JP6003752B2 - Crime prevention device, crime prevention method and crime prevention program - Google Patents

Description

  The present invention relates to a crime prevention device, a crime prevention method, and a crime prevention program.

  Various crime prevention efforts have been made to reduce damage from crimes such as wire fraud. As part of such efforts related to crime prevention, a technique for detecting an abnormality of a user who uses a device that executes transactions such as money transfer, for example, an ATM (automatic teller machine) has been proposed.

  As an example, there is an abnormal transaction detection device that interrupts the transfer when the judgment power estimated from the past transaction history or the transfer instruction operation corresponds to the abnormality determination condition. As another example, there is a mobile phone use detection alarm device that issues a warning regarding the occurrence of wire fraud when a human enters a predetermined area before ATM and a radio wave transmitted from the mobile phone is detected. As another example, it is determined whether or not the psychological state of the identified person is normal by measuring the pulse from the finger inserted into the finger insertion unit. And a personal recognition device for informing the user.

JP 2006-115865 A JP 2010-194005 A JP 2006-279996 A

  However, the above technique cannot improve the crime prevention performance without extra hardware.

  For example, in the above-described abnormal transaction detection device, whether or not to interrupt the transfer is determined based on the past transaction history, but there is no causal relationship between the content of the transaction and the state of the user. In other words, if the user has not encountered a transfer scam, there may be a transaction with no past record, or if the user has encountered a transfer scam, a transaction with a past record will be made. There is also. Further, in the above-described mobile phone use detection alarm device, a warning is not given if the radio wave of the mobile phone is not detected in the area before the ATM, but a call for prompting the transfer is not always made before the ATM. Therefore, there are cases where wire fraud cannot be suppressed. As described above, in the abnormal transaction detection device and the mobile phone use detection alarm device, there is a case in which the user's abnormality cannot be specified at the time of encountering a crime.

  Further, when the above-described mobile phone use detection device or the above-described personal recognition device is mounted, an antenna for detecting electric field strength or a pulse measurement device is installed for each ATM booth. As described above, the mobile phone use detection device and the personal recognition device cannot identify an abnormality of the user without providing an additional antenna or pulse measurement device.

  An object of one aspect is to provide a crime prevention device, a crime prevention method, and a crime prevention program that can improve crime prevention.

  The crime prevention device according to one aspect includes an acquisition unit that acquires an image captured by an imaging device that captures an image of a user of a device that executes a transaction relating to cash. Furthermore, the security device has an extraction unit that extracts a biological region included in the image. Furthermore, the crime prevention apparatus cancels out components in a specific frequency band other than the frequency band in which a pulse wave can be taken between the wavelength components from the representative value signal for each wavelength component of each pixel included in the living body region. A waveform detector for detecting the waveform of the received signal. Furthermore, the security device includes a determination unit that determines whether or not the waveform detected from the living body region is abnormal, and a notification unit that performs notification when the waveform is abnormal.

  According to one embodiment, crime prevention can be improved.

FIG. 1 is a block diagram illustrating a functional configuration of the crime prevention device according to the first embodiment. FIG. 2 is a diagram illustrating an example of a screen. FIG. 3 is a diagram illustrating an example of a screen. FIG. 4 is a diagram illustrating an example of the spectrum of each signal of the G signal and the R signal. FIG. 5 is a diagram illustrating an example of a spectrum of each signal of the R component multiplied by the G component and the correction coefficient k. FIG. 6 is a diagram illustrating an example of a spectrum after calculation. FIG. 7 is a block diagram illustrating a functional configuration of the waveform detection unit. FIG. 8 is a diagram illustrating an example of history information. FIG. 9 is a diagram illustrating an example of a normal distribution of heart rates. FIG. 10 is a diagram illustrating an example of a screen. FIG. 11 is a diagram illustrating an example of a screen. FIG. 12 is a flowchart illustrating the procedure of the transaction control process according to the first embodiment. FIG. 13 is a flowchart illustrating the procedure of the waveform detection process according to the first embodiment. FIG. 14 is a schematic diagram illustrating an example of a computer that executes a crime prevention program according to the first and second embodiments.

  Hereinafter, a crime prevention device, a crime prevention method, and a crime prevention program according to the present application will be described with reference to the accompanying drawings. Note that this embodiment does not limit the disclosed technology. Each embodiment can be appropriately combined within a range in which processing contents are not contradictory.

  First, the functional configuration of the crime prevention device according to the present embodiment will be described. FIG. 1 is a block diagram illustrating a functional configuration of the crime prevention device according to the first embodiment. An ATM (automatic teller machine) 10 shown in FIG. 1 is an automatic teller machine that performs transactions such as deposit, withdrawal, transfer, and balance inquiry using a bankbook or cash card.

  The ATM 10 detects, in a non-contact manner, a pulse wave detected from a face region in an image, that is, a change in blood volume associated with a heart beat, as a part of a security measure for suppressing damage caused by wire fraud. Has a crime prevention function to perform notification when the is abnormal.

  As one aspect, the security function can be implemented by installing or preinstalling a security program provided as package software or online software in an ATM or the like. As another aspect, as a monitoring system separate from ATM, by installing or pre-installing the above-mentioned crime prevention program in a monitoring device connected to a camera that shoots a person who makes a transaction with one or more ATMs It can also be implemented.

  As shown in FIG. 1, the ATM 10 includes a touch panel 11a, a card reader 11b, a camera 11c, and an ATM processing unit 12. Further, the ATM 10 includes an acquisition unit 13, an extraction unit 14, a waveform detection unit 15, a heart rate calculation unit 15a, a heart rate fluctuation calculation unit 15b, a history storage unit 16a, a determination unit 16, and a notification unit 17. Have Note that the ATM 10 may include various functional units included in a known ATM in addition to the functional units illustrated in FIG. For example, the ATM may have a physical key and a printer that can be complementarily operated with the touch panel 11a in addition to a coin processing unit such as a coin mech or a bill validator unit.

  Among these, the touch panel 11a is a displayable and inputable device. As an aspect, the touch panel 11a displays a menu screen including various transactions such as deposit, withdrawal, transfer, and balance inquiry. As another aspect, the touch panel 11a can provide guidance and guidance on shooting so that an image that can easily detect the pulse wave of the user of the ATM 10 can be obtained when “transfer” is selected on the menu screen. Display guidance. As a further aspect, the touch panel 11a displays a notification screen including a warning or the like indicating that there is a possibility of suffering damage such as wire fraud when there is an abnormality in the pulse wave of the ATM 10 user.

