TWI687872B - Transaction system based on face recognitioin for verification and method thereof - Google Patents

Abstract

A transaction system with an automated teller machine (ATM) and a verification server. A camera module of the ATM is configured to get a to-be-verified image of a user’s face and comprises a infrared temperature sensing component to obtain the user’s body temperature. A card-reader module and an input module of the ATM is configured to receive a debit card inserted by the user and a transaction item inputted by the user. A control module of the ATM is configured to instruct a communication module to send the to-be-verified image, the body temperature information, and the transaction item. The verification server communicatively connects with the the ATM. The verification server comprises an account database, which comprises a plurality of account datum with each account data comprising a reference image, and a computing module configured to compare the to-be-verified image and the reference image, determine a variation degree of the body temperature, and generate a continuation signal according to a comparing result and a determination result. A transaction module of the ATM executes a transaction operation according to the continuation signal and the transaction item.

Description

Trading system and method for verification based on face recognition

The invention relates to a transaction system and method, in particular to a transaction system and method for verification based on facial features and facial expression recognition.

Today's social fraud cases are frequent, and money laundering through head account is also heard from time to time; the former is the fraud group after obtaining the victim's trust, defrauding the victim's financial card and withdrawal password, and then the driver carries the card to the ATM to withdraw Cash; the latter is a fraud group that cleverly deceived the account numbers, financial cards and account passwords of ordinary people, and then tricked the victims into remitting money to these head accounts, and then sent drivers to the ATM to withdraw the funds from the head account.

Observing the aforementioned types of theft cases, the same thing is that the person who operates the ATM to withdraw cash is not the account person. Because the withdrawal process of traditional ATMs only relies on financial cards and withdrawal passwords as the basis for account security verification. Therefore, once the card is lost and the password is leaked, the risk of the deposit being stolen will be greatly increased. In addition, even if the account is withdrawn in person, it cannot be ruled out that it is forced to collect money from the ATM because of the threat of gangsters. However, the current ATM has not yet had any mechanism to prevent the theft of the incident.

In view of this, the present invention discloses a transaction system and method for authentication by face recognition, thereby reducing the potential of the ATM being impersonated by others or being forced to withdraw involuntarily.

A transaction system based on face recognition for verification according to an embodiment of the present invention includes: an ATM, including: a camera module including an infrared temperature sensing element, the camera module is used to obtain a waiting Verification image, the infrared temperature sensing element is used to obtain a body temperature of the user; the image to be verified includes information on a user's face and the body temperature; a card reading module is used to place a financial card 1. Acquire an account number of the financial card, send a verification request and receive a verification reply sent by the financial card; an input module is used to input a card password and a transaction content; a control module is electrically connected to the The camera module, the card reading module and the input module, the control module is used to receive the to-be-verified image and the account number, generate the verification request according to the card password, and selectively generate a prompt message according to the verification reply And selectively instruct the camera module to obtain the to-be-verified image, and the prompt message is used to prompt the user to input the transaction content, and the control module is further used by the input module to receive the transaction content; a display mode Group, electrically connected to the control module, the display module is used to present the to-be-verified image taken by the camera module in real time; a communication module is electrically connected to the control module and used to control The instruction of the module sends the account number, the image to be verified and the transaction content; and a transaction module, which is electrically connected to the control module, and is used to perform a transaction operation according to a renewable signal; and a verification server , The communication module connected to the ATM, including: an account database, including a plurality of account information, each of the account information at least includes an account number, a first reference image and a second reference image, wherein The second reference image corresponds to a preset transaction item; an expression recognition module electrically connected to the account database, the expression recognition module is used to analyze an expression of the face in the image to be verified, and the The expression recognition module has one training set of neural network-like; an operation module, which is electrically connected to the account database and the expression recognition module, and the operation module is used to find that the account database is the same as the account number A target account information, compare the first reference image of the image to be verified and the target account information, compare the second reference image of the verification image and the target account information according to the expression, and determine the change of the body temperature Whether the amplitude exceeds a reasonable temperature difference range, and the renewable signal is selectively generated according to a comparison result, wherein the renewable signal is associated with the default transaction item, and the arithmetic module is further used to store the image to be verified And the comparison result to the corresponding target account information and the training set; and a warning module, which is electrically connected to the calculation module, and the warning module is used to selectively send a warning according to the comparison result Signal.

