Intelligent hair system and hairstyle recommendation system

Abstract

A system and method of measuring biomarkers, and a system and method of recommending a hair system are provided. The systems each comprise at least one processor and a memory storing instructions which when executed by the at least one processor configure the at least one processor to perform the method. The method of recommending a hair system comprises receiving an input image of a user, locating a face of the user in the input image, extracting facial features of the user, determining similar model faces to that of the user from a data repository based on the user facial features, and recommending a hair system for the user based on a hairstyle score associated with the model faces. The method for measuring biomarkers comprises receiving biomarker data, and sending the biomarker data to a biomarker monitoring subsystem.

Description

Intelligent Hair System and Hairstyle Recommendation SystemFIELD

[0001] The present disclosure generally relates to wearable sensors, and in particular to an intelligent hair system and hairstyle recommendation system therefor.INTRODUCTION

[0002] Some medical conditions and procedures cause hair loss. Patients often choose to wear a wig when dealing with such conditions. Existing wearable sensors may lack the capability to monitor multiple biomarkers simultaneously. Also, people tend to prefer to try on a wig before purchasing the wig. T rying on wigs can be time consuming and requires that the person physically place the wig on their head. It is desirable to have a system where people can virtually try on wigs.SUMMARY

[0003] In accordance with an aspect, there is provided a system for measuring biomarkers. The system for measuring biomarkers through the scalp comprises at least one processor and a memory storing instructions which when executed by the at least one processor configure the at least one processor to receive biomarker data, and send the biomarker data to a biomarker monitoring subsystem.

[0004] In accordance with another aspect, there is provided a method of measuring biomarkers. The method comprises receiving biomarker data, and sending the biomarker data to a biomarker monitoring subsystem.

[0005] In accordance with another aspect, a system for recommending a hairstyle is provided. The system comprises at least one processor and a memory storing instructions which when executed by the at least one processor configure the at least one processor to receive an input image of a user, locate a face of the user in the input image, extract facial features of the user, determine similar model faces to that of the user from a data repository based on the user facial features, and recommend a hairstyle for the user based on a hairstyle score associated with the model faces.

[0006] In accordance with another aspect, there is provided a method of recommending a hairstyle. The method comprises receiving an input image of a user, locating a face of the user in the input image, extracting facial features of the user, determining similar model faces to that ofthe user from a data repository based on the user facial features, and recommending a hairstyle for the user based on a hairstyle score associated with the model faces.

[0007] In various further aspects, the disclosure provides corresponding systems and devices, and logic structures such as machine-executable coded instruction sets for implementing such systems, devices, and methods.

[0008] In this respect, before explaining at least one embodiment in detail, it is to be understood that the embodiments are not limited in application to the details of construction and to the arrangements of the components set forth in the following description or illustrated in the drawings. Also, it is to be understood that the phraseology and terminology employed herein are for the purpose of description and should not be regarded as limiting.

[0009] Many further features and combinations thereof concerning embodiments described herein will appear to those skilled in the art following a reading of the instant disclosure.DESCRIPTION OF THE FIGURES

[0010] Embodiments will be described, by way of example only, with reference to the attached figures, wherein in the figures:

[0011] FIG. 1 illustrates, in a schematic diagram, an example of an automated hair system / hairstyle recommendation system platform, in accordance with some embodiments;

[0012] FIG. 2 illustrates, in a flowchart, an example of a method of recommending a hair system, in accordance with some embodiments;

[0013] FIG. 3 illustrates, in a flowchart an example of a method of video editing, in accordance with some embodiments;

[0014] FIG. 4 illustrates, in a flowchart, an example of a method of swapping faces in an image, in accordance with some embodiments;

[0015] FIG. 5 illustrates, in a flowchart, another example of a method of swapping faces in an image, in accordance with some embodiments;

[0016] FIG. 6 illustrates, in a flowchart, an example of a method of finding a most similar face, in accordance with some embodiments;

