ES2963861T3 - Method and system to select parameters of a design or security element of banknotes based on neuroanalysis - Google Patents

Abstract

The present invention relates to a system and method for classifying banknotes based on neuroanalysis, comprising: providing a user with visual information of a banknote; acquiring, through sensors of an input module, biometric signals of the user; segmenting the acquired biometric signals into predetermined time periods into a processing module; identify certain events as a result of comparing each of the segments with pre-established patterns; obtain at least one biometric variable based on the identified events; analyze the biometric variables according to previously known results stored in a database; establish a neurometric indicator based on the previous analysis; and classify the bill in an output module according to established neurometric indicators. (Automatic translation with Google Translate, without legal value)

Description

DESCRIPTION

Method and system to select parameters of a design or security element of banknotes based on neuroanalysis

Object of the invention

The present invention refers to the technical field of neuroanalysis of objects through the processing of biometric signals of users exposed to said objects and, more specifically, to the characterization of banknotes and communication materials based on quantifiable information extracted from the biometric signals. , which makes it possible to classify banknotes and communication materials related to them according to an objective perception of users of certain parameters regarding design and security elements.

Background of the invention

Currently, the integrity of any banknote used as a means of payment is guaranteed through the combination of designs and security measures in continuous development, communicating these characteristics through communication materials (communication campaigns, brochures, training material, etc.).

Furthermore, the creation of said banknotes must respond to aesthetic and functional criteria that allow easy recognition, detect their authenticity or simplify their handling while complying with a multitude of technical requirements from both the public and manufacturers and issuing entities. Given that the banknote is a means of communication in itself with which the message expressed in its design is intended to be communicated, the public's requirements should take into account the intellectual and emotional processes of the public on how they perceive these aesthetic and functional aspects. to ensure that the message integrated into the design of the banknotes is received by the public in a manner that is faithful to the communication purpose of the design.

Likewise, communication materials must also be prepared taking into account the intellectual and emotional processes of the public with the objective of generating the greatest possible communicative impact on it, in order to maximize the guarantee that the public has received the training message and, Furthermore, he has understood it as he was expected to. To this end, it is as important to evaluate the content incorporated in the communication materials as the materials themselves (brochures, images, videos, advertisements, etc.) and the distribution of said materials in the different communication channels (web, radio, TV, written press, etc.).

Traditionally, the evaluation of human perception of such aspects of the banknote and related communication materials is justified by decision-making theories that assume that we can intentionally and accurately verbalize our attitudes, emotions and behaviors. Therefore, such theories are based on explicit responses obtained through questionnaires and interviews. However, it has been shown that such explicit measures can be conditioned by “social desirability effects,” which can lead to false accounts of behaviors, attitudes, and beliefs. Furthermore, there can always be different interpretations, leading to results with lower reliability and lower validity. On the other hand, some questions that resort to a user's self-assessment require that people have an open knowledge of their dispositions and this does not always happen.

On the contrary, recent studies demonstrate the considerable influence of implicit processes on psychological constructs and neurocognitive mechanisms of special relevance to humans, such as attitudes, stereotypes, self-confidence, personal relationships, decision making or personal attachment. .

Implicit measures refer to methods and techniques capable of capturing or tracking implicit mental processes or their outcomes, including brain imaging, behavioral monitoring, and psychosomatic outcomes. Neuroscience has shown that our consciousness does not intervene in most of the brain processes that regulate our emotions, attitudes, behaviors and decisions. That is, these implicit processes are brain functions that occur automatically and without conscious control or awareness, which contrasts with explicit processes that occur through conscious executive control.

Neuroscience and, more specifically, measurement techniques based on the biometric response of human beings, have improved greatly in recent years, allowing them to be used in product evaluation studies, digital content and even in real spaces. Obviously, the contribution of implicit measures does not completely invalidate the results and constructions modeled from explicit processes, but rather complements it, since any research activity on human decisions based on data that comes solely and exclusively from explicit process measures It is incomplete and sometimes inaccurate. The document titled “I know what you are reading”, by KAI KUNZE ET, published in PROCEEDINGS OF THE 17TH ANNUAL INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, ISWC 2013, September 8, 2013 (2013-09-08), pages 113-116, DOI: 10.1145/2493988.2494354; ISBN: 978-1-4503-2127-3, discloses a document classification method by measuring the observer's biometric signals.

In accordance with all of the above, having designers, central banks and issuing entities have a methodology based on implicit and explicit measures of the public's perception of banknotes and communication material related to them would be highly beneficial for designing families of banknotes. efficient tickets and communication materials. This efficiency is understood as the combination in the banknote of effective design and security elements that capture the public's attention, adequately communicate the message integrated in its design and facilitate the recognition of the banknote, consequently increasing its security; and the development of banknote communication material capable of generating the greatest possible communicative impact in such a way as to maximize communication to the public of the recognition of the banknote, its design and security measures.

Description of the invention

In order to achieve the objectives and avoid the drawbacks mentioned above, the present invention describes, in a first aspect, a method according to claim 1 for classifying banknotes, based on neuroanalysis, comprising the steps of: providing a user a visual information of a bill; acquiring, by means of a sensor of an input module, at least one biometric signal of the user in response to the visual information of the ticket; segmenting, in a processing module, the biometric signals acquired in predetermined time periods; compare each of the segments with pre-established patterns; identify certain events as a result of comparing each of the segments with pre-established patterns; obtain at least one biometric variable based on the identified events; analyze, in the process module, the biometric variables, according to known results previously stored in a database; establish, in the process module, a neurometric indicator based on the previous analysis; and classify, in an output module, the bill according to the established neurometric indicator.

According to one of the embodiments of the invention, the visual information of the banknote is provided physically, virtually or through a combination of the two in a tangible interface on which virtual elements added to a physical banknote using technology are represented. augmented reality.

The biometric signal according to the invention comprises information about the user's implicit process, being the analysis of gestures in the interaction of the bill with the hands, eye tracking and facial expression analysis.

The biometric signal according to the invention comprises information on a physiological response of the user to be selected between: a brain response, a variation in heart rate and skin conductance.

The biometric variables obtained by the present invention, based on the identified events, are contemplated to comprise quantifiable information of said identified events, to be selected between: number of identified events, average duration of the identified events, frequency of each identified event in a pre-established time, sequence of identified events and number of visits to the same predefined area.

Additionally, the invention contemplates defining at least one area of interest on the ticket and associating the biometric variable acquired from the user to said area of interest. Particularly, in one of the embodiments of the present invention where the visual information comprises a security element arranged on the bill, it is contemplated that the area of interest is greater than or equal to the area of the bill occupied by the security element, and wherein the area of interest includes the area of the bill occupied by said security element. Thus, it is advantageously possible to evaluate each of the elements of the bill separately.

