SYSTEM INCLUDING DEVICES AND ALGORITHMS TO ASSESS SCALP AND HAIR HEALTH

Abstract

SYSTEM INCLUDING DEVICES AND ALGORITHMS FOR ASSESSING SCALP AND HAIR HEALTH. Device for detecting a scalp condition, wherein the scalp condition includes at least the presence or absence of dandruff, including at least one camera configured to view a user's scalp, a diffusion cone arranged around the at least one camera, a lighting module including at least one light source, wherein the at least one light source is configured to emit light under a plurality of lighting conditions, and a processor configured to receive image data from the at least one camera captured during at least one lighting condition from the plurality of lighting conditions, and transmit the image data to an intelligent device for detecting the scalp condition. Figure for abstract: 1

Description

Title of the invention: SYSTEM INCLUDING DEVICES AND ALGORITHMS FOR ASSESSING SCALP AND HAIR HEALTH SUMMARY

[0001] This summary is provided to present a selection of concepts in a simplified form, which are described in greater detail below in the detailed description. This summary is not intended to identify key features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0002] In one aspect, a device for detecting a scalp condition, a hair condition, or both is disclosed herein, where the scalp condition includes at least the presence or absence of dandruff, and the hair condition includes the presence or absence of hair, including at least one camera configured to view a user's scalp, a diffusion cone disposed around at least one camera, a lighting module including at least one light source, where at least one light source is configured to emit light in a plurality of lighting conditions, and a processor configured to receive image data from at least one camera captured during at least one lighting condition from the plurality of lighting conditions, and to transmit the image data to an intelligent device for detecting the scalp condition, the hair condition, or both.

[0003] In some embodiments, the image data comprises a set of images at a location on the user's scalp under each lighting condition of the plurality of lighting conditions. In some embodiments, the plurality of lighting conditions includes a white light condition, a cross-polarized light condition, an ultraviolet (UV) light condition, or a combination thereof. In some embodiments, under the white light condition, white light is emitted in at least one brightness mode of a plurality of brightness modes.

[0004] In some embodiments, at least one camera is a three-lens camera, and where each lens of the three-lens camera has a different focal length.

[0005] In another aspect, a system for detecting a scalp condition, a hair condition, or both is disclosed herein, where the scalp condition includes at least the presence or absence of dandruff, and the hair condition includes the presence or absence of hair, the system including the device as described herein and an intelligent device, where the intelligent device includes a processor of intelligent device, and where the intelligent device processor is configured to receive image data from the device, input an image of the image data in a lighting condition of the plurality of lighting conditions, determine one or more areas of one or more detected features at a pixel level of the image, and display the one or more areas superimposed on the image data.

[0006] In certain embodiments, the intelligent device processor is further configured to segment, at a pixel level, the image data, locate the segmented films, classify the segmented films on the basis of a number of films, a film size and a film shape on the basis of statistical data on the films, provide as output a film severity score and display contour segments of the films superimposed on the image data.

[0007] In certain embodiments, the intelligent device processor is further configured to segment hair strands in the image data based on color, determine the position and direction of the hair strands, measure individual diameters of one or more of the hair strands, determine an average hair diameter, and output a hair score based on the hair condition, wherein the hair score includes an average hair strand diameter, a percentage of white or gray hair, root color detection, or a combination thereof. In certain embodiments, the intelligent device processor is further configured to estimate a number of hair roots in the image data and output the hair score, wherein the hair score further includes a probability of hair loss.

[0008] In some embodiments, a 3-layer convolutional neural network (CNN) having the same structure with different weight sets is used to predict the severity of the dandruff score and a level of scalp redness.

[0009] In certain embodiments, the intelligent device processor is further configured to display hair strands and roots of image data in a plurality of colors on a black background, where the plurality of colors corresponds to individual diameters of one or more of the hair strands. In certain embodiments, the intelligent device processor is further configured to indicate on the displayed image data when a hair strand is smaller than a diameter threshold.

