ATM control method based on face recognition

By capturing and analyzing images of people through the ATM's built-in camera and combining them with the cardholder's identity information, dual verification of the ATM operating environment and the person's identity is achieved, solving the security and reliability issues of ATM terminals and improving the security of ATM operations and the reliability of bank card use.

CN116824767BActive Publication Date: 2025-09-19HUIZHI ANKE (BEIJING) TECHNOLOGY CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202211674186.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-12-26
Publication Date
2025-09-19
Estimated Expiration
2042-12-26

Smart Images

  • Figure CN116824767B_ABST
    Figure CN116824767B_ABST
Patent Text Reader

Abstract

The present invention provides an ATM control method based on face recognition. The method photographs the person in front of the ATM to determine the presence status information of the person in front of the ATM and the facial feature information of the person operating the ATM. In this way, the operation of the ATM is controlled based on both the external environment of the ATM and the identity information of the person operating the ATM, thereby preventing suspicious persons from approaching the ATM and fraudulently using bank cards during the operation of the ATM, thereby improving the security of ATM operation and bank card use.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of ATM intelligent control, and in particular to an ATM control method based on face recognition. Background Art

[0002] Currently, ATMs are pre-configured to operate in a specific mode. Upon detecting the insertion of a bank card, they enter the corresponding mode, allowing users to make inquiries, withdraw funds, or deposit funds through the ATM. Existing ATMs only verify the bank card itself and do not check the identity of the person operating the ATM or the surrounding environment. This makes it impossible to ensure the legality of the person operating the ATM, nor does it allow for comprehensive and accurate screening of the ATM's surroundings, reducing the operational security and reliability of the ATM. Summary of the Invention

[0003] In response to the defects of the prior art, the present invention provides an ATM control method based on face recognition, which uses the ATM's built-in camera to shoot the person in front of the ATM, analyzes the shot person image, and obtains the person's presence status information in front of the ATM, thereby judging whether the ATM is currently in a safe operating environment and performing an adaptive voice message reminder; then, the cardholder's identity information of the bank card inserted into the ATM is compared with the facial feature information of the person in front of the ATM to judge whether the current operation of the ATM is a safe operation, thereby sending a notification message to the bank cardholder's registered mobile phone, and adjusting the ATM's current working mode according to the cardholder's identity information; the above method shoots the person in front of the ATM to determine the person's presence status information and the facial feature information of the person operating the ATM, thereby controlling the ATM operation based on both the external environment of the ATM and the identity information of the person operating the ATM, preventing suspicious persons from approaching the ATM and fraudulently using bank cards during the ATM operation, and improving the security of ATM operation and bank card use.

[0004] The present invention provides an ATM control method based on face recognition, which comprises the following steps:

[0005] Step S1: When the ATM detects that a bank card has been inserted, it instructs the ATM's built-in camera to capture the person currently in front of the ATM to obtain a corresponding person image; the person image is analyzed and processed to determine the presence status of the person in front of the ATM; and based on the person presence status information, it is determined whether the ATM is currently in a safe operating environment.

[0006] Step S2: Based on the above-mentioned determination result regarding the safe operating environment status, the ATM is instructed to generate a corresponding voice reminder message; when the ATM detects an operation from the outside, the ATM reads the bank card registration information from the bank card, obtains the cardholder's identity information based on the registration information, and extracts facial feature information of the person in front of the ATM from the person image;

[0007] Step S3: The cardholder identity information and the facial feature information of the person are synchronously uploaded to the ATM cloud management platform for information comparison and processing to determine whether the current ATM operation is a safe operation; based on the determination result of the safe operation, a notification message is sent to the registered mobile phone of the bank cardholder;

[0008] Step S4: If the current operation on the ATM is a safe operation, the current working mode of the ATM is adjusted according to the cardholder identity information.

[0009] Furthermore, in step S1, when the ATM detects that a bank card has been inserted, it instructs the ATM's built-in camera to capture the person currently in front of the ATM to obtain a corresponding person image; and analyzing and processing the person image to determine the presence status information of the person in front of the ATM specifically includes:

[0010] When the ATM detects that a bank card has been inserted, it instructs the ATM's built-in camera to take a binocular photo of the person currently in front of the ATM to obtain a corresponding binocular image of the person;

[0011] generating a corresponding three-dimensional person image according to the binocular parallax of the binocular person image;

[0012] The number of people in front of the ATM, the sight direction of each person, and the relative distance between each person and the ATM are extracted from the three-dimensional person image as the presence status information of the people in front of the ATM.

[0013] Furthermore, in step S1, judging whether the current ATM is in a safe operating environment state according to the personnel presence status information specifically includes:

[0014] If there is only one person in front of the ATM, the ATM is judged to be in a safe operating environment;

[0015] If there are more than one person in front of the ATM, and only one person's line of sight is directed towards the ATM screen and the relative distance between the person and the ATM is less than a preset distance threshold, then the ATM is judged to be in a safe operating environment state; otherwise, the ATM is judged to be not in a safe operating environment state.