  The card reader 11b is a reading device that reads information recorded on a card inserted from a card insertion slot (not shown). As one aspect, the card reader 11b reads the account number of the user recorded on the card from the card inserted into the card insertion slot. The card reader 11b may be a type that reads information from a magnetic stripe card, or may be a type that reads information from an IC (Integrated Circuit) card.

  The camera 11c is an imaging device that includes an imaging element such as a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS). The camera 11c can be installed at any position as long as the face of the user who uses the ATM 10 is within the imaging range. For example, the camera 11c can be built in the ATM 10 or attached outside the ATM 10. You can also. For example, three or more types of light receiving elements such as R (red), G (green), and B (blue) can be mounted on the camera 11c. Here, the case where the ATM 10 has the camera 11c has been illustrated, but the ATM 10 does not necessarily have the camera 11c when an image showing the user's face can be acquired via a network or a storage device. .

  The ATM processing unit 12 is a processing unit that executes various transactions such as deposit, withdrawal, transfer, and balance inquiry. As an aspect, when accepting insertion of a card via a card insertion slot (not shown), the ATM processing unit 12 controls the card reader 11b to read the account number from the accepted card. Subsequently, after accepting selection of a menu displayed on the menu screen via the touch panel 11a, the ATM processing unit 12 further accepts the content of the transaction related to the menu. Thereafter, when receiving an instruction to execute a transaction, the ATM processing unit 12 determines whether or not the type of the menu that has received the selection is “transfer”.

  At this time, the ATM processing unit 12 communicates with a server device installed in a financial institution (not shown) when the type of the menu that has received the selection is not “transfer”, and the account number read from the card Execute the transaction for the account corresponding to. For example, if the menu type is “deposit”, the ATM processing unit 12 identifies the denomination and the number of coins inserted from a coin slot into a coin mech or bill valid unit (not shown). Then, the ATM processing unit 12 notifies the server device of the financial institution of a request for depositing the amount corresponding to the denomination and the number of sheets into the account balance corresponding to the account number read from the card. Thereafter, the ATM processing unit 12 displays the balance after deposit on the touch panel 11a, or prints out the balance using a printer (not shown). In addition, when the type of menu is “withdrawal”, the ATM processing unit 12 finances a request to withdraw the amount specified as the content of the transaction first from the account balance corresponding to the account number read from the card. Notify the institution's server device. Thereafter, when the completion of the withdrawal is notified from the server device of the financial institution, the ATM processing unit 12 pays out the money corresponding to the amount of the withdrawal, and displays the balance after the withdrawal on the touch panel 11a, Printing is output by a printer (not shown). In addition, when the menu type is “balance inquiry”, the ATM processing unit 12 inquires the balance of the account corresponding to the account number read from the card to the server device of the financial institution. Thereafter, the ATM processing unit 12 displays the balance of the account responded from the server device of the financial institution on the touch panel 11a or prints it out by a printer (not shown).

  On the other hand, when the type of the menu for which the selection has been accepted is “transfer”, the ATM processing unit 12 determines whether there is no abnormality in the pulse wave of the user who performs the transfer at the ATM 10. The acquisition unit 13 starts image acquisition. Thereafter, the ATM processing unit 12 performs transfer according to the content specified as the content of the transaction when the determination unit 16 described later determines that there is no abnormality in the user's pulse wave. That is, the ATM processing unit 12 withdraws the amount instructed to be transferred from the course corresponding to the account number read from the card, and issues a transfer request for paying the amount instructed to the transfer to the account of the transfer destination. Notify the server device. Then, when the completion of the transfer is notified from the server device of the financial institution, the ATM processing unit 12 displays the balance of the account after the transfer, the transfer destination and the amount of money transferred on the touch panel 11a, or a printer (not shown) To print out.

  The acquisition unit 13 is a processing unit that acquires an image. As one aspect, the acquisition unit 13 instructs the camera 11c to take a picture when the ATM processing unit 12 gives an instruction to start taking a picture, and acquires an image taken by the camera 11c. At this time, the acquisition unit 13 guides the position of the user's face within the imaging range of the camera 11c so that an image is captured in a state where the user's face of the ATM 10 is within the imaging range, or during shooting. Can warn you to keep your face still, or alert you that your face is not blocked by clothes or hair. FIG. 2 is a diagram illustrating an example of a screen. For example, as shown in FIG. 2, an aiming screen including an image photographed by the camera 11c can be displayed on the touch panel 11a, and guidance can be provided so that the user's face is reflected in the aiming screen. As another aspect, the acquisition unit 13 acquires an image from an auxiliary storage device such as a hard disk or an optical disk or a removable medium such as a memory card or a USB (Universal Serial Bus) memory that stores an image of the user's face. It can also be acquired. As a further aspect, the acquisition unit 13 can also acquire an image received from an external device via a network. In addition, although the acquisition part 13 illustrated the case where a process is performed using image data, such as two-dimensional bitmap data obtained from the output by image pick-up elements, such as CCD and CMOS, and vector data, it outputs from one detector. It is also possible to acquire the processed signal as it is and execute the subsequent processing.

  The extraction unit 14 is a processing unit that extracts a region that is a pulse wave detection target from the image acquired by the acquisition unit 13. As one aspect, each time an image is acquired by the acquisition unit 13, the extraction unit 14 performs image processing such as template matching on the image to obtain a predetermined facial part such as a user's eyes, nose, and lips. Extract facial regions including cheeks and hair. At this time, the extraction unit 14 can also urge attention so that the face of the user of the ATM 10 does not deviate from the imaging range of the camera 11c during detection of the pulse wave. FIG. 3 is a diagram illustrating an example of a screen. For example, as shown in FIG. 3, when the movement of a face area extracted by image processing, for example, the vertex or the center of gravity of the face area exceeds a predetermined number of pixels between image frames, the face is removed from the aiming screen. It is possible to display a message for calling attention on the touch panel 11a or to output a voice from a speaker (not shown).

  After extracting the face area, the extraction unit 14 performs a predetermined statistical process on the pixel value of each pixel included in the face area. For example, the extraction unit 14 averages the pixel values of each pixel included in the face area for each wavelength component. In addition to the average value, the median value and the mode value may be calculated. In addition to the weighted average, an arbitrary average process such as a weighted average or a moving average may be executed. As a result, an average value of pixel values of each pixel included in the face area is calculated for each wavelength component as a representative value representing the face area.

  The waveform detection unit 15 uses a specific frequency band other than the pulse wave frequency band in which the pulse wave can be taken between the respective wavelength components from the signal of the representative value for each wavelength component of each pixel included in the detection target region of the pulse wave. It is a processing part which detects the waveform of the signal from which these components were mutually canceled.

