Face image uploading method, device and equipment

Abstract

The invention provides a face image uploading method, device and equipment, which can be applied to the technical field of image processing. The method comprises the following steps: acquiring a face image of a user; determining eye distance information of the face image; if it is determined that the eye distance information is smaller than or equal to a preset eye distance threshold value, time information of the face image is determined; if it is determined that the time information is smaller than or equal to a preset time threshold value, determining an eye pitch increase multiple of the face image; and uploading the face image to a cloud server according to the eye distance increase multiple. According to the method provided by the invention, a clear face image can be quickly uploaded in a scene that a user quickly moves, so that an effective alarm can be triggered.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular, to a method, device, and equipment for uploading face images. Background Art

[0002] In face recognition in the current video surveillance field, it is necessary to first detect the user's face and collect the face image through a terminal device, and then upload the collected face image to a cloud server for face comparison.

[0003] In the prior art, based on an artificial intelligence image upload algorithm, duplicate processing is performed on the collected images, that is, if it is determined that the faces are the same within a period, they are not uploaded to control the number of uploaded images.

[0004] However, in the above method, for the images of users collected in the scenario of rapid user movement, due to the unclear images collected at a long distance, the cloud server cannot effectively trigger a face alarm, resulting in a waste of bandwidth resources and processing power consumption of the cloud server. Summary of the Invention

[0005] This application provides a method, device, and equipment for uploading face images to solve the problem that the cloud server cannot effectively trigger a face alarm due to unclear images of users collected in the scenario of rapid user movement.

[0006] In a first aspect, this application provides a method for uploading a face image, and the method includes:

[0007] Obtain a face image of a user, where the face image includes at least one pixel point; and determine the eye distance information of the face image, where the eye distance information represents the number of pixel points between the centers of the two eyes of the user in the face image;

[0008] If it is determined that the eye distance information is less than or equal to a preset eye distance threshold, then determine the time information of the face image; where the time information represents the time interval between the current moment and the moment of the most recent uploaded image;

[0009] If it is determined that the time information is less than or equal to a preset time threshold, then determine the eye distance increase multiple of the face image; where the eye distance increase multiple is the ratio of the eye distance information of the face image to the eye distance information of a historical face image, and the historical face image is the face image of the user collected at an adjacent moment before the collection moment of the face image;

[0010] Upload the face image to the cloud server according to the eye distance increase multiple.

[0011] In one example, determining the eye distance increase multiple of the face image includes:

[0012] Determine the first upload count of the user; wherein, the first upload count is the total number of uploads of the user's face images within the current time period;

[0013] If it is determined that the first upload count is greater than a first preset count, then determine the magnification multiple of the eye distance of the face image.

[0014] In one example, the method further includes:

[0015] If it is determined that the first upload count is less than or equal to the first preset count, then upload the face image to the cloud server.

[0016] In one example, the face image has distance information, and the distance information represents the distance between the user and the image acquisition device when the face image is acquired; uploading the face image to the cloud server according to the magnification multiple of the eye distance includes:

[0017] Determine the moving speed of the user within the current time period; and determine the current magnification multiple threshold according to the distance information of the face image and the moving speed;

[0018] If it is determined that the magnification multiple of the eye distance is less than the current magnification multiple threshold, then determine the second upload count of the user; wherein, the second upload count is the total number of uploads of the face images with the same distance information of the user within the current time period;

[0019] If it is determined that the second upload count is less than a second preset count, then upload the face image to the cloud server.

[0020] In one example, the current magnification multiple threshold M = 1+(vt / c); where v is the moving speed of the user within the current time period, c is the distance information of the face image, and t is the preset frequency.

[0021] In one example, the method further includes:

[0022] If it is determined that the magnification multiple of the eye distance is greater than or equal to the current magnification multiple threshold, then upload the face image to the cloud server.

[0023] In one example, the method further includes:

[0024] If it is determined that the second upload count is greater than or equal to the second preset count, then re-acquire a new face image of the user.

[0025] In one example, the method further includes:

[0026] If it is determined that the interpupillary distance information is greater than the preset interpupillary distance threshold, a new face image of the user is acquired again.

[0027] In one example, the method further includes:

[0028] If it is determined that the time information is greater than the preset time threshold, the face image is uploaded to the cloud server.

