A smart watch payment method based on face recognition

Abstract

The present invention discloses a smart watch payment method based on face recognition, including: establishing a binding relationship between a user account and a smart watch, and generating a payment QR code; setting a response time for the payment QR code on the smart watch; a payment terminal scans the payment QR code within the response time, and sends scanning completion information and information about the fee to be paid to the smart watch, the smart watch obtains a user's face image, determines whether the user's identity is legal based on the face image, and automatically deducts the payment fee from the user's account when the user's identity is determined to be legal. The security of smart watch payment is improved.

Description

Technical Field

[0001] The present invention relates to the field of payment technology, and in particular to a smart watch payment method based on face recognition. Background Art

[0002] At present, the existing transaction methods are divided into cash transactions, card swiping and mobile payment code scanning payment methods (WeChat and Alipay, etc.). The existing smart watches are basically not equipped with payment modules. Even if some watches support payment functions, the payment is not safe enough and is prone to fraud. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems in the above-mentioned technology to a certain extent. To this end, the purpose of the present invention is to propose a smart watch payment method based on face recognition to improve the security of smart watch payment.

[0004] To achieve the above object, the embodiment of the present invention proposes a smart watch payment method based on face recognition, comprising:

[0005] Establish a binding relationship between the user account and the smartwatch, and generate a payment QR code;

[0006] Set the response time for payment QR codes on smartwatches;

[0007] The payment terminal scans the payment QR code within the response time and sends the scanning completion information and the information of the fee to be paid to the smart watch. The smart watch obtains the user's facial image and determines whether the user's identity is legal based on the facial image. When the user's identity is determined to be legal, the payment fee is automatically deducted from the user's account.

[0008] According to some embodiments of the present invention, establishing a binding relationship between a user account and a smart watch includes: inputting a bank card on the smart watch for binding.

[0009] According to some embodiments of the present invention, establishing a binding relationship between a user account and a smart watch includes:

[0010] Obtain the device information of the smart watch and send it to the third-party payment platform;

[0011] After the third-party payment platform confirms that the device information is legitimate, a binding relationship between the smart watch and the third-party payment platform is established, wherein the third-party payment platform is bound to the user's payment account.

[0012] According to some embodiments of the present invention, the further comprising:

[0013] The payment QR code is invalid if the payment terminal fails to scan the QR code within the response time.

[0014] When the payment terminal scans the payment QR code again, the smart watch receives the user's activation instruction and activates the payment QR code.

[0015] According to some embodiments of the present invention, the smart watch receives an activation instruction from a user and activates the payment QR code, including:

[0016] Obtain the acceleration information of the smart watch and determine whether it is greater than the preset acceleration;

[0017] When it is determined that the acceleration information is greater than a preset acceleration, obtaining a gesture action image of the user wearing the smart watch;

[0018] The gesture action image is identified, the gesture action is obtained and it is determined whether it is consistent with the preset gesture action. When it is determined to be consistent, an activation instruction is generated to activate the payment QR code.

[0019] According to some embodiments of the present invention, before determining whether the user identity is legal based on the face image, the method further includes:

[0020] Performing image segmentation on the face image to obtain a plurality of face region images, and performing image analysis on the face region images respectively to obtain image analysis results;

[0021] It is determined whether there is an abnormality in the area corresponding to the facial area image according to the image analysis result, and when it is determined that there is an abnormality, the area with the abnormality is recorded.

[0022] According to some embodiments of the present invention, performing image analysis on the facial region image to obtain an image analysis result includes:

[0023] Performing image preprocessing on the facial region image;

[0024] Obtain the image size of the face area image after image preprocessing;

[0025] Determining the size of the recognition sliding window according to the image size and a preset standard image size;

[0026] The recognition sliding window moves at different positions of the face region image according to a preset rule, and the face region image is divided into a plurality of sub-face region images based on the recognition sliding window;

[0027] Performing Gaussian filtering on the plurality of sub-facial region images to obtain scale spaces corresponding to the sub-facial region images;

[0028] Extracting characteristic pixel points on the sub-facial region image along the scale axis of the scale space, and performing cluster analysis on the characteristic pixel points to generate a plurality of characteristic pixel point sets;

[0029] Obtaining weight information of each feature pixel point, performing image analysis on the sub-facial region image according to the weight information, and obtaining an analysis result of the sub-facial region image;

[0030] An image analysis result is generated according to the movement order of the recognition sliding window and the analysis results corresponding to the plurality of sub-face region images.

