Expression processing method, intelligent AI glasses and storage medium

Abstract

The invention discloses an expression processing method, intelligent AI glasses and a storage medium, and is applied to the intelligent AI glasses, and the intelligent AI glasses comprise a sensor and a communication module. The method comprises: capturing a facial expression image of a target object through the sensor, the target object being a user wearing the intelligent AI glasses, or the target object being a shooting object shot by the intelligent AI glasses; performing image extraction on the facial expression image to obtain a target feature set; generating a target expression image in a preset format according to the target feature set; and sending the target expression image to a specified device through the communication module. By adopting the embodiment of the invention, the intelligence of the intelligent AI glasses can be improved.

Description

Technical Field

[0001] The present application relates to the field of wearable device technology, or the field of artificial intelligence technology, and specifically to an expression processing method, smart AI glasses, and a storage medium. Background Art

[0002] Smart AI glasses are called AI glasses, smart mirrors, smart glasses or AI smart glasses. With the rapid development of science and technology, smart AI glasses are becoming more and more popular. At present, the functions of smart AI glasses are relatively single. Therefore, how to improve the intelligence of smart AI glasses needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present application provide an expression processing method, smart AI glasses, and a storage medium, which can improve the intelligence of the smart AI glasses.

[0004] In a first aspect, an embodiment of the present application provides an expression processing method, which is applied to smart AI glasses, wherein the smart AI glasses include a sensor and a communication module; the method includes:

[0005] Capturing a facial expression image of a target object through the sensor, wherein the target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses;

[0006] Performing image extraction on the facial expression image to obtain a target feature set;

[0007] Generating a target expression image in a preset format according to the target feature set;

[0008] The target expression image is sent to a designated device through the communication module.

[0009] In a second aspect, an embodiment of the present application provides an expression processing device, wherein the smart AI glasses include a sensor and a communication module; the smart AI glasses include: an acquisition unit, an extraction unit, a generation unit, and an interaction unit, wherein:

[0010] The acquisition unit is used to capture a facial expression image of a target object through the sensor, where the target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses;

[0011] The extraction unit is used to perform image extraction on the facial expression image to obtain a target feature set;

[0012] The generating unit is used to generate a target expression image in a preset format according to the target feature set;

[0013] The interaction unit is used to send the target expression image to a designated device through the communication module.

[0014] In a third aspect, an embodiment of the present application provides a smart AI glasses, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0017] The implementation of the embodiments of the present application has the following beneficial effects:

[0018] It can be seen that the expression processing method, smart AI glasses and storage medium described in the embodiments of the present application are applied to smart AI glasses. The smart AI glasses include a sensor and a communication module. The facial expression image of the target object is captured by the sensor. The target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses. The facial expression image is extracted to obtain a target feature set, and a target expression image in a preset format is generated according to the target feature set. The target expression image is sent to a designated device through the communication module. In this way, the user's facial expression image can be collected, and a corresponding target expression image in a preset format can be generated and shared with other users (friends). Therefore, the intelligence and fun of the smart AI glasses can be improved, and the user experience can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1It is a flowchart of an expression processing method provided in an embodiment of the present application;

[0021] Figure 2 It is a structural schematic diagram of a smart AI glasses provided in an embodiment of the present application;

[0022] Figure 3 is a structural schematic diagram of another type of smart AI glasses provided in an embodiment of the present application;

[0023] Figure 4 This is a block diagram of the functional units of the smart AI glasses provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] In an embodiment of the present application, the designated devices may include: smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), PDAs, tablet computers, Bluetooth speakers, smart TVs, smart refrigerators, smart robots, driving recorders, laptops, mobile Internet devices (Mobile Internet Devices, MID) or wearable devices (such as smart AI glasses, smart bracelets, smart watches, Bluetooth headsets), etc. The above are only examples and not exhaustive, including but not limited to the above-mentioned designated devices. The designated devices may also include servers, for example, cloud servers.

[0028] The embodiments of the present application are described in detail below.