[0017] FIG. 7 illustrates an overview of a GFP-GAN framework, in accordance with some embodiments;

[0018] FIG. 8 illustrates an example of swapped, source and target images, in accordance with some embodiments;

[0019] FIG. 9 illustrates examples of GFP-GAN input and output samples, in accordance with some embodiments;

[0020] FIG. 10 illustrates an in-app example of swapping hair based on facial feature analyzation, in accordance with some embodiments;

[0021] FIG. 11 illustrates examples of source, target and output images, in accordance with some embodiments;

[0022] FIG. 12 illustrates, in a component diagram, an example of an intelligent hair system, in accordance with some embodiments;

[0023] FIG. 13 illustrates, in a flowchart, an example of a method of non-invasively measuring biomarkers through the scalp via a hair system, in accordance with some embodiments; and

[0024] FIG. 14 is a schematic diagram of a computing device such as a server or other computer.

[0025] It is understood that throughout the description and figures, like features are identified by like reference numerals.DETAILED DESCRIPTION

[0026] Embodiments of methods, systems, and apparatus are described through reference to the drawings. Applicant notes that the described embodiments and examples are illustrative and non-limiting. Practical implementation of the features may incorporate a combination of some or all of the aspects, and features described herein should not be taken as indications of future or existing product plans.

[0027] Existing wearable sensors often lack the capability to monitor multiple biomarkers simultaneously. The present invention addresses this limitation by integrating a galvanic skin response (GSR) sensor into a commonly worn item, such as a wig cap or other hair system or hair system cap, enabling unobtrusive and continuous monitoring of biomarkers through the analysis of sweat. A hair system includes one of a wig, toupee, closure, frontal and / or hairline transplant, and / or a cap therefor.

[0028] In some embodiments, a wearable sweat-based GSR sensor embedded in an intelligent hair system cap is provided that allows for an unobtrusive and continuous biomarker monitoring.The intelligent hair system cap provides a convenient and efficient means of obtaining real-time data on mental and physical health parameters, with applications in health and performance assessment.

[0029] In some embodiments, a system is provided that allow people to try on hair systems virtually.

[0030] In some embodiments, a hair system recommendation system is provided that recommends a wig, hair system or hairstyle based on a user's skin tone and facial features such as, jaw line, forehead, complexion, face shape, etc.

[0031] FIG. 1 illustrates, in a schematic diagram, an example of an intelligent hair system and recommendation system platform 100, in accordance with some embodiments. The platform 100 may include an electronic device connected to an interface application 130 and external data sources 160 via a network 140 (or multiple networks). The platform 100 can implement aspects of the processes described herein for swapping faces on images, determining features of an individual, training a machine learning model to recommend a hair system / hairstyle for the individual based on their skin tone and other facial features. The platform 100 may also receive biomarker readings from sensors on the hair system and process the readings to monitor the health of the person or patient wearing the hair system.

[0032] The platform 100 may include at least one processor 104 and a memory 108 storing machine executable instructions to configure the at least one processor 104 to receive data in form of images (from e.g., data sources 160). The at least one processor 104 can receive a trained neural network and / or can train a neural network using a machine learning engine 126. The platform 100 can include an I / O Unit 102, communication interface 106, and data storage 110. The at least one processor 104 can execute instructions in memory 108 to implement aspects of processes described herein.

[0033] The platform 100 may be implemented on an electronic device and can include an I / O unit 102, the at least one processor 104, a communication interface 106, and a data storage 110. The platform 100 can connect with one or more interface devices 130 or data sources 160. This connection may be over a network 140 (or multiple networks). The platform 100 may receive and transmit data from one or more of these via I / O unit 102. When data is received, I / O unit 102 transmits the data to processor 104.

[0034] The I / O unit 102 can enable the platform 100 to interconnect with one or more input devices, such as a keyboard, mouse, camera, touch screen and a microphone, and / or with one or more output devices such as a display screen and a speaker.