According to an embodiment of the present invention, analyzing the biometric variables according to previously known results comprises training a supervised learning system of the process module according to the following steps:

- repeat the steps of: providing a user with visual information of a bill; acquiring, by means of a sensor of an input module, at least one biometric signal of the user in response to the visual information of the ticket; and segmenting, in a processing module, the biometric signals acquired in predetermined time periods; for a plurality of different tickets and different users;

- group, for each ticket, the identified events of each user, according to a previously established number of groups;

- assign to each bill an initial value of the neurometric indicator, where said value is based on an analysis of the groups of events identified by an expert user.

Additionally, the possibility of analyzing the biometric variables is contemplated through the supervised learning module of the process module, following the steps of: providing the initial value of the neurometric indicator, assigned to each bill in an input of the learning system; apply a predictive model, through the supervised learning system, on the biometric variables obtained by the process module and the initial value assigned; and validate, through a cross-validation process, with a previously determined number of iterations, the predictive model.

The partial metrics of the present invention, defined herein as neurometric indicators, represent one or more of the following cognitive brain processes of the user: visual interest, attention, evoked emotions, motivation, mental load, stress and arousal level.

It is contemplated in the embodiment of the invention that the user is provided with tactile and sound information about the bill.

A second aspect of the invention refers to a system according to claim 7 for classifying banknotes, based on neuroanalysis, which comprises the following elements:

- an input module comprising at least one sensor, configured to acquire a biometric signal from the user, in response to visual information of the ticket provided to said user;

- a processing module, configured to segment the biometric signal into predetermined time periods; compare each of the segments with pre-established patterns; identify certain events as a result of comparing each of the segments with pre-established patterns; obtain at least one biometric variable based on the identified events; analyze the biometric variables according to known results previously stored in a database; and establish a neurometric indicator based on the analysis; and

- an output module configured to classify the bill, according to the neurometric indicator.

Optionally, in one of the embodiments, the output module has display means, configured to visually represent the neurometric indicators of the bill and a final classification metric, based on the neurometric indicators, associated with the visual information of each bill.

The present invention therefore implies a series of advantages over the state of the art. The neuroanalysis carried out by the present invention is very advantageous for the design and incorporation of security elements in banknotes, where unlike the studies known in the state of the art, it contemplates the integration of metrics that quantify the gestural behavior of interaction of the public with the bill, integrates eye tracking techniques to map fixations on the bill, brain measurement equipment synchronized with the evaluation of each bill, integrates the heart rate variability signal as an indicator of the impact at the level of valence and arousal of the bill banknote design and, ultimately, produces a classification of banknotes based on a precise objective characterization of human perception. The classification of banknotes carried out by the method and system of the present invention follows a process that ensures its replicability and comparison between studies carried out with the same equipment anywhere in the world.

The present invention contemplates the generation of a classifier with neurobehavioral impact, which takes into account metrics from the ocular analysis system, physiological metrics and voluntary responses, to provide design impact indicators that help to compare different design parameters with the in order to determine the design and security elements that will make up a ticket.

Brief description of the figures

To complete the description of the invention and in order to help a better understanding of its characteristics, in accordance with a preferred example of its embodiment, a set of drawings is attached where, with an illustrative and non-limiting nature, they have been represented the following figures:

- Figure 1 shows a block diagram that shows the complete methodology followed in an embodiment of the invention.

Figure 2 schematically shows the process of identifying and quantifying the information extracted from an eye-tracking biometric signal acquired in one of the embodiments of the invention.

- Figure 3 shows a block diagram that shows the generation and training process of the classifier used by the present invention.

Figure 4 graphically associates several examples of the signals measured to each user for the calculation of different neurometric indicators. Five different indicators are specifically represented.

- Figure 5 shows one of the possible visualizations provided at the output of a particular embodiment of the invention, where several areas of interest have been defined on the bill associated with both security elements and design elements.

- Figure 6 schematizes the possibilities of presenting objects for the neuroevaluation of the present invention, preferably banknotes, both in real and virtual format, with or without context.

Detailed description of the invention

The present invention discloses a method and a system for classifying banknotes based on neuroanalysis techniques. Thus, it allows determining which design and security elements should be integrated in the manufacture of a new banknote and its optimal configuration, based on the monitoring of certain conscious and unconscious processes of the public exposed to such elements.

Analogously, the present invention can also be applied to communication material for banknotes, which makes it possible to efficiently produce communication materials that emphasize the main characteristics of banknotes in information brochures, both printed and on web pages, of the issuing entities (accessible for example through the Bank of Spain website). In these booklets, each of the security elements of a banknote (such as embossing, watermarks, security threads, portrait windows, holograms, colors, infrared properties, microtexts or response to standard or special ultraviolet light) is identified and highlighted, both visually and through explanatory texts that tell the user how to recognize it, therefore the application of the present invention on said communication material makes it possible to determine, in an analogous way that in the case of evaluating a banknote, its effectiveness in communicating to the public the design and security features integrated into a banknote, based on the monitoring of certain conscious and unconscious processes of the public exposed to such communication materials.

Banknote neurodesign according to the present invention can be applied to a single or all of the elements that are currently integrated into a banknote or communication material. Preferably, it is applicable to the security elements, since the security of any of the elements that are implemented on a banknote to ensure its authenticity does not come only from the technical characteristics of said elements, which prevent or hinder their imitation, but also which also influences the level of security perceived by the public.

Therefore, the public's perception of a security element is essential to improve its effectiveness because if a security element, such as a holographic sheet, even in the hypothetical case where it was impossible to imitate it, were integrated into a banknote in a way that would go completely unnoticed by the user, the effectiveness of said element in the overall integrity of the bill would be null.

The present invention, therefore, increases the effectiveness of the elements that make up the ticket and the communication materials by providing an evaluation thereof based on several implicit measurements of the user, which are obtained as a result of a quantification of detected events, through the comparison with certain pre-established patterns of the user's biometric signals captured by the corresponding sensors arranged in the system. The quantification of conscious and unconscious responses is carried out using techniques from neuroscience and behavioral measurement, which are used to infer, from the events detected in the biometric signals, various biometric variables that characterize said signals during the exposure time of a user to a visual stimulus. From these biometric variables, the existence of patterns in the unconscious responses and their correlations with the evaluation of the elements of the bill under study are verified, obtaining neurometric indicators that classify these elements based on cognitive responses, such as visual interest or Workload.

The classification of the set of biometric variables into neurometric indicators is carried out using supervised learning techniques, such as neural networks. Subsequently, each of these neurometrics is weighted and merged into a single final metric, based on weights defined by a group of experts, which will allow the design or security element or complete ticket or communication material to be characterized at a general level. being analyzed, thus making it possible to determine whether said element is suitable to be integrated into the banknote, to be put into circulation if a complete banknote is being analyzed, or to be disclosed to the public if it is communication material.