[0029] See also Figure 1 , Figure 1 : is a flow chart of an expression processing method provided in an embodiment of the present application, which is applied to smart AI glasses, wherein the smart AI glasses include a sensor and a communication module; as shown in the figure, the expression processing method includes:

[0030] 101. Capturing a facial expression image of a target object through the sensor, where the target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses.

[0031] Among them, the target object can be a user who admires the smart AI glasses, or the target object can be a subject photographed by the smart AI glasses.

[0032] Among them, Figure 2 As shown, the smart AI glasses include a sensor and a communication module. The sensor is used to capture facial expressions to obtain facial expression images. The communication module can be used to implement communication functions. The communication module can include at least one of the following: a mobile communication module (2G, 3G, 4G, 5G, etc.), wireless fidelity (wireless fidelity, Wi-Fi), a Bluetooth communication module, an infrared communication module, a millimeter wave communication module, a radar communication module, etc., which are not limited here.

[0033] In an embodiment of the present application, the sensor may include one or more sensors, and the sensor may include at least one of the following: a camera, a temperature sensor, a humidity sensor, a material detection sensor, an electromyography sensor, etc., which are not limited here.

[0034] Among them, the material detection sensor can be used to detect the facial skin parameters of the target object, and the electromyography sensor can be used to detect the facial muscle movement parameters of the target object.

[0035] In a specific implementation, when the target object is a user who admires smart AI glasses, the facial expression image of the target object can be captured by a sensor. For example, the face of the target object can be photographed to obtain a facial expression image. Alternatively, when the target object is a subject being photographed by smart AI glasses, the facial expression image of the target object can be captured by a sensor. For example, the face of the subject can be photographed to obtain a facial expression image.

[0036] 102. Perform image extraction on the facial expression image to obtain a target feature set.

[0037] In a specific implementation, the target feature set may include at least one feature, and the feature may include at least one of the following features: feature points, feature patterns, feature regions, feature values, feature vectors, etc., which are not limited here.

[0038] Specifically, image extraction can be performed on facial expression images to obtain a target feature set, which can be used to implement expression recognition.

[0039] 103. Generate a target expression image in a preset format according to the target feature set.

[0040] Among them, the preset format can be pre-set or system default, for example, the preset format can be any emoticon package format, the emoticon package format can be a static emoticon package format or a dynamic emoticon package format, for example, the emoticon package format can include an emoji emoticon package format.

[0041] In a specific implementation, an emoji generator can be used to generate a target emoji image in a preset format according to a target feature set. For example, the emoji generator can be preset or system default. For example, the emoji generator can include a machine learning model, a neural network model, a large model, etc., which are not limited here.

[0042] 104. Send the target expression image to a designated device through the communication module.

[0043] Among them, the designated device can be pre-set or system default, and the designated device can be a part of the smart AI glasses, or it can also be a device that communicates with other than the smart AI glasses.

[0044] The designated device may include one or more devices.

[0045] In a specific implementation, the target expression image can be sent to a designated device through a communication module. In this way, an expression image corresponding to the user can be generated through smart AI glasses, and the target expression image can be obtained and then sent to a designated device. In this way, the intelligence and fun of the smart AI glasses can be improved.

[0046] Optionally, the above step 102, performing image extraction on the facial expression image to obtain a target feature set, may include the following steps:

[0047] Performing feature extraction on the facial expression image to obtain a first feature set;

[0048] Determining a target expression type corresponding to the first feature set;

[0049] Determine features corresponding to the target expression type according to the first feature set to obtain the target feature set.

[0050] In a specific implementation, features may be extracted from the facial expression image to obtain a first feature set, and the first feature set may be input into a classification network to obtain a corresponding expression type, which may include at least one of the following: smile, laugh, wry smile, frustration, embarrassment, staring, etc., which are not limited here. The classification network may also be preset or defaulted by the system, for example, the classification network may include at least one of the following: a convolutional neural network, a large model, etc., which are not limited here.

[0051] In a specific implementation, the target expression type corresponding to the first feature set can be determined based on the classification network. Different expression types require different features when generating the target expression image. Furthermore, the features corresponding to the target expression type can be determined based on the first feature set to obtain the target feature set. In this way, the preset format and the corresponding features of the target expression type can be used to help improve the intelligence and fun of smart AI glasses.