[0031] According to some embodiments of the present invention, when it is determined that the user identity is illegal based on the face image, it is queried whether there is an abnormal area, and it is determined whether the abnormal area is an eye;

[0032] When it is determined that there is an abnormal area and the abnormal area is not the eye, the user's iris image is obtained, and the matching degree between the iris image and the preset iris image is calculated. When it is determined that the matching degree is greater than the preset matching degree, the user's identity is corrected to indicate that the user's identity is legal.

[0033] According to some embodiments of the present invention, determining whether the user identity is legal based on the face image includes:

[0034] Extracting features from the facial image to obtain facial feature data;

[0035] The facial feature data is compared with preset facial feature data in a pre-stored facial database to calculate the similarity, and when it is determined that the similarity is greater than the preset similarity, the user identity is determined to be legitimate.

[0036] In one embodiment, before calculating the matching degree between the iris image and the preset iris image, the method further includes: evaluating the quality of the iris image multiple times to obtain an evaluation mean, and determining whether the evaluation mean is greater than a preset evaluation value, and when it is determined that the evaluation mean is less than the preset evaluation value, performing image quality enhancement processing on the iris image;

[0037] The calculation of the evaluation mean value comprises:

[0038] Calculate the pth evaluation value W of the iris image p :

[0039]

[0040] Wherein, b is the major axis of the pupil ellipse obtained by fitting when evaluating the iris image for the pth time; a is the major axis of the pupil ellipse obtained by fitting when evaluating the iris image for the pth time; k1 is the first weight of the pupil ellipse parameter; S is the area of ​​the iris ring texture region; R is the outer circle radius of the iris in the iris image; r is the inner circle radius of the iris in the iris image; k2 is the second weight of the iris effective area quality evaluation index; M is the number of pixels in the iris image when evaluating the iris image for the pth time; t i is the pixel value of the i-th pixel in the iris image; N is the number of pixels in the preset iris image; t j is the pixel value of the jth pixel in the preset iris image; k3 is the third weight of the quality evaluation index of the pixel mean in the iris image; k1+k2+k3=1;

[0041] Calculate the mean of the evaluation

[0042]

[0043] Wherein, G is the number of times the iris image is evaluated.

[0044] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0045] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0047] Figure 1 The present invention is a flowchart of a smart watch payment method based on face recognition according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0049] like Figure 1 As shown, the embodiment of the present invention proposes a smart watch payment method based on face recognition, including S1-S3:

[0050] S1. Establish a binding relationship between the user account and the smart watch, and generate a payment QR code;

[0051] S2. Set the response time of the payment QR code on the smartwatch;

[0052] S3. The payment terminal scans the payment QR code within the response time, and sends the scanning completion information and the information of the fee to be paid to the smart watch. The smart watch obtains the user's facial image, determines whether the user's identity is legal based on the facial image, and automatically deducts the payment fee from the user's account when it is determined that the user's identity is legal.

[0053] The working principle of the above technical solution is: establish a binding relationship between the user account and the smart watch, and generate a payment QR code; set the response time of the payment QR code on the smart watch; the payment terminal scans the payment QR code within the response time, and sends the scanning completion information and the information of the fees to be paid to the smart watch. The smart watch obtains the user's facial image, determines whether the user's identity is legal based on the facial image, and automatically deducts the payment fee from the user's account when it is determined that the user's identity is legal.

[0054] The beneficial effects of the above technical solution are: contactless payment is realized based on smart watches, which reduces contact with banknotes and avoids unnecessary hygiene problems. At the same time, based on the binding of smart watches with user accounts, payment is safe, fast and convenient; smart watch payment requires facial recognition verification, which avoids the risk of fraud and saves time for both buyers and sellers.

