RU2713762C1 - Method of embedding biometric information into a color image of a face and a device for realizing the method - Google Patents

Abstract

FIELD: data processing.

SUBSTANCE: invention relates to a method for embedding biometric information into color images of persons and a device for realizing the method. Method for embedding biometric information into a color image of a face involves analyzing an input color image of a face, determining an original image size and adjusting thereof based on a selected size of the QR code, calculating coordinates of anthropometric points of a face used as basic biometric information on a person, preparing original messages based on biometric information and given document information, generation of QR code "ANTRO" with biometric information and QR code "INFO" with documentary information, performing decomposition of color image of face on components "R", "G" and "B", corresponding to half-tone images, wherein after calculating coordinates of anthropometric points of the face, calculating the face image brightness values used as additional biometric information on the face phenotype, preparing the original message based on the additional biometric information, QR code "PHENO" is generated on this message, control record of QR-codes "ANTRO", "INFO" and "PHENO" is stored in memory and control reading thereof from memory, LSB-layers of half-tone QR-codes "ANTRO", " INFO" and "PHENO", these LSB-layers are embedded in place of LSB-layers of "R", "G" and "B" components, after which these components are combined into a color image which assumes the role of a filled container image, and this color container image is transmitted to the output of the device.

EFFECT: high universality, security of information and reliability of its storage during exchange operations with memory.

2 cl, 11 dwg

Description

The invention relates to automation and computer technology and can be used to create color images of faces with QR codes embedded in them with facial biometric and documentary information. Such color images of faces are designed to create test databases in the tasks of recognizing people, for registration, authentication, and identification of people in access control systems and cross-border control systems. To search for people in video surveillance systems.

There is a method of presenting images of faces and its phenotype within the QR code ("Simplification of face image using feature points" // Jung E., Kim J., Woo S., Kim S. - Proc. 5th International Conference on Soft Computing and Intelligent Systems, Okayama, Japan, 2010, P. 1071-1073). The method is based on presenting the morpho and phenotype of a color image of a person’s face in a compact numerical form and is implemented so that each individual part of the face (hair, eyebrows, lips and facial skin) is represented by one value of the components “Red”, “Green”, “Blue” and one common verbal representation of the corresponding color scheme. The disadvantage of this method is the extremely simplified presentation of information about the person, his primitives and his phenotype, which turned out to be insufficient for the further use of this combined information in practical applications. In addition, the authors of this method faced the problem of the impossibility of placing even this information in the framework of QR codes for the real sizes and characteristics of phenotypes of facial images.

There is a method of presenting facial biometric information in the form of a bar code "Method for forming a bar code from facial images and a device for its implementation" (patent RU 2542886, Bulletin No. 6 of 02.27.2015). The method is based on the procedure for analyzing the input image of the face and correcting the image by size, extracting a set of features representing the face, converting the values of the features into a final bar code. The disadvantage of this method is its orientation to the symbols of linear bar codes EAN (European Article Number), which have a limited information capacity that does not allow the ability to record alphabetic information and special digital characters. The consequence of this is the inability to record in these symbols the necessary information about the face, as well as the image of the face itself.

The main disadvantages of these methods is the fundamental impossibility of implementing barcodes with a wider representation of biometric and documentary information about individuals, as well as insecurity from unauthorized access to biometric information recorded in barcodes. In addition, none of these methods allows the possibility of representing within the barcodes images of faces as separate graphic objects. Together, all this reduces the possibility of widespread use of the proposed solutions for bar coding in biometry and the versatility of its use in biometric applications.

Closest to the proposed invention and adopted as a prototype is a method for generating color QR codes for facial biometrics problems (Kuharev G.A., Kazieva N., Tsymbal D.A. "Bar coding technologies for facial biometrics problems: current status and new solutions "// Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2018. V. 18. No. 1. P. 72-86. DOI: 10.17586 / 2226-1494-2018-18-1-72-86), which consists in the formation of a color QR code based on three different components, selected from the composition of grayscale images of faces and sex tonal QR codes - by placing them on the places of the "Red", "Green" and "Blue" layers of the generated color QR code, moreover, the biometric and documentary information about the face image contains halftone QR codes included in the color QR code.