[0052] Optionally, the above step of determining the features corresponding to the target expression type according to the first feature set to obtain the target feature set may include the following steps:

[0053] Acquire a feature selection rule set corresponding to the preset format to obtain multiple feature selection rule sets, each feature selection rule set corresponding to an expression type;

[0054] Determine a target feature selection rule set corresponding to the target expression type from the multiple feature selection rule sets;

[0055] The first feature set is screened according to the target feature selection rule set to obtain the target feature set.

[0056] In a specific implementation, a feature selection rule set corresponding to a preset format can be obtained to obtain multiple feature selection rule sets, each of which corresponds to an expression type. The feature selection rule set may include at least one feature selection rule, and the feature selection rule may include at least one of the following: which type of feature is selected (for example, feature points, feature values, feature vectors, feature textures, etc.), which position or region of feature is selected, which degree of feature is selected, etc., which are not limited here.

[0057] Next, a target feature selection rule set corresponding to the target expression type can be determined from multiple feature selection rule sets, and then the first feature set can be screened according to the target feature selection rule set to obtain a target feature set. In this way, the preset format and features corresponding to the target expression type can be used to help improve the intelligence and fun of smart AI glasses.

[0058] Optionally, the above step 103, generating a target expression image in a preset format according to the target feature set, may include the following steps:

[0059] Acquire a reference expression template set corresponding to the preset format, wherein the reference expression template set includes a plurality of reference expression templates, and each reference expression template corresponds to an expression type;

[0060] Determining a target reference expression template corresponding to the target expression type from the reference expression template set;

[0061] The target expression image is determined according to the target feature set and the target reference expression template.

[0062] In a specific implementation, a reference expression template set corresponding to a preset format can be obtained. The reference expression template set can include multiple reference expression templates, and each reference expression template corresponds to an expression type. Then, a target reference expression template corresponding to the target expression type can be determined from the reference expression template set, and then a target expression image can be determined based on the target feature set and the target reference expression template. In this way, a target reference expression template corresponding to the target expression type can be selected, and then a corresponding expression image can be synthesized based on the target reference expression template and the preset format and corresponding features of the target expression type, thereby helping to improve the intelligence and fun of smart AI glasses.

[0063] Optionally, the above step of determining the target expression image according to the target feature set and the target reference expression template may include the following steps:

[0064] Acquire a feature position region corresponding to each feature in the target feature set to obtain at least one feature position region;

[0065] Marking a corresponding region in the target reference expression template according to the at least one characteristic position region to obtain at least one region;

[0066] The target feature set is filled into a corresponding area of ​​the at least one area in the target reference expression template to obtain the target expression image.

[0067] In a specific implementation, the feature position area corresponding to each feature in the target feature set can be obtained to obtain at least one feature position area, and the corresponding area in the target reference expression template can be marked according to at least one feature position area to obtain at least one area. Finally, the target feature set is filled into the corresponding area of ​​at least one area in the target reference expression template to obtain a target expression image, that is, the target feature set can be fused to the corresponding position in the target reference expression template, so that the target expression image incorporates some features of the target object, and the target expression image is deeply related to the facial features of the target object, thereby helping to improve the intelligence and fun of smart AI glasses.

[0068] Optionally, the above step 102, extracting features from the facial expression image to obtain a first feature set, may include the following steps:

[0069] Acquire target shooting parameters of the target expression image;

[0070] Obtaining target skin color parameters of the target expression image;

[0071] Determining a target feature extraction algorithm corresponding to the target skin color parameter;

[0072] Determining target algorithm control parameters of the target feature extraction algorithm corresponding to the target shooting parameters;

[0073] Feature extraction is performed on the facial expression image according to the target feature extraction algorithm and the target algorithm control parameters to obtain the first feature set.

[0074] The target shooting parameters may include at least one of the following: shooting angle, shooting distance, sensitivity, exposure time, etc., which are not limited here.

[0075] The target skin color parameter may include at least one of the following: skin color type, skin color degree, skin color age, etc., which are not limited here.

