TWI813082B - Cardless finance transaction system and its host server - Google Patents

Abstract

A cardless financial transaction system includes an ATM and a host server. The ATM includes an image capturing device and a display screen. The display screen displays a gesture prompt screen to an operator. The image capturing device captures a verification image for the operator. The verification image includes the demonstration gesture shown by the operator according to the gesture prompt screen. The host server includes a database unit, an image recognition unit and a processing unit. The database unit stores a plurality of user hand feature values corresponding to different users. The image recognition unit is used for recognizing the verification image and analyzing a gesture feature value based on the hand that demonstrates the gesture. The processing unit is used to compare and determine whether the gesture feature value matches one of the user's hand feature values.

Description

Cardless financial transaction system and host server

The invention relates to a financial transaction system, in particular to a cardless financial transaction system and a host server.

Generally speaking, in the existing cardless withdrawal system, the withdrawer does not need to insert a financial card into the Automated Teller Machine (ATM) and can withdraw money from the ATM, which improves the user's convenience and interest. An existing method of identity verification is to verify the identity of the withdrawer through vein identification.

However, ATMs that use vein recognition must be equipped with specific vein sensing devices, so additional hardware equipment is required, increasing hardware costs, and thus failing to increase the willingness of operators to install it.

It can be seen that the above-mentioned technology obviously still has inconveniences and defects, and needs to be further improved. Therefore, how to effectively solve the above inconveniences and defects is indeed one of the current important research and development topics, and it has also become an urgent need for improvement in related fields.

One object of the present invention is to provide a cardless financial transaction system and a host server to solve the above difficulties mentioned in the prior art.

One embodiment of the present invention provides a cardless financial transaction system. The cardless financial transaction system includes a host server and at least one automatic teller machine. The automatic teller machine includes a first transmission unit, a first image capture device and a display screen. The display screen is used to display at least one gesture prompt screen to an operator. The first image capture device is used to capture an operator. Verification image, the verification image includes one of the demonstration gestures produced by the operator according to the gesture prompt screen. The host server includes a second transmission unit, a database unit, an image recognition unit and a processing unit. The second transmission unit is electrically connected to the first transmission unit through a network architecture. The database unit stores user hand characteristic values of a plurality of pens corresponding to different users. The image recognition unit is used to recognize and verify the image and perform one of the hand gestures according to the demonstration gesture. After parsing out a gesture characteristic value, the processing unit is electrically connected to the second transmission unit, the database unit and the image recognition unit to compare and determine whether the gesture characteristic value matches one of the user's hand characteristic values.

According to one or more embodiments of the present invention, in the above-mentioned cardless financial transaction system, the host server further includes an identity verification unit. The identity verification unit is electrically connected to the processing unit, and is used to instruct the automatic teller machine to perform a plurality of identity verification steps in sequence, and display a plurality of gesture prompt screens through the display screen in response to these identity verification steps.

According to one or more embodiments of the present invention, in the above-mentioned cardless financial transaction system, these gesture prompt screens are prompts for scissors gesture, rock gesture, paper gesture and digital gesture respectively.

According to one or more embodiments of the present invention, the above-mentioned cardless financial transaction system further includes a bank server. The bank server includes a third transmission unit, a second image capture device and a registration unit. The third transmission unit is electrically connected to the second transmission unit through the network architecture. The second image capturing device is used to capture a registered image of a registered user. The registered image includes another demonstration gesture performed by the registered user's hand. The registration unit is electrically connected to the third transmission unit and the second image capture device, and is used to request the image recognition unit of the host server to recognize the registered image, so that the image recognition unit can analyze the hand characteristics of another user based on one of the hands of another demonstration gesture. value, and allow another user's hand characteristic value to be stored in the database unit of the host server.

According to one or more embodiments of the present invention, in the above-mentioned cardless financial transaction system, the image recognition unit analyzes the gesture feature value based on the wrist fixed point of the hand performing the gesture, the fingertips and the knuckles of the fingers, and based on another The characteristic values of another user's hand are analyzed from the fixed wrist point of the hand demonstrating the gesture, the fingertips and the knuckles of the fingers.

According to one or more embodiments of the present invention, in the above-mentioned cardless financial transaction system, the processing unit obtains the gap range between the feature matrix of the gesture feature value of the demonstration gesture and the feature matrix of one of the user's hand feature values, and When it is determined that the gap range meets a preset range, the processing unit determines that the gesture feature value matches one of the user's hand feature values.