[0029] In a second aspect, the present application provides an apparatus for uploading a face image, the apparatus includes:

[0030] A first determination unit, configured to acquire a face image of a user, where the face image includes at least one pixel point; and determine the interpupillary distance information of the face image, where the interpupillary distance information represents the number of pixel points between the centers of the two eyes of the user in the face image;

[0031] A second determination unit, configured to determine the time information of the face image if it is determined that the interpupillary distance information is less than or equal to the preset interpupillary distance threshold; where the time information represents the time interval between the current moment and the moment of the most recent uploaded image;

[0032] A third determination unit, configured to determine the interpupillary distance increase multiple of the face image if it is determined that the time information is less than or equal to the preset time threshold; where the interpupillary distance increase multiple is the ratio between the interpupillary distance information of the face image and the interpupillary distance information of a historical face image, and the historical face image is a face image of the user acquired at an adjacent moment before the acquisition moment of the face image;

[0033] An upload unit, configured to upload the face image to the cloud server according to the interpupillary distance increase multiple.

[0034] In a third aspect, the present application provides a terminal device, including: a processor, and a memory communicatively connected to the processor;

[0035] The memory stores computer-executable instructions;

[0036] The processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0038] Fifth aspect, the present application provides a computer program product, which includes: a computer program stored in a readable storage medium, and when the computer program is executed by a processor, it is used to implement the method described in the first aspect.

[0039] The method, device, and equipment for uploading a face image provided by the present application determine the interpupillary distance information in the face image, the time interval since the last image upload, and the magnification factor of the interpupillary distance corresponding to the face image in sequence. If the face image collected in the user's fast movement scenario meets the corresponding preset thresholds, it is determined that the face image meets the upload requirements, and the face image is uploaded; furthermore, in the user's fast movement scenario, a clear face image can be quickly uploaded to ensure that an effective alarm can be triggered. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0041] Figure 1 It is a schematic diagram of an application scenario provided by the present application;

[0042] Figure 2 It is a schematic flowchart of a method for uploading a face image provided by an embodiment of the present application;

[0043] Figure 3 It is a schematic diagram of the interpupillary distance of a face provided by an embodiment of the present application;

[0044] Figure 4 It is a schematic flowchart of another method for uploading a face image provided by an embodiment of the present application;

[0045] Figure 5 It is a schematic diagram of a method for calculating the minimum magnification factor of the interpupillary distance of a face picture provided by an embodiment of the present application;

[0046] Figure 6 It is a schematic structural diagram of an apparatus for uploading a face image provided by an embodiment of the present application;

[0047] Figure 7 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application.

[0048] Through the above accompanying drawings, the clear embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and text descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0050] In face recognition in the current video surveillance field, it is necessary to first detect the user's face through an image acquisition device and collect the face image, and then upload the collected face image to the cloud server for face comparison.

[0051] In one example, based on an artificial intelligence image upload algorithm, duplicate removal processing is performed on the collected images, that is, if it is determined that the faces are the same within a period, the images are not uploaded to control the number of uploaded images.

[0052] However, in the above method, for the images of users collected in the scenario where the user moves quickly, due to the unclear images collected at a long distance, the cloud server cannot effectively trigger a face alarm, which in turn causes waste of the bandwidth resources and processing power consumption of the cloud server.

[0053] The method, device, and equipment for uploading face images provided by the present application aim to solve the above technical problems in the prior art.

[0054] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards, and corresponding operation entrances are provided for the user to choose to authorize or refuse.

[0055] Figure 1 This is a schematic diagram of an application scenario provided by the present application. As Figure 1 shown, this scenario includes a terminal device 101 and a cloud server 102. The terminal device 101 first detects the user's face and collects the user's face image, and then the terminal device 101 will determine whether the collected face image needs to be uploaded. If it is determined that the face image needs to be uploaded, the collected face image will be uploaded to the cloud server 102 for face comparison.

[0056] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0057] Figure 2 It is a schematic flowchart of a method for uploading a face image provided by an embodiment of this application. As Figure 2 shown, this method includes:

[0058] 201. Obtain a user's face image, where the face image includes at least one pixel point; and determine the eye distance information of the face image, where the eye distance information represents the number of pixel points between the centers of the user's two eyes in the face image.