[0076] In a specific implementation, the target shooting parameters of the target expression image can be obtained, the target skin color parameters of the target expression image can be obtained, and the mapping relationship between the preset skin color parameters and the feature extraction algorithm can be pre-stored. Then, the target feature extraction algorithm corresponding to the target skin color parameters can be determined based on the mapping relationship. The mapping relationship between the preset shooting parameters and the algorithm control parameters of the target feature extraction algorithm can be pre-stored. Then, the target algorithm control parameters of the target feature extraction algorithm corresponding to the target shooting parameters can be determined based on the mapping relationship.

[0077] Among them, the target algorithm control parameters can be used to control the feature extraction effect of the target feature extraction algorithm, and the feature extraction effect may include at least one of the following: feature type, feature extraction degree, feature extraction speed, feature extraction area, etc., which are not limited here.

[0078] The target feature extraction algorithm may include one or more feature extraction algorithms, and each feature extraction algorithm may be used to extract a type of feature.

[0079] Next, feature extraction can be performed on the facial expression image according to the target feature extraction algorithm and the target algorithm control parameters to obtain a first feature set. In this way, on the one hand, the corresponding target feature extraction algorithm can be determined based on the skin color parameters of the target object, thereby preliminarily ensuring the integrity and accuracy of the feature extraction. On the other hand, the algorithm control parameters of the target feature extraction algorithm can be deeply optimized based on the shooting parameters, so that the final algorithm control parameter depth conforms to the characteristics of the image itself. In this way, the integrity and accuracy of the feature extraction can be deeply guaranteed, thereby helping to ensure that the target expression image is deeply adapted to the target object, and further, helping to improve the intelligence and fun of the smart AI glasses.

[0080] Optionally, the smart AI glasses also communicate with a wearable device of the target object; the above step of determining the target algorithm control parameters of the target feature extraction algorithm corresponding to the target shooting parameters may include the following steps:

[0081] Obtaining a capture moment of the facial expression image;

[0082] Acquiring, by the communication module, a target physiological state parameter of the target object collected by the wearable device;

[0083] Determining a first algorithm control parameter of the target feature extraction algorithm corresponding to the target shooting parameter;

[0084] determining a first optimization parameter corresponding to the target physiological state parameter;

[0085] The target algorithm control parameter is determined according to the first optimization parameter and the first algorithm control parameter.

[0086] The target physiological state parameter may include at least one of the following: blood pressure, muscle movement parameters, blood sugar, blood lipids, brain wave parameters, venous parameters, electrocardiogram, etc., which are not limited here. The target physiological state parameter reflects the emotional state of the target object to a certain extent.

[0087] In a specific implementation, the capture moment of the facial expression image can be obtained, and the target physiological state parameters of the target object collected by the wearable device can be obtained through the communication module. The mapping relationship between the preset physiological state parameters and the optimization parameters can also be pre-stored, and then, the first optimization parameter corresponding to the target physiological state parameter can be determined based on the mapping relationship.

[0088] Among them, the mapping relationship between the preset shooting parameters and the algorithm control parameters of the target feature extraction algorithm can also be pre-stored, and then, the first algorithm control parameter of the target feature extraction algorithm corresponding to the target shooting parameter can be determined based on the mapping relationship, and the target algorithm control parameter can also be determined according to the first optimization parameter and the first algorithm control parameter, that is, the target algorithm control parameter = (1 + first optimization parameter) * first algorithm control parameter. In this way, the algorithm control parameter can be deeply optimized based on the user's physiological characteristics, so that the final algorithm control parameter is further deeply consistent with the emotions of the target object itself. In this way, the integrity and accuracy of the feature extraction can be deeply guaranteed, thereby helping to ensure that a target expression image that is deeply adapted to the target object is obtained, and then, helping to improve the intelligence and fun of the smart AI glasses.

[0089] It can be seen that the expression processing method described in the embodiment of the present application is applied to smart AI glasses. The smart AI glasses include a sensor and a communication module. The facial expression image of the target object is captured by the sensor. The target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses. The facial expression image is extracted to obtain a target feature set, and a target expression image in a preset format is generated according to the target feature set. The target expression image is sent to a designated device through the communication module. In this way, the user's facial expression image can be collected, and a corresponding target expression image in a preset format can be generated and shared with other users (friends). Therefore, the intelligence and fun of the smart AI glasses can be improved, and the user experience can be improved.

