WO2016163594A1 - Method and device for psycho-physiological detection (lie detection) with respect to distortion by using video-based physiological signal detection - Google Patents

Abstract

A method for determining whether a test subject is lying is disclosed. The disclosed method comprises the steps of: acquiring, by using a camera, a video of before and after a statement is given for a predetermined question from the test subject; extracting, from the video, at least one of parameters A1, A3, A4, A1X, A4X, INT0A, INT1A, and INT2A; calculating a standard deviation from the parameter extracted in the aforementioned step; and determining whether the test subject is lying by using the standard deviation.

Description

Method and apparatus for psychophysiological detection (lie detection) against distortion using video-based physiological signal detection

The present invention relates to a method for acquiring a biosignal used in biometrics, electronics, medicine, and the like, and a technique for detecting a lie by applying the same. The present invention relates to a method of determining whether a lie is obtained by analyzing a physiological signal using the same.

The first scientifically based hypothesis of the inseparable relationship between human psychology and physiology was proposed between 1890 and 1895 by Sigmund Freud, the founder of analytical psychology. The hypothesis that any change in human psychology is related to the body's physiological response is widely accepted today. Of course, the interface between these correlations has not yet been defined, and there are many different approaches to this definition.

 Therefore, there have been many studies to obtain such psychophysiologically integrated information about the human body, and some specific contact methods, devices, and systems have been known to date. They use well-known physiological parameters of the human body to assess human emotional and psychological conditions and to make medical diagnoses.

 The most widely known system, also known as a lie detector, is obtained through various channels to measure changes in psychophysiological (mental body) parameters when the human body responds to certain external stimuli, especially horse stimuli. Using physiological information. Analyzing the condition of the human body in the above manner generally takes several hours, requires the sensor to be firmly attached to the subject's body and requires the participation of trained test personnel. Therefore, there are many practical limitations in using the above system extensively to make psychophysiological diagnosis of the human body.

 The method of polygraph detection using polygraph using the response of heart rate and peripheral nervous system, the method using EEG (Electriencephalographic), the method using Voice Technology, and the Facial Recognition Technology And video-based analysis using images.

The technique compared to the present invention is a polygraph method, developed by John Lason, a US police officer and forensic scientist in 1921, which measures and changes graphs of physical functions such as pulse, blood pressure, breathing, and sweating of test subjects. In other words, if the person being tested is lying, the graph changes, which is caused by the emotional reaction that the person is lying. But the results are not always accurate. The countries that use the technology are the United States, Canada, South Korea, and India, which are widely used in practice, but are rejected by law in court.

The present invention provides a method for supplementing and reinforcing the complexities of existing contact lie detection techniques and the disadvantages requiring skilled inspectors.

The present invention provides a method that can ensure a high level of reliability in which the inspection results are matched by 90% or more, compared to the polygraph method, which is a reliable polygraph detection method.

Obtaining continuous image information of the inspector under contrast analysis;

Extracting vibration parameters of the inspector by analyzing the image information;

Determining whether a lie is detected based on the vibration parameter; It includes.

Lie detection system according to the invention:

An image acquisition unit for photographing the inspector to obtain a continuous image;

And a photo detector for continuously capturing the image, an A / D converter for converting the captured image into image data, and a data processor for determining whether a lie is detected by analyzing the converted continuous image data.

The method of polygraph is presented by vibrating imaging technique. Lie detection method using vibration image is a non-contact method and detects lies very precisely. This method can be used to reinforce defects of existing polygraphs or to reduce precision lie analysis by using them prior to primary polygraphing. This is a new way to replace traditional and modern lie detectors.

1 shows a two-dimensional emotional model by James Russell.

2 is a diagram illustrating an emotional classification process according to the present invention.

3 is a schematic diagram of an emotion classification algorithm according to the present invention.

FIG. 4 shows that bioenergy (aura) is radiated around the human body image formed by the amplitude component of the vibration image.

5 shows the bioenergy radiated around the actual image of the human body.

Figures 6 and 7 show the biological image radiation according to the state of the subject, Figure 6 shows a stable state, Figure 7 shows a case of an unstable stress state.

8 is a distribution graph of frequency components (biosignal images) of a human body vibration image in a stable state.

9 is a distribution graph of frequency components (biosignal images) of a human body vibration image under stress.

10 is a radial graph (chart) showing the emotional state of a subject according to the method of the present invention.

11 is a flow chart of a lie detection process in accordance with the present invention.

12 is a schematic block diagram of a lie detection device according to the present invention.

13 is a data processing flowchart in a lie detection process according to the present invention.

14 illustrates an interface screen for extracting vibration parameters (variables).

15 is a table illustrating data analysis through speech recognition.

FIG. 16 is a data table as the basis of FIG.

Fig. 17 shows an example of a screen in which a statement recording image of a subject is analyzed as a vibra image.

18 is a flowchart illustrating a query and statement process according to the present invention.

FIG. 19 is a scatter graph showing the average value of the standard deviation of each variable in the ST and AT sections.

20 is a graph showing the average value change rate of the DI and NDI standard deviations of eight variables in the ST and AT intervals.

21A to 21H are histograms and standard error histograms of standard deviations of DI and NDI in the ST and AT sections of each parameter.

Hereinafter, a lie detection method using a vibration image according to the present invention will be described with reference to the accompanying drawings.

Various theorists thought that all human beings had innate basic feelings. Some research resources define feelings according to more than one dimension. In 1897, feelings were described in three dimensions. "Pleasure & unpleasantness", "Awakening & calmness", "compression & relaxation". In 1980, emotions were classified in a two-dimensional circular space, a model developed by James Russell. As shown in Fig. 1, the languages of emotion in Russell's model are recorded in a two-dimensional circular space with dimensions of arousal and balance. In Fig. 1, arousal is shown on the vertical axis, and emotion (pleasure / discomfort) is on the horizontal axis.

Vibration images represent head movement activity characterized by information of the vestibular-emotional reflex (VER). That is, the vibrating image measures the movement and the micro vibration of the face and the upper body by using the difference in the color values between the frames and the pixels. Since the physiological vibration index of our body is about 10hz, images of 20hz or higher can be properly analyzed. Using this principle, we can measure the change of pixels to correlate with the EEG, and infer the emotion from the image as if we infer the emotion from EEG.

Vibration imaging system is a general image processing process to detect human emotion, mental state, lying element, etc. 1. oscillating image technology aggression, stress, 2., 3. tension / anxiety, 4. doubts, 5.10 balance, 6. Charm, 7. energy, confidence 8., 9. suppression, 10. nervousness such things Get the variable Image and vibration image transformations provide head movements related to the functional state of the body as measured variables calculated in real time by calculus. Each variable is calculated from the equation below and expressed in amplitude and frequency.