An embodiment of the present invention provides a host server. The host server is suitable for a cardless financial transaction system, and the host server includes a transmission unit, a database unit, an image recognition unit and a processing unit. The transmission unit is electrically connected to an automatic teller machine through a network architecture, and is used to receive a verification image from the automatic teller machine, where the verification image includes a demonstration gesture produced by an operator. The database unit stores user hand characteristic values of a plurality of pens corresponding to different users. The image recognition unit is used to recognize and verify the image, and analyze a gesture feature value based on the wrist fixed point of the hand performing the gesture, the fingertips and the knuckles of the fingers. The processing unit is electrically connected to the transmission unit, the database unit and the image recognition unit, and is used to compare and determine whether the gesture feature value matches one of the user's hand feature values.

According to one or more embodiments of the present invention, the above-mentioned host server further includes an identity verification unit. The identity verification unit is electrically connected to the processing unit to instruct the automatic teller machine to perform multiple identity verification steps in sequence and provide multiple corresponding identities. Gesture prompt screen for verification steps to the ATM.

According to one or more embodiments of the present invention, in the above-mentioned host server, these gesture prompt screens are prompts for scissors gestures, rock gestures, paper gestures and digital gestures respectively.

According to one or more embodiments of the present invention, in the above host server, the processing unit obtains the gap range between the feature matrix of the gesture feature value of the demonstration gesture and the feature matrix of one of the user's hand feature values, and determines When the gap range meets a preset range, the processing unit determines that the gesture feature value matches one of the user's hand feature values.

In this way, through the structure described in the above embodiments, the surveillance camera on the existing ATM can be used to quickly and effectively identify whether it is the person. In addition, for banks, there is no need to add additional hardware equipment, which can greatly increase the bank's willingness to set up.

The above is only used to describe the problems to be solved by the present invention, the technical means to solve the problems, the effects thereof, etc. The specific details of the present invention will be introduced in detail in the following embodiments and related drawings.

The following will disclose multiple embodiments of the present invention in the drawings. For the sake of clarity, many practical details will be explained in the following description. However, it will be understood that these practical details should not limit the invention. That is to say, in various embodiments of the present invention, these practical details are not necessary. In addition, for the sake of simplifying the drawings, some commonly used structures and components will be illustrated in a simple schematic manner in the drawings.

Figure 1 is a block diagram of a cardless financial transaction system 10 according to an embodiment of the present invention. As shown in FIG. 1 , the cardless financial transaction system 10 includes a host server 200 and one or more automatic teller machines 100 (ATM). The host server 200 connects these ATMs 100 through a network architecture N.

Figure 2 is a detailed block diagram of the ATM 100 in Figure 1 . As shown in Figures 1 and 2, each ATM 100 allows an operator to perform card-present or card-less financial transactions in person, such as withdrawals, deposits, transfers or inquiries. Each ATM 100 has a first transmission unit 110, a first image capture device 120, a display screen 130, an input unit 140 and a control unit 150. The control unit 150 is electrically connected to the first transmission unit 110, the first image capture device 120, the display screen 130 and the input unit 140, and is used to control the first transmission unit 110, the first image capture device 120, the display screen 130 and the input respectively. Unit 140 works properly. The first transmission unit 110 is used to electrically connect to the corresponding external mechanism through the above-mentioned network architecture N. The display screen 130 is used to display a prompt screen, such as a gesture prompt screen, to the operator. The input unit 140 is used to allow the above-mentioned operator to input execution instructions. The first image capturing device 120 is used to photograph the front side of the ATM 100, for example, to capture a verification image of the operator. The verification image includes demonstration gestures performed by the operator according to the gesture prompt screen. For example, the first transmission unit 110 and the control unit 150 are respectively located in the machine of the ATM 100, and the first image capture device 120, the display screen 130 and the input unit 140 are respectively located in the front edge of the machine of the ATM 100.

Figure 3 is a detailed block diagram of the host server 200 of Figure 1 . As shown in Figures 2 and 3, the host server 200 includes a second transmission unit 210, a database unit 220, an image recognition unit 240, an identity verification unit 250 and a processing unit 260. The second transmission unit 210 is electrically connected to the first transmission unit 110 through the network architecture N (FIG. 1). The database unit 220 stores user hand feature values 230 of a plurality of pens corresponding to different users. The user hand feature values 230 of each user are unique or exclusive, that is, they are unique and non-repeating. The image recognition unit 240 is used to recognize the verification image and analyze a gesture feature value based on the hand performing the gesture. For example, the image recognition unit 240 analyzes the gesture feature value based on the wrist point of the hand performing the gesture, the fingertips and the knuckles of the fingers. The identity verification unit 250 is used to instruct the ATM 100 to perform a plurality of identity verification steps in sequence, and provide a plurality of gesture prompt screens corresponding to these identity verification steps to the display screen 130 . The processing unit 260 is electrically connected to the second transmission unit 210, the database unit 220, the identity verification unit 250 and the image recognition unit 240 to compare and determine whether the gesture feature value matches one of the user hand feature values 230, that is, this The demonstration gesture matches the corresponding data of the specific user in the database unit 220 .