[0090] In accordance with the above embodiment, please refer to Figure 3 , Figure 3: is a structural schematic diagram of another smart AI glasses provided in an embodiment of the present application. As shown in the figure, the smart AI glasses include a processor, a memory, a communication interface and one or more programs. The one or more programs are stored in the memory and are configured to be executed by the processor. In the embodiment of the present application, the smart AI glasses include a sensor and a communication module; the program includes instructions for executing the following steps:

[0091] Capturing a facial expression image of a target object through the sensor, wherein the target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses;

[0092] Performing image extraction on the facial expression image to obtain a target feature set;

[0093] Generating a target expression image in a preset format according to the target feature set;

[0094] The target expression image is sent to a designated device through the communication module.

[0095] Optionally, in the aspect of performing image extraction on the facial expression image to obtain a target feature set, the program includes instructions for executing the following steps:

[0096] Performing feature extraction on the facial expression image to obtain a first feature set;

[0097] Determining a target expression type corresponding to the first feature set;

[0098] Determine features corresponding to the target expression type according to the first feature set to obtain the target feature set.

[0099] Optionally, in determining the features corresponding to the target expression type according to the first feature set to obtain the target feature set, the program includes instructions for executing the following steps:

[0100] Acquire a feature selection rule set corresponding to the preset format to obtain multiple feature selection rule sets, each feature selection rule set corresponding to an expression type;

[0101] Determine a target feature selection rule set corresponding to the target expression type from the multiple feature selection rule sets;

[0102] The first feature set is screened according to the target feature selection rule set to obtain the target feature set.

[0103] Optionally, in the aspect of generating a target expression image in a preset format according to the target feature set, the program includes instructions for executing the following steps:

[0104] Acquire a reference expression template set corresponding to the preset format, wherein the reference expression template set includes a plurality of reference expression templates, and each reference expression template corresponds to an expression type;

[0105] Determining a target reference expression template corresponding to the target expression type from the reference expression template set;

[0106] The target expression image is determined according to the target feature set and the target reference expression template.

[0107] Optionally, in the aspect of determining the target expression image according to the target feature set and the target reference expression template, the program includes instructions for executing the following steps:

[0108] Acquire a feature position region corresponding to each feature in the target feature set to obtain at least one feature position region;

[0109] Marking a corresponding region in the target reference expression template according to the at least one characteristic position region to obtain at least one region;

[0110] The target feature set is filled into a corresponding area of ​​the at least one area in the target reference expression template to obtain the target expression image.

[0111] Optionally, in the aspect of extracting features from the facial expression image to obtain a first feature set, the program includes instructions for executing the following steps:

[0112] Acquire target shooting parameters of the target expression image;

[0113] Obtaining target skin color parameters of the target expression image;

[0114] Determining a target feature extraction algorithm corresponding to the target skin color parameter;

[0115] Determining target algorithm control parameters of the target feature extraction algorithm corresponding to the target shooting parameters;

[0116] Feature extraction is performed on the facial expression image according to the target feature extraction algorithm and the target algorithm control parameters to obtain the first feature set.

[0117] Optionally, the smart AI glasses also communicate with a wearable device of the target object; the above step of determining the target algorithm control parameters of the target feature extraction algorithm corresponding to the target shooting parameters may include the following steps:

[0118] Obtaining a capture moment of the facial expression image;

[0119] Acquiring, by the communication module, a target physiological state parameter of the target object collected by the wearable device;

[0120] Determining a first algorithm control parameter of the target feature extraction algorithm corresponding to the target shooting parameter;

[0121] determining a first optimization parameter corresponding to the target physiological state parameter;

[0122] The target algorithm control parameter is determined according to the first optimization parameter and the first algorithm control parameter.