[0059] Exemplarily, the execution subject of this embodiment can be a terminal device. When performing face recognition based on the terminal device, the terminal device collects the video stream data of the user within a preset time period, and performs face detection and matte extraction processing on the video stream to obtain the face image of the user at a certain moment. The obtained face image includes multiple pixel points. Figure 3 It is a schematic diagram of the face eye distance provided by an embodiment of this application. As Figure 3 shown, the terminal device performs recognition processing on the obtained face image based on image processing technology to identify two pixel points corresponding to the centers of the user's two eyes in the face image, and continues to perform image processing to calculate the number of pixel points included between the two pixel points corresponding to the centers of the user's two eyes in the face image, so as to obtain the eye distance information of this face image for further processing.

[0060] 202. If it is determined that the eye distance information is less than or equal to the preset eye distance threshold, then determine the time information of the face image; where the time information represents the time interval between the current moment and the moment of the most recent uploaded image.

[0061] Exemplarily, in order to ensure that the uploaded image can trigger an alarm, the terminal device pre-sets an eye distance threshold A1, that is, the preset eye distance threshold. For the setting of the eye distance threshold A1, the terminal device respectively collects the user's face pictures in a static scene, a moving scene, and at different distances, and after placing them in the specified directory of the terminal, starts offline analysis. Among them, the detection period of the pictures in the moving scene is about 1m / s. The following tests are obtained by taking a large amount of data through multiple tests, as shown in Table 1 below.

[0062] Table 1 Simulation data statistical table

[0063]

[0064] The simulation conclusion obtained through offline analysis shows that the maximum recognition distance of the terminal device is about 6m. At a distance of 6m, the eye distance is about 25 pixels, so A1 can be set to about 22. The terminal device compares the eye distance information of the newly acquired face image with the preset eye distance threshold. If it is determined that the eye distance information is less than or equal to the preset eye distance threshold, the face image can trigger an alarm. Furthermore, the terminal device determines the time information of the face image, that is, the time interval T between the current moment and the moment of the most recent uploaded image, for further processing.

[0065] 203. If it is determined that the time information is less than or equal to the preset time threshold, determine the eye distance increase multiple of the face image; where the eye distance increase multiple is the ratio between the eye distance information of the face image and the eye distance information of the historical face image, and the historical face image is the face image of the user collected at the adjacent moment before the collection moment of the face image.

[0066] Exemplarily, in order to prevent the face of the user from not moving for a long time and not triggering an alarm, the terminal device sets a forced image upload period T1 (default 30s), that is, the preset time threshold. The terminal device compares the determined time information with the preset time threshold. If it is determined that the time information T corresponding to the face image is less than or equal to the preset time threshold T1, the terminal device acquires the face image of the user collected at the adjacent moment before the collection moment of the face image, that is, the previous collection moment, that is, the historical face image, and determines the eye distance information a1 of the historical face image. Furthermore, the ratio between the eye distance information a2 of the face image and the eye distance information a1 of the historical face image can be determined, that is, the eye distance increase multiple (a2 / a1) corresponding to the face image, for further processing.

[0067] 204. Upload the face image to the cloud server according to the eye distance increase multiple.

[0068] Exemplarily, in order to ensure that the face image will be continuously uploaded according to the distance change when the person moves, the terminal device analyzes and processes the eye distance increase multiple corresponding to the face image. For example, it judges whether the eye distance increase multiple corresponding to the face image meets the preset image clarity, and further judges whether the face image meets the upload requirements. If it is determined that the face image meets the upload requirement of image clarity, the terminal device uploads the face image to the cloud server, so that the cloud server can perform face comparison processing based on the face image, to avoid the problem that the face image is not clear in the case of the user's rapid movement and cannot trigger an alarm, and ensure the effective alarm of abnormal face images.

[0069] In this embodiment, a method for uploading a face image is provided. By sequentially determining the interpupillary distance information in the face image, the time interval since the last image upload, and the magnification of the interpupillary distance corresponding to the face image, it is determined whether the face images collected in the scenario of the user's rapid movement all meet the corresponding preset thresholds. If so, it is determined that the face image meets the upload requirements, and the face image is uploaded; furthermore, in the scenario of the user's rapid movement, clear face images can be quickly uploaded to ensure that an effective alarm can be triggered.

[0070] Figure 4 It is a schematic flowchart of another method for uploading a face image provided by an embodiment of the present application. As Figure 4 shown, the method includes:

[0071] 301. Obtain a face image of the user, where the face image includes at least one pixel point; and determine the interpupillary distance information of the face image, where the interpupillary distance information represents the number of pixel points between the centers of the user's two eyes in the face image.