[0035] The at least one processor 104 can be, for example, any type of general-purpose microprocessor or microcontroller, a digital signal processing (DSP) processor, an integrated circuit, a field programmable gate array (FPGA), a reconfigurable processor, or any combination thereof.

[0036] The data storage 110 can include memory 108, database(s) 112 and persistent storage 114. Memory 108 may include a suitable combination of any type of computer memory that is located either internally or externally such as, for example, random-access memory (RAM), readonly memory (ROM), compact disc read-only memory (CDROM), electro-optical memory, magneto-optical memory, erasable programmable read-only memory (EPROM), and electrically- erasable programmable read-only memory (EEPROM), Ferroelectric RAM (FRAM) or the like. Data storage devices 110 can include memory 108, databases 112 (e.g., graph database), and persistent storage 114.

[0037] The communication interface 106 can enable the platform 100 to communicate with other components, to exchange data with other components, to access and connect to network resources, to serve applications, and perform other computing applications by connecting to a network (or multiple networks) capable of carrying data including the Internet, Ethernet, plain old telephone service (POTS) line, public switch telephone network (PSTN), integrated services digital network (ISDN), digital subscriber line (DSL), coaxial cable, fiber optics, satellite, mobile, wireless (e.g. Wi-Fi, WiMAX), SS7 signaling network, fixed line, local area network, wide area network, and others, including any combination of these.

[0038] The platform 100 can be operable to register and authenticate users (using a login, unique identifier, and password for example) prior to providing access to applications, a local network, network resources, other networks and network security devices. The platform 100 can connect to different machines or entities.

[0039] The data storage 110 may be configured to store information associated with or created by the platform 100. Storage 110 and / or persistent storage 114 may be provided using various types of storage technologies, such as solid-state drives, hard disk drives, flash memory, and may be stored in various formats, such as relational databases, non-relational databases, flat files, spreadsheets, extended markup files, etc.

[0040] The memory 108 may include a face swapping unit 122, a hair system / hairstyle recommendation unit 124, a biometric sensor unit 126, and a machine learning engine 128. In some embodiments, the face swapping unit 122 may be included in the hair system / hairstyle recommendation unit 124. These units 122, 124, 126, 128 will be described in more detail below.

[0041] In some embodiments, a network for generating video level GAN is provided. Other networks using GAN only work on one image at a time. The network provided works on multiple images and then diffuse. The proposed network is unlike video diffusion models that exist currently. Rather, the GAN network has been modified to process at least two to three images at once. Once the user has taken a video of their face / head area it is then uploaded to the cloud which feeds the video to the network. It then takes the input of three images that have been captured from the video and outputs a fourth one (or modifies the third one) as the finished product. The network performs multiplications and linear operations. There are more than 18x multiplications. Since there are a couple million images, the network learns to multiply numbers for certain areas of the face / head. The videos are then saved to use for continued training.

[0042] Somewhat Supervised Learning. In some embodiments, there are two networks provided: one generator and one discriminator. The generator may be given three (or more) consecutive frames of the video. It will then generate an output to the discriminator. The discriminator will decide if this video is real (authentic) or generated. The training is deemed successful once the generator has submitted a generated video that the discriminator believes is a real authentic video.

[0043] FIG. 2 illustrates, in a flowchart, an example of a method of recommending a hairstyle 200, in accordance with some embodiments. The hairstyle may comprise a style to apply to a user’s natural hair and / or a hair system. The method 200 comprises receiving 210 an input image of a user, locating 220 a face of the user in the input image, extracting 230 facial features of the user, determining 240 similar model faces to that of the user from a data repository based on the user facial features, and recommending 250 a hairstyle for the user based on a hairstyle score associated with the model faces. Other steps may be added to the method 200. Other steps may be added to the method 200.