A transaction method based on facial features for verification according to an embodiment of the present invention includes: receiving a financial card with a card reading module of an ATM; after obtaining the financial card by the card reading module, A camera module of the ATM obtains a to-be-verified image including a face of a user, and uses an infrared temperature sensing element of a camera module of the ATM to obtain a body temperature of the user; The control module receives the image to be verified including the body temperature information and instructs a communication module of the ATM to send the image to be verified to a verification server; after the card reader module obtains the financial card, the automatic An input module of the teller machine receives a card password; a control module of the automatic teller machine generates a verification request according to the card password and sends the verification request to the financial card through the card reading module; using the card reading module Receiving a verification reply of the financial card and sending the verification reply to the control module; the control module selectively generates a prompt message based on the verification reply and selectively instructs the camera module to obtain the image to be verified, The prompt message is used to prompt the user to input the transaction content; a display module presents the to-be-verified image captured by the camera module in real time; the control module receives the transaction content and instructs the communication module to send the transaction content The transaction content is sent to the verification server; an operation database of the verification server is used to compare an account database according to the image to be verified, wherein the account database includes a plurality of account information and each of the account information includes at least a first A reference image and a second reference image; an expression recognition module of the verification server analyzes an expression of the face in the image to be verified; the calculation module compares the image to be verified with the expression according to the expression ratio At least one of the second reference images in the account database; when the image to be verified corresponds to one of the account information, the arithmetic module is used to store the image to be verified and the comparison result to the corresponding account Information; use the arithmetic module to determine whether the variation of the body temperature exceeds a reasonable temperature difference range and accordingly generate a judgment result; based on the judgment result, the arithmetic module and the first reference image One of the comparison result and the other comparison result of at least one of the verification image and the second reference images and selectively generates a sustainable signal; the arithmetic module chooses not to generate the sustainable signal When a warning signal is sent by a warning module of the verification server; when the computing module selects to generate the renewable signal, the verification server sends the renewable signal to the ATM; and A transaction module of the ATM performs a transaction operation based on the renewable signal and the transaction content.

With the above-mentioned architecture, the transaction system and method for authentication based on face recognition disclosed in the present invention, on the basis of the original withdrawal with a financial card and a password, add the face of the user who operates the ATM Recognition is used as a verification mechanism. In addition, facial recognition can be added as a further verification method, so it can effectively reduce the risk of non-account identity to the ATM, and it can also immediately detect that the account is under duress and not voluntary withdrawal. Situation, avoid early loss of money in the account itself.

The above description of the disclosure and the following description of the embodiments are used to demonstrate and explain the spirit and principle of the present invention, and provide a further explanation of the scope of the patent application of the present invention.

The following describes in detail the detailed features and advantages of the present invention in the embodiments. The content is sufficient for any person skilled in the relevant art to understand and implement the technical content of the present invention, and according to the contents disclosed in this specification, the scope of patent application and the drawings Anyone skilled in the relevant art can easily understand the purpose and advantages of the present invention. The following examples further illustrate the views of the present invention in detail, but do not limit the scope of the present invention in any way.

Please refer to FIG. 1, which is a diagram illustrating the architecture of a transaction system based on face recognition for verification according to an embodiment of the present invention. This system mainly includes an ATM 1 and a verification server 5. The ATM 1 is communicatively connected to the verification Server 5, in practice, the "communication connection" refers to the connection through wired or wireless means; the wired communication connection means, for example, through a telephone line, Universal Serial Bus (USB), twisted pair, coaxial cable Or optical fiber cable for communication connection; wireless communication connection methods are, for example, through Global System for Mobile Communications (GSM), Worldwide Interoperability for Microwave Access (WiMax), and code division multiple access (Code Division Multiple Access, CDMA), Near Field Communication (NFC), Bluetooth or Wi-Fi, etc. The invention does not limit the type of communication connection.

Please refer to FIG. 1, the ATM 1 includes a camera module 10, a card reading module 11, an input module 12, a control module 13, a communication module 14 and a transaction module 15, wherein the camera module 10 and the card reading module The group 11, the input module 12, the communication module 14, and the transaction module 15 are all electrically connected to the control module 13, as shown in FIG.