[0072] Exemplarily, this step can refer to step 201 and will not be elaborated here.

[0073] After step 301, step 302 or step 303 can be executed.

[0074] 302. If it is determined that the interpupillary distance information is greater than the preset interpupillary distance threshold, obtain a new face image of the user again.

[0075] Exemplarily, after step 301, the terminal device compares the interpupillary distance information of the newly obtained face image with the preset interpupillary distance threshold. If it is determined that the interpupillary distance information is greater than the preset interpupillary distance threshold, a new face image of the user is obtained from the video data of the user collected, and image processing is performed again.

[0076] 303. If it is determined that the interpupillary distance information is less than or equal to the preset interpupillary distance threshold, determine the time information of the face image; where the time information represents the time interval between the current moment and the moment of the most recent image upload.

[0077] Exemplarily, after step 301, this step can refer to step 202 and will not be elaborated here.

[0078] After step 303, step 304 or step 305 can be executed.

[0079] 304. If it is determined that the time information is greater than the preset time threshold, upload the face image to the cloud server.

[0080] Exemplarily, after step 303, the terminal device compares the determined time information with a preset time threshold. If it is determined that the time information T corresponding to the face image is greater than the preset time threshold T1, the terminal device uploads the newly acquired face image to the cloud server and updates the upload times at the same distance and the total upload times.

[0081] 305. If it is determined that the time information is less than or equal to the preset time threshold, determine the first upload times of the user; wherein, the first upload times is the total upload times of the user's face images within the current time period.

[0082] Exemplarily, after step 303, in order to avoid the alarm not being triggered due to the user's face not moving for a long time, the terminal device sets a forced picture upload period T1 (default 30s), that is, the preset time threshold. The terminal device compares the determined time information T with the forced picture upload period T1. If it is determined that the time information T corresponding to the face image is less than or equal to the forced picture upload period T1, the terminal device obtains the total upload times of the face images of the same user within the current time period, that is, the first upload times n1 of the user, for further processing.

[0083] After step 305, step 306 or step 307 can be executed.

[0084] 306. If it is determined that the first upload times is greater than the first preset times, determine the increase multiple of the eye distance of the face image.

[0085] Exemplarily, after step 305, in order to avoid problems such as probabilistic side faces and bowed heads in the acquired face images, the terminal device sets a lower limit N1 (default 2) for the face upload of the same user, that is, the first preset times. The terminal device compares the determined first upload times n1 of the user with the lower limit N1 for face upload. If it is determined that the first upload times n1 is greater than the lower limit N1 for face upload, the terminal device can process according to the eye distance information a1 of the historical face image and the increase multiple of the eye distance (a2 / a1) corresponding to this face image.

[0086] 307. If it is determined that the first upload times is less than or equal to the first preset times, upload the face image to the cloud server.

[0087] Exemplarily, after step 305, the terminal device compares the determined first upload times n1 of the user with the lower limit N1 for face upload. If it is determined that the first upload times n1 is less than or equal to the lower limit N1 for face upload, it means that the upload times of the user's face images is too small. Then the terminal device directly uploads this face image to the cloud server and updates the first upload times n1 to n1 + 1.

[0088] 308. Determine the moving speed of the user within the current time period; and determine the current increase multiple threshold based on the distance information and the moving speed of the face image.

[0089] In one example, the face image has distance information, and the distance information represents the distance between the user and the image acquisition device when the face image is acquired.

[0090] In one example, the current increase multiple threshold M = 1 + (vt / c); where v is the moving speed of the user within the current time period, c is the distance information of the face image, and t is the preset frequency.