[0044] In some embodiments, a K-NN (K Nearest Neighbours) machine learning network may be used to classify individuals. Two convolutional networks may then be used to extract the key facial features of the user and perform an analyzation and classification based on factors down to the very last pixel of the image. A first pretrained convolutional neural network locates faces in an image. Then, the second pretrained convolutional neural network embeds facial features intoa 256 number vector. The values in the number vector refer to facial features. After the process of matching the facial features of the user to the models’ facial features, the system is able to decipher which hairstyle to suggest to the user based on the L2 norm of the user’s and each of the model’s faces. By using the L2 norm, which measures how similar these extracted vectors are, the most similar face is identified. The K-NN method can then be used to cluster groups of users to models, and understand which user matches which model. The system is then ready to produce the image / video back to the user with them (user) in the recommended hairstyle that was generated based on their skin tone and facial features.

[0045] FIG. 3 illustrates, in a flowchart an example of a method of video editing 300, in accordance with some embodiments. The method 300 comprises receiving a video X of a user 302. The video X may be received at a local device (e.g., a smart phone) and then uploaded 304 to a cloud environment (e.g., platform 100). A network Y on the cloud environment may be initialized 306. Hair in all frames f may be swapped 308. For each frame f in x-3 310, frames f, f+1 and f+2 may be fed 312 to the network such that frame f+2, is defined as f+2 = y (f:f+2) and saved 314 to the network. All newly generated frames may be stacked together 316. The resulting video is saved 318 and made available to be downloaded 320 as an input image of a user. Other steps may be added to the method 300.

[0046] FIG. 4 illustrates, in a flowchart, an example of a method of swapping faces in an image 400, in accordance with some embodiments. The method 400 comprises receiving 410 an input image of a user and a target hairstyle of a model, swapping 420 the face of the user with the model having that hairstyle refining 430 the image, and displaying 440 the refined image. Other steps may be added to the method 400. Other steps may be added to the method 400.

[0047] FIG. 5 illustrates, in a flowchart, another example of a method of swapping faces in an image 500, in accordance with some embodiments. The method 500 comprises obtaining 502 a user image X and target video Z. These may be obtained at a local device (e.g., laptop, pad or smartphone). The user image X and target video Z may be uploaded 504 to the cloud environment (e.g., platform 100). Face swapping network Y may be initialized 506. For each frame f in image X 508, the face of the user may be swapped 510 with the target video Z, and the newly generated frame h may be saved 512. All newly generated frames h may be stacked together 514. The resulting video is saved 516 and made available to be downloaded 518. Other steps may be added to the method 500.

[0048] FIG. 6 illustrates, in a flowchart, an example of a method of finding a most similar face 600, in accordance with some embodiments. The method comprises obtaining 602 an image Xof a user. For example, image X may be electronically transferred to, or taken by, a local device (e.g., laptop, pad or smartphone). The image X may be uploaded 604 to the cloud environment (e.g., platform 100). Face recognition network Y may be initialized 606. The feature map m may be obtained by feeding the image X to the network, such that m = Y(X) 608. The models' face features dataset Z and feature map m may be clustered with K-NN 610. The faces which are in the same cluster as m may be located and / or selected 612. The resulting faces may be displayed or otherwise suggested to the user 614. Other steps may be added to the method 600.

[0049] Using the system described above, people may see themselves in real time with the hairstyle of their choice. In some embodiments, GFPGAN and VGGFace2 are used in tandem. For example, a GAN based network designed for high fidelity face swapping may be used. When a user uploads their image / video, the GAN based network detects the most efficient way of isolating the facial identity of the user and then swapping it with the “placeholder face” that would serve as the hair system model. The GAN based network takes the source (user’s face) and places it on the target (hair system model’s face). GFPGAN optimizes the image multiple times to ensure that the end result is of realistic quality and blemish free. GFPGAN is trained on open- source FFHQ dataset. FFHQ is an image dataset containing high-quality images of human faces. It contains thousands of images of people's faces that can be used to train the models. The generator model consists of a degradation removal U-net and a pretrained GAN as prior and a discriminator during the training. The information of the U-net and pretrained GAN are combined together with Channel-Split SFT modules. Since VGGFace2 is a pretrained network, it can be used as the encoder in the generator. The generator's decoder has an architecture similar to VGGFace2, but in the opposite direction. Meaning its first layers are VGGFace2's final layers, and its last layers are VGGFace2's first layers. Given that this network has a new architecture, it must be trained again. The use of this new network and using GFPGAN recursively on the output is novel.