[0055] According to some embodiments of the present invention, establishing a binding relationship between a user account and a smart watch includes: inputting a bank card on the smart watch for binding.

[0056] According to some embodiments of the present invention, establishing a binding relationship between a user account and a smart watch includes:

[0057] Obtain the device information of the smart watch and send it to the third-party payment platform;

[0058] After the third-party payment platform confirms that the device information is legitimate, a binding relationship between the smart watch and the third-party payment platform is established, wherein the third-party payment platform is bound to the user's payment account.

[0059] The working principle of the above technical solution is: binding a bank card through a smart watch; or binding the device information of the smart watch with a third-party payment platform (Alipay, WeChat).

[0060] The beneficial effects of the above technical solution are: it is conducive to realizing contactless payment through smart watches.

[0061] According to some embodiments of the present invention, the further comprising:

[0062] The payment QR code is invalid if the payment terminal fails to scan the QR code within the response time.

[0063] When the payment terminal scans the payment QR code again, the smart watch receives the user's activation instruction and activates the payment QR code.

[0064] The working principle of the above technical solution is: if the payment terminal fails to scan the payment QR code within the response time, the payment QR code is invalid; when the payment terminal scans the payment QR code again, the smart watch receives the user's activation instruction and activates the payment QR code.

[0065] The beneficial effects of the above technical solution are as follows: if the payment QR code is not scanned within the response time, the payment QR code is in an invalid state, thereby avoiding leakage of the payment QR code, effectively preventing fraudulent payment, and improving payment security. When payment is required, the payment QR code is activated, which is more convenient and quick.

[0066] According to some embodiments of the present invention, the smart watch receives an activation instruction from a user and activates the payment QR code, including:

[0067] Obtain the acceleration information of the smart watch and determine whether it is greater than the preset acceleration;

[0068] When it is determined that the acceleration information is greater than a preset acceleration, obtaining a gesture action image of the user wearing the smart watch;

[0069] The gesture action image is identified, the gesture action is obtained and it is determined whether it is consistent with the preset gesture action. When it is determined to be consistent, an activation instruction is generated to activate the payment QR code.

[0070] The working principle of the above technical solution is: obtain the acceleration information of the smart watch and determine whether it is greater than the preset acceleration; when it is determined that the acceleration information is greater than the preset acceleration, obtain the gesture action image of the user wearing the smart watch; identify the gesture action image, obtain the gesture action and determine whether it is consistent with the preset gesture action, and when it is determined to be consistent, generate an activation instruction to activate the payment QR code. The preset gesture action includes the wrist shaking action, etc.

[0071] The beneficial effects of the above technical solution are as follows: when it is determined that the acceleration of the smart watch is greater than the preset acceleration, it means that the smart watch needs to perform a payment operation. At this time, the user's gesture action is judged to ultimately determine whether the payment QR code is in an activated state, thereby improving the accuracy of judging the payment process and facilitating accurate changes in the payment QR code status.

[0072] According to some embodiments of the present invention, before determining whether the user identity is legal based on the face image, the method further includes:

[0073] Performing image segmentation on the face image to obtain a plurality of face region images, and performing image analysis on the face region images respectively to obtain image analysis results;

[0074] It is determined whether there is an abnormality in the area corresponding to the facial area image according to the image analysis result, and when it is determined that there is an abnormality, the area with the abnormality is recorded.

[0075] The working principle and beneficial effects of the above technical solution: A human face includes different areas, such as eyes, forehead, mouth, etc. The face image is segmented to obtain a plurality of face area images, each of which represents an area of ​​the face, and image analysis is performed to obtain image analysis results; according to the image analysis results, it is determined whether there is an abnormality in the area corresponding to the face area image, and when it is determined that there is an abnormality, the area with the abnormality is recorded. In one embodiment, if it is determined that there is a scratch on the user's forehead, the forehead is recorded as an abnormal area, so that when performing face recognition later, the abnormality of the area is taken into account, the accuracy of face recognition is improved, and the accuracy of determining whether the user's identity is legal is improved.