Where A is amplitude, N is frame rate,

Is the signal amplitude at the x and y points in the i th frame,

Is the signal amplitude at the x and y points in the i + 1th frame. The frequency component is calculated from number two.

In the present invention, the signal component corresponding to the EEG signal is extracted from the parameter, thereby evaluating the physiological and psychological state of the subject.

Prior to the description of the emotion classification method of the subject according to the present invention, the relationship between the vibration of each part of the living body and the psychophysiological parameters will be described in relation to the vibration parameter used in the present invention.

In small particle physics, there is no clear boundary between the wave and particulate properties of matter, and the photon energy (ε) is known to be linked to the frequency of photon energy (ν) through Planck's constant (ε = hν). It is hypothesized that the energy emitted from each part of the organism is proportional to the vibration frequency of that part in the space. As a result, in order to record the energy coming from a living thing, it is necessary to record the vibrations (in or between spaces) that occur at various parts of the living thing. This can be done by using a contactless television system with sufficient resolution and fast processing power. In addition, the frequency components of the biosignal images obtained (ie, the vibration (position shift, wave) frequency at each site) have the most information on the bioenergy, or psychophysiological characteristics, of the observed organisms. Analysis of the obtained biosignal image may be performed by a person or mathematically by processing at least one of the obtained digital biosignal image and its components by a program. In order to prepare and analyze algorithms for mathematical processing, it is good to make a biosignal image which is convenient for visual analysis such as pseudo-color image of monitor screen.

In other words, the frequency component of the biosignal image to be obtained allows to continuously and clearly specify the levels of psychophysiological and emotional states of the human body and to distinguish the changes in the human state when various stimuli occur in humans. do. As it turns out, an image showing the human body's bioenergy field represented by an aura located around the human body can be used to evaluate the psychophysiological state of the human body faster and more accurately than other methods.

The term aura refers to an integral characteristic of the psychophysiological state of the human body. These auras appear around the human body and have specific relationships with the bioenergy components of the human body. The image of the human aura provides a lot of information when studying the psychophysiological parameters of the human body, and the following factors are considered. Human emotional state can literally change every second. The average person can not stay in one emotional state for a long time.

Every thought and action or reaction to a situation leads to a momentary change in the emotional state (images of each biosignal). Therefore, it is important to find the optimal correlation between the number of information on the obtained biosignal image (above all, the resolution of the camera) and the rapid processing of the system.

Adds an amplitude modulating of the aura size, and modulates the subject's maximum vibrational frequency by color modulating the frequency of the positional change or average value of the amplitude in a specific region of the human body, Changes can be recorded at a glance and instantaneously. Frequent fluctuations in the brain are known to play a key role in learning, memory, and solving a variety of tasks. Experiments have shown that the most intensive part of vibration in the human body is the brain, and in most cases auras (frequency components of vibration images) may be present only around the human head, much larger than the auras around the body. . Changes that occur in the human body are represented by the collapse of the aura or the appearance of asymmetry in color and form. This is clearly seen in the obtained biosignal image.

There is one point in that the elements of the biosignal image are associated with the elements of the actual image in topology. Experimental results show that the emotional state of the human body that contains the most information is transmitted at the maximum oscillation frequency, and the average level of the frequency or the background level of adjacent points can be shrouded or cover up the true changes that occur when visually accepting the biosignal image. It may be.

Therefore, it is shown that the geometrical correlation of the elements of the biosignal image to the elements of the real image is less effective than the frequency components of the vibration image represented by the aura located around the real image. When the elements of the biosignal image are topologically related to the elements of the actual image, the elements with the maximum vibration frequency are not visible in the entire background when the image is subjected to color-frequency adjustment. In order to mathematically analyze the biosignal image in various forms, the biosignal image to be obtained must be visually controlled in advance. The proposed image of the frequency component of the biosignal image, in the form of an aura, is consistent with the physical concept of bioenergy radiation and enables visual control and analysis of the device-generated image.

Unlike frequency components, the use of amplitude components is more effective in topological relationships. First of all, it is possible to evaluate the quality of the biosignal image obtained by using the amplitude component of the biosignal image, which is topologically connected to the vibration point, and to determine the exact parameters (variables) for adjusting the system.

First, the measurement of the vibration image parameter will be described in detail.

Acquiring information about the level of aggression of a creature consists of constructing a frequency distribution histogram and measuring the head vibration image parameters of the creature.

Aggregation of Aggression Levels (Ag) consists of:

Maximum frequency of frequency distribution density in Fm- histogram

"I" frequency aggregation of frequency distribution density obtained over N frame time in Fi- histogram

Fin-vibration image processing frequency

Aggregate including interframe differences beyond the threshold in n-N frames

The biological head vibration image parameter is measured to obtain information about the stress level of the creature. The stress level St is calculated by the following Equation 4.

-Total amplitude of thermal vibration image "I" in the left part of the subject

-Total amplitude of thermal vibration image "I" in the right part of the subject

-

From

Maximum value of the liver

-"I" thermal vibration image maximum frequency in the left part of the object

Maximum frequency of "I" thermal vibration image on the right side of the subject

-

From

Maximum value of the liver

n-the number of columns

To obtain information about the level of anxiety in the organism, the biological head vibration image parameters are measured. Anxiety level (Tn) is measured by the following Equation 5.

Pi (f)-Vibration Image Frequency Distribution Power Spectrum

fmax-maximum frequency of the vibration image frequency distribution spectrum

To obtain information about the level of compatibility of living things with other organisms, determine histograms of vibration frequency distributions for all individual organisms, construct each histogram, obtain common frequency distributions, and obtain the general law of distribution and the previously obtained co-distribution area. Make the same and find the difference between the general law of distribution and the frequency histogram. The compatibility level C is calculated by the following Equation 6.

K- Obtained Frequency Histogram Generalized Correlation Coefficient

y’- normal distribution density

In determining verbal or nonverbal falsehoods, vibration image parameters of the head of the organism are measured to obtain information about the integrated level of change in the psychophysiological state.

The integrated level of change (L) of the psychophysiological state used in the false decision is summarized in the following equation.

Pi-parameter to change the higher set threshold

Pc-Vibration image parameter measured when determining false level

K-Pi semantic correlation coefficient to be measured

n-the number of parameters to be measured

m-the number of parameters changed

As is well known, cybernetics and information theory examines the applicability of operational methods and techniques to organisms and living systems. Modern concepts of cognitive biology are usually related to the concepts and definitions of signal information and transfer theory, and enable the psychophysiological information of mathematical parameters established in information theory. The author's long study and observation of the study of human head micromovement with the help of statistical parameters used in information theory shows that there is a statistically reliable dependence between the state of human psychophysiology and the head micromovement information statistics parameter. Could know.