[0050] Through experimentation, it was determined that replacing the U-net backbone in GFPGAN with a U-net made with the ConvNext allows for quicker and more precise results. This network is comprised of a CNN architecture. It allows the desired identity mapping to take place. FIG. 7 illustrates an overview of a GFP-GAN 700, in accordance with some embodiments. The GFP-GAN framework 600 comprises a degradation removal module (U-Net) and a pretrained face GAN as facial prior. They are bridged by a latent code mapping and several Channel-Split Spatial Feature Transform (CS-SFT) layers. During training, the following may be employed: 1) intermediate restoration losses to remove complex degradation, 2) Facial component loss withdiscriminators to enhance facial details, and 3) identity preserving loss to retain face identity. In some embodiments when training a network, the network compares its outputs with the output it was supposed to provide. The difference between the two are computed with loss functions. Through back propagation, the network updates its weights and biases. All the loss functions mentioned in 1), 2) and 3) above are mathematical calculations that show how the network's prediction is to change.

[0051] FIG. 8 illustrates examples of swapped, source and target images 800a to 800c, in accordance with some embodiments. Image 800a is a swapped image, image 800b is a source image, and image 800c is a target image.

[0052] FIGs. 9A and 9B illustrate examples of GFP-GAN input 900a and output 900b samples, in accordance with some embodiments.

[0053] FIGs. 10A and 10B illustrate an in-app example of swapping hair based on facial feature analyzation 1000a and 1000b, in accordance with some embodiments.

[0054] FIG. 11 illustrates examples of source, target and output images 1100a to 1100c, in accordance with some embodiments. Image 1100a is a source image, image 1100b is a target image, and image 1100c is an output image.Intelligent Hair System

[0055] Sensors may be placed in a hair system cap (e.g., a wig cap or other cap for any hair system) to monitor biological data.

[0056] FIG. 12 illustrates, in a component diagram, an example of an intelligent hair system 1200, in accordance with some embodiments. The system 1200 may be used to non-invasively measuring biomarkers through the scalp. The system 1200 comprises a hair system cap assembly 1210 and a health monitoring system 1230. The hair system cap assembly 1210 comprises a hair system cap 1212, at least one sensor 1214, a power supply 1216, and a processing unit or readout board 1220. The processing unit 1220 comprises a voltage divider 1222, a filter 1224, an amplifier 1226 and a chip antenna 1228. The hair system cap may comprise any of a wig cap, a toupee cap, a closure cap, a frontal cap, a hairline transplant cap, or any combination therefor.

[0057] A Real-time Sensor which comprises a Biomarker design and readout board is provided. For health monitoring, there are hidden sensors in the hair system caps 1212 that use human biological fluids, such as sweat, to collect data and send them to a processing unit or readoutboard (e.g., an Arduino board) 1220. The Arduino board 1220 processes the information and sends it to a health monitoring system 1230 which may be implemented on a user’s smartphone, where the user may observe their health status.

[0058] In some embodiments, the at least one sensor 1214 may comprise a wearable sweatbased galvanic skin response (GSR) sensor embedded in a hair system cap 1212 for the detection of biomarkers, including sodium, glucose, and cortisol. Since each individual’s biomarker levels are different and unique to their body, there is a probational period in which the sensor 1214 studies the user. After the probational period the sensor 1214 is able to detect normalities and abnormalities in the user’s biomarker levels. The sensor 1214 utilizes sweat analysis to provide real-time monitoring of physiological parameters for health and performance assessment. This wearable may be configured to work in tandem with the health monitoring system 1230. The analyzed data may be displayed in user friendly terms (graph / chart) and offers suggestions on how the user can take a proactive approach to better their health behavior.