  As an aspect, the waveform detection unit 15 includes three wavelength components included in the image, that is, representative values of the two wavelength components of the R component and the G component, which have different blood absorption specifications among the R component, the G component, and the B component. The waveform is detected using the time series data.

  To explain this, there are capillaries on the face surface, and when the blood flow flowing through the blood vessels changes due to the heartbeat, the amount of light absorbed by the bloodstream also changes according to the heartbeat. The brightness that is produced also changes with the heartbeat. Although the amount of change in luminance is small, when the average luminance of the entire face region is obtained, the time-series data of luminance includes a pulse wave component. However, the luminance also changes due to body movement in addition to the pulse wave, and this becomes a noise component of pulse wave detection, so-called body movement artifact. Therefore, a pulse wave is detected with two or more wavelengths having different light absorption characteristics of blood, for example, a G component having a high light absorption characteristic (about 525 nm) and an R component having a low light absorption characteristic (about 700 nm). Since the heart rate is in the range of 30 bpm to 240 bpm when converted to 0.5 Hz to 4 Hz per minute, other components can be regarded as noise components. Assuming that noise does not have wavelength characteristics or is minimal even if it is present, components other than 0.5 Hz to 4 Hz should be equal between the G signal and the R signal. Is different. Therefore, by correcting the sensitivity difference between components other than 0.5 Hz to 4 Hz and subtracting the R component from the G component, the noise component can be removed and only the pulse wave component can be extracted.

  For example, the G component and the R component can be represented by the following formula (1) and the following formula (2). “Gs” in the following equation (1) indicates the pulse wave component of the G signal, “Gn” indicates the noise component of the G signal, and “Rs” in the following equation (1) indicates the R signal. “Rn” indicates the noise component of the R signal. Further, since the noise component has a sensitivity difference between the G component and the R component, the correction coefficient k for the sensitivity difference is expressed by the following equation (3).

Ga = Gs + Gn (1)
Ra = Rs + Rn (2)
k = Gn / Rn (3)

  When the sensitivity difference is corrected and the R component is subtracted from the G component, the pulse wave component S is expressed by the following equation (4). When this is transformed into the formula represented by Gs, Gn, Rs and Rn using the above formula (1) and the above formula (2), the following formula (5) is obtained, and further, the above formula (3 ) To eliminate k and arrange the equations, the following equation (6) is derived.

S = Ga-kRa (4)
S = Gs + Gn−k (Rs + Rn) (5)
S = Gs− (Gn / Rn) Rs (6)

  Here, the G signal and the R signal have different light absorption characteristics, and Gs> (Gn / Rn) Rs. Therefore, the pulse wave component S from which noise is removed can be calculated by the above equation (6).

  FIG. 4 is a diagram illustrating an example of the spectrum of each signal of the G signal and the R signal. The vertical axis of the graph shown in FIG. 4 indicates the signal intensity, and the horizontal axis indicates the frequency (bpm). As shown in FIG. 4, since the sensitivity of the image sensor differs between the G component and the R component, the signal strengths of the two differ. On the other hand, in both the R component and the G component, there is no change in that noise appears outside the range of 30 bpm to 240 bpm, particularly in a specific frequency band of 3 bpm or more and less than 20 bpm. For this reason, as shown in FIG. 4, the signal intensity corresponding to the specified frequency Fn included in the specific frequency band of 3 bpm or more and less than 20 bpm can be extracted as Gn and Rn. The sensitivity difference correction coefficient k can be derived from these Gn and Rn.

  FIG. 5 is a diagram illustrating an example of a spectrum of each signal of the R component multiplied by the G component and the correction coefficient k. In the example of FIG. 5, the result of multiplying the absolute value of the correction coefficient is shown for convenience of explanation. Also in the graph shown in FIG. 5, the vertical axis indicates the signal intensity, and the horizontal axis indicates the frequency (bpm). As shown in FIG. 5, when the spectrum of each signal of the G component and the R component is multiplied by the correction coefficient k, the sensitivity is uniform between the components of the G component and the R component. In particular, the spectrum signal intensity in a specific frequency band is almost the same in most spectrum signals. On the other hand, in the peripheral region 400 of the frequency where the pulse wave is actually included, the signal intensity of the spectrum is not uniform between the G component and the R component.

  FIG. 6 is a diagram illustrating an example of a spectrum after calculation. In FIG. 6, the scale of the signal intensity, which is the vertical axis, is enlarged from the viewpoint of improving the visibility of the frequency band in which the pulse wave appears. As shown in FIG. 6, when the spectrum of the R signal after the multiplication of the correction coefficient k is subtracted from the spectrum of the G signal, a signal in which a pulse wave appears due to a difference in light absorption characteristics between the G component and the R component. It can be seen that the noise component is reduced with the strength of the component maintained as much as possible. In this way, it is possible to detect a pulse wave waveform from which only noise components have been removed.

  Next, the functional configuration of the waveform detector 15 will be described more specifically. FIG. 7 is a block diagram showing a functional configuration of the waveform detector 15. As shown in FIG. 7, the waveform detection unit 15 includes BPFs (Band-Pass Filters) 152R and 152G, extraction units 153R and 153G, LPFs (Low-Pass Filters) 154R and 154G, a calculation unit 155, and a BPF 156R. 156G, a multiplication unit 157, and a calculation unit 158. In the example of FIGS. 4 to 6, the example in which the pulse wave is detected in the frequency space has been described. However, in FIG. 7, the noise in the time series space is reduced from the viewpoint of reducing the time required for the conversion to the frequency component. The functional structure in the case of detecting a pulse wave by canceling components is shown.

  For example, the time-series data of the R signal using the representative value of the R component pixel value of each pixel included in the face region as the signal value is input from the extraction unit 14 to the waveform detection unit 15, and is also input to the face region. The time series data of the G signal having the representative value of the G component pixel value of each included pixel as the signal value is input. Among these, the R signal of the face area is input to the BPF 152R and the BPF 156R in the waveform detection unit 15, and the G signal of the face area is input to the BPF 152G and the BPF 156G in the waveform detection unit 15.

  Each of BPF 152R, BPF 152G, BPF 156R, and BPF 156G is a band-pass filter that passes only signal components in a predetermined frequency band and removes signal components in other frequency bands. These BPF 152R, BPF 152G, BPF 156R, and BPF 156G may be implemented by hardware, or may be implemented by software.

  The difference in the frequency band that the BPF passes will be described. The BPF 152R and the BPF 152G pass a signal component in a specific frequency band in which a noise component appears more noticeably than other frequency bands.