 The present inventors can present their own interpretations of these phenomena and vestibular emotion reflections. First, we will define the interrelationship between psychophysiological energy coordination (metabolism). All typical emotional states can be characterized by a correlation between specific energy consumption and individual physiologically necessary energy and emotional energy. At this time, the physiological energy is formed to realize the physiological process, and the emotional energy is formed as a result of the conscious or unconscious process. For example, the attack state, if it is the same attack condition, should be expressed differently in various people, and natural adjustment process such as age, gender and education level should be considered. However, from a physiological point of view, these differences should not have a fundamental meaning in the relative amounts and locations of energy release within the body. All this leads to visible emotional signs, such as flushing of the face, frequent sighs, rapid heartbeats, and certain micromovements. The main reason for the external manifestation of the emotional state is due to the additional release of energy in the body organs which changes the correlation between physiological and emotional energy. It should be emphasized that the author took into account the body-chemical energy of natural physical processes, which are well known at the level of modern technology development. The progression of physiological processes, and the interruption and triggering processes for human thought and movement processes.

The main challenge of the vestibular system is, above all, to maintain a dynamic equivalence or equality. However, the study proved that the equilibrium state of the semi-closed system is possible only if the dynamics, chemistry, energy, and other systems (systems) forming the subject are equal. Unbalance in any one of these systems results in the destruction of the equilibrium state of the adjacent system, i.e. the breakdown of mechanical balance results in the breakdown of energy balance.

The human head in a vertical, semi-balanced state can be seen as an overly sensitive mechanical indicator of all the energy processes in the body. From a biomechanical point of view, maintaining the vertical balance and equilibrium of the heads far above the center of gravity requires tremendous continuous effort and reduction of the neck-head bone muscles. Moreover, this movement is realized reflexively under vestibular system. All meaningful phenomena in the organs lead to changes in the ongoing physiological process. This is similar to other physiological process changes traditionally used for psychophysiological analysis, such as galvanic skin response (GSR), arterial pressure, and heart rate. In addition, the parameters of head movement vary with the amount of energy expression and the location of energy expression. The spatial three-dimensional trajectory of head movements is very complicated because the shape of the head resembles a sphere. Also, the movement trajectory of each point can vary significantly in the movement of hundreds of neck muscles. Statistical analysis of informative motion parameters enables reliable quantitative parameter differentiation of head movements. In other words, it is possible to measure and confirm the emotional state through the measurement of energy and vestibular response. The laws of mechanics appear to be consistent, and behavior is always reactionary to maintain equality. Energy measurements in the body organs that naturally target a wide variety of people will result in consistent corresponding changes in head movement parameters through vestibular activity.

The overall emotional classification according to the informational / statistical parameters of the presented head movements confirms all emotional states. Currently there is no single, holistic approach to measuring emotional state, so it can be used for initial measurements in terms of other psychophysiological methods or independent experimental evaluations. Modern psychology mainly uses qualitative criteria in the evaluation of emotional state, which essentially makes it impossible to measure quantitatively, and the objective evaluation of human state is difficult. However, the suggested method allows us to measure all emotional states. Given that a change in head movement parameters is functionally related to a change in energy exchange, naturally, head movement parameters are a general characteristic psychophysiological state of man. The accuracy of agreement of the proposed formulas for counting emotional states according to existing assessment criteria is low compared to the emotional state assessment method through head micromovement. This is because there is no overall standard for assessing emotional state at the current level of technology. The proposed method is characteristic in that an integrated approach is possible for all emotion measurements. All previous methods were also used to assess various emotional states. Adopting the proposed concept for measuring emotional state allows the inclusion of psychology in precision science and enables the same emotional measurement.

Acquisition of the signal regarding the head movement of the subject is performed by comparing images by the camera. In terms of spatial and temporal distribution information statistics parameters, the movement speed of the head of the creature is measured as the average frequency of marker movement, determined in units of 10 seconds, which yields the maximum frequency of TV camera work. These characteristics can well reflect human emotional anxiety and can characterize anxiety levels.

When the vibration image simultaneously represents the spatial and temporal distribution of the target motion energy, the number of factors having the same vibration frequency for a specific time is aggregated to obtain a frequency histogram. Histograms therefore exclude information about the spatial distribution of vibration frequencies. This apparent loss of spatial information actually increases the motion information, because in terms of physiological energy, it is not very important in which part of the head the movement is performed unlike the fine movement of the face. The configuration of the frequency histogram is determined according to the following.

As is well known, a new formula has been proposed that takes into account two main factors that differ from the existing contradictory approaches that determine the level of aggression. Two main factors are the average vibration frequency, or human head motion and parameters, and the mean square deviation, which best show the characteristic spread of the vibration. This aggressive person has a high spreading frequency in movement of high frequency of hair fine movement and various points of the head part. Other official correlation coefficients show aggressive correlation coefficients for values from 0 to 1.

Fm- Maximum frequency of frequency distribution density histogram

Number of i-frequency aggregates in frequency distribution density histograms obtained per fi-50 frame hour

Fin-vibration image processing frequency

Aggregate number of interframe differences above the threshold in n-50 frames

This equation allows everyone to determine their level of aggression, with naturally lower aggression levels approaching zero. People with high aggression are close to one. When using the security system of a vibrating imaging system to identify potentially dangerous ones, the threshold for identifying aggressive ones is used.

The next step is to statistically identify meaningful vibration image information parameters that determine vibration image acquisition and subsequent aggression levels. This determines, among other things, vibration symmetry parameters for amplitude and frequency vibration images.

In contrast to the well-known and contradictory approaches that determine the level of aggression, a new formula has been proposed that takes into account the motion amplitude and frequency symmetry for individual columns that scan the human head. As such, the person with the highest level of aggression exhibits maximum symmetry in vibration and fine movement for processing amplitude and frequency vibration images for 20 seconds. At the same time it shows low levels of stress and anxiety.

-Total amplitude of thermal vibration image "I" in the left part of the subject

-Total amplitude of thermal vibration image "I" in the right part of the subject

-

From

Maximum value of the liver

-"I" thermal vibration image maximum frequency in the left part of the object

Maximum frequency of "I" thermal vibration image on the right side of the subject

-

From

Maximum value of the liver

n-the number of columns occupied by the target

Similar to the information statistics parameters presented previously, the formula presented allows us to measure the stress level (St) from 0 to 1, and above all, the minimum stress level corresponds to the minimum measurement, In people with stress levels close to one.