[0059] In some embodiments, the readout board 1220 may comprise an Arduino Nano 33 microcontroller along with a Nordic Semiconductor nRF52832 SoC and chip antenna for Bluetooth low energy is to be used for data acquisition and system programmability. The micro-power integrated circuit LMP91000 is to be used as an analog front end for sensing applications. A built- in 12-bit analog-to-digital converter may be used to acquire and measure the potential to measure the concentration of sodium. A voltage buffer is added between LMP91000 and the microcontroller to avoid electrical loading from the microcontroller. In some embodiments, data markers may be measured at least once every second.

[0060] The wearable sweat-based GSR sensor may comprise a flexible, waterproof sensor unit 1214 embedded in the back part of the inner lining of a wig cap 1212. The sensor unit 1214 may be in direct contact with the user's lower nape / upper neck, allowing for the collection and analysis of sweat. The GSR sensor 1214 measures electrical conductance across the skin, and additional electrodes are included to detect specific biomarkers, including sodium, glucose, and cortisol. The sensor 1214 may be embedded with the aid of conductive thread.

[0061] The sensor unit 1214 may be connected to a processing unit 1218 within the hair system cap 1212, which processes the data and transmits it wirelessly to a mobile device 1230 or a designated receiver for further analysis. The hair sytem cap 1212 may be powered by a rechargeable battery 1222, and the sensor unit 1214 may be replaceable for extended use.

[0062] In some embodiments, a system for non-invasively measuring biomarkers through the scalp via a system is provided. The system comprises at least one processor and a memory storing instructions which when executed by the at least one processor configure the at least one processor to receive biomarker data, and send the biomarker data to a biomarker monitoring subsystem.

[0063] In some embodiments, the biomarker data comprises at least one of temperature, humidity, pulse oximetry, heart rate or mixed vitals.

[0064] In some embodiments, the biomarker data is transmitted over a secure link to a secure link-enabled subsystem.

[0065] In some embodiments, to receive biomarker data from the scalp the at least one processor is configured to enter into a loop and read off sensor values for individual biomarker datum, and measure values over a timeframe and algorithmically package a sample.

[0066] In some embodiments, to send data over a secure link, the at least one processor is activated to emit packets over the secure link in a defined protocol. In one example of a defined protocol, the at least one processor configured to determine interval to send data, apply a method to save battery life to extend its use, and acknowledge data has been sent.Detection Mechanism:

[0067] Galvanic Skin Response (GSR): The GSR sensor 1214 measures the electrical conductance of the skin to assess a user's mental and physical state of health.

[0068] Biomarker Detection: Additional electrodes within the sensor unit 1214 selectively detect biomarkers in sweat, including sodium, glucose, and cortisol, through electrochemical sensing techniques.

[0069] In some embodiments, the intelligent hair system 1200 provides unobtrusive monitoring. I.e., the hair system cap 1212 may be designed to provide continuous monitoring without interfering with daily activities, all while having a fashion-friendly wearable.

[0070] In some embodiments, the intelligent hair system 1200 provides real-time feedback. I.e., the system 1200 may be configured to provide real-time data on biomarker levels for health and performance assessment.

[0071] In some embodiments, the intelligent hair system 1200 provides wireless connectivity. I.e., the system 1200 may be configured to enable seamless data transmission to external devices for further analysis and storage.

[0072] FIG. 13 illustrates, in a flowchart, an example of a method of non-invasively measuring biomarkers through the scalp via a hair system 1300, in accordance with some embodiments. The method comprises receiving 1302 biomarker data from at least one sensor attached to a hair system cap, and sending 1304 the biomarker data to a biomarker monitoring subsystem. In some embodiments, the method 1300 may be performed by the system 1200. Other steps may be added to the method 1300, including functionality performed by the system 1200.