[0016] Furthermore, in step S2, according to the above-mentioned determination result on the safe operating environment state, instructing the ATM to generate a corresponding voice reminder message specifically includes:

[0017] When it is determined that the ATM is currently in a safe operating environment, instructing the ATM to generate a first voice reminder message; the first voice reminder message includes an instructive voice reminder message for operating the ATM;

[0018] When the ATM is not currently in a safe operating environment, the ATM is instructed to generate a second voice reminder message and the ATM screen is instructed to switch to a sleep state; the second voice reminder message includes a voice reminder message about the presence of suspicious persons in the environment around the ATM.

[0019] Furthermore, in step S2, when the ATM is not currently in a safe operating environment, after instructing the ATM to generate a second voice reminder message and instructing the ATM screen to switch to a sleep state, a second determination is made as to whether the ATM is currently in a safe operating environment. The second determination as to whether the ATM is currently in a safe operating environment includes:

[0020] If the number of people in front of the ATM is one after the second voice reminder message is played, it is determined that the ATM is currently in a safe operating environment state;

[0021] If there is more than one person in front of the ATM after the second voice reminder message is played, and the person with their sight line directed towards the ATM screen has no abnormal expression, or there is a person with their sight line directed towards the ATM screen who clicks the cancel sleep mode button on the screen, then the multiple people with their sight line directed towards the ATM screen are considered to be accompanying persons, and the ATM is also determined to be in a safe operating environment. Otherwise, the ATM is determined to be not in a safe operating environment. The process is as follows:

[0022] In step S201, after the second voice reminder message is broadcast, the ATM screen is instructed to switch to a sleep state. In the sleep state, the ATM screen will display a message "Please observe the surrounding environment and personnel for abnormalities". The following formula (1) is used to determine whether the person whose line of sight is directed at the ATM screen at the beginning of the sleep state has observed the surrounding environment and personnel within a preset short time according to the subsequent head movement of the person whose line of sight is directed at the ATM screen at the beginning of the sleep state.

[0023]

[0024] In the above formula (1), X represents the judgment value of whether the person whose sight is directed toward the ATM screen at the beginning of the sleep state observes the surrounding environment and people within a preset short time; n represents the number of people in front of the ATM; Z(a) represents the detection value of the sight of the a-th person in front of the ATM at the beginning of the sleep state directed toward the ATM screen, if the sight of the a-th person in front of the ATM is directed toward the ATM screen at the beginning of the sleep state, then Z(a) = 1, if the sight of the a-th person in front of the ATM is not directed toward the ATM screen at the beginning of the sleep state, then Z(a) = 0; R[a_(t0→t0+T)] represents the detection value of the head swing of the a-th person in front of the ATM at the beginning of the sleep state at t0→t0+T, if the head swing occurs, R[a_(t0→t0+T)] = 1, if the head swing does not occur, then R[a_(t0→t0+T)] = 0; t0 represents the beginning of the sleep state; T represents the preset short time;

[0025] If X=1, it means that the person whose sight line is directed towards the ATM screen at the beginning of the sleep state observes the surrounding environment and people, and the calculation of the following step S202 is performed;

[0026] If X≠1, the result of the second determination of whether the current ATM is in a safe operating environment is determined to be that the current ATM is not in a safe operating environment, and the calculation of the following step S203 is performed;

[0027] In step S202, after confirming that the person whose line of sight is directed toward the ATM screen at the beginning of the sleep state has observed the surrounding environment and people, that is, X=1, after a preset short time, the following formula (2) is used to obtain a secondary judgment value of whether the ATM is currently in a safe operating environment state based on the number of people in front of the ATM, the facial expression detection of the person whose line of sight is directed toward the ATM screen, and the control status of the ATM screen.

[0028]

[0029] In the above formula (2), Y2 represents the secondary judgment value of whether the current ATM is in a safe operating environment state; B[a_(t0+T→t0+2T)] represents the normal expression detection value of the a-th person located in front of the ATM at the time t0+T→t0+2T when the sleep state just begins. If there is no abnormality in the expression, B[a_(t0+T→t0+2T)]=1; if there is an abnormality in the expression, B[a_(t0+T→t0+2T)]=0; L(ATM) represents the control start state value of the ATM screen. If a person presses the ATM screen to start, L(ATM)=1; if no person presses the ATM screen to start, L(ATM)=0;

[0030] If Y2=0, it means that the result of the secondary judgment of whether the current ATM is in a safe operating environment is that the current ATM is in a safe operating environment;

[0031] If Y2=1, it means that the result of the second judgment of whether the current ATM is in a safe operating environment is that the current ATM is not in a safe operating environment;

[0032] In step S203, if the ATM is still not in a safe operating environment after the second determination, the number of notification messages sent to the registered mobile phone of the bank card holder is controlled according to the number of people in front of the ATM using the following formula (3):

[0033]

[0034] In the above formula (3), M represents the number of times notification messages are sent to the registered mobile phone of the bank card holder; int{} represents rounding the values ​​in the brackets.