[0010] In certain embodiments, the intelligent device processor is further configured to detect one or more colors on a pixel level in the porphyrin-indicative image data; determine a number, a size, a shape, or one of their combinations, of porphyrins, provide as output a porphyrin score and display outlines of detected porphyrins superimposed on the image data.

[0011] In yet another aspect, a method for detecting a scalp condition is disclosed herein, wherein the scalp condition includes at least the presence or absence of dandruff, the method comprising placing the device described herein on the user's scalp, emitting light in a plurality of lighting conditions, capturing image data of the user's scalp in each lighting condition of the plurality of lighting conditions, transmitting the image data to an intelligent device processor, analyzing each image of the image data in each lighting condition of the plurality of lighting conditions, detecting one or more areas of one or more detected features at a pixel level of the image, and displaying the detected areas superimposed on the image data.

[0012] In some embodiments, the method further includes segmenting, at a pixel level, films in the image data, classifying the segmented films according to the number of films, the size of the films and the shape of the films on the basis of statistical data on the films, providing as output a film severity score and displaying contour segments of the films superimposed on the image data.

[0013] In some embodiments, the method further comprises segmenting, at a pixel level, strands of hair in the image data on the basis of color, determining a position and direction of the strands of hair, measuring individual diameters of one or more of the strands of hair, determining an average hair diameter and providing as output a hair score, wherein the hair score includes an average diameter of the hair strands, a percentage of white or gray hair, a root color detection, or one of their combinations.

[0014] In some embodiments, the method further includes estimating the number of hair roots in the image data and providing an output of a hair score, in which the hair score includes a probability of hair loss.

[0015] In some embodiments, the method further includes storing image data of one or more areas, one or more states of the scalp, or a combination thereof, as historical data, and tracking the historical data over time to determine a change in one or more states of the scalp.

[0016] In some embodiments, the method further includes the detection of one or more colors on a pixel level in the image data indicative of porphyrins, the determination of a number, size, shape, or one of their combinations, of the porphyrins, the output provision of a porphyrin score and the display of the contours of the detected porphyrins superimposed on the image data.

[0017] In some embodiments, the method further includes the recommendation of one or more treatments for one or more scalp conditions. Description of the drawings

[0018] The foregoing aspects and many related advantages of this invention will be more readily appreciated as they are better understood with reference to the following detailed description, when taken in conjunction with the accompanying drawings, in which:

[0019] [Fig.1A] Fig.1A is a side perspective view of an example of a scalp condition detection device according to the present technology;

[0020] [Fig.IB] Fig.IB is a perspective front view of an example of a scalp condition detection device according to the present technology;

[0021] [Fig.lC] The [Fig.lC] is a perspective front view of another example of a scalp condition detection device, according to the present technology;

[0022] [Fig. 1D] The [Fig. 1D] is an example of an optical sensor for detecting a condition of the scalp, according to the present technology;

[0023] [Fig.2] The [Fig.2] is an example illustrating a plurality of brightness modes, in accordance with the present technology;

[0024] [Fig.3A]-[Fig.3C] Figures 3A to 3C are examples of image data of a scalp under different lighting conditions of a plurality of lighting conditions, in accordance with the present technology.

[0025] [Fig.4A] The [Fig.4A] is a functional diagram of an example of a scalp condition detection system, according to the present technology;

[0026] [Fig.4B] The [Fig.4B] is another functional diagram of an example of a scalp condition detection system, according to the present technology;

[0027] [Fig.4C] The [Fig.4C] is an example of a scalp condition detection system, in accordance with the present technology;

[0028] [Fig.5] The [Fig.5] is an illustration of an example of a device in use, in accordance with the present technology;

[0029] [Fig.6A]-[Fig.6J] Figures 6A to 6J are examples of visualizations, in accordance with this technology;

[0030] [Fig.7] The [Fig.7] is an example of a method for detecting a condition of the scalp, in accordance with the present technology;

[0031] [Fig.8] The [Fig.8] is another example of a method for detecting a condition of the scalp, in accordance with the present technology;

