on digital images (versions) / 2473124Fragments of a digital image similar top human faces are detected in all regions of the digital image; the indicator of the fraction of pixels of skin colours inside the region of a fragment is determined on said fragments; a face is detected if a given threshold value is exceeded; if the threshold value of the fraction of skin colour inside the region of the found face is exceeded, the initial colour palette of human skin is adjusted; outlines of the object of the colour skin are determined; an indicator of geometric similarity of the found outline with typical body outlines is calculated; fragments similar to typical naked body parts are searched; the image is analysed for pornographic visual content. |
 Automatic recognition of symbols on structural background by combination of models of symbols and background / 2249251Method 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. |
 Method for identification of crossed symbols during recognition of hand-written text / 2251736Method 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. |
 Identification device with protected photograph and also means and method for authentication of such an identification device / 2253148Device 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. |
 Portable device for scientific identity identification / 2257613Device 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. |
 Method for facsimile recognition and reproduction of printed product text / 2260208Method 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. |
 Method for recognition of images in optical-digital correlators / 2277257Method 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. |
|
Method for recognition of papillary pattern / 2279128 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. |
|
Method for recognition of papillary patterns / 2279129 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. |
 Method for preventing unsanctioned access to system being protected / 2282240Method 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. |
 Monitoring method / 2282895Method 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. |
FIELD: information technology.
SUBSTANCE: method is realised by inserting an additional feature - the degree measure of the angle - into the signal pattern at each interval thereof, and use thereof along with labels as an identifier in a two-dimensional feature space during identification increases the accuracy of identification and enables quantitative estimation of its value when the analysed signal is compared with a reference signal.
EFFECT: high accuracy of identifying signals with equal labels owing to better utilisation of information which characterises the form of change of the signal in the vicinity of the label.
4 dwg, 3 tbl
The invention relates to the recognition and identification of signals and can be used in systems of restriction of access to protected from third parties services, resources and objects in systems of speech recognition, image, and other applications.
There is a method of validating a signature (US Patent №4190820, IPC G06K 9/00, 26.02.1980), which compares two sequences with marking signs between normalized to a given template segments each sequence by counting the number of these marks in each sequence and compare the results of these calculations to each other. This method is of limited use and lack of accuracy, because a limited number of templates and the individual characteristics of each signature can cause some of the above segments will be attributed not to the template.
There is a method of recognition in real time (US Patent №4783809, IPC G10L 5/06, 08.11.1999). In this way the acoustic characteristics of unknown speech are mapped to the specified templates, resulting in lining up the chain of standard templates which are compared with the stored chains. The disadvantage of this method is the same as the previous one: a limited number of templates is not always able to accurately compare the real sounds of speech.
There is a method of analysis of signals about the state of the object (RF Patent №2090928, IPC G06K 9/00, 20.09.1997), in which the first form several training signals, they create recognize the pattern, and then compare the signal about the state of the object with these recognizing standards. Each pattern is a certain averaging from several teaching signals, and you obviously cannot cover all the diversity of possible investigated signal.
Resolves the shortcomings of the method, which is closest to the claimed (RF Patent №2189075, IPC G06K 9/62, G10L 15/2 10.09.2002). The method consists of the following operations: select a pre-set interval on each of several of the reference signal; treat each reference signal is at a predetermined interval, while integrate at least one pre-specified information setting each reference signal is at a predetermined interval, and determine for each of the preset information parameters of each of the reference signal is at a predetermined interval, the token that represents the point that divides the interval to such part, that the attitude of the integral of this information option on one of these parts to the integral of the same information parameter on the other of these parts is a pre-specified limits, then and memorize all the information about the found markers in a machine-readable database in operations remember; for each signal, subject to recognition, by repeating the operations of selection, processing and storing carry out actions similar to the operation of integration and definitions token; in comparison operations as compared characteristics using markers recognized and reference signals; in operations decision-making take the decision to identify a particular signal, if at least the specified number of markers signal to be identified, with a predetermined accuracy coincides with appropriate markers any of preset reference signals. This method is selected as a prototype.
The disadvantage of this method is low reliability, reflected in the absence of the account of signal form with equal integral characteristics that affect the calculation of the values of the markers following intervals signal during the training phase, and hence the low reliability of recognition of signals only on the markers on the recognition stage.
The objective of the invention is a method that can improve the accuracy of recognition of signals at equality marker (integral values of a signal on the selected interval) through better use of information characterizing the shape of the signal changes in the surroundings of the marker.