[0091] Exemplarily, to ensure that images are not uploaded when a person is stationary and images are continuously uploaded according to distance changes when moving, the terminal device will detect the moving speed of the user within the current time period, such as the moving speed of the user in a captured video. Based on the fact that each captured face image has distance information to represent the distance between the user and the image acquisition device when the face image is acquired, the terminal device performs calculation processing on the distance information of the obtained face image and the moving speed of the user corresponding to the face image based on a preset algorithm, and can obtain the current increase multiple threshold, that is, the set eye distance increase multiple M. Figure 5 It is a schematic diagram of the method for calculating the minimum increase multiple of the eye distance of the face picture provided by the embodiment of the present application. As Figure 5 shown, according to the preset formula a2 / a1 = b1 / b2 = c1 / c2 = (vt + c2) / c2 = 1 + vt / c2, and then the derived formula is obtained that the current increase multiple threshold M = 1 + (vt / c); where v is the moving speed of the user within the current time period, c is the distance information of the face image, and t is the preset frequency. Assume that the person to be measured is at the center of the picture, the eye distance information a1 and the eye distance information a2 are the eye distance information corresponding to two adjacent detected face images, the horizontal width b1 and the horizontal width b2 are the horizontal widths corresponding to two adjacent detected face images, the walking speed of the person v = 1.2 m / s, the face detection and matting frequency t = 1 picture / s, the advancing direction of the person to be measured is facing the terminal device. For example, the farthest recognition distance of the terminal device is 6 m, then the recognition distance at the first acquisition, that is, the human-machine distance c1, is 6 m, and the recognition distance at the second acquisition, that is, the human-machine distance c2, is 4.8 m. Based on the formula a2 / a1 = 1 + vt / c2 = 1 + (1.2 / 4.8), the calculated current increase multiple threshold M is 125%. In the scenario where a person is stationary, the eye distance changes slowly, and in the scenario where a person is walking, the eye distance changes relatively fast. It is necessary to distinguish the scenario where a person is walking to ensure the timely upload of pictures. This multiple M can be used as the threshold for triggering picture upload in the upload algorithm.

[0092] After step 308, step 309 or step 310 can be executed.

[0093] 309. If it is determined that the magnification of the interpupillary distance is greater than or equal to the current magnification threshold, the face image is uploaded to the cloud server.

[0094] Exemplarily, after step 308, the terminal device compares the magnification of the interpupillary distance (a2 / a1) of the obtained face image with the current magnification threshold M. If it is determined that the magnification of the interpupillary distance (a2 / a1) is greater than or equal to the current magnification threshold M, it indicates that the face image obtained in the scenario of the user's rapid movement meets the clarity requirement of the image for triggering an effective alarm. Then, the obtained face image is directly uploaded to the cloud server, the upload count n2 at the same distance is updated to n2 + 1, and the total upload count n1 is updated to n1 + 1.

[0095] 310. If it is determined that the magnification of the interpupillary distance is less than the current magnification threshold, the second upload count of the user is determined; where the second upload count is the total upload count of the face images of the user with the same distance information within the current time period.

[0096] Exemplarily, after step 308, the terminal device compares the magnification of the interpupillary distance (a2 / a1) of the obtained face image with the current magnification threshold M. If it is determined that the magnification of the interpupillary distance (a2 / a1) is less than the current magnification threshold M, the terminal device obtains the total upload count of the face images collected at the same distance, that is, the face images with the same distance information of the user within the current time period, which is the second upload count n2 of this user.

[0097] After step 310, step 311 or step 312 can be executed.

[0098] 311. If it is determined that the second upload count is less than the second preset count, the face image is uploaded to the cloud server.

[0099] Exemplarily, after step 310, to avoid the influence of the person stopping after walking and the accuracy of the face image, the terminal device sets the upper limit N2 (default 2) for uploading faces at the same distance, that is, the second preset count. The terminal device compares the second upload count n2 of this user with the upper limit N2 for uploading faces at the same distance of this user. If it is determined that the second upload count n2 is less than the upper limit N2 for uploading faces at the same distance, the face image is uploaded to the cloud server, and the second upload count n2 is updated to n2 + 1; thus, it can be realized that in the scenario where the object under test is stationary, the face images are uploaded only a limited number of times.

[0100] 312. If it is determined that the second upload count is greater than or equal to the second preset count, a new face image of the user is obtained again.

[0101] Exemplarily, after step 310, the terminal device compares the second upload count n2 of the user with the upload limit N2 of the same-distance human face of the user. If it is determined that the second upload count n2 is greater than or equal to the upload limit N2 of the same-distance human face, a new face image of the user is obtained from the collected video data of the user, and image processing is performed again.

[0102] In this embodiment, on the basis of the above embodiment, on the one hand, it is possible to achieve only a limited number of uploads in the scenario where the object to be measured is stationary; on the other hand, based on the processing of the eye distance information corresponding to the face image, in the scenario where the user moves quickly, a clear face image can be quickly uploaded to ensure that an effective alarm can be triggered.

[0103] Figure 6 The following is a schematic structural diagram of an apparatus for uploading a face image provided by an embodiment of the present application. As Figure 6 shown, the apparatus includes:

[0104] A first determination unit 401, configured to obtain a face image of a user, where the face image includes at least one pixel point; and determine the eye distance information of the face image, where the eye distance information represents the number of pixel points between the centers of the two eyes of the user in the face image.