The camera module 10 is used to obtain an image to be verified. In practice, the camera module is, for example, a camera including a charge-coupled device (Charge-Coupled Device, CCD) or a complementary metal-oxide semiconductor (CMOS) Camera. However, the present invention is not limited to the hardware device of the camera module 10; in addition, the present invention does not limit the number of camera modules 10. The image to be verified must include a facial image, that is, a facial image of a user who operates the ATM 1. Generally speaking, the camera module 10 should be installed at a position on the ATM 1 that is visible to the user. In addition, considering that the heights of users are different, the fixed-height camera module 10 may not be able to take in the faces of users whose height is much higher or lower than this fixed height; therefore, in practice, many Each camera module 10 at a different height or a single camera module 10 is added with a wide-angle lens or a fisheye lens, thereby increasing the shooting range of the camera module 10.

The card reading module 11 is for the user who operates the ATM 1 to insert a financial card. After the user inserts the financial card, the card reading module 11 is further used to send a verification request to the financial card or receive the verification sent by the financial card Reply. In practice, the card reader module 11 is, for example, a card reader or other hardware device that can read chip financial cards or magnetic stripe financial cards.

The input module 12 is used for a user who operates the ATM 1 to input a card password and transaction content. In practice, the input module 12 is, for example, a physical keyboard or a virtual keyboard displayed on the screen. The card password refers to the withdrawal password of the financial card placed in the card reading module 11. The transaction content is, for example, a financial transaction item such as deposit amount, withdrawal amount, transfer amount, or transfer account number.

The control module 13 is used to receive the to-be-verified image captured by the camera module 10; generate a verification request according to the card password input by the user through the input module 12 and send the verification request to the finance through the card reading module 11 At the same time, the verification reply sent by the financial card is received from the card reading module 11. If the verification reply indicates that the card password is correct, the control module 13 generates a prompt message to prompt the user to enter the transaction content, and then the control module 13 receives the transaction content input by the user, and the control module 13 further instructs the communication Module 14 sends the transaction content. If the verification reply indicates that the card password is incorrect, the control module 13 prompts the user to re-enter the password or instructs the communication module to send a warning message. In practice, the control unit 13 is, for example, a central processing unit (CPU), a microprocessor (Microprocessor), a digital signal processor (DSP), or a special application integrated circuit (Application- Specific Integrated Circuit (ASIC), other similar components or a combination of the above components, the invention does not limit the hardware type of the control unit 13.

The communication module 14 is, for example, a network communication chip, which is used to send the image to be verified and the transaction content according to the instruction of the control module 13.

The transaction module 15 is used to perform a transaction operation according to the instructions of the control module 13. For example, the transaction operation provides the same amount of cash to the user according to the withdrawal amount set in the transaction content. The basis indicated by the control module 13 is the verification of the renewable signal and the transaction content sent by the server 5, and the renewable signal will be described later.

In another embodiment of the present invention, the ATM 1 further includes a display module, which is electrically connected to the control module 13 and used to present the image to be verified captured by the camera module 10 in real time for user confirmation The captured image. In addition, the "control module 13 generates a prompt message" and "the control module 13 prompts the user to re-enter the password" mentioned above are also presented in text or image form for display by the user through the display module. In practice, display modules such as: Plasma Display Panel, Liquid-Crystal Display (LCD), Thin Film Transistor Liquid Crystal Display (TFT-LCD), LED Light-Emitting Diode Display (LED Display) Organic Light-Emitting Diode (OLED) or other display devices with similar functions.

In an embodiment of the present invention, when the card reading module 11 detects that the card is inserted, it can notify the control module 13 to enable the camera module 10 to take a picture, and the picture is taken through the communication module 14 in real time. The image to be verified is sent to the verification server 5. In another embodiment of the present invention, the control module 13 enables the camera module 10 to shoot after the card password is entered correctly, and sends the transaction content together with the image to be verified after the user inputs the transaction content To authentication server 5. However, the timing of the control module 13 enabling the camera module 10 to perform shooting in the present invention is not limited to the timing of sending the to-be-verified image with the communication module 14. In practice, the financial institution with the ATM 1 The execution efficiency of the verification server 5 and the transmission efficiency of the communication connection can be comprehensively considered to decide when to shoot and transmit images.

Please refer to Figure 1. The verification server 5 is communicatively connected to the communication module 14 of the ATM 1. In an embodiment of the invention, the verification server 5 includes an account database 50 and a calculation module 51. In practice, the verification server 5 is, for example, a Pedestal server, a rack server, or a blade server. The present invention does not limit the types of hardware of the verification server 5.