Figure 1 shows a block diagram that shows the methodology followed in a complete embodiment of the invention. According to said Figure 1, the present invention contemplates an input 1 that may comprise one or more types of input signals x l =[xj,x^,---,x4], such as real samples of banknotes11, real samples of banknotes with altered security features12, test samples of banknotes that are not in circulation13, or training/education/communication materials on banknotes14. These inputs are entered into a configurable neuroassessment module2 with a given configuration that defines the context21 to be extracted (no context211 may be provided, a real context212 may be provided, or a virtual context213 may be provided), the presentation mode22 of the ticket (it may be a physical presentation mode221 or a virtual presentation222), the users23 to whom the samples will be exposed and the ways24 of obtaining the responses (the response due to human behavior241, the physiological response242 and voluntary responses243 are considered). On the previous inputs, acquired in accordance with the configuration established in the configurable neuroassessment module2, a set of algorithms f l,J-loaded in a neurometric process module3 operate to extract and offer at their output a set of neurometric indicators4, related to the neuroperception of the notex 0 = [x^,x<^, — ,x'^\,which can be shown to the user directly in the output module5 or serve as the basis for a final metric for classifying the notes.

In matrix form, x° = A • xl , with A eMmxn(R) being the neurometric matrix of the banknotes A = quefm,l•fm,naglutinates the set of operations performed in process module 3.

Therefore, the metrics obtained at the output of the process module depend completely on the selected techniques and ways of obtaining user responses. In one of the embodiments of the invention the following responses are contemplated:

- Human behavior response241:

• eye tracking2411: several infrared cameras are arranged to record the pupils of the eyes. After a calibration, where the user focuses on some specific points, the user's gaze is determined by freely available tracking algorithms, referenced in two-dimensional coordinates;

• facial expression analysis2412: a front camera is available to detect gestures on the user's face, which will subsequently be analyzed by applying facial expression analysis algorithms; and • monitoring the user's behavior towards the ticket2413: it includes a compilation of the interactions that the user makes with the ticket, which are obtained through a set of cameras that record their gestures. To do this, several RGB-D cameras are available that, together with specific artificial vision algorithms, allow users to detect and quantify the usual gestures when interacting with the banknote.

- Physiological response242:

• cerebral response2421: a wireless helmet is placed on the user's head, in communication with the rest of the system, for cerebral measurement of electroencephalograms;

• heart rate variability2422, which can be measured, for example, by placing electrodes in the thoracic area or by means of a photoelectric sensor on the index finger; and

• skin conductance2423: optionally it can be measured by applying electrodes to the wrist, the palm of the hand or the middle phalanges of the index and ring fingers to measure skin conductance.

- Voluntary response243:

It does not delve further into the voluntary responses requested from users, since it corresponds to the explicit measures commonly used in the state of the art, that is, those obtained through interviews, questionnaires or other methods usually contemplated.

According to the configuration of module 2, biometric signals are obtained for each of the users at input 31 of the neurometric process module 3. Therefore, the input of the neurometric process module groups the synchronized signals obtained for each user by the corresponding sensors, those related to human behavior, those related to its physiological response and those related to its voluntary response.

These individual signals and measurements collected for each of the users are subjected in the neurometric process module3 to a conditioning process32 that may include techniques to eliminate noise that may have been generated during the measurement process (especially relevant in physiological signals), techniques to rule out possible outliers and techniques for signal normalization if necessary. Conditioning is a necessary process, except for voluntary responses, prior to the extraction of relevant metrics from the signals. Each of the signals used receives specific conditioning as detailed below.

Thus, for example, it is necessary to eliminate excessive noise in the eye tracking signal 2411. Inevitably, this noise will be recorded due to the inherent instability of the eye and, above all, due to blinks, which generate strong signal disturbances. , but these perturbations can be removed depending on the eye tracking recoding device available. It is often the case that the device itself has the ability to filter out blinks, or that it simply returns a value of (0,0) when the eye tracker “loses sight” of the features necessary to record eye movements. In practice, eye tracking data, represented in two-dimensional coordinates, that fall outside a given rectangular range can be considered noise and discarded. Using a rectangular region to denoise the signal (2D) also addresses another current limitation of eye-tracking devices: their accuracy typically degrades in extreme peripheral regions. For this reason (as well as blink elimination), it may be reasonable to simply ignore eye movement data that falls outside the “effective operating range” of the device. This range will often be specified in terms of visual angle.

In the case of signals related to facial expression 2412, conditioning comprises four subprocesses that mainly consist of face detection, feature identification, action identification, and emotion identification. Firstly, all the different frames that make up the video obtained are analyzed to identify the user's face through the application of artificial vision techniques, such as the “Viola Jones Cascaded Classifier” algorithm. Once the user's face has been detected at each of the moments of the test, a detection of the characteristics of the face is carried out using facial coding algorithms, for example, the FACS system ("Facial Action Coding System"), which can identify features such as vectors of the eyelids, corners of the mouth, tip of the nose, etc. This creates a mesh of points that represents the user's face. Based on these characteristics, the so-called “Action Units” are identified by the FACS system, where the fundamental actions of the face are characterized (such as “lowering eyebrows”, “wrinkling the nose”, “ tightening the lips”, “external eyebrow lift”, etc.). Finally, based on the different Action Units identified, a classifier is applied that provides the statistical probability at each moment of experiencing one of the basic emotions, giving a signal from 0 to 1. The emotions included are joy, anger, surprise. , contempt, disgust and sadness. These signals are subsequently corrected using an individualized baseline, using the user's response to a neutral stimulus, thus minimizing individual biases. Therefore, the facial expression signal is finally composed of six independent signals, individually corrected with a baseline, where each of them represents the probability that the subject is experiencing each of the basic emotions at an instant of time. .

For the measurements and signals related to human behavior tracking 2413, the conditioning focuses mainly on the detection of the user's gestures in the video signal, where their hands and interaction with the bill or communication material are observed. First, the video is segmented for each of the tickets, or communication materials, presented to each user. Subsequently, each video segment is analyzed to detect one or more events, for example: “the user turns the bill,” “the user touches the bill looking for a distinctive texture,” “the user turns the bill,” “the user looks at the bill.” bill against the light", "the user manipulates the bill looking for a distinctive sound", "the user folds the bill". The detection of these gestures is preferably carried out through a semi-manual process that, supported by open source libraries, such as "OpenPose" , to characterize the position of the hands, their phalanges and perform an initial identification of the gestures described above, adds a manual review to confirm the correct identification of the gestures detected and processed by the algorithms.

These measures and signals related to the monitoring of human behavior also consider the possibility that the user receives sound and tactile stimuli, as a result of handling the bill, since a bill is usually made with a different paper than that used to write or write. other activities. For this reason, handling the bill produces a characteristic playing sound that cannot be achieved with normal paper, which is one of the most well-known and recognizable security measures for users.