[0035] Furthermore, in step S2, when the ATM detects an operation from the outside, it reads the bank card registration information from the bank card, obtains the cardholder identity information of the bank card based on the registration information; and extracts the facial feature information of the person in front of the ATM from the person image, specifically including:

[0036] When the ATM is currently in a secure operating environment and the ATM keyboard detects a touch operation from the outside, the bank card registration information is read from the bank card; and the facial image information of the registered cardholder corresponding to the bank card is extracted from the registration information;

[0037] Performing face recognition processing on the three-dimensional personnel image, extracting from the three-dimensional personnel image the facial feature information of the person with the minimum relative distance from the ATM.

[0038] Furthermore, in step S3, the cardholder identity information and the person's facial feature information are synchronously uploaded to the ATM cloud management platform for information comparison processing. Determining whether the current ATM operation is a safe operation specifically includes:

[0039] Synchronously uploading the facial image information of the registered cardholder and the facial features information of the person to the ATM cloud management platform for information matching and comparison processing to determine the similarity of the facial features between the facial image information and the facial features information of the person;

[0040] If the similarity of the facial features is greater than or equal to the preset similarity threshold, it is determined that the current operation on the ATM is a safe operation; otherwise, it is determined that the current operation on the ATM is not a safe operation.

[0041] Furthermore, in step S3, sending a notification message to the registered mobile phone of the bank card holder according to the result of the determination of the security operation specifically includes:

[0042] If the current operation on the ATM is a safe operation, a first notification message is sent to the registered mobile phone of the bank card holder; wherein the first notification message includes the location information of the ATM and the type of the current operation on the ATM;

[0043] If the current operation on the ATM is not a safe operation, a second notification message is sent to the registered mobile phone of the bank card holder; wherein the second notification message includes the location information of the ATM and the time information of the current operation on the ATM.

[0044] Furthermore, in step S4, if the current operation on the ATM is a safe operation, adjusting the current working mode of the ATM according to the cardholder identity information specifically includes:

[0045] If the current ATM operation is a safe operation, the actual age of the cardholder is determined based on the cardholder identity information;

[0046] If the actual age is greater than or equal to a preset age threshold, the font size and display brightness of the ATM screen display are increased, and the allowed time length for operating the ATM is increased;

[0047] If the actual age is less than the preset age threshold, the current display state of the ATM screen remains unchanged.

[0048] Compared with the existing technology, the ATM control method based on face recognition uses the ATM's built-in camera to shoot the person in front of the ATM, analyzes the shot person image, and obtains the person's presence status information in front of the ATM, thereby judging whether the ATM is currently in a safe operating environment and performing adaptive voice message reminders; then, the cardholder's identity information of the bank card inserted into the ATM is compared with the facial feature information of the person in front of the ATM to judge whether the current operation of the ATM is a safe operation, thereby sending a notification message to the bank cardholder's registered mobile phone, and adjusting the ATM's current working mode according to the cardholder's identity information; the above method determines the person's presence status information and the facial feature information of the person operating the ATM by shooting the person in front of the ATM, thereby controlling the ATM's operation based on both the external environment of the ATM and the identity information of the person operating the ATM, preventing suspicious persons from approaching the ATM and misusing bank cards during the ATM operation, and improving the security of ATM operation and bank card use.

[0049] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0050] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 The present invention provides a flow chart of the ATM control method based on face recognition. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0054] See Figure 1, is a flow chart of an ATM control method based on face recognition provided by an embodiment of the present invention. The ATM control method based on face recognition comprises the following steps:

[0055] Step S1: When the ATM detects that a bank card has been inserted, it instructs the ATM's built-in camera to capture the person currently in front of the ATM to obtain a corresponding person image; the person image is analyzed and processed to determine the presence status of the person in front of the ATM; and based on the person presence status information, it is determined whether the ATM is currently in a safe operating environment.

[0056] Step S2: Based on the above-mentioned determination result regarding the safe operating environment status, the ATM is instructed to generate a corresponding voice reminder message; when the ATM detects an operation from the outside, the ATM reads the bank card registration information from the bank card, obtains the cardholder's identity information based on the registration information, and extracts facial feature information of the person in front of the ATM from the image of the person;

[0057] Step S3: The cardholder's identity information and the person's facial feature information are simultaneously uploaded to the ATM cloud management platform for information comparison and processing to determine whether the current ATM operation is a safe operation; based on the determination result of the safe operation, a notification message is sent to the registered mobile phone of the bank cardholder;

[0058] Step S4: If the current operation on the ATM is a safe operation, the current working mode of the ATM is adjusted according to the cardholder identity information.