[0076] According to some embodiments of the present invention, performing image analysis on the facial region image to obtain an image analysis result includes:

[0077] Performing image preprocessing on the facial region image;

[0078] Obtain the image size of the face area image after image preprocessing;

[0079] Determining the size of the recognition sliding window according to the image size and a preset standard image size;

[0080] The recognition sliding window moves at different positions of the face region image according to a preset rule, and the face region image is divided into a plurality of sub-face region images based on the recognition sliding window;

[0081] Performing Gaussian filtering on the plurality of sub-facial region images to obtain scale spaces corresponding to the sub-facial region images;

[0082] Extracting characteristic pixel points on the sub-facial region image along the scale axis of the scale space, and performing cluster analysis on the characteristic pixel points to generate a plurality of characteristic pixel point sets;

[0083] Obtaining weight information of each feature pixel point, performing image analysis on the sub-facial region image according to the weight information, and obtaining an analysis result of the sub-facial region image;

[0084] An image analysis result is generated according to the movement order of the recognition sliding window and the analysis results corresponding to the plurality of sub-face region images.

[0085] The working principle of the above technical solution is as follows: the face region image is subjected to image preprocessing, and the image preprocessing includes image denoising, etc. The image size of the face region image after image preprocessing is obtained; the size of the recognition sliding window is determined according to the image size and the preset standard image size; the recognition sliding window is moved at different positions of the face region image according to preset rules, and the face region image is divided into several sub-face region images based on the recognition sliding window; the several sub-face region images are subjected to Gaussian filtering to obtain the scale space corresponding to the sub-face region images; along the scale axis of the scale space, the feature pixels on the sub-face region image are extracted, and the feature pixels are clustered to generate multiple feature pixel sets; the weight information of each feature pixel is obtained, and the sub-face region image is analyzed according to the weight information to obtain the analysis result of the sub-face region image; the image analysis result is generated according to the movement order of the recognition sliding window and the analysis results corresponding to the several sub-face region images. Scale space is a multi-resolution analysis in computer vision or image. Feature pixels are pixels that characterize the features of the sub-face region image on the scale axis. Cluster analysis is performed based on the pixel values ​​of feature pixels.

[0086] The beneficial effects of the above technical solution are as follows: accurately obtaining the analysis results of the sub-facial area image, and accurately obtaining the image analysis results according to the movement order of the recognition sliding window and the analysis results corresponding to several sub-facial area images, thereby ensuring the accuracy of the image analysis results, and then accurately detecting whether there is any abnormality in the user's facial area.

[0087] According to some embodiments of the present invention, when it is determined that the user identity is illegal based on the face image, it is queried whether there is an abnormal area, and it is determined whether the abnormal area is an eye;

[0088] When it is determined that there is an abnormal area and the abnormal area is not the eye, the user's iris image is obtained, and the matching degree between the iris image and the preset iris image is calculated. When it is determined that the matching degree is greater than the preset matching degree, the user's identity is corrected to indicate that the user's identity is legal.

[0089] The working principle of the above technical solution is as follows: when it is determined that the user identity is illegal based on the facial image, it is queried whether there is an abnormal area, and it is determined whether the abnormal area is the eye; when it is determined that there is an abnormal area and the abnormal area is not the eye, the user's iris image is obtained, and the matching degree between the iris image and the preset iris image is calculated. When it is determined that the matching degree is greater than the preset matching degree, the user's identity is corrected, indicating that the user's identity is legal.

[0090] The beneficial effects of the above technical solution are: avoiding the inaccuracy of face recognition due to abnormalities in some areas of the face, which may lead to the situation where the user's identity is determined to be illegal, and reconfirming the user's identity based on the iris image to improve the accuracy of judging whether the user's identity is legal.

[0091] According to some embodiments of the present invention, determining whether the user identity is legal based on the face image includes:

[0092] Extracting features from the facial image to obtain facial feature data;

[0093] The facial feature data is compared with preset facial feature data in a pre-stored facial database to calculate the similarity, and when it is determined that the similarity is greater than the preset similarity, the user identity is determined to be legitimate.