Regarding the conditioning of physiological responses242, the signals and measurements related to the user's brain response 2421 are based on an electroencephalogram (EEG) signal composed of a power signal for each of the electrodes that make up the data acquisition hardware. First, the data from each channel are analyzed to identify damaged channels, using the standardized fourth moment (kurtosis) of the signal from each electrode. In addition, the channel is also considered damaged if the signal is flatter than 10% of its total duration. If a channel is considered damaged, it can be interpolated from its neighboring electrodes. According to one of the particular embodiments, the baseline of the electroencephalogram signal is removed by subtracting the mean and setting a bandpass filter between 0.5 and 40 Hz. The resulting signal is then segmented into periods of one second long. Automatic detection is applied to reject periods where more than two channels contain samples that exceed an absolute threshold, for example 100.00 pV and a gradient of 70.00 pV between the samples. Additionally, an independent component analysis (ICA) is performed to identify and eliminate components due to blinks, eye and/or muscle movements. These components are analyzed through visual inspection by a trained expert to confirm the effectiveness of the algorithms used.

For heart rate variability (HRV) 2422, signal conditioning comprises analyzing an electrocardiogram (ECG) signal, for example through the Pan-Tompkins algorithm, for detection of the QRS interval. This detection allows obtaining a new time series that characterizes the electrocardiogram with the time that passes between beats. To have a good quality signal, the detection carried out by the Pan-Tompkins algorithm is reviewed to detect ectopic beats and artifacts and, finally, a series of RR pulses is obtained that collect the temporal difference between two consecutive pulses and allows the analysis to be carried out. of heart rate variability.

For skin conductance 2423, conditioning consists of a visual inspection for the diagnosis and correction of artifacts that the signal may incorporate. These artifacts are corrected by linear interpolations of the first or second degree. Next, the phasic component of the signal is extracted to the clean signal, which is the one affected by unconscious changes derived from specific stimuli and is not affected by other changes such as temperature. Finally, this signal with the phasic component is standardized using the Venables and Christie formulas to eliminate intersubject differences.

Once the signals have gone through the conditioning process32, the neurometric process module3 applies, signal by signal, algorithms for the extraction of numerical biometric variables of interest33 in each of the conditioned signals. The individual biometric variables of each user are obtained and synchronized with the neuroevaluation phases of the proposed stimuli. This process is repeated for each of the users in the entire sample and for each of the signals recorded in the test analyzed in each case. The values of the biometric variables obtained in this phase generate a database of metrics that is used in the next phase to extract the neurometric indicators, the result of the neuroevaluation of the ticket. Below are some examples of the mathematical techniques applied, according to one of the embodiments of the invention, in each of the signals to obtain the biometric variables that will make up the database on which to calculate the neurometric indicators.

In the case of the eye tracking signal 2411, the process follows the scheme of Figure 2. Thus, in a first step, the basic parameters of the eye tracking 70 are extracted. Through a series of algorithms, the They extract the main parameters of eye tracking, which are differences between fixations and saccadic movements. By fixations we understand the moments in which the eye is focusing on the visual scene to send the visual information to the brain. Saccadic movements mean the movement of the eye in order to focus again on another point of visual interest.

To do this, a detection algorithm is applied to the raw signal, in order to extrapolate whether the analyzed sample is part of a fixation or a saccadic movement. The most used algorithm is the one based on eye speed. By applying a filter to the eye movement with a window of, for example, 0.05 seconds, each raw data of the present embodiment is classified into one of the following two states:

(d> 100 (a/sec) ^ the data is part of a saccadic movement

10< 100 (a/sec) ^ the data is part of a setting

Corrections are calculated across sample groups defined by the fixation, as long as the duration reaches a minimum, set for example to 100 ms. The position of the fixation is defined by the average position of the samples associated with that fixation. Saccade lengths are defined by the distance between continuous fixations.

Additionally, a division of saccadic movements is contemplated, applicable to the vision of the bill or communication material, which divides these eye movements between environmental saccades (those that sweep the bill completely) or focal saccades (those that move around a specific area of the note of interest). In this specific case, to differentiate between environmental and focal movements, the following thresholds are applied:

(8 > 4.8 a ^ ambient saccade movement

18< 4.8 a ^ mov. focal saccade

Once the basic eye tracking parameters 70 have been extracted, in accordance with the above, the translation 71 of the three-dimensional eye tracking parameters to the two-dimensional bill design is carried out. Except for the case in which the bill design is presented on a digital monitor, where the virtual bill is already located from the beginning by the programming of the graphics engine, in the rest of the situations the parameters are adjusted to a three-dimensional coordinate system. , which must be transferred to a two-dimensional model of the bill to facilitate the subsequent calculation of metrics relating to the entire bill and internal areas of interest. To do this, a semi-automatic method is generated that helps to transfer the coordinate system of fixations and saccadic movements from a 3D system to a 2D system, especially centered on the bill that is being evaluated at each moment of the test. This method applies segmentation and object identification algorithms through image analysis to identify the bill under study in space, so that the position of the bill in the 3D coordinate system is known at all times. At the same time and in a synchronized manner, the position of the user's eye is monitored in that same 3D coordinate system, with which a pairing of both values can be carried out on a two-dimensional 2D space, in which the bill can be represented as an image in both faces on which to project the fixations and saccadic movements obtained.

The reference to a “semi-automatic” method is due to the fact that with the previous stages, where the processes are carried out in the first instance by the execution of the algorithm automatically, a manual review by qualified personnel is recommended that allows confirm the results obtained automatically, make corrections where necessary and contribute to fine-tune the algorithms for subsequent analyses.

Following the scheme represented in Figure 2 for the extraction of metrics of interest from the eye tracking signal 2411, in the case of considering the user's visual interest relevant in certain areas of the ticket or communication material, this must be segmented in all the desired areas of interest. Thus, a stage of predefinition of the areas of interest of the bill 72 is contemplated. Each of these areas can cover design elements, security elements or communication elements of the bill about which it is interesting to know the perception of the users. It will only be necessary to mark with a software tool, on each of the faces, the coordinates of the vertices of the areas of interest.

Regardless of whether areas of interest are defined on the banknote, the method of extracting metrics from the eye tracking signal contemplates an extraction 73 of metrics related to the user's visual attention on the entire banknote or communication material in general. These metrics will take into account one or more of the following events: “fixations on the entire bill (on both sides)”, “saccades on the bill”, “blinks of vision on the bill (a measure usually provided by the eye tracking)", “pupil size (a measurement usually provided by eye tracking equipment)". The identification of events in the eye tracking signal encourages the application of a series of mathematical operations to translate these events into quantifiable information , which include, for example: counting the number of events (fixations, saccades, blinks) that occur within the entire bill (on both sides); counting the time each event lasts on average; of definite time or obtain the sequence of these events.

On the other hand, in the event that some specific areas of the banknote or communication material are of special interest and these areas have been predefined in stage72 of Figure 2, the method for extracting metrics from the eye tracking signal contemplates an extraction74 of metrics relating to the user's visual attention on said predefined areas of interest. In this case, an additional basic parameter is previously calculated, associated with the areas of interest, which is the term “visit”. By “visit” we mean a type of event in which more than one continuous fixation occurs and that the time between fixations does not exceed a pre-established time threshold, for example one second. To the metrics with quantifiable information described above, those obtained by “visit” type events are now added, such as detecting whether in the case of visits a visit to the same area occurs again or, in other words, if there are “revisits” and how many.