The account database 50 includes a plurality of account information, and each account information represents a user's personal data. For example, personal data is authorized by a user to provide a financial institution as a basis for personal identity verification when opening an account. Specifically, an account information includes at least a first reference image; this first reference image is, for example, a face image taken by the user when opening an account, or a certificate photo provided by the user, such as an identity card or a driver’s license Face image.

The calculation module 51 is electrically connected to the account database 50, and the calculation module 51 is used to compare whether the verification image matches the first reference image in the account database 50. Specifically, the operation module 51 is, for example, a microprocessor, a digital signal processor, an integrated circuit for special applications, other similar components, or a combination of the foregoing components. Regarding the comparison method of the arithmetic module 51, for example, first, image processing is used to capture the feature points of the image to be verified, and match the feature points of the first reference image stored in the account information to determine the similarity of the two images.

It must be specifically explained here that in one embodiment, the image to be verified is compared with all the first reference images in the account database. In another embodiment, the card reading module 11 further includes an account for obtaining the financial card in advance, and the control module 13 receives the account and instructs the communication module 14 to send the account together with the image and transaction content to be verified to the verification Server 5, and each account information in the account database uses the account number as the primary key of the database (Primary Key), so you can first use the account number to compare the card account and select a target account that is the same as the card account Information, and then compare the first reference image with the account information and the image to be verified, so as to speed up the comparison speed of the image to be verified.

Regarding the feature point recognition part, it can be implemented in one of the whole feature or the local feature; the former is to compare the entire face image as a single feature, and the latter is to first find the local features of the face, such as eyes, nose, The mouth, the corner of the mouth, or the corner of the eye, etc., are then compared for these local features, and finally the results of the comparison of individual local features are integrated to obtain the final recognition result. If the computing module 51 finds a first reference image in the account database that is similar to the image to be verified by a specified ratio or more, it means that the user operating the ATM 1 is indeed the account himself. Therefore, the arithmetic module 51 generates a renewable signal and the verification server 5 sends the renewable signal to the ATM 1. The renewable signal represents the verification procedure of the user through facial recognition. Therefore, after receiving the renewable signal, the ATM 1 can instruct the transaction module 15 to perform a transaction operation according to the transaction content set by the user. Based on the face recognition mechanism described above, the transaction system disclosed in an embodiment of the present invention is more capable of preventing the fraudulent group from sending drivers to take the lead than the traditional ATM transaction system that only uses the card password as a security verification.

Please refer to Figure 1. In another embodiment of the present invention, in order to improve the security of verification based on face recognition, the verification server 5 further includes an expression recognition module 52 electrically connected to the account database 50 and the calculation module 51, and the expression recognition module 52 is used to analyze facial expressions in the image to be verified, such as basic expressions such as anger, disgust, fear, joy, surprise, and sadness, and provide recognition results to the computing module 51. In practice, in order to avoid that different expression change elements of each person cause the expression recognition module 52 to incorrectly recognize the expression of the image to be verified, when creating account information of the account database 51, in addition to storing the user’s facial image as the first In addition to a reference image, it also includes storing a facial expression determined by the user as a second reference image. Therefore, when the verification server 5 receives the transaction content and the to-be-verified image from the ATM 1, in addition to the first reference image in the account database 50 through the arithmetic module 51, the verification image is indeed the account’s own In addition, it also includes analyzing the expression of the image to be verified and the expression of the second reference image through the expression recognition module 52. The expression recognition module 52 sends the analysis result to the arithmetic module 51 to compare the verification image with the second reference image Similarity. In addition, the expression recognition module 52 may further include a machine learning function. In practice, when the image to be verified can correspond to one of the account information, the computing module 51 further includes storing the image to be verified and the comparison result to the corresponding account information. In other words, by adding the to-be-verified image that is retained each time the user performs a transaction operation to the ATM to add to the neural network-like training set of the expression recognition module, the richness and classification of the recognizable types of the expression recognition module can be improved The accuracy of classifying the image to be verified to an expression. On the other hand, the present invention does not limit the second reference image to have only one set of expressions. Users can set up multiple sets of corresponding expressions according to their commonly used transaction items and store them in the second reference image; for example, an expression of 10,000 yuan wins the left eye, an expression of 5,000 yuan wins the right eyebrow. Generally speaking, when the user is coerced or involuntarily picked up by the ATM, the user usually presents an angry, disgusted or scared expression, and the expression recognition module 51 disclosed in the above embodiment of the present invention and the pre-reserved The design of the second reference image will assist the computing module 51 to detect the situation where the user is being forced to withdraw, and then execute countermeasures corresponding to this situation.

