Premature aging detection using dynamic facial imaging

Abstract

Described herein are systems, methods, and apparatuses for identifying a user (e.g., a consumer) at risk for premature aging through dynamic facial imaging assessments. For example, a computing system can receive video data. The video data can be or can include one or more frames associated with a face of a user. The computing device can identify a frame from the video data. The computing device can determine a baseline wrinkle count associated with a first state. The computing device can determine a dissipation wrinkle count (e.g., a peak of a facial expression and a duration after relaxation) associated with a second state. Based on the baseline wrinkle count and the dissipation wrinkle count, the computing device can calculate a residual wrinkle count between the first state and the second state. The computing device can map the residual wrinkle count to a risk of premature aging for the consumer.

Description

Background Technology

[0001] Skin may lose extracellular matrix as it ages. It may also lose its ability to renew itself. The loss of extracellular matrix and / or the loss of its renewal capacity can lead to one or more aging phenotypes, such as fine lines, wrinkles, age spots, hyperpigmentation, uneven skin tone, etc. Dynamic facial imaging assessment may be desired to detect individuals at risk of early skin aging (e.g., premature aging). Summary of the Invention

[0002] This document describes systems, methods, and instruments for identifying users (e.g., consumers) at risk of premature aging (e.g., early skin aging) through dynamic facial imaging assessment. For example, a computing system may receive video data. The video data may be, or may include, one or more frames associated with the consumer's face. In the example, the computing device may receive video data based on at least one of a camera associated with a mobile phone, a self-service terminal, and / or a beauty device (e.g., in a dermatologist's office).

[0003] A computing device can identify frames from video data having one or more frames. In the example, the computing device can identify a first frame. This first frame can be associated with a first state of the consumer's face. In the example, the computing device can identify a second frame. This second frame can be associated with a second state of the consumer's face. The state associated with the consumer's face can be associated with the consumer's facial expression. For example, facial expression can be or can include the consumer laughing, smiling, and / or frowning.

[0004] The computing device can determine the number of baseline wrinkles associated with the first state. The first state of the face can be or can include a relaxed face. For example, the first state can be associated with an initial static position of the face.

[0005] The computing device can determine the number of dissipated wrinkles associated with the second state. The second state of the face can be or can include a duration following a consumer's facial expression. In an example, this duration can be a fraction of a second following the peak of the facial expression. In an example, this duration can be 50 frames following the peak of the facial expression. As described herein, the facial expression can be one or more of the consumer's laughter, smile, frown, etc. For example, the facial expression can be a deviation from a static facial expression.

[0006] Based on the baseline wrinkle count and the number of vanished wrinkles, the computing device can calculate the number of residual wrinkles between the first state and the second state. The number of residual wrinkles can be used to generate a change (e.g., the change between the first state and the second state).

[0007] The computing device can map the number of residual wrinkles to the risk of premature aging in consumers. In one example, the computing device can determine whether the number of residual wrinkles is above or below a threshold. In another example, the computing device can translate the number of residual wrinkles into the risk of premature aging in consumers. For instance, the computing device can assess the number of residual wrinkles indicating premature aging in consumers, for example, via population correlation data between residual wrinkles and the risk of premature aging.

[0008] The threshold can be determined based on the consumer's age. For example, a computing device can determine the consumer's age. Based on the consumer's age, the computing device can determine a threshold associated with identifying the consumer as being at risk of premature aging. In the example, if the consumer's age falls within a first range, the computing device can determine that the threshold is a first threshold. In the example, if the consumer's age falls within a second range, the computing device can determine that the threshold is a second threshold. For example, the second range may be greater than the first range, and the first threshold may be greater than the second threshold.

[0009] In the example, the computing device can determine that the number of residual wrinkles is higher than a threshold. Based on this determination, the computing device can identify a consumer as being at risk of premature aging. The computing device can send a notification indicating that the consumer is at risk of premature aging. In the example, this notification may include recommendations (e.g., product recommendations) to help the consumer mitigate the risk of premature aging.

[0010] In the example, based on determining that the number of residual wrinkles is below a threshold, the computing device can identify a consumer as a characteristic aging individual defined by the threshold (e.g., a normal aging individual, a slow aging individual, etc.). For example, the computing device can send a notification informing the consumer that the risk of premature aging is low.

[0011] In the example, the computing device can determine facial pigmentation, for instance, based on video data. For example, if facial pigmentation is associated with a darker color, the computing device can send a notification to the consumer. This notification may include or may indicate that the consumer has a low risk of premature aging. For example, if facial pigmentation is associated with a lighter color, the computing device can determine that the number of residual wrinkles is above or below a threshold. Attached Figure Description

[0012] Figure 1 This is a block diagram of a computer-implemented system for detecting premature aging using dynamic facial imaging.