  Such a specific frequency band can be determined by comparing with a frequency band that can be taken by a pulse wave. An example of a frequency band that can be taken by a pulse wave is a frequency band of 0.5 Hz to 4 Hz, and a frequency band of 30 bpm to 240 bpm when converted per minute. From this, as an example of the specific frequency band, a frequency band of less than 0.5 Hz and more than 4 Hz that cannot be measured as a pulse wave can be employed. Further, the specific frequency band may partially overlap with the frequency band that can be taken by the pulse wave. For example, it is allowed to overlap with the frequency band that the pulse wave can take in the section of 0.7 Hz to 1 Hz that is difficult to be measured as a pulse wave, and the frequency band of less than 1 Hz and 4 Hz or more is adopted as the specific frequency band. You can also Further, the specific frequency band can be narrowed down to a frequency band in which noise is more noticeable with the frequency band of less than 1 Hz and 4 Hz or more as the outer edge. For example, noise appears more prominently in a lower frequency band than a frequency band in which a pulse wave can be taken, compared to a high frequency band in which the pulse wave can be taken. For this reason, a specific frequency band can also be narrowed down to a frequency band of less than 1 Hz. Further, since there are many differences in the sensitivity of the image sensor of each component in the vicinity of the direct current component where the spatial frequency is zero, the specific frequency band can be narrowed down to a frequency band of 3 bpm or more and less than 60 bpm. Further, the specific frequency band can be narrowed down to a frequency band of 3 bpm to less than 20 bpm in which noise such as flickering of ambient light other than human body movement, for example, blinking or shaking of the body, is likely to appear.

  Here, as an example, the following description will be made assuming that the BPF 152R and the BPF 152G pass a signal component in a frequency band of 0.05 Hz to 0.3 Hz as a specific frequency band. Here, the case where a bandpass filter is used to extract a signal component in a specific frequency band is illustrated, but a low-pass filter is used when a signal component in a frequency band below a certain frequency is extracted. You can also

  On the other hand, the BPF 156R and the BPF 156G pass signal components in a frequency band that can be taken by a pulse wave, for example, a frequency band of 1 Hz to 4 Hz. Hereinafter, a frequency band that can be taken by a pulse wave may be referred to as a “pulse wave frequency band”.

  The extraction unit 153R extracts the absolute intensity value of the signal component in the specific frequency band of the R signal. For example, the extraction unit 153R extracts the absolute intensity value of the signal component in the specific frequency band by executing a multiplication process that powers the signal component in the specific frequency band of the R component. Further, the extraction unit 153G extracts the absolute intensity value of the signal component in the specific frequency band of the G signal. For example, the extraction unit 153G extracts the absolute intensity value of the signal component in the specific frequency band by executing a multiplication process that powers the signal component in the specific frequency band of the G component.

  The LPF 154R and the LPF 154G are low-pass filters that perform a smoothing process that responds to time changes on time-series data of absolute intensity values in a specific frequency band. The LPF 154R and the LPF 154G are the same except that the signal input to the LPF 154R is an R signal and the signal input to the LPF 154G is a G signal. By such smoothing processing, absolute value intensities R′n and G′n in a specific frequency band are obtained.

  The calculation unit 155 divides the absolute value strength G′n of the specific frequency band of the G signal output by the LPF 154G by the absolute value strength R′n of the specific frequency band of the R signal output by the LPF 154R. n / R'n "is executed. Thereby, a correction coefficient k for the sensitivity difference is calculated.

  The multiplier 157 multiplies the signal component in the pulse wave frequency band of the R signal output from the BPF 156R by the correction coefficient k calculated by the calculator 155.

  The arithmetic unit 158 subtracts the signal component of the pulse wave frequency band of the G signal output by the BPF 156G from the signal component of the pulse wave frequency band of the R signal multiplied by the correction coefficient k by the multiplier 157 “k * Rs. -Gs "is executed. The time series data of the signal obtained by such calculation corresponds to the waveform of the pulse wave. The waveform of the pulse wave detected from the face region in this way is output to the heart rate calculation unit 15a and the heart rate fluctuation calculation unit 15b.

  Returning to the description of FIG. 1, the heart rate calculation unit 15 a is a processing unit that calculates a heart rate from a signal detected by the waveform detection unit 15. As one aspect, the heart rate calculation unit 15a detects a peak of a signal waveform, for example, a maximum point, over a detection period in which the signal is detected by the waveform detection unit 15, for example, 30 seconds or 1 minute. As a result, an R wave, a T wave, or the like included in a single heartbeat signal can be detected. After that, the heart rate calculation unit 15a counts the number of peaks detected during the detection period, and converts the number of peaks into the number of peaks per unit time. For example, when the detection period is 30 seconds and the unit time is 1 minute, the number of peaks detected in 30 seconds is divided by the detection period of 30 seconds, and the divided value is 60 seconds (= 1). Heart rate is calculated by multiplying by (min). In addition, although the case where the heart rate is calculated by counting the number of peaks in the detection period is illustrated here, the time series data of the signal is converted into a frequency component and the signal is transmitted in a pulse wave frequency band of 1 Hz to 4 Hz. It is also possible to calculate the frequency of the peak intensity as the heart rate. For such conversion to frequency components, discrete Fourier transform, so-called DFT (Discrete Fourier Transform), Fourier transform, Fast Fourier Transform (FFT), Discrete Cosine Transform (DCT), or the like is applied. Can do.

  The heart rate variability calculation unit 15 b is a processing unit that calculates heart rate variability from the signal detected by the waveform detection unit 15. As one aspect, the heart rate variability calculation unit 15b detects a peak of a signal waveform, for example, a maximum point, over a detection period in which the signal is detected by the waveform detection unit 15, for example, 30 seconds or 1 minute. As a result, an R wave, a T wave, or the like included in a single heartbeat signal can be detected. The heart rate variability calculation unit 15b measures a peak interval, so-called RRI (R-R Interval), and converts the time variation of RRI, that is, heart rate variability, into frequency components. After that, the heartbeat fluctuation calculation unit 15b calculates a low frequency component LF and a high frequency component HF from the spectrum of the heartbeat fluctuation. Then, the heartbeat fluctuation calculation unit 15b calculates the ratio of the low frequency component LF to the high frequency component HF, for example, LF / HF. As an example of the low frequency component LF, a representative value of the signal intensity in the frequency band of 0.05 Hz to 0.2 Hz, for example, an average value or an integral value can be employed. As an example of the high frequency component HF, 0. A representative value of signal intensity in a frequency band of 2 Hz to 0.35 Hz can be adopted.