In the method, the input data is represented by a color image of a person whose original size is defined as: M × N × 3, where M and N are the number of rows and columns of the image, with M> N. Further, in the method, the original face image size is corrected taking into account the selected size of the generated QR code, the size of which is M _QR × M _QR is determined by the ratio M _QR = 17 + 4 × V, for integer values of the parameter V - versions of QR codes 1 <V≤ 40. Then, if M _QR > M, then the input image is enlarged to the size of M _QR × (M _QR (N / M)). Otherwise, the input image is reduced to size M _QR × (M _QR (N / M));

The coordinates of the anthropometric points of the face, which represent basic biometric information, are calculated;

Receive documentary information at a separate entrance and compose messages on biometric and documentary information;

Halftone QR codes generate QR _INFO and QR _ANTRO according to messages, representing them with matrices of size M _QR × M _QR ;

Decompose the color image of the face into components "R", "G" and "B" so that:

where I is the color image after correction, size M _QR × M _QR × 3;

A color QR code is generated by the selected components from "R", "G", "B" and the generated QR codes so that:

where: QR _XXX is a matrix of size M _QR × M _QR × 3, representing the generated color QR code.

The formation of a color QR code according to the described method is associated with the following procedures: analysis of the input color image of the face, determination of the original image size and its adjustment according to the selected size of the QR code, calculation of the coordinates of the anthropometric points of the face used as basic biometric information about the face, preparation original messages on biometric information and preset documentary information, generating the QR code "ANTRO" with biometric information and the QR code "INFO" with documentary and formation, decomposition of the color image of the face into components "R", "G" and "B", corresponding to grayscale images, the formation of a color QR code for three different components from the set {"R", "G", "B" and halftone QR codes "ANTRO" and "INFO"}.

These procedures explicitly determine the entire composition of the blocks of the device that implements the method, and the sequence of procedures determines the communication in the device. This device for implementing the method consists of an input color image analysis unit, a message preparation unit, a message QR code generation unit, a color image decomposition unit, a color QR code generation unit, the first input of the device being the input of an input color image analysis unit, the first the output of which is connected to the first input of the message preparation unit, the second input of which is the second input of the device, the output of the message preparation unit is connected to the input of the QR-code generation unit the output of which is connected to the first input of the color QR code generation unit, the second input of which is connected to the output of the color image decomposition unit, the input of which is connected to the second output of the input color image analysis unit, the output of the color QR code generation unit is the output of the device.

The disadvantages of the prototype are: the impossibility of reconstructing the color image of the face according to the components included in the biometric color QR code, since it can contain only two different components of the three - "R", "G" and "B"; instability of "direct" reading of information from color QR codes; as well as the need for the simultaneous use of several types of color QR code for recording various facial biometric characteristics (for example, except for anthropometry, also the phenotype, and morpho type and others).

The problem of improving the methods for presenting facial biometric information, introducing additional biometric information is being solved. This problem is solved by achieving a technical result, which consists in increasing the universality and security of information, as well as increasing the reliability of storage of biometric and documentary information in the process of exchange operations with memory.