This problem is solved by the fact that the actions of the prototype method, including the stages of training and recognition, at the preliminary stage, select the interval value to represent the signal into a sequence of these intervals, for each interval perform integration and determine the token that represents the point that divides the interval to such part, that the attitude of the integral of this information option on one of these parts to the integral of the same information parameter on the other of these parts is a pre-specified limits memorize all the information about the found markers in a machine-readable database, in recognition for each signal repeat select, process and remember for dependencies that are found in the operation of the decision for reference signals, perform the comparison found dependency location of the marker, advanced during the training phase, after the operation signal processing and retrieving the values of the markers perform the following steps: for each reference signal S j , containing intervals with equal values of the markers M i , in the vicinity of the token values allotted the land plot of signal containing at least two meanings: the previous and following the token counts, describing change of physical parameters of the signal in time, between two values of the highlighted portion of the signal relative to the zero value expect additional sign - the value of degree measures the angle
α M ithey complement the ID value of the interval
V M i, two-dimensional vector from the value of the token M i degree and measure of angle
α M iIDs intervals for each of the reference signal S j recorded in a machine-readable memory, at the stage of recognition for each the alarm interval S i define markers M i , for intervals of equal values of the markers M i , in the vicinity of the token values allotted the land plot of signal, containing at least two meanings: the previous and following the token counts, describing change of physical parameters of the signal in time, between two values of the highlighted portion of the signal relative to the zero value calculated value of the degree measure of angle
α M ithey complement the ID value of the interval
V M i, the amount of matching IDs of all intervals
V M isignal S i calculate the indicator of the reliability of reference of the signal S i to the benchmark S j .
The introduction of an additional sign - the value of degree measures the angle
α M ibetween two values of the highlighted portion of the signal in the vicinity of the marker relative to the zero value together with markers prototype - will improve the accuracy of recognition and identification signals, having allocated with equal intervals integral values and markers on the prototype method, but a different form of the signal in the interval. The possibility of using these characteristics in the aggregate more accurately to carry out the process of recognition. The more different physical nature characteristics are taken into account at formation of image recognition, the more full of this image in the space of possible options.
The claimed method is illustrated by drawings, showing:
figure 1 - algorithm explaining the method of marking and detection of signals;
figure 2 - the geometric interpretation of many of the figures with equal areas and one for all figures marker;
figure 3 - scan time peak values of the word "dog" in Russian;
figure 4 - graph digital sample sequence of signal phase corresponding to the consonance of "BA" from the word "dog".
For a better understanding of the essence of the proposed method on the figure 1 presents an algorithm of the method of marking and detection of signals. Between the terminating resistors at the beginning and end (Modelling of systems: Textbook for universities / Baseflow, Saakavili - 4-e Izd., erased. - M: High school. 2005. - P.93) the algorithm consists of separate procedures. Procedure 3, 5-7 correspond to the stage of training, procedures 9, 11-15 meet the recognition stage in the identification signal. Blocks 2, 4, 8, 10 and 14 are blocks of the conditions. Block 1 is a block of data entry, and block 16 - unit of output. Below is a list of rooms that blocks input and output, procedures and blocks the conditions of the algorithm:
1 - Block of input data, considering the following variables and constants:
S - many signals that are subject to recognition;
Z - the maximum level of quantization for the representation of the signal in the form of many digital samples;
n - number of samples in each signal;
m - the number of intervals dividing each signal.
2 - Block execution of the conditions defining the learning stage for a positive outcome or recognition stage and the transition to block 3, negative outcome or formed in the early stages of learning the structure of vectors recognition
V M i, recorded in a machine-readable memory (MPP), the transition to the unit 9.
7 - Unit records vector recognition
V M iin machine-readable memory.
8 - Block the fulfillment of the condition that defines the end of the training period with a positive outcome, and the transition to the unit 2, or continue training with the negative result and the transition to the unit 4.
9 - power calculation procedure marker M i , carries out actions similar to the action of block 3.
10 - Block execution of the conditions defining the calculation of the additional indicative values in the vector recognition
V M i, carries out actions similar to the action of unit 4.
11 - Block allocation interval region (vivo) marker M j .
12 - Unit of calculating the degree measure of angle
α M i .13 - forming Unit vector recognition
V M ifor each interval.
14 - Block execution of the conditions defining the last interval of signal in case of positive outcome, and the transition to the block 15 or negative outcome of the transition to the block 11.
15 - Block of calculation of the index of reliability of recognition of Q, the ratio of the total number of matching vectors recognition
V M isignal S i with vectors recognition of reference signals S j to the total number of intervals signal m.
16 - Unit output value pairs S j the reference signal and the confidence factor Q of reference of the signal S i to the benchmark S j .