The extraction of numerical biometric variables of interest33, for the specific case of the facial expression signal 2412, includes characterizing the response of each user to each of the banknotes shown based on several independent emotions identified and processed. To do this, the signals are segmented according to the presentation time of the stimuli, extracting several independent signals that characterize each bill. Three types of variables are obtained from these signals: the first are general metrics, computing the average of the signal in the stimulus (e.g.: average of the probability of “joy”); the second are metrics based on thresholds, in where a function is applied to each signal that analyzes whether the probability of being in a particular emotion is greater than X, to subsequently calculate the percentage of time that the subject has been above said threshold, where said threshold can be defined in two levels, for example 0.5 to detect the percentage of time that the subject has been experiencing that emotion, regardless of intensity, and 0.8 to calculate the percentage of time that the subject has been intensely experiencing that emotion; , the third type of metrics are ratio metrics, such as the ratio between positive and negative emotions.

For the biometric variables monitoring human behavior 2413, based on the conditioned signal, the number of times a gesture is executed while viewing a bill is counted and the percentage it represents compared to the total number of gestures.

Of the signals associated with the brain response 2421, the extraction of numerical biometric variables of interest includes, from the signals conditioned after the conditioning process32, a spectral analysis of the encephalogram signal to estimate the spectral power in each second, within the classical frequency band: 0 (4-8 Hz), a (8-12 Hz), p (13-25 Hz), and (25-40 Hz). According to one of the embodiments, it is carried out using the Welch method with 50% overlap, from which metrics are derived that characterize the power of each of the bands in each second and, from them, other metrics are derived. such as frontal asymmetry, which can be interpreted as the amount of motivation (approach) or rejection in the face of a stimulus. It is defined as:

Frontal Asymmetry Index = \nr KA Alp l ph ha a p po ow we er r r li es fh tt FF34)', with F4 and 1F3 being the electrodes placed in that position according to the international 10-20 system.

In addition to metrics derived from spectral power, in one embodiment of the invention those that characterize cognitive states are also calculated. These variables use previously trained classifiers that, based on some initial tasks that the user must perform to calibrate the classifier, allow predicting the level of “engagement” and “workload”. “Engagement” reflects the general level of engagement. , commitment, attention and concentration during visual scanning to collect user information, while “workload” refers to any cognitive process that involves an executive process, such as analytical reasoning, problem solving or memory. of work.

The extraction of numerical biometric variables of interest33, for the specific case of the heart rate variability signal 2422, includes three types of variables: those derived from the time domain, those derived from the frequency domain and those that quantify non-linear dynamics.

The time domain analysis includes the following characteristics: mean and standard deviation of the RR intervals, the square root of the mean of the sum of the squares of the differences between adjacent RR intervals (RMSSD), the number of successive differences of intervals differing by more than 50 ms (pNN50), the triangular interpolation of the heart rate variability histogram (h Rv) and the reference width of the RR histogram evaluated by triangular interpolation (TINN).

The characteristics in the frequency domain are calculated using the power spectrum density (PSD), applying the Fast Fourier Transform. The analysis is performed in three bands: VLF (very low frequency, <0.04 Hz), LF (low frequency, 0.04-0.15 Hz) and HF (high frequency, 0.12-0.4 Hz) . For each of the three frequency bands, the maximum value (which corresponds to the frequency that has the maximum magnitude) and the power of each frequency band are calculated in absolute and percentage terms. The normalized power (n.u.) for the LF and HF bands and the percentage of total power are calculated, previously subtracting the VLF power from the total power. The LF/HF ratio is calculated to quantify sympathovagal balance and to reflect sympathetic modulations. Additionally, the total power is calculated.

Finally, several features are also extracted using non-linear analyses, as they have been shown to be important quantifiers of cardiovascular control dynamics. First, a Poincaré analysis is applied, which is a visual and quantitative technique, in which the shape of a plot is classified into functional classes, providing summary information on the behavior of the heart. A transverse axis (SD1) is associated with rapid beat-to-beat variability and a longitudinal axis (SD2) analyzes long-term R-R variability. An entropy analysis is also included, using existing state-of-the-art methods such as “Sample entropy” (SampEn), “Approximate entropy” (ApEn) and DFA correlations.

For the conductivity of the skin 2423, from the clean signal that represents the phasic component of the EDA (electrodermal activity), two types of biometric variables will be generated that characterize the user's activation level when viewing a ticket or communication material. The first type is made up of the average of the signal in the segment of each stimulus, while the second type of variable analyzes the peaks experienced by the user while viewing the bill. These spikes will be characterized by the number of spikes per minute and their average amplitude.

Regarding the extraction of biometric variables from the user's voluntary responses 243, if tasks such as ticket recognition, reading or viewing communication material are incorporated, these responses are quantified with the percentage of successes and failures. In addition, the average response time in each of the tasks is calculated. Examples of interviews and questionnaires carried out are the following: after viewing each banknote (front and back) on the monitor by the user, questions are asked about certain semantic axes such as aesthetics, quality, design, durability, pleasure or emotional aspects, in addition to an unconscious evaluation and association of open attributes for each of the bills; After viewing all the banknotes by the user, a questionnaire consisting of questions is completed to find out which banknotes, what security elements are remembered, where on the banknote a certain security element is located or what content the communication material incorporates, and recognition questions that show images of banknotes that ask the user whether or not they were shown during the test; After the physical interaction with each banknote by the user, a questionnaire is completed to evaluate the physical support of the banknote (paper, plastic or their variants) or the communication material and attributes similar to the previous phase, but adding attributes related to the manipulation of the bill such as geometry, texture, sound and/or relief.

After the complete stage of extraction of biometric variables of interest 33 with quantifiable information from the conditioned signals 32 previously obtained through the different biometric sensors, according to the configuration established in the configurable neuroassessment module 2, and presented in entry 31 of the module of neurometric process, the neurometric process module 3 of the present invention applies a classification algorithm in a predictive module 34, to obtain at the output a set of neurometric indicators 4 of the user's neuroevaluation.