In yet another embodiment of the present invention, the camera module 10 further includes an infrared temperature sensing element, such as an infrared thermal imager, to obtain the body temperature of the user when operating the ATM 1, and the communication module 14 sends The temperature information is also included in the image to be verified. After receiving the temperature information, the arithmetic module 51 of the verification server 5 determines whether the variation range exceeds a reasonable temperature difference range. Generally speaking, when human beings are in nervous or emotional state, their body temperature will rise involuntarily. Therefore, if the computing module 51 finds this phenomenon from the temperature information, it will increase its own criterion for determining the similarity between the image to be verified and the first reference image, and also increase the expression recognition module 52 to the image to be verified and the second The standard value is judged with reference to the similarity of the images. Through the above mechanism, it is possible to effectively detect the gangster disguising the original account user by masking or disguising the original account, and also to detect the gangster’s abnormal change in body temperature due to the tension of the illegal act, thus further improving the present invention The security of the transaction system described based on face recognition for verification.

In still another embodiment of the present invention, the verification server 5 further includes an alarm module electrically connected to the calculation module 51. The warning module is used to selectively send a warning signal according to the comparison result of the computing module 51. The warning signal is, for example, dialing a phone to contact the police unit or sending a short message to the emergency contact person set in this account.

Please refer to FIG. 2, the following is a flow chart of the automatic teller machine 1 in a transaction system disclosed in an embodiment of the present invention for verifying based on face recognition according to a user’s operation. Verified transaction method.

Please refer to step S0: Insert a financial card; specifically, the user inserts the financial card into the first card reading module 11 of the ATM 1.

Please refer to step S1: shooting the image of the user's face to be verified; in detail, after the financial card is inserted into the card reading module 11, the control module 13 of the ATM 1 then enables the camera module 10 to obtain the pending verification Image, and the image to be verified includes the user's face.

Please refer to step S2: input the password; after the financial card is inserted into the card reading module 11, the user inputs the password of the financial card through the input module 11 of the ATM.

Please refer to step S3: verification by password; in detail, after the user enters the password in step S2, the control module 13 of the ATM 1 generates a verification request based on the password and sends the verification request to the finance through the card reader module 11 The card and financial card will generate a verification response according to the verification request. The card reader module 11 can receive the verification response and send it to the control module 13 to determine whether the entered password is correct.

Please refer to step S4: input transaction content; after the control module 13 determines that the password verification is passed in step S3, the control module 13 prompts the user to enter a transaction content, for example, the transaction content is a withdrawal amount.

Please refer to step S5: prompt password error; as described in step S3, if the control module 13 judges that the password verification fails according to the verification reply, it prompts the user to enter the wrong password, and returns to step S2 to allow the user to enter the password again. In practice, after the user enters the wrong password for a specified number of times (for example, three times), the financial card will be locked. This is the protection method known to the ATM 1 and is not described here. The steps are in the flowchart of this embodiment.

Please continue to refer to step S6 to send the transaction content and the image to be verified; specifically, this step is that the control module 13 instructs the communication module 15 of the ATM to send the transaction content input in step S4 and the pending verification captured in step S1 Image to authentication server 5. It must be noted here that in another embodiment of the present invention, step S1 can also be executed in step S4, in other words, the control module 13 enables the camera module 10 only after the user passes the password verification The image to be verified is captured, so as to ensure that the face image is captured when the user password is entered correctly, thus reducing unnecessary power consumption of the camera module 10. In yet another embodiment of the present invention, the communication module 15 can obtain the image to be verified in step S1 in advance, and then immediately send the image to be verified to the verification server 5, so that the user can verify the server during the transaction input by the user 5 Simultaneously perform the comparison of the images to be verified, so it can reduce the time the user waits for the facial verification process to complete.