[0094] The working principle of the above technical solution is: extract features from the facial image to obtain facial feature data; compare the facial feature data with preset facial feature data in a pre-stored facial database to calculate the similarity, and when it is determined that the similarity is greater than the preset similarity, the user identity is determined to be legal.

[0095] The beneficial effects of the above technical solution are: based on face recognition, the security of payment is improved.

[0096] In one embodiment, before calculating the matching degree between the iris image and the preset iris image, the method further includes: evaluating the quality of the iris image multiple times to obtain an evaluation mean, and determining whether the evaluation mean is greater than a preset evaluation value, and when it is determined that the evaluation mean is less than the preset evaluation value, performing image quality enhancement processing on the iris image;

[0097] The calculating and evaluating mean value comprises:

[0098] Calculate the pth evaluation value W of the iris image p :

[0099]

[0100] Wherein, b is the major axis of the pupil ellipse obtained by fitting when evaluating the iris image for the pth time; a is the major axis of the pupil ellipse obtained by fitting when evaluating the iris image for the pth time; k1 is the first weight of the pupil ellipse parameter; S is the area of ​​the iris ring texture region; R is the outer circle radius of the iris in the iris image; r is the inner circle radius of the iris in the iris image; k2 is the second weight of the iris effective area quality evaluation index; M is the number of pixels in the iris image when evaluating the iris image for the pth time; t i is the pixel value of the i-th pixel in the iris image; N is the number of pixels in the preset iris image; t j is the pixel value of the jth pixel in the preset iris image; k3 is the third weight of the quality evaluation index of the pixel mean in the iris image; k1+k2+k3=1;

[0101] Calculate the mean of the evaluation

[0102]

[0103] Wherein, G is the number of times the iris image is evaluated.

[0104] The working principle and beneficial effects of the above technical solution are as follows: the iris image quality is evaluated multiple times to obtain an evaluation mean, and it is determined whether it is greater than a preset evaluation value. When it is determined that the evaluation mean is less than the preset evaluation value, the iris image is subjected to image quality enhancement processing, which is beneficial to ensuring the image quality of the acquired iris image and improving the accuracy of recognition. It is also beneficial to improve the accuracy of the next step of calculating the matching degree between the iris image and the preset iris image. Calculate the pupil edge during iris recognition, fit it to obtain the pupil ellipse parameters, and perform squint detection. The effective area of ​​the iris is the effective area of ​​the iris that is not blocked. The size of this parameter determines the accuracy of iris recognition. The larger the parameter, the higher the recognition accuracy and the greater the evaluation value when other parameters remain unchanged. At the same time, the pupil diffusion and contraction caused by external light changes are taken into account to determine the distortion of the iris area. Calculating the pixel difference between the iris image and the preset iris image when evaluating it is helpful to make the calculated evaluation value more accurate. Taking the evaluation mean based on multiple evaluations is helpful to reduce measurement or recognition errors and more objectively compare the evaluation mean with the preset mean.