Figure 4 is a detailed block diagram of the bank server 300 in Figure 1 . As shown in Figures 2 and 4, the above-mentioned cardless financial transaction system 10 further includes one or more bank servers 300 (Figure 1). Each bank server 300 includes a third transmission unit 310, a second image capture device 320 and a registration unit 330. The third transmission unit 310 is electrically connected to the second transmission unit 210 through the network architecture N. The second image capturing device 320 is used to photograph a registered user 400 , for example, capture a registered image of the registered user 400 . The registered image includes another demonstration gesture performed by the registered user 400's hand. The registration unit 330 is electrically connected to the third transmission unit 310 and the second image capture device 320, and is used to require the image recognition unit 240 of the host server 200 to recognize the registration image, so that the image recognition unit 240 parses the hand according to another demonstration gesture. Another user's hand characteristic value 230 is stored in the database unit 220 of the host server 200 . For example, the image recognition unit 240 parses the gesture feature value based on the wrist fixed point of the hand of another demonstration gesture, the fingertips and the knuckles of the fingers. In addition, the first gesture prompt screen and the second gesture prompt screen may be, for example, a scissors gesture, a rock gesture, a paper gesture, any number (such as 1 to 5) gesture, or other clear and common gesture prompts. However, the present invention is not limited to this.

Figure 5A is a schematic diagram of the hand 410 of a registered user 400 being imaged. As shown in Figures 4 and 5A, when the registered user 400 goes to a bank branch to apply for a cardless financial transaction service, the bank server 300 of the bank branch begins to create a user hand characteristic value 230 for the user. The steps include the following. First, the registration unit 330 of the bank server 300 requires the hand 410 of the registered user 400 to show a demonstration gesture according to at least one gesture prompt, and causes the second image capture device 320 to photograph the hand 410 of the registered user 400; Then, it is transmitted to the image recognition unit 240 of the host server 200, so that the image recognition unit 240 analyzes a user hand feature value 230 based on the hand 410 demonstrating the gesture, and allows the user hand feature value 230 to be stored in the host server. The database unit 220 of the device 200 becomes one of a plurality of pens in the database unit 220 corresponding to the user hand characteristic values 230 of different users.

It should be understood that the more user hand characteristic values 230 each user stores into the database unit 220, the more difficult it is to forge and thereby improve system reliability. In addition, the front or back image of the hand 410 captured through the second image capturing device 320 can be used to establish the above-mentioned user hand feature value 230 .

Figure 5B is a schematic diagram of the gesture feature value 500 of the hand 410 of the registered user 400 in Figure 5A. As shown in Figures 4 and 5B, for example, when the registered user 400 performs the cloth gesture, the image recognition unit 240 will use the hand 410 performing the gesture based on the fixed point of the wrist and the pointing of the fingers. Multiple (for example, 21) hand feature points 510 are analyzed from the positions of the tip and knuckles. In other words, these hand feature points 510 are respectively distributed on the palm, such as the fixed point of the wrist (feature code 0, Figure 5B), the fingertips of each finger (feature code 4, 8, 12, 16 and 20, Figure 5B). Figure) and finger joints (feature codes 1~3, 5~7, 9~11, 13~15 and 17~19, Figure 5B). Next, the image recognition unit 240 obtains a feature vector 520 in the coordinates of the line connecting any two adjacent hand feature points 510 . Next, the image recognition unit 240 obtains a feature matrix after calculating a specific standard deviation of each feature vector 520 . In this way, the set of these feature matrices represented by these feature vectors 520 in the demonstration gesture is collectively referred to as the above-mentioned user hand feature value 230. Similarly, the image recognition unit 240 also parses the gesture feature values from the feature matrices represented by the feature vectors 520 of the demonstration gesture in the verification image according to the above method.

More specifically, the processing unit 260 compares the feature matrix of the gesture feature value 500 of the demonstration gesture with the feature matrix of one of the user's hand feature values 230, and obtains the gap range between the two; then, determines whether the gap range meets A preset range. If it is determined that the gap range meets the preset range, the processing unit 260 determines that the gesture feature value 500 matches one of the user hand feature values 230; otherwise, it determines that the gesture feature value 500 does not match one of the user hand feature values 230. The user hand feature value is 230.