Please continue to refer to step S7 to compare the reference image of the account database 50 with the image to be verified; in detail, the arithmetic module 51 of the verification server 5 compares the account database 50 with the image to be verified, wherein the account database 50 includes A plurality of account information and each account information includes at least a first reference image. In an embodiment of the invention, the arithmetic module 51 executes an algorithm related to face recognition (such as the Lucas-Kanade method) to calculate the image value to be verified and the first reference image one by one to obtain the similarity between the two and determine Whether the similar procedure exceeds a predetermined threshold. In another embodiment of the present invention, the computing module 51 finds in advance a target account information with the same account number as the card account from the account database (the account number is obtained by the card reading module 11 in step S0 and Sent to the control module 13 and transmitted to the verification server 5 through the communication module 14 in step S6), and then the calculation module 51 only compares the first reference image of the target account information with the image to be verified and generates a comparison result.

In another embodiment of step S7, in addition to determining whether it is the account itself based on the first reference image and the image to be verified, the verification server 5 has an expression recognition module 52 for determining the expression of the image to be verified and determining the account database 51 The expression of the second reference image corresponding to the account in. The second reference image is also a face image pre-reserved by the user in the financial institution, and is characterized in that the face image contains an expression determined by the user, so the second reference image can be identified by the expression recognition module The determination of the facial expression is to determine the facial expression of the image to be verified, and to confirm whether the user is in a state of being forced to withdraw.

Please refer to step S8 "Compare Pass" and step S9 "Send Renewable Signal" together, following step S7, if the computing module 51 can find an account information in the account database, its first reference image and the image to be verified are both If the similarity of the persons is above a predetermined threshold, it can be determined that the user who took the image to be verified is indeed the account. Therefore, the computing module 51 generates a renewable signal according to the image to be verified and passes the verification server 5 The communication connection with the ATM 1 sends this continuation signal.

Please refer to step S10 to execute the transaction operation; in detail, when the control module 13 of the ATM 1 receives the renewable signal, it instructs the transaction module 15 to execute the items set by the transaction content, such as issuing five thousand cash notes Yuan to users.

Please refer to step S11 to send a warning signal; following step S8, if the computing module 51 cannot find the first reference image that matches the image to be verified in the account database, it means that the current ATM 1 is likely to be impersonated, so The verification server 1 can send a warning signal to the police unit, financial institution, account person, or emergency contact person set by the account person to achieve the effect of real-time notification.

In summary, the transaction system and method for verification based on face recognition disclosed in the present invention, by shooting the user's face image on the ATM side and targeting the face image and its expression on the remote verification server Perform analysis and comparison to determine whether the user is the cardholder and whether the user's facial expression is abnormal, thus effectively reducing the possibility of fraud group fraudulently obtaining the victim's account or stealing the head account through the driver. At the same time, it can immediately reflect the situation of the account being threatened and not voluntary withdrawal. In other words, the present invention adds a check procedure to the user's account security based on the recognition mechanism of the user's face, and on the premise of not excessively affecting the user's original operation process on the ATM, the face-based disclosure of the present invention Identifying and verifying transaction systems and methods are undoubtedly more secure for personal account security; for financial institutions, they can achieve instant anti-fraud or money laundering and other illegal financial activities.

Although the present invention is disclosed as the foregoing embodiments, it is not intended to limit the present invention. Without departing from the spirit and scope of the present invention, all modifications and retouching are within the scope of patent protection of the present invention. For the protection scope defined by the present invention, please refer to the attached patent application scope.

1‧‧‧ATM 10‧‧‧Camera module 11‧‧‧Card reader module 12‧‧‧input module 13‧‧‧Control module 14‧‧‧Communication module 15‧‧‧ Trading Module 5‧‧‧Verification server 50‧‧‧ Account database 51‧‧‧ arithmetic module 52‧‧‧Emoji recognition module S0~S11‧‧‧Step

FIG. 1 is an architecture diagram of a transaction system for verification based on face recognition according to an embodiment of the invention. FIG. 2 is a flowchart of a transaction method based on face recognition for verification according to an embodiment of the invention.