The technical result is achieved due to the fact that the method of embedding biometric information in the color image of the face, which consists in analyzing the input color image of the face, determining the original size of the image and adjusting it for the selected size of the QR code, calculating the coordinates of the anthropometric points of the face used as the main biometric information about a person, preparing original messages on biometric information and given documentary information, generating the QR code "ANTRO" with biometric information and the QR code "INFO" with documentary information, decomposition of the color image of the face into components "R", "G" and "B" corresponding to grayscale images, and differs from the known technical solution in that after calculating the coordinates of the anthropometric points faces calculate the brightness values of the face image used as additional biometric information about the phenotype of the face, prepare an original message from the additional biometric information, generate a QR code "PHENO" p about this message, they carry out control recording of QR codes "ANTRO", "INFO" and "PHENO" in memory and control reading them from memory, select LSB layers of grayscale QR codes "ANTRO", "INFO" and "PHENO", embed these LSB layers instead of the LSB layers of the "R", "G" and "B" components, after which these components are combined into a color image that assumes the role of a filled container image, and this color container image is output to the device.

The method is implemented by a device for embedding biometric information in a color image of a face, including an input color image analysis unit, a message preparation unit, a QR code generation unit, a color image decomposition unit, the first input of the device being an input of an input color image analysis unit, one output of which is connected to the input of the decomposition unit of the color image, the other output of the analysis unit of the input color image is connected to one input of the message preparation unit, the other input to otorogo is the second input of the device, the output of the message preparation unit is connected to the input of the QR-code generation unit, and differs from the well-known technical solution in that it contains a unit for recording QR codes in memory and reading from memory, an LSB layer allocation block from QR -codes, a block for embedding QR codes in an image container, wherein the output of the QR-codes generation unit is connected to the input of the QR-codes recording unit into memory and readings from the memory, the output of which is connected to the input of the LSB layer allocation block from QR codes, the output of which is connected to one input of the unit in traivaniya QR-codes in the image container, the other input of which is connected to the output of the color image decomposition, and an output unit embedding a QR-code-image output device is a container.

Improving the methods for presenting facial biometric and documentary information is achieved by the ability to use various facial biometric characteristics, calculated at the stage of analyzing the input image of the face, and supplementing each biometric characteristic with brief documentary information from its main content, as well as storing all facial information in standard QR codes, embedded as “watermarks” in the LSB layers (Least Significant Bit) of the “R”, “G” and “B” components of the input color image of the face. At the same time, the input color image of the face, which was originally an empty container image, after embedding QR codes in it with the information embedded in them, becomes a filled color image container that compactly represents the input color image of the face and all facial biometric and documentary information him.

Improving the security, versatility and safety of facial information is achieved by using the QR codes embedded in the input image of the face as custodians and carriers of this information, which will protect this information by restricting open access to it, and also create conditions for the exchange of information according to universal standards and international channels without loss of any part of it and / or its substitution. At the same time, the QR codes embedded in the color image do not detect the fact of their existence in it, and the information embedded in the QR codes can be read and decoded only in accordance with the rule for preparing the initial messages when generating QR codes.

In aggregate, all the factors noted will expand the scope of application of the color image of the face obtained by the proposed method, not only in biometry, but also in digital anthropometry, forensic science, medical morphological studies and other applications, and also allow the creation of new types of test databases of facial images for such applications.

The invention is illustrated by drawings:

in FIG. 1 shows a diagram of the process of embedding biometric information in color images of faces;

in FIG. 2 shows a block diagram of a device;

in FIG. Figure 3 shows the procedure for adjusting the size of the input color image (hereinafter, as an example of the input image of the face, we used the image of the CUHK Face Sketch Database CUFS test base located on the site: http://mmlab.ie.cuhk.edu.hk/archive/facesketch .html - X. Wang and X. Tang, "Face Photo-Sketch Synthesis and Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 31, 2009).

in FIG. 4 shows the result of displaying the calculated coordinates of the APT on the face image and a QR code with biometric information embedded in it.

in FIG. 5 shows graphs of pixel brightness values in the coordinates of anthropometric points representing the characteristics of the phenotype of the face, and the corresponding QR code is shown, with additional information on the phenotype embedded in it.