  The history storage unit 16a is a storage unit that stores a history of pulse waves related to a customer who has an account at a financial institution. As one aspect of the history storage unit 16a, information in which the customer's heart rate distribution is associated with each customer's account number can be employed. FIG. 8 is a diagram illustrating an example of history information. In FIG. 8, the history of one customer that has been detected in the past as the heart rate of the customer is illustrated by a histogram. In the example shown in FIG. 8, it can be seen that the customer's heart rate is concentrated in a range of approximately 70 bpm or more and less than 100 bpm. In addition, although the case where the heart rate history is stored for each individual is illustrated here, the heart rate history of a standard person can also be stored. In this case, the heart rate history can be stored by classification by age and gender. Further, here, the case of storing the history of the heart rate of the customer is illustrated, but the history of heart rate variability, for example, the history of heart rate variability and LF / HF can be stored for each customer.

  The determination unit 16 is a processing unit that determines whether or not there is an abnormality in the waveform of the signal detected by the waveform detection unit 15. As one aspect, the determination unit 16 calculates an “abnormal score” described below using the heart rate calculated by the heart rate calculation unit 15 a and the LF / HF calculated by the heart rate fluctuation calculation unit 15 b. The “abnormal score” referred to here is an index whose value is set higher as the pulse wave of the ATM 10 user is more likely to be abnormal. For example, the heart rate and heart rate variability deviate from the standard values. A higher value is calculated as the degree is higher. In the following, a case where an abnormal score is calculated is exemplified, but a normal score that increases as the possibility that the pulse wave is normal may be calculated.

  More specifically, the determination unit 16 searches the history storage unit 16a for a history of pulse waves that matches the account number read from the card. At this time, if the history of the pulse wave that matches the account number read from the card exists in the history storage unit 16a, that is, if the history of the user of the ATM 10 exists, the determination unit 16 determines the history storage unit 16a. To read the history of the user of ATM10. On the other hand, when there is no ATM 10 user history in the history storage unit 16 a, the determination unit 16 reads a standard person history from the history storage unit 16 a. Thereafter, the determination unit 16 calculates a heart rate abnormality score and a heart rate variability abnormality score using the pulse wave history read from the history storage unit 16a.

  For example, when calculating an abnormal score of heart rate, the determination unit 16 calculates a normal distribution of heart rates after calculating the average and variance of the heart rate history. FIG. 9 is a diagram illustrating an example of a normal distribution of heart rates. FIG. 9 shows a normal distribution calculated from the heart rate history shown in FIG. For example, the determination unit 16 increases the score value as the heart rate calculated by the heart rate calculation unit 15a deviates from a predetermined interval of the normal distribution of heart rates, for example, the 95% interval corresponding to the fill shown in FIG. Calculate a higher anomaly score. As an example, the determination unit 16 calculates the abnormal heart rate score as “0” when the heart rate calculated by the heart rate calculation unit 15a is included in the 95% section. On the other hand, when the heart rate calculated by the heart rate calculation unit 15a is not included in the 95% interval, the determination unit 16 increases the value of the heart rate so as to deviate from the lower limit value or the upper limit value of the 95% interval. Calculated as an abnormal score. The degree of deviation from the threshold value of the lower limit value or the upper limit value and the rate of increase of the abnormal score may be linear or non-linear. Here, when a user of ATM 10 encounters a transfer fraud, it is highly likely that the user is in a tense state. Therefore, when the heart rate falls below the lower limit of the 95% interval, the degree of deviation from the threshold is the same. Even if the heart rate is higher than the upper limit value of the 95% interval, a lower abnormal score may be derived. If the heart rate is lower than the lower limit value of the 95% interval, the pulse wave Remeasurement may be performed.

  Here, the case where the abnormal score of the heart rate is calculated has been described. Similarly, after calculating the normal distribution of LF / HF, the LF / HF calculated by the heart rate variability calculation unit 15b and the normal distribution of 95 are calculated. An abnormal score of heart rate variability can be calculated by comparing the% interval. Here, the low frequency component LF is affected by the sympathetic nerve and the parasympathetic nerve, the high frequency component HF is subjected to the parasympathetic nerve, and furthermore, when the ratio LF / HF is low, the stress is low. It is known that it can be estimated that the state is high. Therefore, the abnormality score when LF / HF falls below the lower limit value of the 95% interval can be calculated higher than the abnormality score when LF / HF exceeds the upper limit value of the 95% interval.

  Thus, after calculating the abnormal score of heart rate and the abnormal score of heart rate variability, the determination unit 16 calculates the total abnormal score. For example, the determination unit 16 can also calculate the sum of the abnormal heart rate score and the abnormal heart rate fluctuation score as the total abnormal score, and the average of the abnormal heart rate score and the abnormal heart rate score can be calculated as the overall abnormal score. It can also be calculated as a score. The determination unit 16 can also calculate a total abnormality score by performing a predetermined weighting on the abnormality score of the heart rate and the abnormality score of the heart rate variability, and then calculating the sum and average. As an example of such weighting, a larger weight can be given to a heart rate and a heart rate variability that can be expected to have a higher detection accuracy, and a smaller weight can be given to a higher probability that the detection accuracy is lower. Although the case where the abnormal score is calculated using two of the heart rate and the heart rate variability is illustrated here, the abnormal score may be calculated by focusing on one of them.

  Here, the determination unit 16 determines whether or not the total abnormality score is equal to or less than a predetermined threshold. At this time, when the total abnormality score is equal to or less than the threshold value, it can be estimated that the user of the ATM 10 is in a state where there is no excessive tension or stress. In this case, it can be determined that there is a low possibility that the user of the ATM 10 is suffering from a crime such as a transfer fraud. On the other hand, when the total abnormality score exceeds the threshold, it can be estimated that the user of ATM 10 feels excessive tension or stress. In this case, it can be determined that there is a risk that the user of the ATM 10 is suffering from a crime such as a transfer fraud.

  The alerting | reporting part 17 is a process part which alert | reports to the user of ATM10. As an aspect, when the determination unit 16 determines that the total abnormality score exceeds the threshold, the notification unit 17 determines whether the number of pulse wave detection retries is less than a predetermined number. At this time, when the number of pulse wave detection retries is less than a predetermined number, the notification unit 17 causes the waveform detection unit 15 to retry detection of the pulse wave.

  As described above, the reason why the abnormality is not notified immediately because the total abnormality score exceeds the threshold value is because the cause of the fluctuation of the heart rate rise or heart rate fluctuation is not always a crime such as a transfer fraud. . In other words, factors other than crime, such as running up to ATM10, climbing up and down stairs and hills, etc., may cause heart rate fluctuations and heart rate fluctuation fluctuations. It is.