[0013] Figure 2 An exemplary flowchart for detecting premature aging using dynamic facial imaging is shown.

[0014] Figure 3AAn example of dynamic wrinkle analysis is shown, for example, at the peak of a facial expression (e.g., a smile). Figure 3B An example of dynamic wrinkle analysis is shown, for example, for the duration following the peak of a facial expression (e.g., upon initial return to a stationary position).

[0015] Figure 4A An example of fading lines after facial expressions is shown in individuals who are aging rapidly (e.g., users at risk of premature aging). Figure 4B Examples of diffuse lines are shown for individuals with characteristic aging traits (e.g., those aging normally, those aging slowly, users at low risk of premature aging, etc.).

[0016] Figures 5A through 5C illustrate examples of different states of facial expression. Figure 5A shows an example of a user's initial, still face. Figure 5B shows the duration of the peak of a user's facial expression (e.g., a smile). Figure 5C shows an example of a user's still face (e.g., after a facial expression).

[0017] Figures 6A through 6C illustrate examples of different states of facial expression. Figure 6A shows an example of a user's initial, still face. Figure 6B shows the duration of the peak of a user's facial expression (e.g., a smile). Figure 6C shows an example of a user's still face (e.g., after a facial expression).

[0018] Figures 7A to 7D Examples of different states associated with a user's facial expressions are shown. Detailed Implementation

[0019] Figure 1 This is a block diagram of a computer-implemented system 100. An exemplary computer-implemented system 100 may include an image capture device 136 and / or a computing device 102. The image capture device 136 and / or the computing device 102 may be connected to a network 134.

[0020] Image capture device 136 may be a device capable of recording high-speed video and / or capturing dynamic facial images associated with a user. The user described herein may be interchangeably referred to as a consumer. In the example, the device capable of recording high-speed video may be one or more cameras associated with a mobile phone, tablet computer, computer (e.g., laptop computer, desktop computer, etc.), self-service terminal, beauty device (e.g., in a dermatologist's office and / or beauty shop), etc. As described herein, image capture device 136 may capture video associated with one or more dynamic fine lines and / or wrinkles of the user. Although Figure 1 The image capture device 136 depicted is a device separate from the computing device 102, but the image capture device 136 may be part of the computing device 102.

[0021] The computing device 102 may include a processor 108, a memory 104, a user interface device 110, a communication interface device 112, a recommendation generator 132, a data storage device 114, and / or a video analyzer 118.

[0022] Processor 108 may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, etc. Processor 108 may perform signal encoding, data processing, power control, input / output processing, and / or any other functions that enable computing device 102 to operate in a wireless environment. Processor 108 may be coupled to a communication interface device 112 (e.g., a transceiver). The communication interface device may be, may include, or may be coupled to a transmitting / receiving element (not shown). Although Figure 1 While the processor 108 and the communication interface device 112 are depicted as separate components, it should be understood that the processor 108 and the communication interface device 112 may be integrated together in an electronic package or chip.

[0023] The processor 108 of computing device 102 may be coupled to user interface device 110 and may receive user input data from the user interface device. Examples of user interface devices may include, but are not limited to, speakers / microphones, keypads, displays / touchpads (e.g., liquid crystal display (LCD) units or organic light-emitting diode (OLED) display units). The processor 108 may also use the user interface (e.g., speakers / microphones, keypads, displays / touchpads, etc.) to output aging parameters and / or notifications. Furthermore, the processor 108 may access information from any type of suitable memory 104 and store data in that memory. Memory 104 may be non-removable memory and / or removable memory. In examples, non-removable memory may include random access memory (RAM), read-only memory (ROM), hard disks, or any other type of memory storage device. In examples, removable memory may include subscriber identity module (SIM) cards, memory sticks, secure digital storage (SD) cards, etc. In other embodiments, processor 108 may access information and store data in memory that is not physically located on computing device 102 (such as on a server (not shown), a home computer (not shown), or network 134).

[0024] Memory 104 may include computer-executable instructions 106 and / or applications 107 configured to operate one or more methods described herein. For example, processor 108 may be configured to use application 107 to receive video data, analyze the video data to identify one or more frames, determine the number of baseline wrinkles, the number of dissipated wrinkles, and / or the number of residual wrinkles, and map the number of residual wrinkles to the user's risk of premature aging. In the example, application 107 may be and / or may include a threshold generator (not shown) to generate a threshold associated with determining whether the user is at risk of premature aging. In the example, application 107 may be and / or may include a risk identifier (not shown) to determine whether the user is at risk of premature aging. In the example, application 107 may be and / or may include a recommendation generator (132) to generate recommendations (e.g., product recommendations) to the user based on the analysis of the risk of premature aging.