[0123] It can be seen that the smart AI glasses described in the embodiments of the present application include a sensor and a communication module. The facial expression image of the target object is captured by the sensor. The target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses. The facial expression image is extracted to obtain a target feature set, and a target expression image in a preset format is generated according to the target feature set. The target expression image is sent to a designated device through the communication module. In this way, the user's facial expression image can be collected, and a corresponding target expression image in a preset format can be generated and shared with other users (friends). Therefore, the intelligence and fun of the smart AI glasses can be improved, and the user experience can be improved.

[0124] Figure 4 400 is a functional unit block diagram of a smart AI glasses 400 involved in an embodiment of the present application. The smart AI glasses include a sensor and a communication module; the smart AI glasses 400 include: an acquisition unit 401, an extraction unit 402, a generation unit 403 and an interaction unit 404, wherein:

[0125] The acquisition unit 401 is used to capture a facial expression image of a target object through the sensor, where the target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses;

[0126] The extraction unit 402 is used to perform image extraction on the facial expression image to obtain a target feature set;

[0127] The generating unit 403 is used to generate a target expression image in a preset format according to the target feature set;

[0128] The interaction unit 404 is used to send the target expression image to a designated device through the communication module.

[0129] Optionally, in the aspect of performing image extraction on the facial expression image to obtain a target feature set, the extraction unit 402 is specifically used for:

[0130] Performing feature extraction on the facial expression image to obtain a first feature set;

[0131] Determining a target expression type corresponding to the first feature set;

[0132] Determine features corresponding to the target expression type according to the first feature set to obtain the target feature set.

[0133] Optionally, in determining the features corresponding to the target expression type according to the first feature set to obtain the target feature set, the extraction unit 402 is specifically configured to:

[0134] Acquire a feature selection rule set corresponding to the preset format to obtain multiple feature selection rule sets, each feature selection rule set corresponding to an expression type;

[0135] Determine a target feature selection rule set corresponding to the target expression type from the multiple feature selection rule sets;

[0136] The first feature set is screened according to the target feature selection rule set to obtain the target feature set.

[0137] Optionally, in the aspect of generating the target expression image in a preset format according to the target feature set, the generating unit 403 is specifically used for:

[0138] Acquire a reference expression template set corresponding to the preset format, wherein the reference expression template set includes a plurality of reference expression templates, and each reference expression template corresponds to an expression type;

[0139] Determining a target reference expression template corresponding to the target expression type from the reference expression template set;

[0140] The target expression image is determined according to the target feature set and the target reference expression template.

[0141] Optionally, in determining the target expression image according to the target feature set and the target reference expression template, the generating unit 403 is specifically configured to:

[0142] Acquire a feature position region corresponding to each feature in the target feature set to obtain at least one feature position region;

[0143] Marking a corresponding region in the target reference expression template according to the at least one characteristic position region to obtain at least one region;

[0144] The target feature set is filled into a corresponding area of ​​the at least one area in the target reference expression template to obtain the target expression image.

[0145] Optionally, in the aspect of extracting features from the facial expression image to obtain the first feature set, the extraction unit 402 is specifically used for:

[0146] Acquire target shooting parameters of the target expression image;

[0147] Obtaining target skin color parameters of the target expression image;

[0148] Determining a target feature extraction algorithm corresponding to the target skin color parameter;

[0149] Determining target algorithm control parameters of the target feature extraction algorithm corresponding to the target shooting parameters;

[0150] Feature extraction is performed on the facial expression image according to the target feature extraction algorithm and the target algorithm control parameters to obtain the first feature set.

[0151] Optionally, the smart AI glasses further communicate with a wearable device of the target object; in determining the target algorithm control parameter of the target feature extraction algorithm corresponding to the target shooting parameter, the extraction unit 402 is specifically used to:

[0152] Obtaining a capture moment of the facial expression image;

[0153] Acquiring, by the communication module, a target physiological state parameter of the target object collected by the wearable device;

[0154] Determining a first algorithm control parameter of the target feature extraction algorithm corresponding to the target shooting parameter;

[0155] determining a first optimization parameter corresponding to the target physiological state parameter;

[0156] The target algorithm control parameter is determined according to the first optimization parameter and the first algorithm control parameter.