The following is a statistical analysis of meaningful vibration image information parameters that determine vibration image acquisition and subsequent anxiety levels. This relates, among other things, to the fast activity signal frequency spectrum construction of amplitude and frequency vibration images.

Unlike the well-known and contradictory existing approaches that determine the level of anxiety, a new formula has been proposed that takes into account the fact that high anxiety increases high frequency spectral density rather than low frequency spectral density.

Tn-anxiety level

Pi (f)-Vibration Image Frequency Spread Power Spectrum

fmax-vibration image frequency spread spectrum maximum frequency

The presented formula, similar to the previously presented information statistics parameters, allows us to measure the level of anxiety from 0 to 1. In addition, the minimum level of anxiety meets the minimum measure, and those with high levels of anxiety have stress levels close to one. The fast signal frequency spread spectrum of the vibration image appears for the operator's or system operator's control.

Another example is to find statistically meaningful informative parameters of the vibration image that determine the vibration image acquisition and then the level of compatibility between the people. Best of all, this consists of a vibration image histogram configuration at each individual frequency.

In contrast to the well-known and contradictory existing approaches that determine the level of compatibility, a new formula that considers the compatibility possibility characterized by a close proximity to the total oscillation frequency histogram of both sides of the distribution normal law Presented.

K-normalized correlation coefficient of initial histogram

y ': normal distribution density

Similar to the parameters presented previously, the proposed formula measures the level of compatibility from 0 to 1. In addition, the minimum measure corresponds to the minimum compatibility (compatibility), and the high level of compatibility measure on both sides appears close to one.

Next is to find a statistically meaningful information parameter of the vibration image that determines the vibration image acquisition and human false level. First of all, it is related to the acquisition of temporary dependence of the maximum amount of vibration image parameters with the least correlation between them.

A new formula has been proposed for the detection of lies that differs from the well-known existing psychophysiological approaches. False in this formula is determined by the change in vibration image parameter measurements compared to the reporting time. The formula presented allows us to determine whether we are verbal and nonverbal. Basically, the linguistic false decision in the time dimension utilizes the time to the start of the test subject's answer. In the case of non-verbal false analysis, it is made by comparing the parameters with one time period and another time period.

 The integrated level of change (L) of the psychophysiological state used in the false decision is calculated by the formula:

Pi-change parameter for a higher set threshold

Pc-Vibration image parameter changes when determining false level

K-Measured Pi Semantic Correlation Coefficient

n-number of measurement parameters (may vary from the number of visual parameters)

m- number of change parameters

Similar to the parameters presented previously, the formula presented allows us to measure false levels from 0 to 1. In addition, the minimum level of false matches the minimum measure, while the highest level of false has a value close to one.

This does not mean, however, that the present invention is utilized solely for the measurement of emotional and psychophysiological states of humans presented above. For reference, there are over 200 classifications of human state characteristics according to various classification systems. Above all, the present invention allows us to describe all human conditions through the head micromovement parameters and / or the head vibration image parameters. In psychology, it is an unclear principle to translate the traditional concept of motion into reflex micromovement of the human head using reliable statistical parameters. However, based on the proposed approach, it is possible to determine the human state similarly to the technical information system and to utilize the information parameters to characterize the human state. For example, it is possible to determine the level of human information and thermodynamic entropy according to the formula.

As a basis for the computation of information entropy, a head motion frequency distribution histogram is constructed. The computation of this information entropy follows the following formula.

As a basis for the thermodynamic entropy calculation, a histogram of the frequency distribution of the micro-movement of the head is constructed. The thermodynamic entropy (S) calculation follows the following formula.

These individual information statistics parameters are applied to better identify any emotional state in humans. For example, experiments have shown that there is a high correlation between informational entropy on false levels. It was found that there is a big connection with.

Based on body and thermodynamic parameters, we were able to more fully characterize and determine human behavior, energy and charismatic aspects. For example, using the Vibration Image 7.1 version system, human energy (E) could be calculated based on the difference between the mean square error and the frequency peak, based on the frequency histogram showing the highest frequency of the vibration image.

Quantitative analysis of the reflexive micromovement of the head makes it possible to measure the psychophysiological state of humans more objectively and scientifically and to solve many problems in medicine, psychology, psychology, and everyday life. Through independent experiments with the system developed and the quantitative assessment of the psychological status of passengers at the airport according to aggression, stress, anxiety and potential risk levels, the present invention is positive (more than 90%) to the expert's professional evaluation. I could tell the truth. This confirms the practical feasibility of the present invention.

Hereinafter, look at the experimental method of the present invention. 2 illustrates the progress of the experiment. In this experiment, we measured children with relatively easy induction of emotion. The response before and after the stimulus coming from the leader was used to analyze the pattern through the amount of change. The pleasant-displeased axis and the awakening and relaxation axis divided into four quadrants were used as stimuli. Data before and after each stimulus (neutral, pleasant-wake, pleasant-relaxation, discomfort-wake, discomfort-relaxation) are compared to find relevance.

A total of five children studied consisted of one female, four males, and an average of 5.0 years old with a standard deviation of 0.8. Subject had no cardiovascular or neurological abnormalities and subject was placed in an independent space. There is no interference between the camera and the test subject and it is performed in the measuring room with white background. The collected images were masked for all but the subjects for better results.

As a research tool, the vibration image technique according to the algorithm described above has been found by tracking the points in the head of the children in real time in order to detect the change of emotion. The basic specifications of the video camera are a resolution of 640x480 pixels, a frequency of 15.0 frames / sec, an 80dB dynamic range (the sensor's light receiving width), and a distance of 1.5m.

In the actual experiment, the subject was allowed to sit in a chair for 10 minutes to rest and stare at the camera for 3 minutes as a pre-measurement. The emotion-induced stimulus caused a pattern of psychophysiological responses. Five different oral assimilations (neutral, pleasant-wake, pleasant-relaxation, discomfort-wake, displeasure-relaxation) were used for about 20 minutes. The post-mortem condition was also recorded for 3 minutes.

The measured images were analyzed by vibration image processing software applying an algorithm using a vibration image as described above, and the average values of the 10 parameters after the analysis were presented as analysis results. After collecting data from five children, we divide them into common and effective variables to distinguish the differences in the four stimuli on a neutral basis. The extracted valid variables are used to make decisions based on Russell's emotional model.

As a result of analyzing the above experimental results, we found out the effective variables extracted for each stimulus among 10 variables through five children. The common variables extracted from the stimulus of pleasant-wake and pleasant-relaxation based on neutral stimulation can be used as the common variables of pleasant emotion, and the variables extracted from the pleasant-wake and discomfort-wake are the vibrations associated with the arousal stimulus. It can be called an image valid variable. Repeat this to find the parameters associated with each emotion axis. By comparing the pattern of the rate of change of the vibration image variable, the common variables of 'arousal-wake' and 'discomfort-wake' are aggression and stress, and 'tension / anxiety' and 'neural hypersensitivity' are 'awakening' and 'relaxation'. It can be used to divide. Table 1 below shows the results of pattern changes in different stimuli. Using these variables, we can create an algorithm that can infer backwards as shown in FIG.