[0032] [Fig.9] Fig.9 is yet another example of a method for detecting a scalp condition according to the present technology; and

[0033] [Fig.10A]-[Fig.10G] Figures 10A to 10G show an example of model training and validation for scoring, dandruff segmentation and hair segmentation. Detailed description

[0034] Dandruff is a common condition that causes the scalp to peel. Symptoms include flaking and sometimes mild itching. This can lead to social or self-esteem problems. Although dandruff can be detected by visual inspection, it can be difficult to determine its classification, whether a dandruff treatment is effective, and what the cause of the dandruff might be. For example, dandruff can be caused by the fungus Malassezia, a naturally occurring organism found on the skin and scalp. Dandruff can also be caused by oily hair, psoriasis, or eczema. In each case, the treatments differ.

[0035] Porphyrins are intermediate metabolites in the biosynthesis of vital molecules, including thyroglobulin, cobalamin, and chlorophyll. Bacterial porphyrins are known to be pro-inflammatory, with elevated levels linked to inflammatory skin diseases. Porphyrins on the scalp can cause inflammation, redness, sores, and acne. It can also be difficult to detect porphyrins on the scalp and therefore to treat them.

[0036] In addition, an individual may wish to know and / or treat other scalp conditions, such as hair health, the presence of oil, the diameter of hair strands, hair diversity / thickness, grey hair, and the like.

[0037] A scalp and / or hair reader, or a device equipped with machine learning algorithms for quantitatively analyzing the scalp and hair health of consumers based on images, is described herein. The device is used to capture images of the scalp under multiple lighting conditions. The results of the scalp and hair health assessments are analyzed and delivered to consumers. Scores are provided for scalp dandruff level, porphyrin level, hair diameter, and hair follicle count. Based on the images captured by the device, predictions are made by algorithms. In some embodiments, the analysis is based on an overall scalp health index and / or an overall hair loss risk index, which are correlations based on the output of the algorithms and / or responses to a user questionnaire. Areas requiring care on the observed scalp and the diversity of fiber diameters are also detected and visualized by algorithms. Recommended products and treatments can then be provided based on the analysis results.

[0038] In certain embodiments, a set of algorithms is used that take raw scalp images as input and predict scores corresponding to the scalp dandruff level, porphyrin level, redness level, average hair diameter, and number of roots, respectively. In addition to the score predictions, visualizations of segmented dandruff, porphyrins, hair fibers, and hair roots are masked by algorithms. The score prediction and visualization algorithms for all the aforementioned scalp and hair parameters are built on the basis of deep learning models and conventional image processing methods. In one example, the deep learning models include deep learning models based on a convolutional neural network (CNN).Statistical data, such as the number and size distribution of dandruff / porphyrins and the diameters of hair fibers, are analyzed by the algorithms. To ensure the accuracy of the algorithms, a large dataset of scalp images was collected. The algorithms were trained and tested on this specially collected dataset for high accuracy.

[0039] Fig. 1A is a side perspective view of an example of device 100 detection of a scalp condition, in accordance with the present technology. In some embodiments, the device 100 includes a diffusion cone 105, a body 110, one or more actuators 115A, 115B, 115C, a processor 120, a power indicator 125 and a battery 130.

[0040] In some embodiments, the scattering cone 105 is a projection located on a front side of the body 110. The scattering cone can be configured to be widest towards the body 110 and taper as it extends from the body 110. In some embodiments, a length of the scattering cone is determined based on the distance required for an optical sensor (as shown in [Fig. 1B]) to capture image data of a scalp when one end of the scattering cone 105 comes into contact with the scalp (as shown in [Fig. 5]). In some embodiments, the scattering cone 105 is configured to block the light from a light source (as shown in Figures IB and 1D) so that an optical sensor can capture image data of the scalp under a particular light condition, as described in detail here.