[0059] The beneficial effects of the above technical solution are as follows: the ATM control method based on face recognition uses the ATM's built-in camera to photograph the person in front of the ATM, analyzes the photographed person image, and obtains the person's presence status information in front of the ATM, thereby determining whether the ATM is currently in a safe operating environment and providing an adaptive voice message reminder; then, the cardholder's identity information of the bank card inserted into the ATM is compared with the facial feature information of the person in front of the ATM to determine whether the current operation of the ATM is a safe operation, thereby sending a notification message to the bank cardholder's registered mobile phone, and adjusting the ATM's current operating mode according to the cardholder's identity information; the above method photographs the person in front of the ATM to determine the person's presence status information and the facial feature information of the person operating the ATM, thereby controlling the ATM's operation based on both the external environment of the ATM and the identity information of the person operating the ATM, preventing suspicious persons from approaching the ATM and fraudulently using bank cards during the ATM operation, and improving the security of ATM operation and bank card use.

[0060] Preferably, in step S1, when the ATM detects that a bank card has been inserted, it instructs the ATM's built-in camera to capture the person currently in front of the ATM to obtain a corresponding person image; and analyzing and processing the person image to determine the person presence status information in front of the ATM specifically includes:

[0061] When the ATM detects that a bank card has been inserted, it instructs the ATM's built-in camera to take a binocular photo of the person currently in front of the ATM to obtain a corresponding binocular image of the person;

[0062] generating a corresponding three-dimensional person image according to the binocular parallax of the binocular person image;

[0063] The number of people in front of the ATM, the direction of each person's sight, and the relative distance between each person and the ATM are extracted from the three-dimensional person image as the presence status information of the people in front of the ATM.

[0064] The beneficial effect of the above technical solution is that, through the above method, when the ATM port detects the insertion of a bank card, the ATM's built-in camera will perform binocular photography of the person in front of the ATM. This allows for a comprehensive capture of all people in front of the ATM, thereby capturing the real-time status of people approaching the ATM. Furthermore, based on the captured binocular person images, corresponding 3D person images are generated. These 3D person images are then analyzed and processed to extract the number of people in front of the ATM, each person's line of sight, and the relative distance between each person and the ATM. This allows for a comprehensive characterization of the people in front of the ATM and their relative relationship to the ATM.

[0065] Preferably, in step S1, judging whether the current ATM is in a safe operating environment state according to the personnel presence status information specifically includes:

[0066] If there is only one person in front of the ATM, the ATM is judged to be in a safe operating environment;

[0067] If there are more than one person in front of the ATM, and only one person's line of sight is directed towards the ATM screen and the relative distance between the person and the ATM is less than a preset distance threshold, then the ATM is judged to be in a safe operating environment state; otherwise, the ATM is judged to be not in a safe operating environment state.

[0068] The beneficial effect of the above technical solution is that, through the above method, it is possible to effectively determine whether the ATM's current operating environment is safe when there is only one person in front of the ATM or when there are multiple people at the same time. When there is only one person in front of the ATM, it indicates that only one person is operating the ATM at this time, and no other person is peeping nearby, that is, the ATM is currently in a safe operating environment state. When there are multiple people in front of the ATM, and only one person's line of sight is directed at the ATM screen and the relative distance between them and the ATM is less than a preset distance threshold, it indicates that only one person is operating the ATM at this time, and no other person is peeping nearby, that is, the ATM is currently in a safe operating environment state. Otherwise, it indicates that there are other people peeping nearby, that is, the ATM is currently not in a safe operating environment state.

[0069] Preferably, in step S2, according to the above-mentioned determination result on the safe operating environment state, instructing the ATM to generate a corresponding voice reminder message specifically includes:

[0070] When it is determined that the ATM is currently in a safe operating environment, instructing the ATM to generate a first voice reminder message; the first voice reminder message includes an instructive voice reminder message for operating the ATM;

[0071] When the ATM is not currently in a safe operating environment, the ATM is instructed to generate a second voice reminder message and the screen of the ATM is instructed to switch to a sleep state; the second voice reminder message includes a voice reminder message about the presence of suspicious persons in the environment around the ATM.

[0072] The beneficial effects of the above technical solution are: through the above method, when the ATM is currently in a safe operating environment, the ATM provides personnel with instructive voice reminder messages on how to operate and use the ATM, thereby improving the efficiency of personnel operating the ATM; and when the ATM is currently not in a safe operating environment, the ATM provides personnel with voice reminder messages about the presence of suspicious persons in the environment around the ATM, which can remind personnel to increase their vigilance. In addition, the ATM screen is instructed to switch to a sleep state (that is, the ATM screen is instructed to turn off), which can prevent the information displayed on the screen from being peeped.