in FIG. 6 shows three components “R”, “G” and “B” and their constituent bit layers for the input color image in a state where this image “is still an empty container image”

in FIG. 7 shows three components "R", "G" and "B" of the input color image, which has switched to the "filled image-container" state, and the LSB layers of the components R "," G "and" B "contain the corresponding QR codes: "ANTRO", "INFO" and "PHENO", as well as all other bit layers;

in FIG. Figure 8 shows the three components of the input color image with other than the figure 6, embedded QR codes. Here, instead of the QR code "PHENO", the second QR code with additional documentary information was used - the QR code "INFO LAB", and this QR code is embedded in the LSB layer of component "B".

in FIG. 9 shows the “R” component of a color image in three states: - in the initial state with the original LSB layer; - as a filled image-container, that is, with the built-in QR code "INFO" in the LSB layer of the "R" component; - with the display of the brightness level - the weighted cumulative sum of the current layers;

in FIG. Figure 10 shows the “R” component (grayscale face image), as a filled container image, the “ANTRO” QR code read from it, the coordinates of the anthropometric points read from the QR code and presented in a regular grid, and other biometric information: a face image with anthropometric points plotted on it according to the original data and “circles” according to the read data.

in FIG. 11 shows an example of original documentary messages and a screenshot of the stage of their comparison with read messages from QR codes "INFO" and "INFO LAB".

A method for embedding biometric information in color images of faces is shown schematically in FIG. 1 and is marked by arrows pointing left to right from the input color image (as an empty container image to a filled one). At the same time, biometric information (the coordinates of the anthropometric points of the face and the brightness values of the pixels of the face image in these coordinates - as an integral characteristic of the face phenotype, size of the input image and morphometric parameters of the face) are obtained directly from the input color image of the face. The necessary documentary information comes with the original color image of the face, as an accompanying document. Based on the calculated biometric and received documentary information, initial messages are prepared according to which three QR codes are further generated. LSB layers of QR codes are embedded in the “R”, “G” and “B” components of the input color image by replacing their LSB layers and, thus, are “watermarks in the form of QR codes” in each of the components R "," G "and" B ". Further, these components are combined into an output color image, which in fact becomes a filled image container.

Depicted in FIG. 2, a device for embedding biometric information in a color image of a face, comprises an input color image analysis unit (BAVCI) 1, a message preparation unit (BPS) 2, a QR-code generation unit (BGQR) 3, a color image decomposition unit (BDCI) 4, a recording unit QR codes in memory and readings from memory (B3QR) 5, a block for extracting the LSB layer from QR codes (BBLSB) 6, a block for embedding QR codes in a container (BBQRK) 7, the first input of the device being the input of the input color analysis block image, one output of which is connected to the input of the color decomposition unit image, the other output of the input color image analysis unit is connected to one input of the message preparation unit, the other input of which is the second input of the device, the output of the message preparation unit is connected to the input of the QR code generation unit, the output of the QR code generation unit is connected to the input of the recording unit QR codes in the memory and readings from the memory, the output of which is connected to the input of the LSB layer allocation block from QR codes, the output of which is connected to one input of the block of embedding QR codes in a container, the other input of which is connected to the output the decomposition unit of the color image, and the output of the embedding unit of QR codes in the container is the output of the device.

A digital digital image of the face is fed to the first input of the device, and the face in the image is the only object that occupies more than 80% of the image area and does not require face detection.

In block 1, the analysis of the input image is performed, including the determination and adjustment of the original size of the face image, the determination of the coordinates of the anthropometric points, the brightness values in these coordinates, and other necessary morphometric data. At this stage, the methods presented are implemented: in the monograph "Methods of processing and recognition of facial images in biometrics problems". -Ed. M.V. Khitrova - St. Petersburg: Polytechnic / 2013 and article by Kazemi V., Sullivan J. "One millisecond face alignment with an ensemble of regression trees" // Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, USA, 2014. P. 1867-1874.