[0105] A second determination unit 402, configured to determine the time information of the face image if it is determined that the eye distance information is less than or equal to a preset eye distance threshold; where the time information represents the time interval between the current moment and the moment of the most recent uploaded image.

[0106] A third determination unit 403, configured to determine the eye distance increase multiple of the face image if it is determined that the time information is less than or equal to a preset time threshold; where the eye distance increase multiple is the ratio of the eye distance information of the face image to the eye distance information of a historical face image, and the historical face image is the face image of the user collected at an adjacent moment before the collection moment of the face image.

[0107] An upload unit 404, configured to upload the face image to the cloud server according to the eye distance increase multiple.

[0108] The apparatus in this embodiment can execute the technical solutions in the above method, and the specific implementation process and technical principle are the same, which will not be elaborated here.

[0109] An embodiment of the present application further provides an apparatus for uploading a face image, and the apparatus includes:

[0110] A first determination unit, configured to obtain a face image of a user, where the face image includes at least one pixel point; and determine the eye distance information of the face image, where the eye distance information represents the number of pixel points between the centers of the two eyes of the user in the face image.

[0111] A second determination unit, configured to determine the time information of the face image if it is determined that the interpupillary distance information is less than or equal to a preset interpupillary distance threshold; wherein, the time information represents the time interval between the current moment and the moment when the image was last uploaded.

[0112] A third determination unit, configured to determine the interpupillary distance increase multiple of the face image if it is determined that the time information is less than or equal to a preset time threshold; wherein, the interpupillary distance increase multiple is the ratio between the interpupillary distance information of the face image and the interpupillary distance information of a historical face image, and the historical face image is the face image of the user collected at an adjacent moment before the collection moment of the face image.

[0113] A first upload unit, configured to upload the face image to the cloud server according to the interpupillary distance increase multiple.

[0114] In one example, the third determination unit includes:

[0115] Determine the first upload count of the user; wherein, the first upload count is the total number of uploads of the user's face images within the current time period.

[0116] If it is determined that the first upload count is greater than a first preset count, determine the interpupillary distance increase multiple of the face image.

[0117] In one example, the third determination unit further includes:

[0118] If it is determined that the first upload count is less than or equal to the first preset count, upload the face image to the cloud server.

[0119] In one example, the face image has distance information, and the distance information represents the distance between the user and the image acquisition device when the face image is acquired; the first upload unit includes:

[0120] Determine the moving speed of the user within the current time period; and determine the current increase multiple threshold according to the distance information and the moving speed of the face image.

[0121] If it is determined that the interpupillary distance increase multiple is less than the current increase multiple threshold, determine the second upload count of the user; wherein, the second upload count is the total number of uploads of the face images with the same distance information of the user within the current time period.

[0122] If it is determined that the second upload count is less than a second preset count, upload the face image to the cloud server.

[0123] In one example, the current increase multiple threshold M = 1 + (vt / c); wherein, v is the moving speed of the user within the current time period, c is the distance information of the face image, and t is a preset frequency.

[0124] In one example, the first uploading unit further includes:

[0125] If it is determined that the magnification of the interpupillary distance is greater than or equal to the current magnification threshold, the face image is uploaded to the cloud server.

[0126] In one example, the first uploading unit further includes:

[0127] If it is determined that the second uploading times is greater than or equal to the second preset times, a new face image of the user is retrieved again.

[0128] In one example, the device further includes:

[0129] An obtaining unit, configured to retrieve a new face image of the user again if it is determined that the interpupillary distance information is greater than a preset interpupillary distance threshold.

[0130] In one example, the device further includes:

[0131] A second uploading unit, configured to upload the face image to the cloud server if it is determined that the time information is greater than a preset time threshold.

[0132] The device in this embodiment can execute the technical solutions in the above method, and the specific implementation process and technical principle are the same, which will not be elaborated here.

[0133] Figure 7 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As Figure 7 shown, the terminal device includes: a memory 501, a processor 502; the memory 501; a memory for storing executable instructions of the processor 502.

[0134] Wherein, the processor 502 is configured to execute the method provided in the above embodiment.

[0135] The terminal device further includes a receiver 503 and a transmitter 504. The receiver 503 is used to receive instructions and data sent by other devices, and the transmitter 504 is used to send instructions and data to external devices.