[0041] While the body 110 is shown as a cylinder in [Fig. IA], it should be understood that the body 110 can have any form factor. In some embodiments, the body 110 is rounded, angular, organically shaped, or similar. In some embodiments, the body 110 is made of plastic, metal, ceramic, or a combination thereof. In some embodiments, the body 110 is configured to be held in the hand of an operator or user. In some embodiments, a hair clip (not shown in [Fig. 1A]) can be used to hold the hair in place and allow the device 100 to better visualize the scalp and / or hair.

[0042] One or more actuators 115A, 115B, 115C can be configured to perform a variety of functions, including, but not limited to, turning device 100 on / off, emitting or stopping the emission of light from a light source (as shown in Figures IB to ID), changing a lighting condition or light mode of the light, as explained herein, capturing scalp image data, and / or pairing device 100 with another device (such as smart device 1000 in [Fig.4C]) via a wireless connection, such as Wi-Fi, Bluetooth LTETM, Zigbee or similar. In some embodiments, actuators 115A, 115B, 115C are buttons, but in other embodiments, actuators 115A, 115B, 115C may be switches, touch-type capacitive buttons, levers, or the like.

[0043] Those skilled in the art should understand that the processor 120 is internal to the body 110 but is illustrated in [Fig. 1A] for clarity. In some embodiments, the processor 120 is configured to capture and store image data from one or more optical sensors (as shown in Figures 1B to 1D), control one or more light sources, and / or transmit image data to another device (such as the smart device 1000 in [Fig. 4C]). In some embodiments, the processor is configured to communicate with a smart device via a wireless or wired connection.

[0044] In some embodiments, the device 100 includes a power indicator 125. In some embodiments, the power indicator 125 indicates the power level of the device. In some embodiments, the power indicator 125 is configured to emit a variety of colors to convey the status of the device 100, such as green for charged, red for low power, yellow for charging, or similar. In some embodiments In realization, the power indicator 125 can indicate a device status that is not related to the power supply of device 100, such as flashing to indicate that device 100 is paired with an external device, using a flash to indicate that image data has been captured, a color associated with a particular light condition, or similar.

[0045] The battery 130 may be internal or external to the device 100. In some embodiments, the battery 130 may be accessed by removing one end of the device 100. In some embodiments, the battery 130 is a single-use battery, but in other embodiments, the battery 130 is a rechargeable battery or a capacitor. In some embodiments, the battery 130 may be charged via a wired or wireless connection.

[0046] In operation, the device 100 is configured to be held by a user or operator, such as a beauty salon technician or pharmacist. In some embodiments, the operator places the diffusion cone 105 on a client's scalp, as shown in [Fig. 5]. In some embodiments, the operator moves the client's hair aside, for example, by manually moving it, brushing it, or securing it with a clip or other fastener. In some embodiments, the diffusion cone 105 separates one or more optical sensors, light sources, or the like from the scalp so as to capture image data and / or emit light under a plurality of lighting conditions (as described in Figures 1B to 1D). The operator can actuate one or more actuators 115A, 115B, 115C to start and / or stop image data capture.After capturing image data under one or more lighting conditions, the processor 120 can transmit the image data to an external device for processing and / or detecting a scalp condition. As used here, a scalp condition includes at least the presence or absence of dandruff, the presence or absence of porphyrin, the presence or absence of oil, the presence or absence of gray hair, hair thickness, the likelihood of hair loss, hair diversity, and / or the presence or absence of redness. In some embodiments, the diagnosis of the hair and / or scalp condition is determined with a single "point," i.e., when multiple images are taken from a single location on the scalp. In other embodiments, the diagnosis of the hair and / or scalp condition is determined with multiple "points."In such embodiments, a user or operator can move the device 100 to multiple locations on the scalp. The image data from each of these locations can be analyzed separately, or together, to determine the condition of the hair and / or scalp. In some embodiments, the device... 100 can request the user to move the device 100 to multiple locations, for example with a vibration, an alert, a tone, or another instruction.

[0047] Figure 1B is a perspective front view of an example of a scalp condition detection device 100 according to the present technology. In some embodiments, the device 100 includes a scattering cone 105, a body 110, a light source 135, and an optical device 140. Figure 1B shows one end of the scattering cone 105. In some embodiments, the light source 135 and the optical device 140 are located on the body 110, but inside the scattering cone 105.