Let the original size of a color image of a face be determined by three dimensions: M × N × q, where M and N are the number of rows and columns of the image, with M> N and aq = 3, for color images. Correction of the original size of the face image is performed taking into account the size of the generated QR code, the size of which is M _QR × M _QR is determined by the ratio M _QR = 17 + 4 × V, for integer values of the version parameter of QR codes 1 <V≤40.

Then, if M _QR > M, then the input image is enlarged to the size of M _QR × [M _QR (N / M)). Otherwise, the input image is reduced to size M _QR × (M _QR (N / M)). In these operations (increase and decrease), the proportion between the width and height of the face is taken into account. Correction ends by "attaching" to the result white fields with a brightness of 255, aligning the image width to the value of M _QR . The original size of the color image of the face is saved for subsequent recording in a biometric QR code. Examples of the described adjustments are shown in FIG. 3.

In block 2, the preparation of the initial messages is implemented by compiling into the data of the "string" type obtained in block 1 of digital data of biometric information and alphanumeric data of documentary information coming from input 2. Here, the methods described in detail in the article by G. Kuharev are implemented , Kazieva N., Tsymbal D.A. “Bar coding technologies for facial biometrics problems: current status and new solutions” // Scientific and Technical Bulletin ITMO, 2018. V. 18. No. 1. S. 72-86.

So, for example, based on 68 calculated coordinates of the face APT:

составляется следующее сообщение M1:two face image size values containing M rows and N columns, and a face name, for example,

The following M1 message is compiled:

which for specific data takes, for example, the following form:

Here, the "#" sign acts as a separator for separating a person’s name from numerical information (which is used, for example, when decrypting a message from a QR code).

The brightness values of the pixels of the color image of the face in 68 coordinates of the APT in the initial form are represented as an array of 68 × 3 numerical values, and in the form of the original message, as a string of 204 numbers formed as a result of the concatenation of 68 × 3 numerical values. In this case, the message M2 takes the form:

Where:

Documentary information, for example, representing the face image test base: CUHK Face Sketch Database (CUFS), the original name of the face input image: 'photo: f-039-01.jpg'

and the site where this database is located:

http://mmlab.ie.cuhk.edu.hk/archive/facesketch.html is written in three short messages with their separator characters:

which are further combined into a common original message:

Messages preserve the semantic structure of digital data of biometric information and the structure of documentary information, which simplifies the process of generating QR codes from them, as well as their decoding and reading messages from them.

In block 3, the procedure for generating binary QR codes is implemented in accordance with the "Program for online generation of QR code with the coordinates of anthropometric points of the image of the face" (certificate No. 2018612643 dated February 21, 2018), the implementation of these

of the procedures are presented in the article: N. Kazieva “Module of an online system for generating a QR code with coordinates of anthropometric points for facial images” // Proceedings of the VII All-Russian Congress of Young Scientists (St. Petersburg, April 17–20, 2018) - 2018. . 2. - S. 28-30. So in FIG. Figure 3 shows the input color image of the face with anthropometric points on it and the result of the generation of the QR code "ANTRO" according to the anthropometric points of the face and its name, as well as the result of the generation of the QR code "INFO" according to the documentary data given above when describing the functions block 2. Under all the images shown their size. QR codes are generated as binary and for the order of the matrices MQR = 117 representing them, which corresponds to the value of the parameter V = 25;

For various biometric applications, other complete sets of QR codes can be optionally generated. For example, one with biometric information, and two with documentary information - basic and advanced, or all three QR codes with biometric information. So the figure 5 shows the brightness values of the color image of the face in 68 coordinates of anthropometric points. These brightness values can be interpreted as an integral characteristic of the phenotype of the face, and the corresponding QR code "PHENO" is shown on the right in figure 5.

However, the total number of QR codes used below remains no more than three.

In block 4, the input color image is decomposed into three components "R", "G" and "B", which mathematically can be represented as:

where I is the input color image represented by the matrix M _QR × M _QR × 3.

As a result of this, we obtain three matrices of size M _QR × M _QR , and each of them contains eight bit layers.