[0136] According to an embodiment of the present application, the present application further provides a non-transitory computer-readable storage medium including instructions, such as a memory including instructions, and the above instructions can be executed by the processor of the terminal device to complete the solution provided in any of the above embodiments. For example, the non-transitory computer-readable storage medium may be a random access memory, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0137] According to an embodiment of the present application, the present application further provides a non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the terminal device, enabling the terminal device to execute the solution provided in any of the above embodiments.

[0138] According to an embodiment of the present application, the present application further provides a computer program product, which includes: a computer program stored in a readable storage medium, and at least one processor of the terminal device can read the computer program from the readable storage medium, and the execution of the computer program by the at least one processor causes the terminal device to execute the solution provided in any of the above embodiments.

[0139] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include common general knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present application are pointed out by the following claims.

[0140] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A method for uploading a face image, characterized in that, The method includes: Obtaining a face image of a user, where the face image includes at least one pixel point; and determining eye distance information of the face image, where the eye distance information represents the number of pixel points between the centers of the two eyes of the user in the face image; If it is determined that the eye distance information is less than or equal to a preset eye distance threshold, then determine the time information of the face image; where the time information represents the time interval between the current moment and the moment of the most recent image upload; If it is determined that the time information is less than or equal to a preset time threshold, then determine the eye distance increase multiple of the face image; where the eye distance increase multiple is the ratio of the eye distance information of the face image to the eye distance information of a historical face image, and the historical face image is a face image of the user collected at an adjacent moment before the collection moment of the face image; Upload the face image to the cloud server according to the eye distance increase multiple.

2. The method according to claim 1, wherein Determining the eye distance increase multiple of the face image includes: Determining the first upload count of the user; where the first upload count is the total number of uploads of the user's face images within the current time period; If it is determined that the first upload count is greater than a first preset count, then determine the eye distance increase multiple of the face image.

3. The method according to claim 2, wherein The method further includes: If it is determined that the first upload count is less than or equal to the first preset count, then upload the face image to the cloud server.

4. The method according to claim 1, wherein The face image has distance information, and the distance information represents the distance between the user and the image acquisition device when the face image is acquired; Uploading the face image to the cloud server according to the eye distance increase multiple includes: Determining the moving speed of the user within the current time period; and determining a current increase multiple threshold according to the distance information of the face image and the moving speed; If it is determined that the eye distance increase multiple is less than the current increase multiple threshold, then determine the second upload count of the user; where the second upload count is the total number of uploads of face images with the same distance information of the user within the current time period; If it is determined that the second upload count is less than a second preset count, then upload the face image to the cloud server.

5. The method according to claim 4, wherein The current increase multiple threshold M = 1+(vt / c); where v is the moving speed of the user within the current time period, c is the distance information of the face image, and t is a preset frequency.

6. The method according to claim 4, characterized in that The method further includes: If it is determined that the eye distance increase multiple is greater than or equal to the current increase multiple threshold, then upload the face image to the cloud server.

7. The method according to claim 4, wherein The method further includes: If it is determined that the second upload count is greater than or equal to the second preset count, then re-obtain a new face image of the user.

8. The method according to claim 1, wherein The method further includes: If it is determined that the eye distance information is greater than the preset eye distance threshold, then re-obtain a new face image of the user.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: If it is determined that the time information is greater than the preset time threshold, then upload the face image to the cloud server.

10. An apparatus for uploading a face image, characterized in that, The device includes: A first determination unit, configured to obtain a face image of a user, where the face image includes at least one pixel point; and determine eye distance information of the face image, where the eye distance information represents the number of pixel points between the centers of the two eyes of the user in the face image. A second determination unit, configured to determine time information of the face image if it is determined that the eye distance information is less than or equal to a preset eye distance threshold; where the time information represents the time interval between the current moment and the moment when the most recent image was uploaded. A third determination unit, configured to determine an eye distance increase multiple of the face image if it is determined that the time information is less than or equal to a preset time threshold; where the eye distance increase multiple is the ratio between the eye distance information of the face image and the eye distance information of a historical face image, and the historical face image is a face image of the user collected at an adjacent moment before the collection moment of the face image. An upload unit, configured to upload the face image to a cloud server according to the eye distance increase multiple.

11. A terminal device, characterized in that, Comprising: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to any one of claims 1 to 9.

Images