[0025] Data storage device 114 may be or may include video data 116 and / or database 117. Data storage device 114 may be a physical data storage device and / or may be associated with cloud computing storage (e.g., may not be part of computing device 102). Video data 116 stored in data storage device 114 may come from one or more video data sources of image capture device 136. Database 117 may be associated with determining thresholds and / or other relevant information for determining whether a user is at risk of premature aging as described herein.

[0026] The video analyzer 118 may include a frame recognizer 120, a baseline recognizer 122, a dissipation recognizer 124, and / or a residual recognizer 126. In this example, the video analyzer may receive video data. The video analyzer may identify one or more frames associated with the received video data. For example, the frame recognizer 120 may be configured to recognize one or more frames.

[0027] A video analyzer can extract markers from a user's (e.g., a consumer's) face, which are located in a specific region of the user's face. In an example, the video analyzer can extract markers from a first region of the user's face. As described herein, the first region of the user's face can be associated with a stationary portion and / or an initial stationary portion of the user's face in a received video. The extracted markers associated with the stationary portion and / or the initial stationary portion of the user's face can be, or can be associated with, the first frame of the video data. As described herein, the video analyzer can analyze the number of baseline wrinkles in the first frame of the video data. For example, a baseline recognizer 122 can be configured to determine and / or calculate the number of baseline wrinkles in the first frame of the video data.

[0028] A video analyzer can extract markers on a user's (e.g., a consumer's) face, which are located in a second region of the user's face. These markers, located in the second region of the user's face, can be associated with and / or be located within a second frame of video data. The second region of the user's face associated with the second frame of video data can be associated with a first portion of facial motion. As described herein, facial motion can be or can include the user smiling, laughing, frowning, and / or any deviation from the initial static position of the face.

[0029] A video analyzer can extract markers from a user's (e.g., a consumer's) face, specifically those markers located in a third region of the user's face. This third region can be a peak of facial movement. The markers present in this third region of the user's face can be associated with and / or located within the third frame of the video data.

[0030] The video analyzer can extract markers on a user's (e.g., a consumer's) face, which are located in a fourth region of the user's face. The fourth region of the user's face can be the duration following a peak in facial movement. The markers present in the fourth region of the user's face can be associated with and / or located within a fourth frame of the video data. The duration following a peak in facial movement can be a fraction of a second and / or approximately 50 frames. The video analyzer can determine the number of dissipated wrinkles in the fourth frame of the video data. For example, a dissipation recognizer 124 can be configured to determine and / or calculate the number of dissipated wrinkles in a frame of video data (e.g., the fourth frame of the video data).

[0031] The video analyzer can extract markers from a user's (e.g., a consumer's) face, which are located in a fifth region of the user's face. These markers in the fifth region of the user's face can be associated with and / or located within the fifth frame of the video data. The fifth region of the user's face associated with the fifth frame of the video data can be associated with a still portion and / or a return to the initial still portion.

[0032] The video analyzer can determine the number of residual wrinkles between the baseline number of wrinkles and the number of vanished wrinkles. For example, the residual wrinkle recognizer 126 can be configured to calculate the number of residual wrinkles.

[0033] As described herein, a computing device can be configured to identify several frames from a plurality of frames associated with video data. For example, the computing device can identify a first frame associated with an initial static face of a user. The computing device can identify a second frame associated with the duration following a peak in facial expression.

[0034] The video analyzer described herein can be configured to analyze, detect, and / or determine dynamic facial imaging (DFI). For example, video data associated with a user can be and / or may include continuous and / or transient cues associated with the user's facial movements. For example, continuous and / or transient cues can be one or more fine line formations observed during facial muscle movement. One or more cues may not be captured by static imaging. DFI can be a tool for recording one or more videos of facial skin movement during repetitive facial actions, such as facial lines during smiling, laughing, frowning, etc. One or more recorded videos can be analyzed by video analyzer 118 and / or algorithms (e.g., Sponsor's Iterative DeepFlow Algorithm). Video analyzer 118 and / or algorithms can analyze and / or determine one or more samples associated with skin features in the video data and / or track facial movements. DFI can be configured to determine the effects of pre-aging and / or premature aging based on skin movement during facial muscle activation and / or the effect of skin movement on the appearance of fine lines and wrinkles.