The development of technology is changing from machine-centric to human-centered for a better life. Application technologies using various biosignals have been developed to build a heterogeneous environment. Like the eye movement tracking system using EGO and EMG or the electric wheelchair control system using EEG, the computer or the surrounding environment can identify the human state and make the human life more comfortable. Technologies are being developed.

The present invention proposes a method of making an algorithm that can infer emotions from extracted variables using vibration image technology and to determine a lie.

By using image technology based on psychophysiological mechanism, vibration image technology can be used instead of contact bio-signal measurement technology that users can feel rejection. Proved.

FIG. 4 shows that an aura of bioenergy is radiated around an image of a human body formed of an amplitude component of a vibration image.

As described above, the internal biosignal image expresses the magnitude of the change in position of each part in color. Through this it is possible to visualize the size of the position change of each part of the subject (1). The external biosignal image appears around the internal biosignal image and modulates the average peak vibration frequency into color.

5 illustrates that a biosignal image, which is bioenergy, is radiated around an actual image of a human body. In FIG. 5B, the internal biosignal image is not represented and only the biosignal image is displayed around the actual image.

6 and 7 show biosignal images in a stable state and an unstable state, respectively. FIG. 6 is a biosignal image of a subject in a stable or finished state, and FIG. 7.

Referring to FIG. 6, the biosignal image is sufficiently symmetrical in shape and color, and the color of the biosignal image is about halfway between the selected color scale (overall color-green). It can be seen from the biosignal image that the subject is in a stable state.

On the other hand, referring to FIG. 7, the aura contains a lot of red components in the biosignal image. Therefore, it can be seen that the subject in this state is an unstable state. When a person is irritated, for example, exposed to a violent scene through the screen, the subject becomes stressed or aggressive and the color of the biosignal image changes to a reddish color.

FIG. 8 is a distribution graph of frequency components (biological signal images) of a human body vibration image in a stable state, and FIG. 7B is a distribution graph of frequency components (biological signal images) of a human body vibration image in a stress state.

The graph shown in FIG. 9 shows a typical frequency distribution of a person in a normal working state. The results show that the majority of people in a calm state generally have a distribution of distributions similar to a single-mode distribution rule. The subject's state changes as shown in FIG. 7 when subjected to a certain negative effect such as watching a violence scene on the screen. If in fear, stress and aggressive conditions, the mean (medium) value of the frequency distribution (M) shifts towards increasing. In a stable and relaxed state, the mean (middle) value of the frequency distribution value (M) is shifted toward decreasing. The frequency axis (X) can be expressed not only in relative units, but also in real units or time (㎐ or sec.). The distance between the display values is determined by the actual parameters of the camera's rapid processing and the software's settings (time to accumulate images and the number of images in the processing sequence).

10 is a radial graph (chart) showing the emotional state of a subject measured according to the method of the present invention.

Hereinafter, the method of detecting a physiological signal according to the present invention will be described with respect to a technique for detecting a lie.

First, as shown in FIG. 11, a control analysis is performed to detect a lie (11), and a biopsy subject undergoing psychophysiological change, that is, a test subject undergoing a control analysis investigation, is photographed to acquire a continuously changing image (12). Each image is processed (analyzed) to generate vibration parameters (13). As shown in the analysis of the physiological signal obtained on the existing polygraph, the response of the answer corresponding to each question is analyzed and analyzed (14) to finally determine whether the lie (15).

This method may be implemented by a device having a structure as shown in FIG. 12 is a functional block diagram of a lie detection device. Referring to Fig. 12, the physiological signal detecting apparatus according to the present invention includes a vibration parameter (parameter) using a camera 21 for photographing a subject, a processor 22 for analyzing an image obtained from the camera, and a signal from the image processor. ) And a signal analyzer 23 for generating a physiological signal using the same, and a lie determination unit 24 for determining a lie by applying a physiological signal obtained from the signal analyzer.

 Hereinafter, the process of discriminating (detecting) a lie about the present invention will be described. As shown in FIG. 13, a physiological signal is received from a control analysis video of a subject, and only the following parameters (INT2A, INT1A, INT0A, A1X, A1, A3, A4X, and A4) related to the lie among the physiological signals are extracted. (31), a concrete analysis is performed using the extracted values (32), and the values of the RQ (Relevant Question) and CQ (Comparative Question) sections are compared to the maximum value (LD ( M)), the average value LD (a), the integral value LD (i), and the VR value are compared (33) to synthesize the judgment results in each process (34) and finally based on the combined values. Determine if a lie (35). Specifically, through the comparison of the response variable values for the comparison question (CQ) and the event question (RQ), the two values are true if the CQ value is greater than the RQ value and a false response if the RQ value is greater than the CQ value. If the difference is within the range of 10%, it cannot be determined. "

As described above, parameters A1 to A4 represent the amplitude of vibration, A1 is the frame difference between two consecutive frames, A3 is the frame difference between N consecutive frames, and A4 is the numerical value of variable A1 filtering 10 frames. Say. INT2A is the integration of 10 consecutive amplitude values, INT1A is the integration of two consecutive amplitude values, and INT0A is the integration of N amplitude values.

Here, VR (Visualization rate) means a weight for each parameter that is roughly compared to CR (calculation rate). VR is weighted as 1 when there is one section larger than the threshold in the analysis section and 2 when there are two sections larger than the threshold.

The determination of the lie using the mean in the maximum value LD (M), the average value LD (a), the integral value LD (i), and the VR value is based on the following numbers 16 to 18.

DI- False Suspicious Interval

NDI- No False Suspects Found

INC- not determined

RQ-Respond to Questions Related to Events

Response to questions to check against CQ-RQ

However, in the case of the average value LD (a), the integral value LD (i), and the VR value, if the difference between the values of RQ and CQ is less than 10%, it is processed as INC.

Lie determination using the maximum value in the maximum value LD (M), the average value LD (a), the integral value LD (i), and the VR value is based on the numbers 19 to 21.

DI- False Suspicious Interval

NDI- No False Suspects Found

INC- not determined

RQmax-maximum response from a question related to an event

Maximum value of responses in question to check against CQmax-RQ

However, in the case of the average value LD (a), the integral value LD (i), and the VR value, if the difference between the values of RQ and CQ is less than 10%, it is processed as INC. In other words, if the CQ value is greater than the RQ value, it is a true response. If the RQ value is greater than the CQ value, it is a false response. It cannot be determined.