In block 5, control recording of QR codes in memory and reading them from memory are performed. At the same time, QR codes are recorded in the memory as grayscale in the “.png” format, which ensures their presentation without compression noise, ensures complete storage of information in exchange operations with memory, as well as noise-undisturbed restoration of the recorded information during further presentation of QR codes in LSB form - layers (layers with least significant bits).

In block 6, LSB layers are selected from halftone QR codes obtained from block 5. The allocation is carried out using the “modulo 2 capture” procedure in the following way:

LSB _QR = (QR) mod2,

where: QR - grayscale QR-code size M _QR × M _QR , containing 8 identical layers;

LSB _QR - low-order bit layer of size M _QR × M _QR ;

mod2 - take operation modulo 2.

Then for three QR codes - "ANTRO", "INFO" and "PHENO" we get three LSB layers:

In block 7, the selected LSB layers of QR codes are embedded into the place of the LSB layers of the “R”, “G”, and “B” components of the input color image. This is achieved by performing the following two steps: 1. By performing the following three operations of matrix algebra:

where: R _QR , G _QR , B _QR - components "R", "G" and "B" with QR codes embedded in them.

Thus, upon completion of action "1", each component from the composition of R _QR , G _QR , B _QR contains a corresponding QR code built into it with the original message recorded in it.

2. By performing the recording procedure of the components R _QR , G _QR , B _QR into the general graphic object I _QR , which again becomes a color image of the face:

where I _QR is a matrix of size M _QR × M _QR × 3, which is a filled image container.

Upon completion of step 2, the color image of the face I _QR becomes a “filled image-container”, with three QR codes embedded in it containing the original messages recorded in them.

For a more complete and clear understanding of the internal "transformation" of the three components I _QR , G _QR , B _QR during the transition from the input color image I to the filled image-container I _QR , we present graphical examples in FIG. 6 - FIG. 9.

In FIG. Figure 6 shows the three components "R", "G" and "B" and their constituent bit layers for the input color image in a state where this image is "still an empty container image" (shown earlier in Fig. 3). Numbers 1-8 indicate layer numbers. And we pay attention to the fact that in all components the LSB layers (bit layer 1) most resemble random fields of light and dark pixels. It is these LSB layers that will be replaced with the corresponding QR codes.

In FIG. 7 shows three components of an input color image that has already transitioned to the state of a “filled image container”. Numbers 1-8 indicate layer numbers. The LSB layers of the R, G, and B components contain the corresponding QR codes: ANTRO, INFO, and PHENO. It can be seen that the structure of these LSB layers is different from the noise data (shown above in FIG. 6), since the original LSB layer in all components was replaced with the corresponding QR code, while the second to eighth bit layers are original for each component and do not change during the embedding of QR codes in LSB layers (layer 1).

Note that the order of placement of QR codes in the components "R", "G" and "B" can be different, as well as any other QR codes generated in block 3 (as noted above). In addition to this remark, in FIG. 8 and FIG. 9 shows relevant examples.

In FIG. Figure 8 shows the three components of the input color image with other than the figure 7, embedded QR codes. Here, instead of the QR code "PHENO", the second QR code with additional documentary information was used - the QR code "INFO LAB", and this QR code is embedded in the LSB layer of component "B". At the same time, the QR code "INFO LAB" - represents documentary information about the laboratory performing research on the subject of "biometric color QR codes." The full message can be seen in FIG. 11. In FIG. 9 shows the “R” component of a color image in three states:

- in the initial state (that is, as if it were an empty container image) with the original LSB layer;

- as a filled image container — that is, with the built-in QR code “INFO” in the LSB layer of the “R” component;

- with display of brightness level - weighted cumulative sum of current

layers.