[0035] As part of the aging process, the skin may lose its extracellular matrix and / or its ability to renew itself, for example, due to aging. Loss of the extracellular matrix and / or loss of skin renewal capacity can lead to aging phenotypes, such as the appearance of fine lines, wrinkles, age spots, hyperpigmentation, uneven skin tone, etc. According to aging research, one or more skin changes (e.g., basic skin changes) can occur at any age. For example, one or more skin changes may occur in one or more identified populations that exhibit signs of accelerated aging compared to their biological age. As described herein, one or more methods may be available to detect premature aging using dynamic facial imaging.

[0036] Dynamic fine lines and / or wrinkles may appear as the skin moves during facial expressions such as laughing, smiling, or frowning. Although fine lines and / or wrinkles disappear quickly when the face is relaxed, the time it takes for them to disappear can vary. And over time, the accumulation of residual wrinkles can lead to permanent wrinkles. The formation of such permanent wrinkles may contribute to pre-aging (e.g., accelerated signs of aging compared to a person's biological age).

[0037] Data from clinical studies can be analyzed to understand fundamental skin changes at different ages. Data may indicate that signs of aging, as assessed by experts such as dermatologists, increase as early as age 25, with skin elasticity significantly decreasing with age. Using cluster data analysis, within younger populations (e.g., under 30), there may be a group of rapidly aging individuals. This group may exhibit more signs of aging (e.g., statistically significantly more signs of aging), more dynamic wrinkle formation, and / or more residual wrinkles (e.g., statistically significantly more residual wrinkles). As disclosed herein, such data can be used to identify appropriate analytical thresholds to accurately categorize subsequent consumers into defined categories (e.g., normal aging, slow aging, rapid aging, at risk of premature aging, at risk of early skin aging, etc.). For example, determining thresholds can represent the output of an assessment from such clinical study data.

[0038] Figure 2 An exemplary flowchart 200 for premature aging detection using dynamic facial imaging is shown. As described herein, the dynamic facial imaging assessment described herein can be used to identify users (such as consumers) at risk of premature aging and / or early skin aging. Users (e.g., consumers) can perform rapid, repetitive facial movements (such as smiling) to generate dynamic fine lines and wrinkles on the face.

[0039] like Figure 2 As shown, the computing device can receive video data 202. In this example, the computing device can receive video data from an image capture device (e.g., such as...). Figure 1 (136) receives video data. In the example, the computing device can receive video data from a network (e.g., such as...). Figure 1 (134) Receive video data. In the example, the computing device can receive video data from an image capture device within the computing device.

[0040] The image capture device described herein can be a camera associated with a mobile phone, self-service terminal, beauty device (e.g., in a dermatologist's office and / or beauty shop). The image capture device described herein can be capable of recording high-speed video. The image capture device can capture video data associated with one or more dynamic fine lines and / or wrinkles of a user.

[0041] like Figure 2 As shown, the computing device can extract one or more frames and / or still images from video data. For example, the computing device can identify one or more frames associated with video data 204. Based on the identified frames, the computing device can determine one or more regions of interest. For example, the computing device can extract facial regions (e.g., as shown in the image). Figure 3A , Figure 3BFigures 5A to 5C, Figures 6A to 6C and / or Figures 7A to 7D (As shown) is identified as the region of interest.

[0042] In the example, the computing device can recognize a first frame. This first frame can be associated with a first state of the user's face. In the example, the computing device can recognize a second frame. This second frame can be associated with a second state of the user's face. The state associated with the user's face can be associated with the user's facial expressions. For example, facial expressions can be or can include the user laughing, smiling, and / or frowning.

[0043] Based on identified regions of interest (e.g., in the first frame and / or the second frame), the computing device can use computer algorithms and / or machine learning processes to analyze the face. The computing device can detect fine lines and / or wrinkles in the user.

[0044] like Figure 2 As shown, the computing device can determine the number of baseline wrinkles associated with the first state 206. The first state of the face can be or can include a relaxed face. For example, the first state can be associated with an initial static position of the face.

[0045] like Figure 2 As shown, the computing device can determine the number of dissipated wrinkles associated with the second state 208. The second state of the face can be or can include the duration following the peak of the consumer's facial expression. In the example, this duration can be a fraction of a second following the peak of the facial expression. In the example, the duration can be 50 frames following the peak of the facial expression (e.g., Figure 3A , Figure 3B Figures 5A to 5C, Figures 6A to 6C and / or Figures 7A to 7D As described in this article, facial expressions can be one or more of the following: a consumer laughing, smiling, frowning, or any deviation from a stationary position.