The classification algorithm, which will later be applied to each of the users' responses on the banknotes, needs to be previously calibrated. Figure 3 comprises a block diagram that represents the two parts into which the calibration is divided: first the generation of a true reference set 300 ("ground truth" in English) and, second, the creation of the predictive model 310. Thus, for the generation of the true reference set, the biometric variables 33 obtained for a set of banknotes will be used, for example one hundred banknotes. Preferably the set of banknotes covers the widest possible range of responses at a cognitive, emotional and emotional level. This set is preferably chosen by a multidisciplinary team of experts selected from different fields/sectors (such as banking, psychology or neuroscience) and contains both real banknotes and ad-hoc designs that guarantee a large disparity of responses. 301 only the biometric variables related to the neurometric indicator, from the set of neurometric indicators 4, which is being generated at each moment (some examples are included later of the relationship between the selected biometric variables and the different neuroassessment indicators). With the values of the metrics selected in the set of banknotes or communication material evaluated by each of the users, an unsupervised clustering-type machine learning algorithm (k-means) is applied to group 302 the banknotes based on their answers. In this way, the hundred bills are divided into different groups according to their response in the different metrics that make up the indicators. Subsequently, the mean of each group is calculated, which represents the average response in each group. The team of experts validates 308 the groups and analyzes in depth 303 the responses of each group based on their average and assigns a value 304 of the indicator to this group of banknotes, for example following a Likert scale from 1 to 5.

Once the reference set of the one hundred banknotes in the example has been generated 300, where each one has been assigned 304 a value in each of the indicators, we proceed to create 310 the classification model. To do this, a data set is created where the inputs are the selected biometric variables 301 and the output is the value already assigned 304 to the corresponding neurometric indicator. With this set of data, the predictive model 306 is designed based on artificial neural networks. The training 305 of the neural network, which is fed with the selected metrics301 and the assigned values304, is validated307 by applying a k-iteration cross-validation algorithm with a k of 10 and, subsequently, the model is tested with 15% of the sample , which has been previously extracted from the validation process. Once the predictive model306 has been validated and tested, it can be applied to the biometric variables of any banknote, giving a rating on each of the neurometric indicators.

The output of the predictive module34 includes the indicators generated according to the predictive models obtained, which are applied to the numerical biometric variables of interest33 and produce as a result a value for each of the neuroevaluation indicators of each banknote for each user.

Figure 4 shows a diagram with the measured signals of each user to be taken into account for the calculation of certain indicators. According to one of the embodiments of the invention, in which five indicators are contemplated, for the calculation of a first visual interest indicator 41 (BVIS) the human behavioral responses241 represented by eye tracking signals2411 and facial expression analysis2412 are considered relevant. , none of the physiological responses are necessary242 and voluntary responses in the form of interviews2433, questionnaires2434 and response to tasks2431 are taken into account; For the calculation of a second engagement indicator 42 (BEI), the human behavioral response241 represented by eye tracking signals2411, the physiological responses242 represented by the brain response2421 and heart rate variability2422, and voluntary responses in the form of questionnaires2434 are considered relevant; For the calculation of a third workload indicator 43 (BWI), human behavioral responses241 represented by eye tracking signals2411, facial expression analysis2412 and user behavior tracking2413 signals, physiological responses242 represented by the brain response2421 and responses are considered relevant. voluntary in the form of response to tasks2431 and reaction time2432; For the calculation of a fourth emotional indicator 44 (BEII), human behavioral responses241 represented by facial expression analysis2412, physiological responses242 represented by heart rate variability2422 and skin conductance2423, and voluntary responses in the form of interviews2433 and questionnaires2434 are considered relevant. ; For the calculation of a fifth safety indicator 45 (BSCI), human behavioral responses241represented by eye-tracking signals2411and user behavior tracking2413, physiological responses242represented by skin conductance2423and voluntary responses in the form of an interview2433 are considered relevant. questionnaire2434, response to tasks2431 and reaction time2432.

The Banknote Visual Interest Score (41BVIS) is a metric related to the visual interest aroused by the banknote design. This high-level metric focuses on a non-linear model that establishes a score of the interest at a visual level that the perception of the bill design generates and that allows its comparison between different types of design. To do this, the indicator is calculated through supervised learning techniques applied to the biometric variables of interest33, extracted from the selected conditioned signals. , which contain quantifiable information and which in this embodiment specifically includes:

• metrics related to the viewing time of the areas of interest related to the design of the ticket or communication material vs. the viewing time of security zones or other areas of interest relative to the content of communication materials;

• metrics relating to the total time spent viewing the ticket or communication material versus visual navigation away from the ticket or communication material;

• metrics related to how the eye scans the bill or communication material and the relationship between scanning (environmental saccades) and focusing (focal saccades);

• metrics related to the sequence of the gaze in viewing the design elements of the ticket or communication material vs. the security elements or other area of interest related to the content of the communication materials;

• ratio of quadrants per second of the bill that the user's eye navigates, dividing the bill into a certain number of quadrants;

• percentage of bill scanned; and

• ratio between the number of wide movements vs. short movements of the eye within the bill.

Additionally, in this indicator of visual interest, some values related to the voluntary response are considered as a global assessment of the design of the evaluated banknotes; memory of banknotes and areas of interest on the banknote; and the times allocated to carry out the ticket evaluation tasks.

One of the cognitive indicators, the engagement indicator42BEI (from the English “Banknote Engagement Index”), refers to the level of sustained functional attention that the person is applying to the perception of the banknote or communication material. This indicator is of great interest because it reflects whether the ticket or communication material arouses enough interest to focus on it. Furthermore, it allows us to discern whether the subject is focused on the task and therefore the rest of the metrics obtained at that moment are of value.

One of the cognitive indicators used in one of the embodiments of the present invention, the workload indicator 43BWI (Banknote Workload Index), refers to the cognitive load or mental effort that the perception process entails for the subject. and assessment of certain attributes of the ticket or communication material.

It is very important because a high cognitive load can mean that there is information saturation, which leads to rejection, but at the same time a low value can indicate boredom of the subject, which is also negative.

In one of the embodiments of the invention, a cognitive indicator is contemplated that combines the two previous ones, engagement indicator42BEI and workload indicator43BWI.

The emotional indicator 44BEII (from the English “Banknote Emotional Induction Index”) used in one of the embodiments of the invention, is a metric related to the emotional induction capacity of the banknote or communication material. Specifically, the BEI indicator is based on the calculation and representation of a point on a two-dimensional spatial axis in which the capacity for emotional arousal (arousal) and the capacity to generate a positive or negative emotion (valence) are extracted. To calculate these two dimensions that support the BEII indicator, use is made. from the processing of the signal coming from behavioral measurements (for example, facial micro-expressions while viewing the bill) and from the physiological response (asymmetry of the cerebral hemispheres, cardiac variability and skin conductance).

The security indicator 45BSCI (Banknote Security Capacity IndeX), used in one of the embodiments of the invention, is a metric relating to the security of the banknote. Specifically, this indicator reflects the ability of the design and security elements of the bill to be authenticated by the public. Its calculation is based on several parameters related to the behavioral signal (such as eye tracking of the security elements of the bill, automatic tracking of the participant's interaction gestures with the bill) and voluntary response values of the subject. Through the modeling of these parameters, an absolute index can be obtained that allows the comparison of new designs and security elements on the same banknote or the comparison of current designs and security elements of different types of banknote.