[0073] Preferably, in step S2, when the ATM is not currently in a safe operating environment, after instructing the ATM to generate a second voice reminder message and instructing the ATM screen to switch to a sleep state, a second determination is made as to whether the ATM is currently in a safe operating environment. The second determination as to whether the ATM is currently in a safe operating environment includes:

[0074] If the number of people in front of the ATM is one after the second voice reminder message is played, it is determined that the ATM is currently in a safe operating environment state;

[0075] If there is more than one person in front of the ATM after the second voice reminder message is played, and the person with their sight line directed towards the ATM screen has no abnormal expression, or there is a person with their sight line directed towards the ATM screen who clicks the cancel sleep mode button on the screen, then the multiple people with their sight line directed towards the ATM screen are considered to be accompanying persons, and the ATM is also determined to be in a safe operating environment. Otherwise, the ATM is determined to be not in a safe operating environment. The process is as follows:

[0076] In step S201, after the second voice reminder message is broadcast, the ATM screen will be instructed to switch to a sleep state. In the sleep state, the ATM screen will display a message "Please observe the surrounding environment and personnel for abnormalities". The following formula (1) is used to determine whether the person whose line of sight is directed at the ATM screen at the beginning of the sleep state has observed the surrounding environment and personnel within a preset short time according to the subsequent head movement of the person whose line of sight is directed at the ATM screen at the beginning of the sleep state.

[0077]

[0078] In the above formula (1), X represents the judgment value of whether the person whose sight is directed toward the ATM screen at the beginning of the sleep state observes the surrounding environment and people within a preset short time; n represents the number of people in front of the ATM; Z(a) represents the detection value of the sight of the a-th person in front of the ATM at the beginning of the sleep state directed toward the ATM screen, if the sight of the a-th person in front of the ATM is directed toward the ATM screen at the beginning of the sleep state, then Z(a) = 1, if the sight of the a-th person in front of the ATM is not directed toward the ATM screen at the beginning of the sleep state, then Z(a) = 0; R[a_(t0→t0+T)] represents the detection value of the head swing of the a-th person in front of the ATM at the beginning of the sleep state at the time t0→t0+T, if the head swing occurs, R[a_(t0→t0+T)] = 1, if the head swing does not occur, then R[a_(t0→t0+T)] = 0; t0 represents the beginning of the sleep state; T represents the preset short time;

[0079] If X=1, it means that the person whose sight line is directed towards the ATM screen at the beginning of the sleep state observes the surrounding environment and people, and the calculation of the following step S202 is performed;

[0080] If X≠1, the result of the second determination of whether the current ATM is in a safe operating environment is determined to be that the current ATM is not in a safe operating environment, and the calculation of the following step S203 is performed;

[0081] In step S202, after confirming that the person whose line of sight is directed toward the ATM screen at the beginning of the dormant state has observed the surrounding environment and people, that is, X=1, after a preset short period of time, the following formula (2) is used to obtain a secondary judgment value of whether the ATM is currently in a safe operating environment state based on the number of people in front of the ATM, the facial expression detection of the person whose line of sight is directed toward the ATM screen, and the control status of the ATM screen.

[0082]

[0083] In the above formula (2), Y2 represents the secondary judgment value of whether the current ATM is in a safe operating environment state; B[a_(t0+T→t0+2T)] represents the normal expression detection value of the a-th person in front of the ATM at the time t0+T→t0+2T when the dormant state just begins. If there is no abnormality in the expression, B[a_(t0+T→t0+2T)]=1; if there is an abnormality in the expression, B[a_(t0+T→t0+2T)]=0; L(ATM) represents the control start state value of the ATM screen. If a person presses the ATM screen to start, L(ATM)=1; if no person presses the ATM screen to start, L(ATM)=0;

[0084] If Y2=0, it means that the result of the secondary judgment of whether the current ATM is in a safe operating environment is that the current ATM is in a safe operating environment;

[0085] If Y2=1, it means that the result of the second judgment of whether the current ATM is in a safe operating environment is that the current ATM is not in a safe operating environment;

[0086] In step S203, if the ATM is still not in a safe operating environment after the second determination, the number of notification messages sent to the registered mobile phone of the bank card holder is controlled according to the number of people in front of the ATM using the following formula (3):

[0087]

[0088] In the above formula (3), M represents the number of times notification messages are sent to the registered mobile phone of the bank card holder; int{} represents rounding the value in the brackets.

[0089] The beneficial effects of the above technical solution are as follows: using the above formula (1), according to the subsequent head swing of the person whose sight line is directed to the ATM screen at the beginning of the sleep state, it is judged whether the person whose sight line is directed to the ATM screen at the beginning of the sleep state has observed the surrounding environment and people within a preset short time, thereby ensuring that the user observes the surrounding situation before making further judgments. If there is a person whose sight line is directed to the ATM screen who does not observe the surrounding situation, the secondary judgment result is directly used to determine that the current ATM is not in a safe operating environment state, thereby ensuring the overall safety and reliability of the system; then using Using the above formula (2), according to the number of people in front of the ATM, the facial expression detection of people whose sight lines are aligned with the ATM screen, and the control of the ATM screen, a secondary judgment value of whether the current ATM is in a safe operating environment is obtained. Therefore, when the facial expression of the people is normal or there is a person who clicks to open the screen, it is determined that the current ATM is in a safe operating environment, thereby preventing excessive protection from causing a decrease in user experience. Finally, using the above formula (3), according to the number of people in front of the ATM, the number of notification messages sent to the registered mobile phone of the bank card holder is controlled to achieve the purpose of reminding the user to the greatest extent.