[0157] It can be seen that the smart AI glasses described in the embodiments of the present application include a sensor and a communication module. The facial expression image of the target object is captured by the sensor. The target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses. The facial expression image is extracted to obtain a target feature set, and a target expression image in a preset format is generated according to the target feature set. The target expression image is sent to a designated device through the communication module. In this way, the user's facial expression image can be collected, and a corresponding target expression image in a preset format can be generated and shared with other users (friends). Therefore, the intelligence and fun of the smart AI glasses can be improved, and the user experience can be improved.

[0158] It can be understood that the functions of each program module of the smart AI glasses of this embodiment can be specifically implemented according to the method in the above method embodiment. The specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here.

[0159] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments.

[0160] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the above method embodiment. The computer program product may be a software installation package.

[0161] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0162] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0163] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0164] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0165] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0166] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0167] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0168] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for processing facial expressions, characterized in that: Applied to smart AI glasses, the smart AI glasses include a sensor and a communication module; the method includes: Capturing a facial expression image of a target object through the sensor, wherein the target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses; Performing image extraction on the facial expression image to obtain a target feature set; Generating a target expression image in a preset format according to the target feature set; The target expression image is sent to a designated device through the communication module.

2. The method according to claim 1, characterized in that The step of performing image extraction on the facial expression image to obtain a target feature set includes: Performing feature extraction on the facial expression image to obtain a first feature set; Determining a target expression type corresponding to the first feature set; The features corresponding to the target expression type are determined according to the first feature set to obtain the target feature set.

3. The method according to claim 2, characterized in that The step of determining the features corresponding to the target expression type according to the first feature set to obtain the target feature set includes: Acquire a feature selection rule set corresponding to the preset format to obtain multiple feature selection rule sets, each feature selection rule set corresponding to an expression type; Determining a target feature selection rule set corresponding to the target expression type from the multiple feature selection rule sets; The first feature set is screened according to the target feature selection rule set to obtain the target feature set.

4. The method according to claim 3, characterized in that Generating a target expression image in a preset format according to the target feature set includes: Acquire a reference expression template set corresponding to the preset format, wherein the reference expression template set includes a plurality of reference expression templates, and each reference expression template corresponds to an expression type; Determining a target reference expression template corresponding to the target expression type from the reference expression template set; The target expression image is determined according to the target feature set and the target reference expression template.

5. The method according to claim 4, characterized in that The step of determining the target expression image according to the target feature set and the target reference expression template comprises: Acquire a feature position region corresponding to each feature in the target feature set to obtain at least one feature position region; Marking a corresponding region in the target reference expression template according to the at least one characteristic position region to obtain at least one region; The target feature set is filled into a corresponding area of ​​the at least one area in the target reference expression template to obtain the target expression image.

6. The method according to claim 2, characterized in that The step of extracting features from the facial expression image to obtain a first feature set includes: Acquire target shooting parameters of the target expression image; Obtaining target skin color parameters of the target expression image; Determining a target feature extraction algorithm corresponding to the target skin color parameter; Determining target algorithm control parameters of the target feature extraction algorithm corresponding to the target shooting parameters; Feature extraction is performed on the facial expression image according to the target feature extraction algorithm and the target algorithm control parameters to obtain the first feature set.

7. A smart AI glasses, characterized in that: The smart AI glasses include a sensor and a communication module; the smart AI glasses include: an acquisition unit, an extraction unit, a generation unit and an interaction unit, wherein: The acquisition unit is used to capture a facial expression image of a target object through the sensor, where the target object is a user who admires the smart AI glasses, or the target object is a subject photographed by the smart AI glasses; The extraction unit is used to perform image extraction on the facial expression image to obtain a target feature set; The generating unit is used to generate a target expression image in a preset format according to the target feature set; The interaction unit is used to send the target expression image to a designated device through the communication module.

8. The smart AI glasses according to claim 7, characterized in that: In the aspect of performing image extraction on the facial expression image to obtain the target feature set, the extraction unit is specifically used for: Performing feature extraction on the facial expression image to obtain a first feature set; Determining a target expression type corresponding to the first feature set; The features corresponding to the target expression type are determined according to the first feature set to obtain the target feature set.

9. A smart AI glasses, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the program comprises instructions for executing the steps in the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 6.

Images