[0073] FIG. 14 is a schematic diagram of a computing device 1400 such as a server or other computer. As depicted, the computing device includes at least one processor 1402, memory 1404, at least one I / O interface 1406, and at least one network interface 1408.

[0074] Processor 1402 may be an Intel or AMD x86 or x64, PowerPC, ARM processor, or the like. Memory 1404 may include a suitable combination of computer memory that is located either internally or externally such as, for example, random-access memory (RAM), read-only memory (ROM), compact disc read-only memory (CDROM).

[0075] Each I / O interface 1406 enables computing device 1400 to interconnect with one or more input devices, such as a keyboard, mouse, camera, touch screen and a microphone, or with one or more output devices such as a display screen and a speaker.

[0076] Each network interface 1408 enables computing device 1400 to communicate with other components, to exchange data with other components, to access and connect to network resources, to serve applications, and perform other computing applications by connecting to a network (or multiple networks) capable of carrying data including the Internet, Ethernet, plain old telephone service (POTS) line, public switch telephone network (PSTN), integrated services digital network (ISDN), digital subscriber line (DSL), coaxial cable, fiber optics, satellite, mobile, wireless (e.g. Wi-Fi, WiMAX), SS7 signaling network, fixed line, local area network, wide area network, and others.

[0077] The foregoing discussion provides example embodiments of the inventive subject matter. Although each embodiment represents a single combination of inventive elements, the inventive subject matter is considered to include all possible combinations of the disclosed elements. Thus, if one embodiment comprises elements A, B, and C, and a second embodiment comprises elements B and D, then the inventive subject matter is also considered to include other remaining combinations of A, B, C, or D, even if not explicitly disclosed.

[0078] The embodiments of the devices, systems and methods described herein may be implemented in a combination of both hardware and software. These embodiments may beimplemented on programmable computers, each computer including at least one processor, a data storage system (including volatile memory or non-volatile memory or other data storage elements or a combination thereof), and at least one communication interface.

[0079] Program code is applied to input data to perform the functions described herein and to generate output information. The output information is applied to one or more output devices. In some embodiments, the communication interface may be a network communication interface. In embodiments in which elements may be combined, the communication interface may be a software communication interface, such as those for inter-process communication. In still other embodiments, there may be a combination of communication interfaces implemented as hardware, software, and combination thereof.

[0080] Throughout the foregoing discussion, numerous references will be made regarding servers, services, interfaces, portals, platforms, or other systems formed from computing devices. It should be appreciated that the use of such terms is deemed to represent one or more computing devices having at least one processor configured to execute software instructions stored on a computer readable tangible, non-transitory medium. For example, a server can include one or more computers operating as a web server, database server, or other type of computer server in a manner to fulfill described roles, responsibilities, or functions.

[0081] The technical solution of embodiments may be in the form of a software product. The software product may be stored in a non-volatile or non-transitory storage medium, which can be a compact disk read-only memory (CD-ROM), a USB flash disk, or a removable hard disk. The software product includes a number of instructions that enable a computer device (personal computer, server, or network device) to execute the methods provided by the embodiments.

[0082] The embodiments described herein are implemented by physical computer hardware, including computing devices, servers, receivers, transmitters, processors, memory, displays, and networks. The embodiments described herein provide useful physical machines and particularly configured computer hardware arrangements.

[0083] Although the embodiments have been described in detail, it should be understood that various changes, substitutions and alterations can be made herein.

[0084] Moreover, the scope of the present application is not intended to be limited to the particular embodiments of the process, machine, manufacture, composition of matter, means, methods and steps described in the specification.

[0085] As can be understood, the examples described above and illustrated are intended to be exemplary only.