Figure 6 is a schematic sequence diagram of the cardless financial transaction system of this embodiment. As shown in Figures 2 and 6, when an operator P goes to the ATM 100 to perform a cardless financial transaction, the host server 200 randomly provides a first gesture prompt screen to the display screen 130 of the ATM 100. For the operator P to display a first demonstration gesture H1 (such as the number five gesture) accordingly.

If the host server 200 determines that the first demonstration gesture H1 matches the corresponding data of a specific user in the database unit 220 according to the above method, the display screen 130 of the ATM 100 will continue to randomly provide a second gesture prompt screen for operation. Accordingly, the person P shows a second demonstration gesture H2 (such as the gesture of number three); on the contrary, if it is judged that it is not consistent, the host server 200 sends a recognition error message from the display screen 130 .

Then, if the host server 200 determines based on the above method that the second demonstration gesture H2 (such as the gesture of number three) matches the corresponding data of the specific user in the database unit 220, the display screen 130 of the ATM 100 continues to randomly provide a first The three-gesture prompt screen is for the operator P to display a third demonstration gesture H3 (such as the gesture of number two); on the contrary, if it is determined that it is not consistent, the host server 200 will send an identity verification error message from the display screen 130.

Then, if the host server 200 determines based on the above method that the third demonstration gesture H3 (such as the gesture of number two) matches the corresponding data of the specific user in the database unit 220, the host server 200 will issue a message from the display screen 130 that the identity verification is correct. message and agreed to allow operator P to continue conducting cardless financial transactions.

It should be understood that in the above embodiments, the host server 200 and the bank server 300 are, for example, server devices or other similar components. The first transmission unit 110, the second transmission unit 210 and the third transmission unit 310 are, for example, a network interface controller (NIC) or other similar components. The first image capturing device 120 and the second image capturing device 320 are, for example, a photography device or other similar components. The input unit 140 is, for example, a keyboard, a touch panel, or other similar components. The database unit 220 may be, for example, any type of fixed or removable random access memory (Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), flash memory (flash memory), Hard disk (Hard Disk Drive, HDD), solid state drive (Solid State Drive, SSD) or similar components or combinations of the above components, the present invention is not limited thereto. The control unit 150 , the processing unit 260 and the registration unit 330 are, for example, a central processing unit (CPU), or other programmable general-purpose or special-purpose microprocessor (Microprocessor) or digital signal processor (Digital signal processor). Signal Processor (DSP), programmable controller, application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or other similar components or combinations of the above components, the invention is not limited thereto. The automatic teller machine 100 (ATM) is a conventional device and will not be described in detail in this article.

In this way, through the structure described in the above embodiments, the surveillance camera on the existing ATM can be used to quickly and effectively identify whether it is the person. In addition, for banks, there is no need to add additional hardware equipment, which can greatly increase the bank's willingness to set up.

Finally, the above disclosed embodiments are not intended to limit the present invention. Anyone skilled in the art can make various modifications and modifications without departing from the spirit and scope of the present invention, and all of them are protected by the present invention. Inventing. Therefore, the protection scope of the present invention shall be determined by the appended patent application scope.

10:Cardless financial transaction system 100:ATM 110: First transmission unit 120: First image capture device 130:Display screen 140:Input unit 150:Control unit 200: Host server 210: Second transmission unit 220: Database unit 230: User hand feature value 240:Image recognition unit 250: Identity verification unit 260: Processing unit 300:Bank server 310: Third transmission unit 320: Second image capture device 330:Registration unit 400:Registered user 410:Hand 500: Gesture feature value 510: Hand feature points 520: Feature vector P:Operator H1: The first demonstration gesture H2: Second demonstration gesture H3: The third demonstration gesture N: Network architecture

In order to make the above and other objects, features, advantages and embodiments of the present invention more apparent and understandable, the accompanying drawings are described as follows: Figure 1 is a block diagram of a cardless financial transaction system according to an embodiment of the present invention; Figure 2 is a detailed block diagram of the automatic teller machine of Figure 1; Figure 3 is a detailed block diagram of the host server in Figure 1; Figure 4 is a detailed block diagram of the bank server in Figure 1; Figure 5A is a schematic diagram of a registered user's hand being imaged; Figure 5B is a schematic diagram of the gesture feature values of registered users in Figure 5A; and Figure 6 is a schematic sequence diagram of the cardless financial transaction system of this embodiment.