[0090] Preferably, in step S2, when the ATM detects an operation from the outside, it reads the bank card registration information from the bank card, obtains the cardholder identity information of the bank card based on the registration information; and extracts the facial feature information of the person in front of the ATM from the person image, specifically including:

[0091] When the ATM is currently in a secure operating environment and the ATM keyboard detects a touch operation from the outside, the bank card registration information is read from the bank card; and the facial image information of the registered cardholder corresponding to the bank card is extracted from the registration information;

[0092] The three-dimensional person image is subjected to face recognition processing, and the facial feature information of the person with the smallest relative distance from the ATM is extracted from the three-dimensional person image.

[0093] The beneficial effects of the above technical solution are: through the above method, the registration information of the bank card is read from the bank card, and then the facial image information of the registered cardholder corresponding to the bank card is obtained based on the registration information, and the facial feature information of the person with the smallest relative distance between the ATM and the ATM (that is, the person currently operating the ATM) is extracted from the three-dimensional person image, which facilitates the subsequent identity verification of the person currently operating the ATM.

[0094] Preferably, in step S3, the cardholder identity information and the person's facial feature information are synchronously uploaded to the ATM cloud management platform for information comparison processing. Determining whether the current ATM operation is a safe operation specifically includes:

[0095] Upload the registered cardholder's facial image information and the person's facial features information to the ATM cloud management platform for information matching and comparison to determine the similarity between the facial image information and the person's facial features information in terms of facial features;

[0096] If the similarity of the facial features is greater than or equal to the preset similarity threshold, it is determined that the current operation on the ATM is a safe operation; otherwise, it is determined that the current operation on the ATM is not a safe operation.

[0097] The beneficial effect of the above technical solution is that, through the above method, facial feature contour similarity is calculated and threshold comparison is performed through face recognition, thereby determining whether the current ATM operation is safe. Specifically, when the facial feature contour similarity is greater than or equal to a preset similarity threshold, it indicates that the person currently operating the ATM is the registered cardholder of the bank card, thus confirming that the current bank card inquiry, withdrawal, or deposit operation at the ATM is safe. When the facial feature contour similarity is less than the preset similarity threshold, it indicates that the person currently operating the ATM is not the registered cardholder of the bank card, thus confirming that the current bank card inquiry, withdrawal, or deposit operation at the ATM is unsafe and illegal.

[0098] Preferably, in step S3, sending a notification message to the registered mobile phone of the bank card holder according to the result of the determination on the security operation specifically includes:

[0099] If the current operation on the ATM is a safe operation, a first notification message is sent to the registered mobile phone of the bank card holder; wherein the first notification message includes the location information of the ATM and the type of the current operation on the ATM;

[0100] If the current operation on the ATM is not a safe operation, a second notification message is sent to the registered mobile phone of the bank card holder; wherein the second notification message includes the location information of the ATM and the time information of the current operation on the ATM.

[0101] The beneficial effect of the above technical solution is that: through the above method, the mobile phone of the registered cardholder of the bank card can be notified in time by mobile phone text message, thereby improving the security of bank card operations through ATM.

[0102] Preferably, in step S4, if the current operation on the ATM is a safe operation, adjusting the current working mode of the ATM according to the cardholder identity information specifically includes:

[0103] If the current ATM operation is a safe operation, the actual age of the cardholder is determined based on the cardholder's identity information;

[0104] If the actual age is greater than or equal to the preset age threshold, the font size and display brightness of the ATM screen display are increased, and the allowed time length for operating the ATM is increased;

[0105] If the actual age is less than the preset age threshold, the current display state of the ATM screen remains unchanged.

[0106] The beneficial effect of the above technical solution is: through the above method, based on the actual age of the person currently operating the ATM (i.e., the registered cardholder of the bank card), the font size and display brightness of the ATM screen display, as well as the allowed time length for operating the ATM are adaptively adjusted. In this way, older people can clearly see the corresponding information from the ATM screen and have sufficient time to operate the ATM, avoiding the situation where the person exceeds the allowed operation time of the ATM due to slow operation, resulting in automatic exit from the current operation interface.

[0107] As can be seen from the contents of the above embodiment, the ATM control method based on face recognition utilizes the ATM's built-in camera to photograph the person in front of the ATM, analyzes the photographed person image, and obtains the person's presence status information in front of the ATM, thereby determining whether the ATM is currently in a safe operating environment and providing an adaptive voice message reminder; then, the cardholder's identity information of the bank card inserted into the ATM is compared with the facial feature information of the person in front of the ATM to determine whether the current operation of the ATM is a safe operation, thereby sending a notification message to the bank cardholder's registered mobile phone, and adjusting the ATM's current operating mode based on the cardholder's identity information; the above method photographs the person in front of the ATM to determine the person's presence status information in front of the ATM and the facial feature information of the person operating the ATM, thereby controlling the ATM's operation based on both the external environment of the ATM and the identity information of the person operating the ATM, preventing suspicious persons from approaching the ATM and fraudulently using bank cards during the ATM operation, and improving the security of ATM operation and bank card use.