  In this case, the notification unit 17 displays the screen illustrated in FIG. 10 on the touch panel 11a. FIG. 10 is a diagram illustrating an example of a screen. As shown in FIG. 10, when the user of the ATM 10 is prompted to wait on the touch panel 11a, the user waits until the next notification is made. For this reason, even if the user is exercising vigorously, the heart rate rise and heart rate fluctuation fluctuations can be returned to the state before the exercise. In addition, even if the user encounters a crime such as wire fraud, even if the detection of the pulse wave is retried, the transfer is still not completed, and the cause of the heart rate rise and abnormal heart rate fluctuation has been resolved Therefore, the overall abnormality score calculated next time is also likely to exceed the threshold. Therefore, time can be gained without any crime prevention effect.

  On the other hand, the notification unit 17 notifies the abnormality when the number of retries for detecting the pulse wave is equal to or greater than a predetermined number. For example, the notification unit 17 displays the screen shown in FIG. 11 on the touch panel 11a, and a user of the ATM 10 uses a transfer fraud or the like on a terminal used by an operator of the ATM 10 or a staff of a financial institution, such as an intercom or a mobile terminal. Notify you that you may have encountered a crime. FIG. 11 is a diagram illustrating an example of a screen. For example, as shown in FIG. 11, the user of ATM 10 is notified that the operator has been called. Thereafter, the operator who has arrived at the ATM 10 can explain to the user of the ATM 10 that he / she has encountered a crime such as a transfer fraud. Thereby, the user of ATM10 can judge the necessity of transfer appropriately, and, as a result of suppressing a transfer fraud, can improve crime prevention.

  The ATM processing unit 12, the acquisition unit 13, the extraction unit 14, the waveform detection unit 15, the heart rate calculation unit 15a, the heart rate fluctuation calculation unit 15b, the determination unit 16, and the notification unit 17 are described above. It can be realized by causing a CPU (Central Processing Unit) or MPU (Micro Processing Unit) to execute a security program. Each functional unit described above can also be realized by a hard wired logic such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  Further, a semiconductor memory element or a storage device can be adopted for the history storage unit 16a. For example, examples of the semiconductor memory device include a video random access memory (VRAM), a random access memory (RAM), a read only memory (ROM), and a flash memory. Further, examples of the storage device include storage devices such as a hard disk and an optical disk.

[Process flow]
Next, the flow of processing of the ATM 10 according to the present embodiment will be described. Here, after (1) transaction control processing executed by the ATM 10 is described, (2) waveform detection processing executed as a subroutine of the transaction control processing will be described.

(1) Transaction Control Processing FIG. 12 is a flowchart illustrating a transaction control processing procedure according to the first embodiment. This transaction control process is started when a card is inserted into the card insertion slot by a user of the ATM 10.

  As shown in FIG. 12, when the insertion of the card is received through a card insertion slot (not shown), the ATM processing unit 12 controls the card reader 11b to read the account number from the card that has accepted the insertion (step S101).

  Subsequently, after accepting selection of the menu displayed on the menu screen via the touch panel 11a, the ATM processing unit 12 further accepts the content of the transaction related to the menu (Step S102 and Step S103). Thereafter, when receiving an instruction to execute a transaction (step S104), the ATM processing unit 12 determines whether or not the type of the menu that has been selected in step S102 is “transfer” (step S105).

  At this time, if the menu type is not “transfer” (No in step S105), the ATM processing unit 12 communicates with the server device installed in the financial institution and sets the account number read from the card. Transaction is executed for the corresponding account (step S106), and the process is terminated.

  On the other hand, when the menu type is “transfer” (Yes in step S105), a pulse wave frequency band between each wavelength component from a representative value signal for each wavelength component of each pixel included in the face area in the image. “Waveform detection processing” is executed to detect the waveform of the signal in which the components in the specific frequency band other than those are canceled out (step S107).

  Thereafter, the heart rate calculation unit 15a calculates the heart rate from the signal detected by the waveform detection unit 15, and the heart rate variation calculation unit 15b calculates the heart rate variation from the signal detected by the waveform detection unit 15 (step). S108). Subsequently, the determination unit 16 searches the history storage unit 16a for the pulse wave history that matches the account number read from the card, that is, the history of the user of the ATM 10 (step S109).

  At this time, when the ATM 10 user history exists (step S109 Yes), the determination unit 16 reads the ATM 10 user history from the history storage unit 16a (step S110). On the other hand, when there is no ATM 10 user history (No in step S109), a standard person history is read from the history storage unit 16a (step S111).

  Thereafter, the determination unit 16 calculates a total abnormality score of the heart rate and the heart rate variability using the heart rate and heart rate variability calculated in step S108 and the history of the pulse wave read in step 110 or step S111. (Step S112).

  Here, the determination unit 16 determines whether or not the total abnormality score is equal to or less than a predetermined threshold (step S113). At this time, when the total abnormality score is equal to or less than the threshold (Yes in step S113), it can be determined that the user of the ATM 10 is unlikely to have suffered a crime such as a transfer fraud. In this case, the ATM processing unit 12 communicates with the server device installed in the financial institution, and sends the designated amount to the designated transfer destination for the account corresponding to the account number read from the card. The transaction “transfer” to be transferred is executed (step S106), and the process is terminated.

  On the other hand, when the total abnormality score exceeds the threshold (No in step S113), it can be estimated that the user of the ATM 10 feels excessive tension or stress. In this case, it can be determined that there is a risk that the user of the ATM 10 is suffering from a crime such as a transfer fraud. In this case, the notification unit 17 determines whether or not the number of pulse wave detection retries is less than a predetermined number (step S114).

  At this time, when the number of retries for detecting the pulse wave is less than the predetermined number (step S114 Yes), the notification unit 17 notifies the user that the pulse wave is to be measured again via the touch panel 11a (step S115). The processes from step S107 to step S113 are repeated.

  Further, when the number of pulse wave detection retries is equal to or greater than the predetermined number (No in step S114), the notification unit 17 notifies the operator that the operator is being called, and the income or mobile terminal used by the operator. In such a case, the fact that there is a possibility that the user of the ATM 10 has encountered a crime such as a transfer fraud is notified (step S116), and the process is terminated.

(2) Waveform Detection Processing FIG. 13 is a flowchart illustrating a procedure of waveform detection processing according to the first embodiment. This process is a process corresponding to step S107 shown in FIG. 12, and is started when the menu type is “transfer”.

  As illustrated in FIG. 13, the acquisition unit 13 acquires an image captured by the camera 11c (step S201), and displays a face aiming screen including the image acquired in step S201 on the touch panel 11a (step S202). .

  Subsequently, the extraction unit 14 performs image processing such as template matching on the image acquired in step S201 to thereby include a face area including predetermined face parts, for example, the user's eyes, nose, lips, cheeks and hair. Is extracted (step S203).