Once the predictive models306 have been applied to the selected biometric variables, which contain numerical metrics of interest with quantifiable information, and the neuroevaluation indicators have been obtained for each ticket or communication materials, these indicators are processed in an output module5 equipped with different functionalities. In this output module5, neurometric indicators4 are treated statistically to successfully characterize a banknote or communication materials. On the one hand, the general response of the banknote, or communication materials, is measured using data aggregation techniques (for example the arithmetic mean or standard deviation) and, on the other hand, depending on specific conditions and cases, the different additional analyzes were carried out to determine if there are significant differences that allow inferring final conclusions related to the objective of the neuroevaluation study. For example, in addition to mean comparison techniques, correlation techniques and clustering techniques can be used. All of this statistical analysis is implemented automatically ensuring reproducibility and comparison of the same studies completed on multiple dates and in multiple locations. Therefore, the statistical inference analysis extracts the significant differences in the biometric variables with numerical metrics of interest33. By contrasting different models, such as analysis of variance or Kruskal-Wallis test, the indicators calculated according to different groupings are compared. These analyzes are applied to analyze the differences in neurometric indicators between different banknotes presented and/or the differences with different designs of the same banknote (due to changes in the design, size or position of elements of the banknote design), which may be weighted by additional factors such as the user's gender, age or familiarity with cash handling.

Subsequent to the calculation of the indicators, in one of the embodiments of the invention, the output module5 calculates a final metric that encompasses all the calculated indicators and offers a snapshot of the performance of the banknote, or communication material, which allows a quick assessment, comparison and classification against other banknotes evaluated. This final metric is based on a score from 1 to 10 through a mathematical equation in which each of the calculated neurometric indicators influences with a certain weight.

The higher the score, the better the performance of the evaluated design. If in any case you want to dispense with an indicator, the model recalculates the value, canceling the impact of the value of that neurometric indicator. In this way, the indicator is dynamic and reflects only the indicators that are of interest in each specific case (for example, the previous final score can be recalculated so that it only reflects the impact of the visual and cognitive indicators or even only one of them). .

One of the embodiments contemplates the graphic representation, for example through heat maps, two-dimensional axes, curves or percentages, of all the biometric variables, neurometric indicators and statistical inferences obtained during the process carried out by each of the modules of the invention. . Figure 5 represents one of these particular visualizations, where one side of a bill is represented and, associated with each of the defined areas of interest, the values of the indicators (not shown in the figure) obtained for said areas of interest are represented. . For example, for an area of interest defined to encompass a security element incorporated into the banknote, such as a hologram52, a watermark53, a special ink imprint54, or a window55, the represented indicators encode the neuroevaluation obtained from the users' perception of that security element. In one embodiment, a score in percentage of visit time, visitors and return visits is associated with each of the areas of interest, which is also complemented by a heat map and the sequence of visits of the different areas. areas of interest. For example, after analyzing the area of interest that includes the hologram52, a visit time of 14.92% of the total time invested in inspecting the bill is obtained, 86.53% of users who have observed it and 78.72% of users who have revisited it. These types of measurements are what make it possible to build the indicators for the comparison between banknotes, comparison of elements and classification.

In one of the embodiments, the present invention classifies in the output module5 a complete sample of banknotes according to the indicators obtained associated with the areas of interest that include security elements. The level of security of the security elements is determined by public perception and is a determining factor in evaluating their incorporation in future legal tender banknotes. The classification of banknotes based on the users' perception of the security elements allows security elements to be selected between acceptable and unacceptable to be incorporated into legal tender, establishing a minimum threshold in the indicators to determine that the perception of the public of the security element is sufficient to be incorporated into the banknote. These minimum thresholds can be calibrated using modified security elements and analyzing how users' perception varies with modifications to different security elements. Thus, the modified security elements that obtain a better classification in the perception of users will be the most appropriate security elements to be incorporated into legal tender banknotes. Considering, for example, eye tracking signals, the number of revisits by the user to the security element or the time spent viewing said element with respect to the rest of the ticket is decisive.

Apart from the comparison between elements of the same type, in one of the embodiments of the invention it is particularly advantageous to monitor the influence of some parameters on others and, mainly, the influence of the variation of one parameter on another. For example, the color of the bill versus the perceived security of a certain security feature. If the objective is to determine the color of the banknote that provides the most security, the set of banknotes that will be subjected to neuroanalysis will differ only in the color of their design, but will keep their security elements unchanged. The neuroanalysis of user perception will make it possible to determine whether color variations have an influence on the perception of security elements, characterize the different banknotes based on the users' perception and finally classify them in an orderly manner in an objective manner, with the banknote being The best classified is the one corresponding to the most appropriate color for the security of the bill. For example, a gray color for the bill could greatly nullify the security of a hologram-type element or a metallic appearance security thread element, which would be practically camouflaged and go unnoticed by a user. That is, according to the approach of the example, the classification will indicate how each of the test colors disturbs the perception of the security elements integrated into the banknote, so the final classification determines the color to be included in the banknote. manufacture.

In accordance with other objectives that pursue the design of other banknote parameters other than color, such as the size of the banknote, the size of a certain element, the position of a certain element or the use of different materials, banknote samples and the areas of interest are selected so that it is precisely those parameters that vary from one banknote to another and, in an analogous way to the previous case, the characterization of the users' perception objectively indicates the influence that these parameters have. on the ticket. For example, defining an area of interest56 that includes the value of the banknote (50 euros, for example), it is interesting to compare the influence that different sizes and positions have on the perception of the design and security elements of the banknote. In this specific case, the watermark53 may have its perceived security affected by a certain size of the representation of the banknote value, or a position that is too close, since it attracts the user's visual attention excessively and would nullify or reduce the perception. of the watermark, which reduces the security of the banknote for the user. Even other elements of the bill that apparently have no more than a purely aesthetic function, such as the decoration collected by the area of interest57, are also important in the overall evaluation of the bill and their color, size or position can influence its security. , so in one of the realizations the analysis of absolutely all the elements of the bill is contemplated.

In addition to the graphical representation shown in Figure 5, other comparative results are contemplated that can be displayed graphically. Mainly, the comparison of viewing times of the areas of interest associated with normalized billet design elements in reference to the physical space they occupy is contemplated; curves of the effect of position vs. the BVIS visual interest indicator (useful in the case of presenting position variants of the same element of the bill to be neuroevaluated); and curves of the effect of size vs. BVIS visual interest indicator (useful in the case of presenting size variants of the same element of the bill to be neuroevaluated).

Figure 6 schematizes the possibilities of presenting objects for the neuroevaluation of the present invention, preferably banknotes or communication materials, both in real and virtual format. The samples of banknotes or communication materials to be analyzed include different security characteristics, design or content of the communication materials according to, among others, different materials, designs, sizes and positions, which influence the public's perception of the ticket. The context of the banknote samples can be presented to the user using different techniques21, which include not providing any context211, adding a real context212or adding a virtualized context213 where, using digital and computer graphics techniques, different scenarios are reproduced, among which The following are contemplated: a virtual reality scenario, where the evaluation configuration is used in laboratory conditions under a virtual replica of the real world, which may consist of two-dimensional (2D) models of the real context; an augmented reality scenario, where the assessment setup is used in real-life conditions, but complemented with some 3D virtual elements; and an augmented virtuality scenario, where the assessment setup is used under laboratory conditions, but an augmented virtual replica of the real context is presented to the user.