[0108] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. ATM control method based on face recognition, characterized in that: It includes the following steps: Step S1: When the ATM detects that a bank card has been inserted, it instructs the ATM's built-in camera to capture the person currently in front of the ATM to obtain a corresponding person image; the person image is analyzed and processed to determine the presence status of the person in front of the ATM; and based on the person presence status information, it is determined whether the ATM is currently in a safe operating environment. Step S2, instructing the ATM to generate a corresponding voice reminder message based on the determination result of the above-mentioned safe operating environment status; When the ATM detects an operation from the outside, it reads the bank card registration information from the bank card and obtains the cardholder's identity information based on the registration information; and extracts the facial feature information of the person in front of the ATM from the person image; Step S3: The cardholder identity information and the person's facial feature information are uploaded to the ATM cloud management platform for information comparison and processing to determine whether the current ATM operation is a safe operation; Sending a notification message to the registered mobile phone of the bank card holder based on the determination result regarding the security operation; Step S4: If the current operation on the ATM is a safe operation, the current operating mode of the ATM is adjusted according to the cardholder identity information; In step S2, according to the above-mentioned determination result on the safe operating environment status, instructing the ATM to generate a corresponding voice reminder message specifically includes: When it is determined that the ATM is currently in a safe operating environment, instructing the ATM to generate a first voice reminder message; the first voice reminder message includes an instructive voice reminder message for operating the ATM; When the ATM is not currently in a safe operating environment, the ATM is instructed to generate a second voice reminder message and the ATM screen is instructed to switch to a sleep state; the second voice reminder message includes a voice reminder message about the presence of a suspicious person in the environment around the ATM; wherein, in step S2, when the ATM is not currently in a safe operating environment, the ATM is instructed to generate the second voice reminder message and the ATM screen is instructed to switch to a sleep state, a second determination is performed to determine whether the ATM is currently in a safe operating environment. The second determination of whether the ATM is currently in a safe operating environment includes: If the number of people in front of the ATM is one after the second voice reminder message is played, it is determined that the ATM is currently in a safe operating environment state; If there is more than one person in front of the ATM after the second voice reminder message is played, and the person with their sight line directed towards the ATM screen has no abnormal expression, or there is a person with their sight line directed towards the ATM screen who clicks the cancel sleep mode button on the screen, then the multiple people with their sight line directed towards the ATM screen are considered to be accompanying persons, and the ATM is also determined to be in a safe operating environment. Otherwise, the ATM is determined to be not in a safe operating environment. The process is as follows: In step S201, after the second voice reminder message is broadcast, the ATM screen is instructed to switch to a sleep state. In the sleep state, the ATM screen will display a message "Please observe the surrounding environment and personnel for abnormalities". The following formula (1) is used to determine whether the person whose line of sight is directed at the ATM screen at the beginning of the sleep state has observed the surrounding environment and personnel within a preset short time according to the subsequent head movement of the person whose line of sight is directed at the ATM screen at the beginning of the sleep state. In the above formula (1), X represents the judgment value of whether the person whose sight is directed toward the ATM screen at the beginning of the sleep state observes the surrounding environment and people within a preset short time; n represents the number of people in front of the ATM; Z(a) represents the detection value of the sight of the a-th person in front of the ATM at the beginning of the sleep state directed toward the ATM screen, if the sight of the a-th person in front of the ATM is directed toward the ATM screen at the beginning of the sleep state, then Z(a) = 1, if the sight of the a-th person in front of the ATM is not directed toward the ATM screen at the beginning of the sleep state, then Z(a) = 0; R[a_(t0→t0+T)] represents the detection value of the head swing of the a-th person in front of the ATM at the beginning of the sleep state at t0→t0+T, if the head swing occurs, R[a_(t0→t0+T)] = 1, if the head swing does not occur, then R[a_(t0→t0+T)] = 0; t0 represents the beginning of the sleep state; T represents the preset short time; If X=1, it means that the person whose line of sight is directed toward the ATM screen at the beginning of the sleep state observes the surrounding environment and people, and the calculation of the following step S202 is performed; if X≠1, the result of the secondary determination of whether the current ATM is in a safe operating environment is determined to be that the current ATM is not in a safe operating environment, and the calculation of the following step S203 is performed; In step S202, after confirming that the person whose line of sight is directed toward the ATM screen at the beginning of the sleep state has observed the surrounding environment and people, that is, X=1, after a preset short time, the following formula (2) is used to obtain a secondary judgment value of whether the ATM is currently in a safe operating environment state based on the number of people in front of the ATM, the facial expression detection of the person whose line of sight is directed toward the ATM screen, and the control status of the ATM screen. In the above formula (2), Y2 represents the secondary judgment value of whether the current ATM is in a safe operating environment state; B[a_(t0+T→t0+2T)] represents the normal expression detection value of the a-th person located in front of the ATM at the time t0+T→t0+2T when the sleep state just begins. If there is no abnormality in the expression, B[a_(t0+T→t0+2T)]=1; if there is an abnormality in the expression, B[a_(t0+T→t0+2T)]=0; L(ATM) represents the control start state value of the ATM screen. If a person presses the ATM screen to start, L(ATM)=1; if no person presses the ATM screen to start, L(ATM)=0; If Y2=0, it means that the result of the secondary judgment of whether the current ATM is in a safe operating environment is that the current ATM is in a safe operating environment; If Y2=1, it means that the result of the second judgment of whether the current ATM is in a safe operating environment is that the current ATM is not in a safe operating environment; In step S203, if the ATM is still not in a safe operating environment after the second determination, the number of notification messages sent to the registered mobile phone of the bank card holder is controlled according to the number of people in front of the ATM using the following formula (3): In the above formula (3), M represents the number of times notification messages are sent to the registered mobile phone of the bank card holder; int{} represents rounding the values ​​in the brackets.