Domestic storage information (please note in order of storage institution, date and number) without Overseas storage information (please note in order of storage country, institution, date, and number) without

10:Cardless financial transaction system

100:ATM

200: Host server

300:Bank server

N: Network architecture

Claims (8)

A cardless financial transaction system includes: at least one automatic teller machine, including a first transmission unit, a first image capture device and a display screen, the display screen is used to display a plurality of gesture prompt screens to an operator, The first image capture device is used to capture a verification image of the operator, the verification image includes a demonstration gesture produced by the operator based on the gesture prompt screens; and a host server includes a second transmission unit, an identity verification unit, a database unit, an image recognition unit and a processing unit, the second transmission unit is electrically connected to the first transmission unit through a network architecture, and the database unit stores a plurality of pens corresponding to different The user's hand feature value, the demonstration gesture matches the specific corresponding data of the user in the database unit, each of the user hand feature values includes a feature matrix containing a plurality of feature vectors, and they are all unique and If not repeated, the image recognition unit is used to recognize the verification image and analyze a gesture feature value including the feature matrix based on one of the hands demonstrating the gesture, wherein the image recognition unit is based on the wrist of the hand demonstrating the gesture. Multiple hand feature points are analyzed at the locations of fixed points, fingertips and knuckles, and one of the feature vectors is obtained by taking the line connecting any two adjacent hand feature points in the coordinates. The processing unit is electrically connected to the second transmission unit, the database unit and the image recognition unit to compare and determine whether the gesture characteristic value matches one of the user hand characteristic values, so that Able to identify whether it is the corresponding user himself, the identity verification unit is electrically connected to the processing unit to instruct the ATM to perform multiple identity verification steps in sequence, And randomly provide the gesture prompt images corresponding to the identity verification steps to the display screen. The cardless financial transaction system as described in claim 1, wherein the gesture prompt screens are scissors gesture, rock gesture, paper gesture and digital gesture prompts respectively. The cardless financial transaction system as described in claim 1 further includes: a bank server, including: a third transmission unit electrically connected to the second transmission unit through the network architecture; a second image capture device , used to capture a registration image of a registered user, the registration image including another demonstration gesture produced by one hand of the registered user; and a registration unit electrically connected to the third transmission unit and the second image capture The device is used to require the image recognition unit of the host server to recognize the registered image, so that the image recognition unit can parse the characteristic value of another user's hand based on one of the hands of the other demonstration gesture, and allow the other user's hand to Some characteristic values are stored in the database unit of the host server. The cardless financial transaction system as described in claim 3, wherein the other user's hand characteristic value is analyzed based on the wrist fixed point of the hand, the fingertips and the knuckles of the other demonstration gesture. The cardless financial transaction system as described in claim 3, wherein the processing unit obtains the gap range between the feature matrix of the gesture feature value of the demonstration gesture and the feature matrix of one of the user's hand feature values, And when it is determined that the difference range meets a preset range, the processing unit determines that the gesture feature value matches one of the user's hand feature values. A host server suitable for a cardless financial transaction system, including: a transmission unit, electrically connected to an automatic teller machine through a network architecture, for receiving a verification image from the automatic teller machine, the verification image including a A demonstration gesture produced by the operator, which corresponds to the specific corresponding data of the user in the database unit; a database unit stores user hand characteristic values of a plurality of pens corresponding to different users, each of which Some user hand feature values include a feature matrix containing a plurality of feature vectors, all of which are unique and non-repeating; an image recognition unit used to recognize the verification image, and based on the wrist position of one hand of the demonstration gesture, The positions of the fingertips and knuckles of the fingers are analyzed to obtain multiple hand feature points, and a line connecting any two adjacent hand feature points is used to obtain one of the feature vectors in the coordinates to obtain a gesture feature. value; a processing unit, electrically connected to the transmission unit, the database unit and the image recognition unit, for comparing and determining whether the gesture feature value matches one of the user hand feature values, so that it can be distinguished whether it is Correspondence The user himself; and an identity verification unit electrically connected to the processing unit for instructing the ATM to perform a plurality of identity verification steps in sequence, and randomly providing a plurality of gesture prompt screens corresponding to the identity verification steps to the ATM. The host server as described in claim 6, wherein the gesture prompt screens are prompts for scissor gestures, rock gestures, paper gestures and digital gestures respectively. The host server as described in claim 6, wherein the processing unit obtains the gap range between the feature matrix of the gesture feature value of the demonstration gesture and the feature matrix of one of the user's hand feature values, and determines When the difference range is found to be within a preset range, the processing unit determines that the gesture feature value matches one of the user's hand feature values.

Images