 The method of integrating the maximum value LD (M), the average value LD (a), the integral value LD (i), and the VR value is based on Eq. 22.

LD (M) max-The result of judging the lie using the maximum value among the interval analysis results based on the maximum value

LD (M)-Lie determination result using average value of interval analysis result based on maximum value

LD (a) max- The result of judging the lie using the maximum value among the interval analysis results based on the average value

LD (a)-The result of judging lie using average value of interval analysis result based on average value

LD (i) max- The result of judging the lie using the maximum value among the interval analysis results based on the integral value

LD (i)-Lie determination result using average value of interval analysis result based on integral value

Results of judging the lie using the maximum value among the interval analysis results based on VRmax- VR value

Finally, the method of judging a lie using the result of the synthesis consists of <23>.

DInum- false suspect interval found

NDInum- Number of False Suspects Not Found

INCnum-Number of Undetermined

In addition, the method of receiving the physiological signal from the control analysis video is to distinguish the control intervals such as each RQ, CQ, GQ through voice recognition, as shown in Figure 14 and to receive only the values from the corresponding intervals, and to proceed with the detailed analysis The method of comparing the maximum value LD (M), average value LD (a), integral value LD (i), and VR value is performed manually using a table as shown in FIG. The parameters constituting the table of FIG. 15 consist of the data of FIG. 16 generated through the operation shown in FIG.

Hereinafter, the lie analysis method according to the present invention will be described in more detail through experimental examples.

In the experiment of the present invention, in order to measure the effectiveness of the image-based hierarchical statement analysis lie detection system using the Vibra-image technology, the actual events commissioned to each local government offices such as the Seoul Metropolitan Police Agency, the existing lie detector (US The Stalling's product was compared with the Stalling company. Examine the actual event first with the existing polygraph and draw the result by analyzing the result chart. Secondly, by using the Vibra image program, the raw data is recorded using the Vibra image program. After analyzing and comparing the results with the results of the existing lie detector, this study attempts to confirm the possibility of finding and evaluating the effective variables involved in authenticity through the image.

There are three concepts that can be applied to Vibra Image's technology: Vestibular Emotional Reflex (VER), Vestibulo-Ocular Reflex (VOR) and Symmetry (VA). Minkin, 2007).

The vestibular organ, which is the core element of the above concepts, is located in the home and is responsible for the sense of balance. The vestibular organ that contributes to human balance and spatial orientation is the sensory organ that provides the sense of movement and equilibrium. Vestibular organs respond to stimuli and the stimulus acting on a person is gravity. Therefore, to keep the body balanced, the vestibular organ must operate at all times, and the coordination of the vertical head muscle movement and the vertical head coordination is constant, and the reflex is continuously made according to the process. Will be. The vestibular-visual reflex concept is a reflex eye movement that stabilizes the image on the retina while the head is moving by moving the eye in the opposite direction to the head movement. This allows the image to be placed and maintained in the visual center. Symmetry uses the cooperation of vertical head muscle movements for energy regulation because natural head movements are not regular vibrational movements in accordance with certain patterns. This naturally causes left and right movement with respect to the vertical center point, and different analyzes are possible depending on the degree of movement.

Depending on the human state, signals are sent from the vestibular receptor to the autonomic nervous system and the brain and muscles are transmitted at different time differences, which depend on the cooperation of the emotional state and vestibular head muscle movement, or emotional reflex (VER) by the vestibular system. It means that it is.

Vibra image technology records and analyzes human's micro-vibration by camera, and visualizes emotion level by measuring micro-vibration of digital pixel by concept of vibration frequency and amplitude parameter.

The micromovement of the human head is related to the human vestibular-emotion response (VER) function, which allows human emotions to be recognized by controlling the three-dimensional head-neck movement and flow accumulated in the frame. A screen in which a statement recording image of a subject is analyzed as a vibra image is shown in FIG. 17, for example.

Contrast analysis is a general question test technique that confirms the statements of subjects used in the existing polygraph test, and includes the killer technique, the Baxter technique, and the Utah technique. There is usually a structured questionnaire, in which the subject can only answer “yes or no”.

Unlike conventional statement analysis, image-based hierarchical statement analysis detects and analyzes psychophysiological signals in oral statements in a structured or semi-structured interview form of subjects and examiners, rather than written statements. How to analyze the level

18 schematically shows the experimental sequence of the present invention.

 Phase I: Stable Phase

This is a psychologically prepared adaptation concept for programming Phase II where this question is asked.

I-1. State Tracking ("ST") allows the interviewee to take a 1-minute, front-line gaze without a statement for initial baseline settings to measure a stable state without any stimulus.

I-2. Adaptive Preparation ("AP") is a pre-warm-up question for psychological preparation before this question that asks for an innocent, general, personal subject that does not involve large amounts of rapport formation and emotional factors. . For example, ask, “What do you usually do in your free time on weekends?” Or “Talk about your favorite hobby.”

II. Question steps

II-1. The Issue Recollection (IR) calls for a free statement within three minutes, recalling the subject and process of the case.

For example, you can ask for a free statement by asking, "Please explain in three minutes how the clock goes from 00:00 to 00."

II-2. The Concrete Clarification (CC) is a concept of inquiries about the content stated in the IR stage, which consists of at least two additional questions for the specification of poor statements and clarification of key points.

CC asks questions that explain contradictions of evidence, asks for explanations of the suspected reasons (in clear facts → symptom facts → suggested facts), substantiation of concealment or omissions or poor statements. Ask questions, ask for an active explanation of why you are innocent, or change your perspective or reorder in cognitive interviews.

In this process, however, open questions should be asked as much as possible. Induction and pressure questions are excluded, and abundant statements are voluntary rather than short answers.

III. End step

III-1. Ending Preparation (hereinafter referred to as EP) is a psychological preparation process that finalizes the examination and is a formal and courtesy question for identifying additional information and for expanding the interviewee's self-advocacy. (Yes, “What is the last thing you want to say about this event?“ Is there anything else I should know about this event? ”)

III-2. The static phase (Arrange Tracking, hereinafter referred to as AT) is a phase tracking of the late ballast, which again requires a frontal gaze without a statement for one minute and ends with the previous ST value.

Hereinafter, an image analysis method for detecting a lie according to the present invention will be described.

<Recording condition>

The subject conducts a statement analysis in accordance with the questioning method before the existing lie detection test is conducted, and records the statement analysis process through a webcam and analyzes the recorded video file. However, as recorded in the introduction of Vibra image, the video container should be in AVI format and the recording method should be recorded in Uncompressed RGB format.