[0105] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0106] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0107] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0109] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A smart watch payment method based on face recognition, characterized in that: include: Establish a binding relationship between the user account and the smartwatch, and generate a payment QR code; Set the response time for payment QR codes on smartwatches; The payment terminal scans the payment QR code within the response time, and sends the scanning completion information and the information of the fee to be paid to the smart watch. The smart watch obtains the face image of the user, determines whether the user's identity is legal according to the face image, and automatically deducts the payment fee from the user's account when the user's identity is determined to be legal. Before determining whether the user identity is legal based on the face image, the method further includes: Performing image segmentation on the face image to obtain a plurality of face region images, and performing image analysis on the face region images respectively to obtain image analysis results; Determining whether there is an abnormality in the area corresponding to the facial area image according to the image analysis result, and recording the area with the abnormality when it is determined that there is an abnormality; When it is determined that the user identity is illegal based on the face image, query whether there is an abnormal area, and determine whether the abnormal area is an eye; When it is determined that there is an abnormal area and the abnormal area is not the eye, an iris image of the user is obtained, and a matching degree between the iris image and a preset iris image is calculated, and when it is determined that the matching degree is greater than a preset matching degree, the identity of the user is corrected to indicate that the identity of the user is legal; Before calculating the matching degree between the iris image and the preset iris image, the method further includes: evaluating the quality of the iris image multiple times to obtain an evaluation mean, and determining whether the evaluation mean is greater than a preset evaluation value, and when it is determined that the evaluation mean is less than the preset evaluation value, performing image quality enhancement processing on the iris image; Calculate the evaluation mean, including: Calculate the pth evaluation value W of the iris image p : Wherein, b is the major axis of the pupil ellipse obtained by fitting when evaluating the iris image for the pth time; a is the minor axis of the pupil ellipse obtained by fitting when evaluating the iris image for the pth time; k1 is the first weight of the pupil ellipse parameter; S is the area of ​​the iris annular texture region; R is the outer circle radius of the iris in the iris image; r is the inner circle radius of the iris in the iris image; k2 is the second weight of the iris effective area quality evaluation index; M is the number of pixels in the iris image when evaluating the iris image for the pth time; t i is the pixel value of the i-th pixel in the iris image; N is the number of pixels in the preset iris image; t j is the pixel value of the jth pixel in the preset iris image; k3 is the third weight of the quality evaluation index of the pixel mean in the iris image; k1+k2+k3=1; Calculate the mean of the evaluation Wherein, G is the number of times the iris image is evaluated.

2. The smart watch payment method based on face recognition as claimed in claim 1, characterized in that: The establishing of the binding relationship between the user account and the smart watch includes: inputting a bank card on the smart watch for binding.

3. The smart watch payment method based on face recognition as claimed in claim 1, characterized in that: The establishing of a binding relationship between the user account and the smart watch includes: Obtain the device information of the smart watch and send it to the third-party payment platform; After the third-party payment platform confirms that the device information is legitimate, a binding relationship between the smart watch and the third-party payment platform is established, wherein the third-party payment platform is bound to the user's payment account.

4. The smart watch payment method based on face recognition as claimed in claim 1, characterized in that: Also includes: The payment QR code is invalid if the payment terminal fails to scan the QR code within the response time. When the payment terminal scans the payment QR code again, the smart watch receives the user's activation instruction and activates the payment QR code.

5. The smart watch payment method based on face recognition as claimed in claim 4, characterized in that: The smart watch receives an activation instruction from a user and activates the payment QR code, including: Obtain the acceleration information of the smart watch and determine whether it is greater than the preset acceleration; When it is determined that the acceleration information is greater than a preset acceleration, obtaining a gesture action image of the user wearing the smart watch; The gesture action image is identified, the gesture action is obtained and it is determined whether it is consistent with the preset gesture action. When it is determined to be consistent, an activation instruction is generated to activate the payment QR code.

6. The smart watch payment method based on face recognition as claimed in claim 1, characterized in that: The performing image analysis on the facial region image to obtain an image analysis result includes: Performing image preprocessing on the facial region image; Obtain the image size of the face area image after image preprocessing; Determining the size of the recognition sliding window according to the image size and a preset standard image size; The recognition sliding window moves at different positions of the face region image according to a preset rule, and the face region image is divided into a plurality of sub-face region images based on the recognition sliding window; Performing Gaussian filtering on the plurality of sub-facial region images to obtain scale spaces corresponding to the sub-facial region images; Extracting characteristic pixel points on the sub-facial region image along the scale axis of the scale space, and performing cluster analysis on the characteristic pixel points to generate a plurality of characteristic pixel point sets; Obtaining weight information of each feature pixel point, performing image analysis on the sub-facial region image according to the weight information, and obtaining an analysis result of the sub-facial region image; An image analysis result is generated according to the movement order of the recognition sliding window and the analysis results corresponding to the plurality of sub-face region images.

7. The smart watch payment method based on face recognition as claimed in claim 1, characterized in that: Determining whether the user's identity is legal based on the facial image includes: Extracting features from the facial image to obtain facial feature data; The facial feature data is compared with the preset facial feature in the pre-stored face database. The data is compared and the similarity is calculated. When it is determined that the similarity is greater than the preset similarity, Make sure the user is legitimate.

Images