[0046] like Figure 2 As shown, based on the baseline wrinkle count and the number of dissipated wrinkles, the computing device can calculate the number of residual wrinkles 210 between the first state and the second state. The number of residual wrinkles can be used to generate a change (e.g., the change between the first state and the second state). In this example, the computing device can use an algorithm to calculate the number of residual wrinkles. In this example, the computing device can calculate the number of residual wrinkles based on the absolute difference between the number of dissipated wrinkles in the second state and the baseline wrinkle count in the first state.

[0047] like Figure 2As shown, the computing device can map the number of residual wrinkles to the risk of premature aging in consumers.212 For example, the computing device can compare the amount of wrinkle formation (e.g., baseline wrinkles and / or fading wrinkles) and residual wrinkles with a database corresponding to the user's age. Based on the mapping and / or comparison, the computing device can determine that users with more dynamic wrinkles and / or residual wrinkles will be identified as being at risk of rapid aging.

[0048] In the example, the computing device can determine whether the number of residual wrinkles is above or below a threshold. In the example, the computing device can translate the number of residual wrinkles into the risk of premature aging in consumers. For example, the computing device can assess the number of residual wrinkles indicating premature aging in consumers, for instance, via population correlation data between residual wrinkles and the risk of premature aging.

[0049] In the example, based on the number of residual wrinkles, the computing device can use algorithms and / or machine learning processes. For example, the computing device can input the number of residual wrinkles into the algorithm and / or machine learning process. The algorithm and / or machine learning process can be configured to compare the number of wrinkles against a database. The database can include one or more of the following as factors: overall fine lines, cheek wrinkles, crow's feet, overall hardness, dark circles, discrete pigmentation, lack of luster, lack of clarity, speckled hyperpigmentation, overall evenness, overall light damage, yellowishness, tactile roughness, under-eye wrinkles, etc. For example, the algorithm and / or machine learning process can use data standardization (e.g., standard deviation) to consider one or more factors described herein. The algorithm and / or machine learning process configures the data into k groups (e.g., clusters) based on having one or more similar features and / or patterns. For example, the algorithm and / or machine learning process can identify three clusters: low signs of aging (e.g., young); moderate signs of aging (e.g., transitional); and high signs of aging (e.g., old). The algorithm and / or machine learning process can output comparisons (e.g., clusters) and can determine aging parameters. For example, aging parameters can be or may include: slow aging (e.g., biologically older users who appear younger), an older baseline (e.g., biologically older users who appear older and / or match their biological age), a younger baseline (e.g., biologically younger users who appear younger and / or match their biological age), and / or rapid aging (e.g., biologically younger users who show signs of early aging). In the example, the database could indicate that rapid aging users may have a higher percentage of signs of premature aging (e.g., approximately 31% more signs of aging) compared to younger baseline users.

[0050] The threshold can be determined based on the consumer's age (e.g., biological age). For example, a computing device can determine the consumer's age. Based on the consumer's age and / or the output of the algorithms and / or machine learning processes described herein, the computing device can determine a threshold associated with identifying the consumer as being at risk of premature aging. In the example, if the consumer's age falls within a first range, the computing device can determine that the threshold is a first threshold. In the example, if the consumer's age falls within a second range, the computing device can determine that the threshold is a second threshold. For example, the second range may be greater than the first range, and the first threshold may be greater than the second threshold.

[0051] In the example, the computing device can determine that the number of residual wrinkles exceeds a threshold. Based on this determination, the computing device can identify a consumer as being at risk of premature aging. The computing device can then send a notification indicating that the consumer is at risk of premature aging. In this example, the notification may include recommendations for the consumer to mitigate the risk of premature aging.

[0052] In the example, based on determining that the number of residual wrinkles is below a threshold, the computing device can identify a consumer as someone who is aging slowly. The computing device can then send a notification informing the consumer that the risk of premature aging is low.

[0053] In the example, the computing device may determine facial pigmentation (e.g., skin color) based, for example, on video data. As an example, facial pigmentation may include one or more of the following: white, off-white, brown, dark brown, or black.

[0054] When facial pigmentation is associated with darker colors (e.g., brown, dark brown, and / or black), the computing device may send a notification to the consumer. This notification may include or may indicate a low risk of premature aging. When facial pigmentation is associated with lighter colors (e.g., white, off-white, and / or brown), the computing device may determine whether the number of residual wrinkles is above or below a threshold, as described herein.