Therefore, QPlayCap, which was developed for CCTV video recording, was used. This software is freeware that can be distributed. Video analysis requires a Windows-based PC, performance requires a CPU that supports two or more threads at 2.0Ghz or higher, and at least 2GB of memory. The PC used for analysis is a specification that meets this specification.

Analytical Samples and Analytical Procedures

Samples of this study were received from the Seoul Police Agency, Jeonbuk Police Office, and Chungbuk Police Office since February 2014, except for those that were not suitable for analysis. A total of 64 image data from dogs, 15 from Jeonbuk City Police Agency and 7 from Chungbuk City Police Agency were analyzed. Statement analysis samples consist of samples of subjects who were relatively clearly judged by the existing polygraph.

The interval used in the image analysis was determined by comparing the pre-ST and post-AT intervals, which can identify the pure base-line of the subject's psychobiological signal without affecting each examiner to ensure reliability. The average of the values of the standard deviations of each parameter in the intervals was used as the standard. The first 20 seconds of the ST and AT sections were excluded and calculated to measure psychobiological signal values at a more accurate stabilization stage.

When the image of each 5-10 minutes measured according to the question method is loaded into the Vibra image program and the measurement is started, a total of 69 Vibra parameters are generated.

The analysis finds the standard deviation of each variable for the ST section of the initial ballast and the AT section of the post-ballast for 64 samples and all vibra variables. The standard deviations are then categorized as data determined as false (DI) and not false (NDI) in the existing polygraph. After the average of the standard deviations of DI and NDI for all variables, see the rate of change in the ST and AT sections (see Figure 19).

Fig. 19 is a scatter graph showing the average value of the standard deviation of each variable in the ST and AT sections. In Fig. 19, DI is shown as a triangle and NDI is shown as a circle, and are INT2A, INT1A, INT0A, C3, FN01, and X1 in order from the left of the X axis.

Vibra image parameters are largely represented as vibration amplitude parameters (Series A), vibration frequency parameters (Series F), and symmetry related parameters (Series S), and combinations (P series), which represent the mean values of the standard deviations of all variables. Significant Vibra variables that do not overlap with the error bars through the standard error bar and showed a total of eight variables INT2A, INT1A, INT0A, A1X, A1, A3, A4X, A4 (Fig. 20, Figs. 21A to 21G). The meaning of each variable is as follows.

The parameters A1 to A4 mean the amplitude of vibration. Here, A1 is a value obtained by dividing a frame difference between two consecutive frames, that is, a difference in pixel brightness values between two frames and dividing by a specified brightness value. A2 is the sum of the difference in pixel brightness values between ten frames divided by the specified brightness value. A3 is a value obtained by dividing a frame difference between n consecutive frames, that is, a difference in pixel brightness values between n frames, and dividing by a specified brightness value. And, A4 refers to the numerical value of the variable A1 that filtered 10 frames. In addition, A1X and A4X represent the value which reduced the calculation period to 1/5 about A1 and A4, respectively.

Ca is the number of pixels in a given region, Cn is a pixel having a specified brightness value or more, and I is the brightness value of the pixel. INTEGR2A (INT2A) refers to the integration of 10 successive amplitude values, INTEGR1A (INT1A) refers to the integration of two successive amplitude values, and INTEGR0A (INT0A) refers to the integration of 100 amplitude values. Table 2 below shows the average values of the standard deviations of the ST and AT sections for the DI and NDI of the eight variables (INT2A, INT1A, INT0A, A1X, A1, A3, A4X, and A4).

variable	Judgment	ST standard deviation	AT standard deviation
INT2A	DI	1.705414561	5.874764465
INT2A	NDI	5.815323191	3.559773972
INT1A	DI	1.29207956	4.477642012
INT1A	NDI	5.122958741	2.724356877
INT0A	DI	0.533670826	1.567165346
INT0A	NDI	2.051277313	1.008865469
A1X	DI	0.022223139	0.068672766
A1X	NDI	0.067571792	0.0385023
A1	DI	0.128552334	0.388887857
A1	NDI	0.386579294	0.245803341
A3	DI	1.53244868	3.708567997
A3	NDI	3.6197355	2.174494412
A4X	DI	0.014232559	0.058963932
A4X	NDI	0.059123002	0.029261681
A4	DI	0.077705751	0.270309635
A4	NDI	0.311361106	0.161979558

21A to 21H are mean graphs and standard error histograms of standard deviations of DI and NDI in the ST and AT sections of each parameter.

As a result of data analysis using the average values of the standard deviations of the DI and NDI sections of the ST and AT sections of eight vibra variables, as shown in Table 3 below, DI has a minimum maximum rate of change in the ST and AT sections. NDI showed negative characteristics, and the minimum maximum rate of change in the ST and AT sections was negatively small.

	DI		NDI
	STAT SD MIN ROC%	STAT SD MAX ROC%	STAT SD MIN ROC%	STAT SD MAX ROC%
INT2A	134.97	405.016	-14.3	-56.276
INT1A	136.38	408.048	-25.55	-62.015
INT0A	100.31	330.513	-31.14	-64.87
A1X	110.78	353.027	-20.23	-59.3
A1	106.35	343.496	-10.98	-54.583
A3	65.073	254.785	-15.9	-57.091
A4X	182.59	507.363	-30.71	-64.648
A4	137.28	409.98	-27.17	-62.841

In the case of DI, the standard deviation of the AT section is larger than the standard deviation of the ST section, and in contrast to the NDI, the standard deviation of the ST section is larger than that of the AT section (Table 1). However, as a result of examining the mean values of 8 standard deviations by applying this primary criterion to individual samples, as shown in Table 4 below, the concordance rate between the primary criterion and the existing polygraph is shown. The concordance rate with the detection test result was remarkably decreased.

From here,

: Standard Deviation,

: Standard Error, *

: State Tracking (1 minute before the statement)

: Arrange tracking (frontal staring for 1 minute after statement). In the above equation, Droc is the rate of change of the standard deviation of the ST section and the AT section with standard errors in the DI determined data, and Nroc is the standard deviation of the ST section and the standard deviation of the AT section with standard errors from the determined data. The rate of change is shown.

The intermediate judgment result R is obtained from the following equation.

Here, X is the rate of change of the ST section standard deviation and the AT section standard deviation of the data obtained from the image. If the final result is 0 or 3, the judgment is impossible, 1 is the false symptom richness (DI), and 2 is false. It is determined by the small indication (NDI).

Variable name	% Match
INT2A	50
INT1A	45.3
INT0A	51.6
A1X	50
A1	51.6
A3	50
A4X	51.6
A4	45.3

Again, this study examined the agreement rate by dividing DI and NDI by setting the middle value of the upper and lower limits of each standard error as the threshold in the ST and AT sections of eight significant variables.