1‧‧‧ATM

10‧‧‧Camera module

11‧‧‧Card reader module

12‧‧‧input module

13‧‧‧Control module

14‧‧‧Communication module

15‧‧‧ Trading Module

5‧‧‧Verification server

50‧‧‧ Account database

51‧‧‧ arithmetic module

52‧‧‧Emoji recognition module

Claims (3)

A transaction system for verification based on face recognition, including: an ATM, including: a camera module including an infrared temperature sensing element, the camera module is used to obtain an image to be verified, and the infrared temperature sensing element It is used to obtain a body temperature of the user; the image to be verified includes information of a user's face and the body temperature; a card reading module is used for placing a financial card, obtaining an account of the financial card, Send a verification request and receive a verification reply sent by the financial card; an input module is used to input a card password and a transaction content; a control module is electrically connected to the camera module and the card reading module And the input module, the control module is used to receive the to-be-verified image and the account number, generate the verification request according to the card password, selectively generate a prompt message and selectively instruct the camera module according to the verification reply Obtain the to-be-verified image, and the prompt message is used to prompt the user to input the transaction content, and the control module is used to receive the transaction content from the input module; a display module is electrically connected to the control module Group, the display module is used to present the to-be-verified image captured by the camera module in real time; a communication module is electrically connected to the control module and used to send the account number and the account according to the instruction of the control module The image to be verified and the transaction content; and a transaction module, which is electrically connected to the control module and used to perform a transaction operation according to a renewable signal; and a verification server, which is communicatively connected to the ATM The communication module includes: an account database, including a plurality of account information, each of which includes at least an account number, a first reference image, and a second reference image, where the second reference image corresponds to a pre- Set transaction items; an expression recognition module, electrically connected to the account database, the expression recognition module is used to analyze an expression of the face in the image to be verified, and the expression recognition module has a neural network-like A training set; a computing module, electrically connected to the account database and the expression recognition module, the computing module is used to find the target account information in the account database that is the same as the account number, and compare The first reference image of the to-be-verified image and the target account information, compare the verification image and the second reference image of the target account information according to the expression ratio, and determine whether the variation range of the body temperature exceeds a reasonable temperature difference range, and The renewable signal is selectively generated according to a comparison result, wherein the sustainable signal is associated with the default transaction item, and the arithmetic module is further used to store the image to be verified and the comparison result to the corresponding The target account information and the training set; and a warning module electrically connected to the computing module, the warning module is used to selectively send a warning signal according to the comparison result. A transaction method for verification based on facial features includes: receiving a financial card with a card reading module of an ATM; after acquiring the financial card with the card reading module, acquiring with a camera module of the ATM Including a to-be-verified image of a face of a user, and using an infrared temperature sensing element of a camera module of the ATM to obtain a body temperature of the user; receiving information including the body temperature with the control module The image to be verified and instructs a communication module of the ATM to send the image to be verified to a verification server; after the card reader module obtains the financial card, an input module of the ATM receives a card Password; a control module of the ATM generates a verification request based on the card password and sends the verification request to the financial card through the card reading module; the card reading module receives a verification reply of the financial card and Sending the verification reply to the control module; the control module selectively generates a prompt message based on the verification reply and selectively instructs the camera module to obtain the image to be verified, the prompt message is used to alert the user Input the transaction content; present the to-be-verified image captured by the camera module with a display module; receive the transaction content with the control module and instruct the communication module to send the transaction content to the verification server; An operation module of the verification server compares an account database according to the image to be verified, wherein the account database includes a plurality of account information and each of the account information includes at least a first reference image and a second reference image Analyzing an expression of the face in the image to be verified with an expression recognition module of the verification server; using the arithmetic module to compare the image to be verified with the second references in the account database according to the expression ratio At least one of the images; when the image to be verified corresponds to one of the account information, the calculation module is used to store the image to be verified and the comparison result to the corresponding account information; the calculation module determines the Whether the variation range of body temperature exceeds a reasonable temperature difference range and accordingly generate a judgment result; the calculation module uses the comparison result and the verification based on the judgment result, at least one of the to-be-verified image and the first reference images Another comparison result of at least one of the image and the second reference images and selectively generate a sustainable signal; when the arithmetic module chooses not to generate the sustainable signal, one of the verification servers is used The warning module sends a warning signal; when the computing module selects to generate the renewable signal, the verification server is used to send the renewable signal to the ATM; and a transaction module of the ATM is used according to the The transaction signal and the transaction content can be used to execute a transaction operation. The transaction method for verifying based on facial features according to claim 2, wherein: when the card reading module receives the financial card, it further includes receiving an account number of the financial card with the card reading module; in the control When the module instructs the communication module to send the transaction content to the verification server, the control module further instructs the communication module to send the account number; and the calculation module compares the account data according to the image to be verified Before the library, it also includes comparing the account number and the account number of each of the account information with the computing module, and using the first reference image of the account information with the account number and the account number and the to-be-verified The images are compared.

Images