The display of brightness levels, in the form of weighted cumulative sums (CumSum) for the current layers, are obtained as follows:

where: S _(i) is the i-th layer, defined for all i, as a binary matrix of order M _QR ;

- весовой коэффициент, учитывающий позицию слоя;

- weight coefficient taking into account the position of the layer;

CumSum (j) is a numerical matrix of size MQR × MQR, the values of which are determined by positive integers d≤255. For j = 8, this matrix represents a grayscale image.

In FIG. Figure 8 shows how the appearance of a grayscale image of a face from layer to layer is restored, and in the final cumulative result, noises from the QR code embedded in the “R” component are completely invisible. This is because the LSB layer (or embedded QR code) contains only the bit values “0” and “1” with a weight coefficient of “1”, and the changes they bring to the cumulative sum are not noticeable to the human eye.

We also note that the reading of all information from the filled container image is carried out by extracting the components "Red", "Green" and "Blue" from the LSB layers, QR codes embedded in them, decoding the messages from QR codes in a standard way, and reading information contained in the messages in accordance with the rule used to prepare the original message. In fact, as seen in FIG. 1, then in this case processes with the reverse movement are realized - from the filled image-container to the empty image-container in the direction from right to left. The results of reading information from a filled container image are shown in FIG. 10 and FIG. 11.

Thus, the proposed method allows to solve both the problem of creating three “watermarks in the form of QR codes” embedded in a color image of a face, and the task of placing both basic and additional biometric and documentary information in these watermarks, and all biometric information obtained directly from the original image of the face, and thus contains objective information about the specific person’s face, transferring it along with the original image of the face and protecting it from simple access to it.

The resulting compact representation of all information, including a color image of the face, additional facial biometric and documentary information in it, will expand the scope of this compact representation in various applications, and the use of QR codes as custodians and carriers of this information will allow for the exchange of data according to universal standards and international channels without loss of any part of it and / or its substitution and will limit unauthorized access to it.

Moreover, a device for implementing the proposed method is performed in the form of a board, which includes at least one signal processor.

Claims (2)

1. The method of embedding biometric information in a color image of a face, which consists in analyzing the input color image of the face, determining the original size of the image and adjusting it for the selected size of the QR code, calculating the coordinates of the anthropometric points of the face used as the main biometric information about the face, preparing original messages on biometric information and specified documentary information, generating the QR code "ANTRO" with biometric information and the QR code "INFO" with document information, performing decomposition of the color image of the face into components "R", "G" and "B", corresponding to grayscale images, characterized in that after calculating the coordinates of the anthropometric points of the face, the brightness values of the face image are used, which are used as additional biometric information of the face phenotype , prepare the original message for additional biometric information, generate a QR code "PHENO" for this message, perform control recording of QR codes "ANTRO", "INFO" and "PHENO" in memory and control To read them from memory, select LSB layers of grayscale QR codes "ANTRO", "INFO" and "PHENO", embed these LSB layers instead of the LSB layers of the "R", "G" and "B" components, after whereby these components are combined into a color image that assumes the role of a filled image container, and this color image container enters the output of the device. 2. A device for embedding biometric information in a color image of a face, including an input color image analysis unit, a message preparation unit, a QR code generation unit, a color image decomposition unit, the first input of the device being an input of an input color image analysis unit, one output of which is connected to the input of the decomposition unit of the color image, the other output of the analysis unit of the input color image is connected to one input of the message preparation unit, the other input of which is T With the device’s input, the output of the message preparation unit is connected to the input of the QR-code generation unit, characterized in that it contains a block for writing QR codes to and from memory, an LSB layer allocation block from QR codes, a QR- embedding unit codes into the container, and the output of the QR-codes generation unit is connected to the input of the QR-codes recording unit into memory and readings from the memory, the output of which is connected to the input of the LSB layer allocation unit from QR codes, the output of which is connected to one input of the QR embedding unit -codes in a container, the other input of which is connected to the output b a color image decomposition lock, and the output of the QR code embedding unit in the container is the output of the device.

Images