[0055] Figure 3A An example of dynamic wrinkle analysis at the peak of facial movements / facial expressions (e.g., smiling) is shown. Figure 3BAn example of dynamic wrinkle analysis is shown, illustrating the duration following a peak in a facial expression (e.g., upon initial return to a stationary position). As described herein, the computing device can identify, for example, an initial stationary position (e.g., a relaxed face) associated with the first frame of video data. The computing device can identify a portion of the user's facial movements (e.g., a first portion of facial movement). As described herein, facial movements can be one or more of smiling, frowning, laughing, etc. For example, this portion of facial movement can be, or may include, a deviation from the user's identified initial stationary position. The computing device can identify other portions of the user's facial movements (e.g., a second portion of facial movement). For example, the second portion of facial movement can be, or may include, the peak in a facial expression. Figure 3A An example of the peaks in a facial expression is shown.

[0056] The computing device can identify another part of the user's facial movement (e.g., a third part of the facial movement). This third part of the facial movement can be associated with a second frame of the video data. Figure 3B An example of dynamic wrinkle analysis in a third location is shown. In the example, dynamic wrinkle analysis may include analysis performed on an image representing the duration following a peak in a facial expression. For example, the third part of facial movement may be, or may include, the duration following a peak in a facial expression. As described herein, this duration may be a fraction of a second and / or 50 frames following the peak and relaxation of the facial expression.

[0057] In the example, dynamic wrinkle analysis may include analysis performed on an image representing the duration associated with a return to a resting position after a peak in facial expression. For example, this duration could be identified as consistent with an initial return to the resting position. Alternatively, it could be identified as consistent with a return to the resting position with minimal relaxation buffer.

[0058] A third location of facial movement can represent any definable location after peak facial expression and during relaxation, and can be used to identify and quantify short-term residual wrinkles (e.g., wrinkles that dissipate over time after facial expression relaxation). For example, such wrinkles may persist for a period of time after other wrinkles formed during facial expression have been smoothed out. Analyzable aspects of these residual wrinkles can be correlated with skin health and / or skin type clusters.

[0059] In this example, the third location can be chosen to conform to a protocol defined for clinical research data collection. For example, as disclosed herein, a clinical study can be performed to collect data and determine one or more thresholds. This study may include a protocol for identification (e.g., defining a third location). Subsequent facial analyses may employ similar and / or identical protocols. This consistency can improve the validity of thresholds and analyses to accurately assess subsequent consumers.

[0060] As described herein, a computing device can determine whether a user is at risk of premature aging based on the number of residual wrinkles. For example, if a user is at risk of premature aging, their skin may take longer (e.g., longer than others who match their biological age or are younger than their biological age) to return to its initial resting state. By analyzing the number of residual wrinkles and / or calculating the difference in the number of wrinkles between two frames, as described herein, a computing device can determine whether a user is prone to premature aging. In the example, a rapidly aging person (e.g., a user at risk of premature aging) may show a trend of up to four times more residual wrinkles. For example, a rapidly aging person (e.g., a user at risk of premature aging) may show a trend of up to four times more residual wrinkles compared to a normally aging person.

[0061] Figure 4A An example of fading lines after facial expressions is shown in individuals who are aging rapidly (e.g., users at risk of premature aging). Figure 4B An example of fading lines is shown in individuals who age slowly (e.g., users at low risk of premature aging). As described herein, users at risk of premature aging may take longer (e.g., approximately several seconds) for fading lines (e.g., fading wrinkles) to disappear after the peak of a facial expression and / or upon returning to a resting position compared to users at low risk of premature aging. For example, Figure 4A The vanishing patterns shown can be compared to Figure 4B The length of the vanishing fringes shown.

[0062] The number of residual wrinkles and / or the term "residual wrinkles" as described herein can be the difference in wrinkle scores between two frames. For example, the wrinkle score difference can be associated with the difference between a first frame and a second frame, where the first frame is associated with the baseline number of wrinkles during a user's face being in a static position, and the second frame is associated with the number of dissipating wrinkles over a duration following the peak of a facial expression, as described herein. An example wrinkle score associated with a young baseline user could be 452.39. An example wrinkle score associated with an older baseline user could be 4781.94. An example wrinkle score associated with rapidly aging individuals could be 1855.69. An example wrinkle score associated with slowly aging individuals could be 1098.73. The wrinkle scores described herein can be configured to determine a threshold.