Threshold of DI: ST standard error upper limit + {(AT lower limit – ST upper limit) / 2}

NDI Threshold: AT standard error upper limit + {(ST lower limit – AT upper limit) / 2}

Based on this equation, the secondary criterion was divided into the case where DI was smaller than the threshold and the NDI was larger than the threshold, based on the STD threshold. Another third criterion is based on the standard error threshold of the AT section, DI is larger than the threshold value and NDI is smaller than the threshold value, and the concordance rate is examined. The results are shown in Table 5.

In the above, the determination result in the Rst: ST section is the standard deviation of the ST section of the data obtained from the Xst: image.

The determination result (Result) is obtained by the following formula.

In the false sign judgment, if the result of determination is 0, false sign is less (NDI), 1 is undeterminable, and 2 is false sign rich (DI).

Variable name	ST Threshold%	AT Threshold%
INT2A	46.9	59.4
INT1A	48.4	56.3
INT0A	51.6	62.5
A1X	46.9	57.8
A1	48.4	59.4
A3	53.1	62.5
A4X	50	56.3
A4	48.4	56.3

As a result, it was shown that the determination of AT standard error threshold shows higher agreement rate than that of ST standard error threshold value.

This low probability of agreement seems to be due to the fact that dividing DI and NDI based on specific thresholds is not appropriate because the deviation values of these variable values vary greatly within individual samples. In addition, these eight variables are variables that are very sensitive to movement, and there are many movements such as subjects moving, coughing, or suddenly turning their heads during the ballast period. Therefore, noise due to these movements is not considered. This is also because the data values were calculated in batches. In some cases, the data of some subjects may have an unusually high or low baseline even during the stabilization phase, and these uncommon individual data affect the mean value, which is a factor that improperly sets the threshold. .

In future work, critical ranges should be reset after removing them with appropriate groups, taking into account severe noise in individual data and abnormal data showing too high or low baselines. In addition, events that have very high traumatic emotional fluctuations (e.g., sex-related events) may have very large emotional changes in the Vibra Image program, so these events may be classified separately and revalidated. Also needed ..

Through the experiments that accompany the study of the present invention, we designed an algorithm for inferring a lie from the psychophysiological state of humans in a contactless manner. Effective variables for emotion inference were found as vibration image variables that were proved due to the differences between the induced stimuli of the neutral versus two-dimensional emotion model and the accompanying features. Through the present invention, the effective variables related to the lie according to the emotional state were found and through this, an algorithm capable of inferring the lie was designed. By identifying the parameters that show the same pattern when given the same stimulus, it was confirmed that vibration image technology can contribute to infer emotional state and classify emotional state. As the number of test subjects is small, there may be a limit in improving the accuracy of the algorithm, and the lighting may be the point of not finding a reference point for the numerical expression of each variable. However, by creating an algorithm that analyzes lies that can be inferred by inferring human basic emotions using images only, it shows the possibility of a new measurement method of lies.

To date, various exemplary embodiments of the present disclosure have been described and illustrated in the accompanying drawings. However, it should be understood that these embodiments are only part of the various embodiments. Various other modifications may occur to those skilled in the art.

Claims (13)

1. Acquiring a video from the subject before and after the statement about the predetermined question using a camera;
   Extracting at least one of parameters A1, A3, A4, A1X, A4X, INT0A, INT1A, INT2A from the video;
   Calculating a standard deviation from the parameters extracted in the above step;
   Determining whether the subject is false by using the standard deviation;
   Wherein said parameter is defined as follows.
   A1: The difference in pixel brightness values between two successive frames, divided by the specified brightness value
   A3: The sum of the difference in pixel brightness values between n frames divided by the specified brightness value
   A4: Number of variable A1 filtered 10 frames
   A1X, A4X: Reduced calculation period to 1/5 for each of A1 and A4
   INT2A: accumulation of 10 consecutive amplitude values
   INT1A: integration of two consecutive amplitude values,
   INT0A is the integration of 100 amplitude values.
2. The method of claim 1,
   And said standard deviation is an AT (Arrange Tracking) standard deviation after a statement obtained from a parameter extracted from a video after a testee's statement.
3. The method according to claim 1 or 2,
   The rate of change of the mean value of the standard deviation is obtained, and the lie detection method is characterized in that it is determined by using the rate of change.
4. The method of claim 3,
   In acquiring the video,
   Psychological preparation for the subject;
   This question step; And
   Finishing step; comprising a lie detection method comprising a.
5. The method according to claim 1 or 2,
   In acquiring the video,
   Psychological preparation for the subject;
   This question step; And
   Finishing step; comprising a lie detection method comprising a.
6. The method of claim 5,
   The psychological preparation step includes a stabilization step and an adaptation step;
   The present question step includes a filing step and a deepening step; and
   Wherein the finishing step comprises a terminating step and a static step.
7. The method of claim 4, wherein
   The psychological preparation step includes a stabilization step and an adaptation step;
   The present question step includes a filing step and a deepening step; and
   Wherein the finishing step comprises a terminating step and a static step.
8. The method of claim 1,
   Present a comparative question (CQ) and a relevant question (RQ) to the subject, and if the CQ value is greater than the RQ value by comparing the response variable values for the CQ and RQ questions, the response is true. , If the RQ value is greater than the CQ value is a false reaction, if the difference between the two values in the range of 10% detection is determined as undeterminable.
9. A lie detection device for performing the method according to claim 1,
   A camera photographing the subject;
   A processor configured to analyze an image obtained from a camera;
   A signal analyzer for extracting vibration parameters (parameters) using signals from the image processor and generating physiological signals using the signals; And a lie determination unit determining a lie by applying a physiological signal obtained from the signal analyzer.
10. The method of claim 9,
    And said standard deviation is an AT (Arrange Tracking) standard deviation after a statement obtained from a parameter extracted from a video after a testee's statement.
11. The method of claim 9,
    Present a comparative question (CQ) and a relevant question (RQ) to the subject, and if the CQ value is greater than the RQ value by comparing the response variable values for the CQ and RQ questions, the response is true. , If the RQ value is greater than the CQ value is a false reaction, if the difference between the two values in the range of 10% detection is determined as undeterminable.
12. The method according to claim 9,
    The rate of change of the average value of the standard deviation is obtained, and the lie detection device is characterized in that it is determined by using the rate of change.
13. The method of claim 12,
    Psychological preparation, including a stabilization and adaptation phase;
    The present question process including a filing step and an intensification step; And
    Lie detection device for determining whether the subject lies through the finishing process including the end step and the static step.

Images