  Then, the extraction unit 14 calculates the representative value of the pixel value of each pixel included in the face area extracted in step S203 for each wavelength component of the G component and the R component (step S204). As a result, an R signal that is a representative value of the R component of the face area is output to the BPF 152R and the BPF 156R, and a G signal that is a representative value of the G component of the face area is output to the BPF 152G and the BPF 156G.

  Subsequently, the BPF 152R extracts a signal component of a specific frequency band of the R signal, for example, a frequency band of 3 bpm or more and less than 20 bpm, and the BPF 152G extracts a signal component of the specific frequency band of the G signal (Step S205A).

  Then, the extraction unit 153R extracts the absolute intensity value of the signal component in the specific frequency band of the R signal, and the extraction unit 153G extracts the absolute intensity value of the signal component in the specific frequency band of the G signal (step S206). .

  After that, the LPF 154R executes a smoothing process for responding to the time change on the time series data of the absolute intensity value in the specific frequency band of the R signal, and the LPF 154G A smoothing process for responding to time changes is executed on the series data (step S207).

  Subsequently, the calculation unit 155 divides the absolute value strength G′n of the specific frequency band of the G signal output by the LPF 154G by the absolute value strength R′n of the specific frequency band of the R signal output by the LPF 154R. The correction coefficient k is calculated by executing “G′n / R′n” (step S208).

  In parallel with the processing in step S205A, the BPF 156R extracts a signal component in the pulse wave frequency band of the R signal, for example, a frequency band of 42 bpm or more and less than 240 bpm, and the BPF 156G is a signal in the pulse wave frequency band of the G signal. Components are extracted (step S205B).

  Thereafter, the multiplication unit 157 multiplies the signal component in the pulse wave frequency band of the R signal extracted in step S205B by the correction coefficient k calculated in step S208 (step S209). Then, the calculation unit 158 subtracts the signal component in the pulse wave frequency band of the G signal extracted in step S205B from the signal component in the pulse wave frequency band of the R signal multiplied by the correction coefficient k in step S209. “K * Rs−Gs” is executed (step S210). The time-series data of the signal obtained by the calculation in step S210 corresponds to the pulse wave waveform.

  Subsequently, the acquisition unit 13 determines whether or not a predetermined detection period, for example, 30 seconds has elapsed since the start of pulse wave detection (step S211). At this time, if the detection period has not elapsed (No in step S211), the extraction unit 14 determines whether the movement of the face area extracted by image processing between image frames is within an allowable range, for example, a face It is determined whether or not the amount of movement such as the vertex or the center of gravity of the region is within a predetermined number of pixels (step S212).

  If the movement of the face area is outside the allowable range (No in step S212), the extraction unit 14 displays a message on the touch panel 11a so as not to remove the face from the aiming screen, or from a speaker (not shown). The voice is output (step S213), and the processing from step S201 to step S210 is repeatedly executed.

  As described above, the processing from step S201 to step S210 is repeatedly executed until the detection period elapses after the detection of the pulse wave (No in step S211), and the detection period elapses after the detection of the pulse wave is started. Then (Yes in step S211), the process ends.

[Effect of Example 1]
As described above, the ATM 10 according to the present embodiment detects a signal in which noise other than the pulse wave component has been removed from the representative value signal of the face area reflected in the image captured by the user who performs the transfer, etc. Notification is executed when the signal is abnormal. For this reason, in ATM10 which concerns on a present Example, a pulse wave can be detected from an image non-contactingly, and installation and mounting | wearing of a sensor etc. can be made unnecessary. Furthermore, in ATM10 which concerns on a present Example, since it determines whether the pulse wave which has a close relationship with a user's tension | tensile_strength and stress is abnormal, abnormality which appears to a user at the time of encounter of crimes, such as a transfer fraud, is detected. Can be identified. Therefore, according to ATM10 which concerns on a present Example, crime prevention can be improved without extra hardware.

  Although the embodiments related to the disclosed apparatus have been described above, the present invention may be implemented in various different forms other than the above-described embodiments. Therefore, another embodiment included in the present invention will be described below.

[Application Example 1]
In the first embodiment, the example in which it is determined whether or not the pulse wave is abnormal when the type of the menu is “transfer” has been described. It may be possible to determine the abnormality. For example, if the amount specified for the transfer is greater than or equal to the specified amount, or if the amount of money that has been transferred in the past is referred to and exceeds the average, median, or maximum value, the pulse wave is judged to be abnormal. You may make it do.

[Application 2]
In the first embodiment, the case where the notification is executed based on whether the pulse wave is abnormal is exemplified. However, it may be controlled whether the notification is executed from another phenomenon. Absent. For example, the ATM 10 further applies an algorithm such as a corneal reflection method to an image captured by the camera 11c, and further includes a gaze detection unit that detects a position of the viewpoint pointed by the direction of the gaze from the center position of the pupil of the eyeball, that is, a so-called gaze point. It can also be implemented. In addition, the ATM 10 can also perform notification when the frequency at which the viewpoint position moves over a certain distance or more exceeds a predetermined number of times. Moreover, ATM10 can perform alerting | reporting, when the frequency | count that the position of the viewpoint turned to the back of a user, or the frequency | count which turned to the arrangement position of a guard exceeds a predetermined frequency | count. The determination using the position of the line of sight described above and the determination using the heart rate or heart rate variability described in the first embodiment may be implemented in combination. In this case, as an example, after calculating an abnormal score for the line of sight, a total abnormal score can be obtained between the abnormal score for heart rate and / or the abnormal score for heart rate variability.

[Application Example 3]
In the first embodiment described above, an example in which notification is executed when the total abnormality score exceeds the threshold value has been described. However, not only the notification but also other crime countermeasures can be executed. For example, the ATM 10 can stop the transaction itself when the total abnormal score exceeds a threshold value.

  In the first embodiment, the case where the notification is controlled based on whether the abnormal score exceeds the threshold is exemplified. However, the normal distribution in which the pulse wave is calculated from the history without necessarily being scored. For example, you may control whether alerting | reporting is performed by whether it is contained in a 95% area. In the first embodiment, the history is set as the appropriate range. However, the standard heart rate range or LF / HF is set as the appropriate range, and whether the heart rate deviates from the appropriate range or whether LF / HF is Whether or not the notification is executed may be controlled depending on whether or not the appropriate range is deviated.

[Scope of application]
In the first embodiment, the case where two types of R signal and G signal are used as input signals when detecting a pulse wave is illustrated. However, any type of signal may be used as long as the signal has a plurality of different light wavelength components. And any number of signals can be input signals. For example, two signals of any combination among signals having different optical wavelength components such as R, G, B, IR, and NIR can be used, or three or more signals can be used.