On the other hand, depending on the human sensory channel that is intended to be exploited, the context can be provided through a single or a combination of the following immersive interfaces: visual devices (such as conventional monitors, vertically positioned monitors with stereoscopic 3D vision and 3D tracking of the position of the main user ("fish tank" interface), horizontally positioned monitor with stereoscopic 3D vision and 3D tracking of the main user's position ("workbench" interface), surround displays composed of large projection-based screens and/or o large monitors, hemispheric displays or virtual reality headsets (HMD-Head Mounted Displays) and/or augmented reality and/or mixed reality); auditory displays (where for example contextual sounds are reproduced using 3D sound generation techniques with headphones and/or external speakers); olfactory displays (where aromas are delivered through electronic noses and/or any commercial olfactory displays); or haptic displays (where tactile and kinesthetic signals are provided through a haptic touch display device, such as terrestrial references, body references, tactile, or a combination of the above). Regarding the presentation of the banknotes22, leaving aside the context, the present invention also contemplates several alternatives shown in Figure 6. Mainly two techniques are used depending on their capacity for fidelity to reproduce real life situations: using a physical ticket221, where the user is presented with a real physical model of the ticket; or use a digital ticket222, where a digital replica of the ticket is presented using either a virtual ticket model that reproduces, in two or 3 dimensions, a digital image of the real ticket, or in a virtual ticket model based on a tangible interface that the user can manipulate with his hands. This tangible interface can represent graphic elements on physical paper in three dimensions using spatial augmented reality techniques. The final result of the overlay techniques can be presented to the user through a virtual reality headset or alternatively, this type of device can be dispensed with and opt for digital projectors that display the information directly on the physical bill.

The present invention should not be limited to the embodiments described herein. Other configurations can be made by those skilled in the art in view of the present description. Consequently, the scope of the invention is defined by the following claims.

Claims (8)

1. Method for selecting parameters of at least one design or security element that will be incorporated into the manufacturing of a banknote to facilitate the recognition of the banknote, thus increasing security, characterized in that it comprises the following steps: a) providing a user with a plurality of banknotes (1) that differ in at least one parameter of at least one design or security element (52, 53, 54, 55, 56, 57) of the banknote; b) for each ticket, define at least one area of interest that includes the area of the ticket occupied by the at least one design or security element; c) acquiring, through sensor means integrated in an input module, biometric signals for eye tracking (2411), gestural behavior (2413), facial expression analysis (2412), brain response (2421), heart rate variability (2422) and skin conductance (2423), in response to visual, tactile and sound stimulation of the user with the plurality of bills; as well as explicit responses to provided questionnaires; d) conditioning (32) the acquired biometric signals by segmenting, in a process module (3), the biometric signals acquired in predetermined periods of time, where said biometric signals are associated with at least one defined area of interest; e) compare each of the biometric signal segments with pre-established patterns and identify certain events as a result of the comparison; f) obtain at least one biometric variable (33) based on the identified events; g) analyze, in the process module (3), the biometric variables, according to known results previously stored in a database using automated learning techniques, and generate partial neurometric indicators (4) associated with each bill, comprising a visual interest indicator (41), an engagement indicator (42), a workload indicator (43), an emotional indicator (44) and a user safety indicator (45); h) establish a global neurometric indicator as a result of a weighting of the partial neurometric indicators; and i) select the parameters of at least one design or security element that will be incorporated into the manufacture of the banknote in accordance with the global neurometric indicator established for each banknote. 2. Method according to claim 1, wherein the plurality of banknotes is provided physically, virtually or through a combination of the two in a tangible interface on which virtual elements added to a physical banknote using technology are represented. augmented reality. 3. Method according to any of the preceding claims, wherein the at least one biometric variable comprises quantifiable information about the identified events, to be selected from: number of identified events, average duration of the identified events, frequency of each event identified in a pre-established time, sequence of identified events and number of visits to the same predefined area. 4. Method according to any of the preceding claims, wherein analyzing the biometric variables, according to previously known results, further comprises training a supervised learning system of the process module according to the following steps: - repeating steps a)-c) of claim 1 for a plurality of different banknotes and different users; - group, for each ticket, the identified events of each user, according to a previously established number of groups; - assign to each bill an initial value of the neurometric indicator, where said value is based on an analysis of the groups of events identified by an expert user. 5. Method according to claim 4, wherein analyzing the biometric variables through the supervised learning system also comprises the steps of: - provide the initial value of the neurometric indicator, assigned to each banknote, in an input of the learning system; - apply a predictive model, through the supervised learning system, on the biometric variables obtained by the process module and the initial value assigned; and - validate, through a cross-validation process, with a previously determined number of iterations, the predictive model. 6. Method according to any of the preceding claims, wherein the neurometric indicators represent one or more of the following cognitive brain processes of the user: visual interest, attention, evoked emotions, motivation, mental load, stress and level of arousal. 7. System for selecting parameters of at least one design or security element that will be incorporated into the manufacturing of a banknote to facilitate the recognition of the banknote, thus increasing security, characterized in that it comprises: - an input module (2) comprising sensor means, configured to acquire biometric signals for eye tracking (2411), gestural behavior (2413), facial expression analysis (2412), brain response (241) , heart rate variability (2422) and skin conductance (2423), in response to visual, tactile and sound stimulation of a user with a plurality of bills (1) that differ in at least one parameter of at least least one design or security element (52, 53, 54, 55, 56, 57) of the banknote, as well as explicit responses to provided questionnaires; - a process module (3) configured to: define at least one area of interest in each bill that includes the area of the bill occupied by the at least one design or security element; conditioning the biometric signals comprising segmenting the biometric signals into predetermined time periods, wherein said biometric signals are associated with at least one of the defined areas of interest; compare each of the segments of the biometric signals with pre-established patterns; identify certain events as a result of the comparison; obtain at least one biometric variable (33) based on the identified events; analyze the biometric variables according to known results previously stored in a database using automated learning techniques; generate partial neurometric indicators (4) associated with each ticket, which include a visual interest indicator (41), an engagement indicator (42), a workload indicator (43), an emotional indicator (44) and an indicator security (45); and establish a global neurometric indicator as a result of a weighting of the partial neurometric indicators; and - an output module (5) configured to select the parameters of at least one design or security element that will be incorporated into the manufacture of the bill in accordance with the global neurometric indicator established for each bill. 8. System according to claim 7, wherein the output module comprises display means, configured to visually represent the neurometric indicators of the bill and a final classification metric, based on the neurometric indicators resulting from the neuroanalysis of each bill.