Claims

WHAT IS CLAIMED IS:

1. A system for recommending a hairstyle, the system comprising: at least one processor; and a memory storing instructions which when executed by the at least one processor configure the at least one processor to: receive an input image of a user; locate a face of the user in the input image; extract facial features of the user; determine similar model faces to that of the user from a data repository based on the user facial features; and recommend a hairstyle for the user based on a hairstyle score associated with the model faces.

2. The system as claimed in claim 1 , wherein the at least one processor is configured to: receive a target hairstyle of a model; swap the face of the user with the model having that hairstyle; refine the image; and display the refined image.

3. The system as claimed in any one of claim 1 or claim 2, wherein the hairstyle includes at least one of: natural hair of the model; a wig; a toupee; a closure; a frontal; a hairline transplant; orany combination thereof.

4. A computer-implemented method of recommending a hairstyle, the method comprising: receiving an input image of a user; locating a face of the user in the input image; extracting facial features of the user; determining similar model faces to that of the user from a data repository based on the user facial features; and recommending a hairstyle for the user based on a hairstyle score associated with the model faces.

5. The method as claimed in claim 4, comprising: receiving a target hairstyle of a model; swapping the face of the user with the model having that hairstyle; refining the image; and displaying the refined image.

6. The computer-implemented method as claimed in any one of claim 4 or claim 5, wherein the hairstyle includes at least one of: natural hair of the model; a wig; a toupee; a closure; a frontal; a hairline transplant; or any combination thereof.

7. A system for non-invasively measuring biomarkers through the scalp via a system comprising: at least one processor, anda memory storing instructions which when executed by the at least one processor configure the at least one processor to: receive biomarker data from at least one sensor attached to a hair system cap; and send the biomarker data to a biomarker monitoring subsystem.

8. The system as claimed in claim 7, wherein the biomarker data comprises at least one of temperature, humidity, pulse oximetry, heart rate or mixed vitals.

9. The system as claimed in claim 7, wherein the biomarker data is transmitted over a secure link to a secure link-enabled subsystem.

10. The system as claimed in 7, wherein to receive biomarker data from the scalp the at least one processor is configured to: enter into a loop and read off sensor values for individual biomarker datum; and measure values over a timeframe and algorithmically package a sample.

11. The system as claimed in 11, wherein to send data over a secure link, the at least one processor is activated to emit packets over the secure link in a defined protocol, the at least one processor configured to: determine interval to send data; apply a method to save battery life; and acknowledge data has been sent.

12. The system as claimed in any one of claims 7 to 11 , wherein the hair system cap comprises at least one of: a wig cap; a toupee cap; a closure cap; a frontal cap; a hairline transplant cap; orany combination thereof.

13. A computer-implemented method of non-invasively measuring biomarkers through the scalp via a hair system, the computer-implemented method comprising: receive biomarker data from at least one sensor attached to a hair system cap; and send the biomarker data to a biomarker monitoring subsystem.

14. The computer-implemented method as claimed in claim 13, wherein the biomarker data comprises at least one of temperature, humidity, pulse oximetry, heart rate or mixed vitals.

15. The computer-implemented method as claimed in claim 13, wherein the biomarker data is transmitted over a secure link to a secure link-enabled subsystem.

16. The computer-implemented method as claimed in 13, wherein to receive biomarker data from the scalp comprises: entering into a loop and read off sensor values for individual biomarker datum; and measuring values over a timeframe and algorithmically package a sample.

17. The computer-implemented method as claimed in 16, wherein to send data over a secure link comprises emitting packets over the secure link in a defined protocol, wherein the computer- implemented method further comprises: determining an interval to send data; applying a method to save battery life; and acknowledging data has been sent.

18. The computer-implemented method as claimed in any one of claims 13 to 17, wherein the hair system cap comprises at least one of: a wig cap; a toupee cap; a closure cap; a frontal cap;a hairline transplant cap; or any combination thereof.

Images