[Distribution and integration]
In addition, each component of each illustrated apparatus does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the acquisition unit 13, the extraction unit 14, the waveform detection unit 15, the heart rate calculation unit 15a, the heart rate fluctuation calculation unit 15b, the determination unit 16, or the notification unit 17 may be connected as an external device of the ATM 10 via a network. . Further, the acquisition unit 13, the extraction unit 14, the waveform detection unit 15, the heart rate calculation unit 15a, the heart rate variability calculation unit 15b, the determination unit 16 or the notification unit 17 are respectively provided in different devices and cooperated by being connected to a network. Thus, the function of the ATM 10 may be realized.

[Security program]
The various processes described in the above embodiments can be realized by executing a prepared program on a computer such as a personal computer or a workstation. In the following, an example of a computer that executes a security program having the same function as that of the above embodiment will be described with reference to FIG.

  FIG. 14 is a schematic diagram illustrating an example of a computer that executes a crime prevention program according to the first and second embodiments. As illustrated in FIG. 14, the computer 100 includes an operation unit 110a, a speaker 110b, a camera 110c, a display 120, and a communication unit 130. Further, the computer 100 includes a CPU 150, a ROM 160, an HDD 170, and a RAM 180. These units 110 to 180 are connected via a bus 140.

  As shown in FIG. 14, the HDD 170 includes an acquisition unit 13, an extraction unit 14, a waveform detection unit 15, a heart rate calculation unit 15 a, a heart rate fluctuation calculation unit 15 b, a determination unit 16, and a notification unit illustrated in the first embodiment. The crime prevention program 170a which exhibits the same function as 17 is stored in advance. About this security program 170a, each component of each acquisition unit 13, extraction unit 14, waveform detection unit 15, heart rate calculation unit 15a, heart rate fluctuation calculation unit 15b, determination unit 16 and notification unit 17 shown in FIG. Similarly to the above, they may be appropriately integrated or separated. In other words, all data stored in the HDD 170 need not always be stored in the HDD 170, and only data necessary for processing may be stored in the HDD 170.

  Then, the CPU 150 reads the crime prevention program 170 a from the HDD 170 and expands it in the RAM 180. Accordingly, as shown in FIG. 14, the crime prevention program 170a functions as a crime prevention process 180a. The security process 180a expands various data read from the HDD 170 in an area allocated to itself on the RAM 180, and executes various processes based on the expanded data. The security process 180a is performed by the acquisition unit 13, the extraction unit 14, the waveform detection unit 15, the heart rate calculation unit 15a, the heart rate fluctuation calculation unit 15b, the determination unit 16, and the notification unit 17 illustrated in FIG. For example, the processing shown in FIGS. 12 to 13 is included. In addition, each processing unit virtually realized on the CPU 150 does not always require that all processing units operate on the CPU 150, and only a processing unit necessary for the processing needs to be virtually realized.

  Note that the security program 170a is not necessarily stored in the HDD 170 or the ROM 160 from the beginning. For example, each program is stored in a “portable physical medium” such as a flexible disk inserted into the computer 100, so-called FD, CD-ROM, DVD disk, magneto-optical disk, or IC card. Then, the computer 100 may acquire and execute each program from these portable physical media. Each program is stored in another computer or server device connected to the computer 100 via a public line, the Internet, a LAN, a WAN, etc., and the computer 100 acquires and executes each program from these. It may be.

10 ATM
11a Touch panel 11b Card reader 11c Camera 12 ATM processing unit 13 Acquisition unit 14 Extraction unit 15 Waveform detection unit 15a Heart rate calculation unit 15b Heart rate variability calculation unit 16 Determination unit 16a History storage unit 17 Notification unit

Claims (7)

An acquisition unit that acquires an image captured by an imaging device that captures an image of a user of a device that executes transactions relating to cash;
An extraction unit for extracting a biological region included in the image;
From a representative value signal for each wavelength component of each pixel included in the living body region, a waveform of a signal in which components in a specific frequency band other than a frequency band in which a pulse wave can be taken between the wavelength components is canceled is detected. A waveform detector;
A determination unit for determining whether or not the waveform detected from the biological region is abnormal;
A crime prevention device comprising: a notification unit that performs notification when the waveform is abnormal. A heart rate calculating unit that calculates a heart rate from the waveform detected by the waveform detecting unit;
The crime prevention device according to claim 1, wherein the determination unit determines whether or not the heart rate deviates from a predetermined appropriate range. A heart rate variability calculating unit that calculates heart rate variability from the waveform detected by the waveform detecting unit;
The crime prevention device according to claim 1, wherein the determination unit determines whether or not the heartbeat variability deviates from a predetermined appropriate range. A heart rate calculation unit that calculates a heart rate from the waveform detected by the waveform detection unit;
A heart rate variability calculation unit that calculates heart rate variability from the waveform detected by the waveform detection unit;
A calculation unit that calculates an index representing the degree of deviation of the heart rate and the heart rate variability from a predetermined appropriate range;
The crime prevention device according to claim 1, wherein the determination unit determines whether or not the index exceeds a predetermined threshold value. The waveform detector
Extract the component of the specific frequency band for each wavelength component,
Correction by which the signal of the representative value is multiplied when the difference of the signal of the representative value is calculated between the wavelength components by comparing the magnitude of the component of the specific frequency band between the wavelength components Calculating a correction coefficient that is a coefficient and is minimized after the component of the specific frequency band is calculated;
Multiplying at least one of the signals of representative values of each wavelength component by the correction coefficient,
The signal waveform in which the components of the specific frequency band are canceled each other is detected by calculating a difference in the signal of the representative value between the respective wavelength components after multiplication of the correction coefficient. The crime prevention device according to any one of 4. Computer
Obtain an image captured by an imaging device that captures a user of a device that executes transactions related to cash,
Extracting a biological region included in the image;
From the signal of the representative value for each wavelength component of each pixel included in the living body region, a waveform of a signal in which components in a specific frequency band other than a frequency band in which a pulse wave can be taken between each wavelength component is canceled is detected. ,
Determining whether the waveform detected from the biological region is abnormal,
A crime prevention method, comprising: performing a notification when the waveform is abnormal. On the computer,
Obtain an image captured by an imaging device that captures a user of a device that executes transactions related to cash,
Extracting a biological region included in the image;
From the signal of the representative value for each wavelength component of each pixel included in the living body region, a waveform of a signal in which components in a specific frequency band other than a frequency band in which a pulse wave can be taken between each wavelength component is canceled is detected. ,
Determining whether the waveform detected from the biological region is abnormal,
A crime prevention program characterized by causing a process to execute notification when the waveform is abnormal.

Images