[0063] In the example, the wrinkle score described herein can be correlated with the amount of time (e.g., in seconds) for the skin to return to its initial resting position. In the example, this is associated with users at low risk of premature aging (e.g., those who age slowly, and as...). Figure 4B Compared to (as shown), users at risk of premature aging may take longer to return their skin to its initial resting position (e.g., as shown). Figure 4A(As shown). Based on the number of residual wrinkles remaining on a user's face, the duration following a peak facial expression can be an indicator of whether a user is at risk of premature aging or has a low risk of premature aging. The detection analysis described herein can make invisible wrinkles visible. For example, fading wrinkles following a peak facial expression may be invisible during a normal resting position (e.g., thus making fading wrinkles invisible). By using DFI and / or as described herein, a computing device can use fading wrinkles and assess whether a user is at risk of premature aging.

[0064] Figures 5A through 5C and / or 6A through 6C illustrate examples of different states of facial expression. As described herein, Figure 5A shows an example of a user's initial still face. Figure 5B shows an example of a facial state for a duration following a peak in a user's facial expression (such as a smile). Figure 5C shows an example of a user's still face (e.g., after a facial expression and returning to the initial still face). Similarly, Figure 6A shows an example of a user's initial still face. Figure 6B shows an example of a facial state for a duration following a peak in a user's facial expression. Figure 6C shows an example of a user's still face (e.g., after a facial expression and returning to the initial still face).

[0065] Figures 7A to 7D Examples of different facial expressions are shown. As described in this article, Figure 7A An example of a user's initial still face is shown. A computing device can determine the initial still face associated with the first frame of video data. Figure 7B An example of a peak in a user's facial expression (such as a frown) is shown. As described herein, a computing device can determine the peak of a facial expression associated with a second frame in the video data. Figure 7C An example of the duration following a peak in a user's facial expression (e.g., a frown) is shown. As described herein, a computing device can determine the duration following a peak in a facial expression associated with a third frame of video data. Figure 7D An example of a user's still face (e.g., after a facial expression and returning to the initial still face) is shown. As described herein, a computing device can determine a return to a still face (e.g., after a peak in the facial expression) associated with a fourth frame in the video data.

[0066] When a computing device determines that a user is at risk of premature aging, it can send a notification to the user. This notification can inform the user of the risk of premature aging. The notification may also be, or may include, a recommendation. For example, the recommendation may be, or may include, a product with anti-aging properties, such as those for mitigating and / or delaying premature aging.

[0067] One or more methods described herein can be configured into software, device applications, diagnostic guidelines (e.g., for dermatologists and / or cosmetic stores), analytical tools for treatment (e.g., for those at risk of premature aging), and tools for detecting genetic predispositions. For example, those skilled in the art will understand that one or more methods described herein can be applied to various combinations of devices, software, and / or diagnostic tools as described herein.

[0068] Although the above features and elements are described in a specific combination, each feature or element may be used alone without other features and elements of the preferred embodiment, or in various combinations with or without other features and elements.

[0069] The above processes and / or methods may be implemented in computer programs, software, and / or firmware incorporated in a computer-readable medium for execution by a computer and / or processor. Examples of computer-readable media may include, but are not limited to, electronic signals (transmitted via wired and / or wireless connections) and / or computer-readable storage media. Examples of computer-readable storage media may include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media (such as, but not limited to, internal hard disks and removable disks), magneto-optical media, and / or optical media (such as optical disc (CD)-ROMs and / or digital versatile discs (DVDs)). The processor associated with the software may be used to implement a radio frequency transceiver used in computing devices, networks, etc.

Claims

1. An apparatus, the apparatus comprising: Processor, the processor being configured to: Receive video data, wherein the video data includes multiple frames associated with the consumer's face; Identify a first frame and a second frame from the plurality of frames, wherein the first frame is associated with a first state of the consumer's face and the second frame is associated with a second state of the consumer's face; Determine the number of baseline wrinkles associated with the first state; Determine the number of dissipated wrinkles associated with the second state; Based on the baseline wrinkle count and the dissipated wrinkle count, calculate the residual wrinkle count between the first state and the second state; as well as The number of residual wrinkles is mapped to the consumer's risk of premature aging.

2. The apparatus according to claim 1, wherein, Mapping the number of residual wrinkles includes configuring the processor to: Determine whether the number of residual wrinkles exceeds a threshold; and Based on the determination that the number of residual wrinkles is higher than the threshold, the consumer is identified as being at risk of premature aging, and a notification is sent indicating that the consumer is at risk of premature aging, and the notification also includes recommendations for the consumer to mitigate the risk of premature aging.

3. The apparatus according to claim 2, wherein, The processor is configured to: Based on the determination that the number of residual wrinkles is below the threshold, the consumer is identified as a person experiencing normal aging; and Sending a notification indicates that the consumer is not at risk of premature aging.