Low reliability of the use as a sign of recognition of the value of the token on each interval of signal S i enclosed the procedure of determination of this marker, as total and integral values can not cover all the diversity of signals at equal values of the markers. The confirmation of this fact allows to reveal the geometric interpretation presented on figure 2. Let marker on the interval BF specified point M and forms with the crossing point of the signal period of DM. The number of elementary figures in the form of triangles ΔCBF and ΔEFB, rectangle GKFB and trapezoid with equal values of the area, held by one party through some point D, counts the total number equal to the value of the Z - maximum bit analog-to-digital Converter (in our case, Z=256). This statement follows from the expression that defines the area of a trapezoid R depending on the height of a trapeze and lengths adjacent sides:
P = a + b 2 h , ( 1 )where a, b, adjacent to the height of the sides of the line,
h - the height of a trapeze.
In figure 2 the General height of a trapeze for many trapezes, educated in the limit parallel sections ST. and EF is cut BF. Any period, for example G 1 K 1 , passing through point D on sections of the army and EF, cuts relative to cut BF adjacent to the height of the sections that define the area of the resulting closed geometric shapes on the formula 1. In the case of intersection of the lines of boundary values of a trapezoid degenerate into a rectangular triangles ACBF and DEEV, the area of which is calculated by the formula 1. Different figures with equal values of areas, such as trapeze G 1 K 1 FB, and triangle ΔEFB vary degree measure angles α and beta relatively common side BF. Thus, with equal values of the markers on the interval sufficient and compact presentation of the character of change of the signal in the interval is the degree measure of angle
α M ibetween two values: previous
Z M i - 1and the next
Z M i + 1for token value
Z M ithe highlighted portion of the signal relative to the zero value.
The numerical value
α M idegree measures the angle between adjacent samples of the signal relative to the marker is calculated by the formula:
α M i = arcsin [ Z M i + 1 - Z M i - 1 Z ] , ( 2 )where arcsin - function arcsine,
Z M i + 1- the value following the token neighboring reference
Z M i - 1- the previous value before the marker neighboring reference
Z - the maximum level of quantization for the representation of the signal in the form of many digital samples.
For each interval t and each signal recognition formed IDs recognition
V ( M i ) mas a vector:
V ( M i ) m = [ n M i α M i ] , ( 3 ) where n M i- token value for the method prototype,
α M i- the value of degree measures the angle stated in the way.
Calculation of parameters of reliability Q the assignment of S i to the benchmark S j is calculated by the formula:
Q = Σ ( V M i ) m = 1 m , ( 3 ) when V ( M i ) m = { 1, if d i ≤ dthreshold
0, if d i > d p about R about g , ( 4 )d threshold - threshold value measures in two-dimensional space, allowing the merger of the two vectors in one class recognition.
To calculate measures of similarity d i in two-dimensional space between the vectors a and b is enough to use the Euclidean distance d ab , calculated by the formula (Theory of pattern recognition and scene analysis: Per. from English. / R.O. Duda, Pehart; Under. Ed. Vlasceanu. M: Mir, 1976. - 511 S.):
d a b = ∑ i = 1 k ( a i - b i ) 2 , ( 5 )where k is the number of signs in the vector;
i - the current value of the vector.
The proposed method is in addition to the method prototype. Is carried out simultaneously with the method of the prototype, the procedure of allocation of additional characteristic signs happens after defining token values in the range of the signal.
The implementation of marker method of recognition of signals will be shown by the following example.
There is a signal sequence of sounds in Russian, evolving over time in the phrase "dog". Scan time-amplitude values of the word "dog" in Russian presented in the figure 3. For further analysis of this signal with him conducted the normalization procedure digital signal with a maximum capacity of analog-digital Converter. Graph digital sample sequence of signal phase corresponding to the consonance of "BA" from the word "dog"is presented on figure 4. The selection of the sequence carried out with the aim to show the fact of the equality of markers on equal selected intervals for various forms of signals. So, in the range of 47 times: from 1 to 47 countdown to sound "B" is defined in S 1 and a 283 329 the countdown for the sound "a" is defined in S 2 , for which the sum of readings on the interval equal value 6091. The values of the samples for equal intervals of different signals S 1 of sound "B" and S 2 audio "And" with values equal the amounts of readings on these intervals are given in table 1. From the equality of the sum of the intervals should be the same location markers for these intervals relative to the time of the signal and its ordinal value of reference.