2. The ATM control method based on face recognition as claimed in claim 1, characterized in that: In step S1, when the ATM detects that a bank card has been inserted, it instructs the ATM's built-in camera to take a picture of the person currently in front of the ATM to obtain a corresponding image of the person; Analyzing and processing the personnel image to determine the presence status of the person in front of the ATM specifically includes: When the ATM detects that a bank card has been inserted, it instructs the ATM's built-in camera to take a binocular photo of the person currently in front of the ATM to obtain a corresponding binocular image of the person; generating a corresponding three-dimensional person image according to the binocular parallax of the binocular person image; The number of people in front of the ATM, the sight direction of each person, and the relative distance between each person and the ATM are extracted from the three-dimensional person image as the presence status information of the people in front of the ATM.

3. The ATM control method based on face recognition as claimed in claim 2, characterized in that: In step S1, judging whether the current ATM is in a safe operating environment state according to the personnel presence status information specifically includes: If there is only one person in front of the ATM, the ATM is judged to be in a safe operating environment; If there are more than one person in front of the ATM, and only one person's line of sight is directed towards the ATM screen and the relative distance between the person and the ATM is less than a preset distance threshold, then the ATM is judged to be in a safe operating environment state; otherwise, the ATM is judged to be not in a safe operating environment state.

4. The ATM control method based on face recognition as claimed in claim 1, characterized in that: In step S2, when the ATM detects an operation from the outside, it reads the registration information of the bank card from the bank card and obtains the cardholder's identity information based on the registration information; The facial feature information of the person in front of the ATM is extracted from the person image and specifically includes: When the ATM is currently in a secure operating environment and the ATM keyboard detects a touch operation from the outside, reading the registration information of the bank card from the bank card; and extracting facial image information of the registered cardholder corresponding to the bank card from the registration information; Performing face recognition processing on the three-dimensional personnel image, extracting from the three-dimensional personnel image the facial feature information of the person with the minimum relative distance from the ATM.

5. The ATM control method based on face recognition as claimed in claim 4, characterized in that: In step S3, the cardholder identity information and the person's facial feature information are synchronously uploaded to the ATM cloud management platform for information comparison and processing. Determining whether the current ATM operation is a safe operation specifically includes: Synchronously uploading the facial image information of the registered cardholder and the facial features information of the person to the ATM cloud management platform for information matching and comparison processing to determine the similarity of the facial features between the facial image information and the facial features information of the person; If the similarity of the facial features is greater than or equal to the preset similarity threshold, it is determined that the current operation on the ATM is a safe operation; otherwise, it is determined that the current operation on the ATM is not a safe operation.

6. The ATM control method based on face recognition according to claim 5, characterized in that: In step S3, according to the determination result regarding the security operation, sending a notification message to the registered mobile phone of the bank card holder specifically includes: If the current operation on the ATM is a safe operation, a first notification message is sent to the registered mobile phone of the bank card holder; wherein the first notification message includes the location information of the ATM and the type of the current operation on the ATM; If the current operation on the ATM is not a safe operation, a second notification message is sent to the registered mobile phone of the bank card holder; wherein the second notification message includes the location information of the ATM and the time information of the current operation on the ATM.

7. The ATM control method based on face recognition according to claim 6, characterized in that: In step S4, if the current operation on the ATM is a safe operation, adjusting the current working mode of the ATM according to the cardholder identity information specifically includes: If the current ATM operation is a safe operation, the actual age of the cardholder is determined based on the cardholder identity information; If the actual age is greater than or equal to a preset age threshold, the font size and display brightness of the ATM screen display are increased, and the allowed time length for operating the ATM is increased; If the actual age is less than the preset age threshold, the current display state of the ATM screen remains unchanged.

Citation Information

Patent Citations

  • ATM intelligent security system and monitoring method

    CN101556717A

  • Financial self-service device and anti-peeping system and anti-peeping method thereof

    CN102610035A