4. The apparatus according to claim 1, wherein, The first state of the face includes a relaxed face, and the second state of the face includes a duration following the initial relaxation of the consumer's facial expression.

5. The apparatus of claim 4, wherein the duration comprises at least one of a fraction of a second or 50 frames following the peak of the facial expression and the relaxation.

6. The apparatus according to claim 4, wherein, The facial expression includes at least one of the consumer's laughter, smile, or frown.

7. The apparatus according to claim 1, wherein, The processor is further configured to: Determine the age of the consumer; and Based on the consumer's age, a determination threshold is selected that is associated with identifying the consumer as being at risk of premature aging, wherein the determination threshold represents the output of an assessment based on clinical research data.

8. The apparatus according to claim 7, wherein, The processor is further configured to: Given that the consumer's age falls within a first range, the threshold is determined to be a first threshold. as well as Given that the consumer's age falls within a second range, the threshold is determined to be a second threshold, wherein the second range is greater than the first range, and wherein the first threshold is greater than the second threshold.

9. The apparatus according to claim 1, wherein, The processor is configured to: Based on the video data, the pigmentation of the face was determined; When the pigmentation on the face is associated with darker skin, a low-risk notification is sent to inform the consumer of a low risk of premature aging. as well as Under the condition that the pigmentation on the face is associated with lightness, the number of residual wrinkles is determined to be above or below a threshold.

10. The apparatus according to claim 1, wherein, Mapping the number of residual wrinkles includes configuring the processor to: The number of residual wrinkles is converted into the risk of premature aging for the consumer, wherein the conversion includes configuring the processor to assess the number of residual wrinkles for premature aging for the consumer via population correlation data between residual wrinkles and the risk of premature aging.

11. A method, the method comprising: Receive video data, wherein the video data includes multiple frames associated with the consumer's face; Identify a first frame and a second frame from the plurality of frames, wherein the first frame is associated with a first state of the consumer's face and the second frame is associated with a second state of the consumer's face; Determine the number of baseline wrinkles associated with the first state; Determine the number of dissipated wrinkles associated with the second state; Based on the baseline wrinkle count and the dissipated wrinkle count, calculate the residual wrinkle count between the first state and the second state; as well as The number of residual wrinkles is mapped to the consumer's risk of premature aging.

12. The method according to claim 11, wherein, Mapping the number of residual wrinkles to the consumer's risk of premature aging includes: Determine whether the number of residual wrinkles exceeds a threshold; and Based on the determination that the number of residual wrinkles is higher than the threshold, the consumer is identified as being at risk of premature aging, and a notification is sent indicating that the consumer is at risk of premature aging, and the notification also includes recommendations for the consumer to mitigate the risk of premature aging.

13. The method according to claim 12, wherein, The method includes: Based on the determination that the number of residual wrinkles is below the threshold, the consumer is identified as a person experiencing normal aging; and Sending a notification indicates that the consumer is not at risk of premature aging.

14. The apparatus according to claim 11, wherein, The first state of the face includes a relaxed face, and the second state of the face includes a duration following the initial relaxation of the consumer's facial expression.

15. The method of claim 14, wherein the duration comprises at least one of a fraction of a second or 50 frames following the peak of the facial expression and the relaxation, and wherein the facial expression comprises at least one of the consumer laughing, smiling, or frowning.

16. The method according to claim 11, wherein, The method further includes: Determine the age of the consumer; and Based on the consumer's age, a threshold is determined that is associated with identifying the consumer as being at risk of premature aging.

17. The method according to claim 16, wherein, The method further includes: Given that the consumer's age falls within a first range, the threshold is determined to be a first threshold; and Given that the consumer's age falls within a second range, the threshold is determined to be a second threshold, wherein the second range is greater than the first range, and wherein the first threshold is greater than the second threshold.

18. The method according to claim 11, wherein, The method includes: Based on the video data, the pigmentation of the face was determined; Under conditions where the pigmentation on the face is associated with darker skin, a low-risk notification is sent, informing the consumer of a low risk of premature aging; and Under the condition that the pigmentation on the face is associated with lightness, the number of residual wrinkles is determined to be above or below a threshold.

19. The method according to claim 11, wherein, Mapping the number of residual wrinkles includes: The number of residual wrinkles is converted into the risk of premature aging for the consumer, wherein the conversion includes assessing the number of residual wrinkles for premature aging for the consumer via population correlation data between residual wrinkles and the risk of premature aging.

20. The method according to claim 11, wherein, The video data is received based on at least one of a camera associated with a mobile phone, a self-service terminal, or a beauty device.

Images