Table 1The values of the samples for signal S 1 of sound "B" and S 2 of the sound "a" and their amounts
n S 1 S 2 n S 1 S 2 n S 1 S 2 n S 1 S 2 n S 1 S 2 ∑ 1 47 S 1 ∑ 1 47 S 2 1 152 124 11 118 197 21 105 101 31 156 114 41 136 245 6091 6091 2 151 145 12 115 190 22 108 177 32 158 139 42 129 209 3 149 187 13 110 158 23 113 218 33 162 168 43 127 97 4 148 234 14 104 113 24 118 203 34 160 171 44 119 41 5 143 219 15 101 118 25 124 181 35 158 150 45 115 20 6 140 114 16 100 147 26 128 94 36 155 125 46 109 58 7 136 37 17 100 134 27 136 67 37 154 112 47 104 137 8 132 6 18 99 93 28 138 67 38 149 131 9 128 46 19 99 52 29 146 80 39 144 173 10 125 140 20 99 42 30 152 99 40 139 218The interval from 47 counts is divided into two equal parts by a serial token value, equal to 23. Adjacent values of the samples on the token are summarized in table 2.
Table 2Values neighboring relatively token counts for signals S 1 of sound "B" and S 2 audio "And"
n 23 Z M i - 1 Z M i + 1 S 1 108 118 S 2 218 181For these values by using the expression 2 calculate degree measure angles for S 1 of sound "B" and S 2 of the sound "a".
( α n 23 ) S 1 = arcsin [ 118 - 108 256 ] = arcsin [0,0390625
] = 2,238 ∘ . ( 6 ) ( α n 23 ) S 2 = arcsin [ 181 - 218 256 ] = arcsin [ -0,14453125
] = - 8,310 ∘ . ( 7 )With the received expressions 6 and 7 of the values of IDs recognition for these areas signals S 1 of sound "B" and S 2 audio "And" are summarized in table 3.
Table 3Identity values for n 23 interval S 1 of sound "B" and S 2 audio "And"
V ( M i ) m n 23 α n 23 S 1 23 2,238 S 2 23 -8,310The calculation of similarity measure d i in a two-dimensional feature space between vectors from table 3, according to the expression 5, in contrast to the zero value for the method prototype, for the claimed method will amount is equal to 10,548. This, in turn, will increase the confidence factor Q of reference of S 1 of sound "B" and S 2 audio "And" to different classes, the calculation of this indicator expressions 3 and 4.
Thus, introduction to prototype method of additional sign - degree measures the angle
α M iand use it together with markers allow to increase the accuracy of recognition and quantify its value in allocating the analyzed signal to the reference.
The analysis of existing methods has allowed to establish that the analogues, identical features of the declared technical solutions are not available, which indicates compliance of the claimed process condition of patentability of "novelty". Introduced distinctive feature is the use of degree measures the angle
α M ibetween two values previous
Z M i - 1and the next
Z M i + 1for token value
Z M ithe highlighted portion of the signal relative to the zero values as additional characterizes the dynamics of change of the signal at equal values of the markers and analogues not found. Therefore, the declared method satisfies the criterion of "inventive step".
Method of marking and detection of signals is applicable not only to speech recognition, as illustrated above, but can be used in many other spheres. This method is applicable also to the recognition of images. Using this method it is possible to identify an exit for limits controlled in various control systems. The stages of way realizable in the current element base.
Method of marking and detection of signals, including the preliminary stage, the stage of learning and the recognition stage, while at the preliminary stage select the interval value to represent the signal into a sequence of these intervals, for each interval perform integration and determine the token that represents the point that divides the interval to such part, that the attitude of the integral of this information option on one of these parts to the integral of the same information parameter on the other of these parts is a pre-specified limits, remember all the information about the found markers in a machine-readable database, in recognition for each signal repeat selection, processing and remember to dependencies found in the operation of the decision for reference signals, perform the comparison found dependency, wherein during the training phase after the operation signal processing and retrieving the values of the markers is additionally carried out the following: for each reference signal S j , containing intervals with equal values of the markers M i , in the vicinity of the token values allotted the land plot of signal, containing at least two meanings: the previous and following the token counts, describing change of physical parameters of the signal in time, between two values of the highlighted portion of the signal relative to the zero value expect additional sign - the value of degree measures the angle , they complement the ID value of the interval in the form of a two-dimensional vector from the value of the token M i degree and measure of angle , IDs intervals for each of the reference signal S j recorded in a machine-readable memory, at the stage of recognition for each interval of signal S i define markers M i , for intervals of equal values of the markers M i , in the vicinity of the token values allotted the land plot of signal, containing at least two meanings: previous and following the token counts, describing change of physical parameters of the signal in time, between two values of the highlighted portion of the signal relative to the zero value calculated value of degree measures the angle , they complement the ID value of the interval , the number of matching IDs of all intervals signal S i expect confidence factor Q of reference of the signal S i to the benchmark S j .