[0048] In some embodiments, the light source 135 is a light-emitting diode (LED). In some embodiments, the light source 135 is configured to emit light under a plurality of lighting conditions (as shown in Figures 3A to 3C). In some embodiments, the plurality of lighting conditions includes white light (i.e., light emitted at a wavelength of 400 to 700 nm), cross-polarized light (i.e., where two polarizers oriented perpendicular to each other are used on incident and reflected light), and / or ultraviolet (UV) light (i.e., light emitted at a wavelength of 100 to 400 nm). In some embodiments, the light source 135 is also configured to emit white light in a plurality of brightness modes (as shown and described in [Fig.2]).

[0049] In some embodiments, the optical device 135 is a camera. In some embodiments, the optical device 135 is configured to capture image data of a scalp. In some embodiments, the optical system 135 is a single-lens camera. In some embodiments, the optical device 135 is communicatively coupled to a processor (such as the processor 120). In some embodiments, the optical device 135 transmits the captured image data to the processor.

[0050] During operation, a user or operator places the diffusion cone 105 on the scalp. The light source 135 emits light under a first light condition from the plurality of light conditions. The optical sensor 140 can then capture image data of the scalp under the first light condition. In some embodiments, the image data is one or more still images, but in other embodiments, the image data can be a video. The light source 135 can then emit a second light condition from the plurality of light conditions. The optical sensor 140 can then capture image data of the scalp under the first light condition. This This process is repeated until the optical sensor 140 captures image data under all lighting conditions of the plurality of lighting conditions or under a predetermined subset of the lighting conditions of the plurality of lighting conditions. A processor (such as the processor 120) can then transmit the image data captured by the optical sensor 140 to an external device (such as the intelligent device 1000 in [Fig. 4C]).

[0051] Figure [IC] is a perspective front view of another example of a scalp condition detection device 100 according to the present technology. In some embodiments, the device 100 includes a plurality of light sources 135A, 135B, 135C.

[0052] In certain embodiments, each light source of the plurality of light sources 135A, 135B, 135C is configured to emit a different light condition from the plurality of light conditions. For example, if there are three light sources of the plurality of light sources 135A, 135B, 135C, a first light source 135A can emit white light, a second light source 135B can emit cross-polarized light, and a third light source 135C can emit UV light.

[0053] Figure 1D is an example of an optical sensor 140 for detecting a scalp condition, according to the present technology. In some embodiments, the optical sensor 140 is a camera. In some embodiments, the optical sensor 140 is a three-lens camera. In some embodiments, the optical sensor has a first lens 145A, a second lens 145B, and a third lens 145C. In some embodiments, each lens 145A, 145B, and 145C of the three-lens camera has a different focal length.

[0054] In operation, each lens in the optical sensor 140 is configured to capture image data at a predetermined focal length, so that multiple focal length images of the scalp can be captured. In some embodiments, instead of a three-lens camera, the optical sensor 140 is a plurality of optical sensors, each optical sensor being configured to capture image data at a plurality of focal lengths.

[0055] Figure 2 is an example illustrating a plurality of brightness modes according to the present technology. In some embodiments, one or more light sources (as shown in Figures IB and IC) are configured to emit light in a plurality of brightness modes (or "light"). While five modes are shown in Figure 2, it should be understood that any number of light modes can be emitted by one or more light sources. In some embodiments, as the number of light modes increases, the brightness level of the The light level decreases (i.e., Mode 5 is the darkest and Mode 0 is the brightest). In some embodiments, a processor (such as processor 120) controls the brightness mode based on the light detected by an optical sensor (such as optical sensor 140). In some embodiments, one or more actuators (such as one or more actuators 115A, 115B, 115C) can be actuated to control the brightness mode.

[0056] Figures 3A to 3C are examples of image data of a scalp under various lighting conditions, in accordance with the present technology. [Fig. 3A] shows image data of a scalp under white light, [Fig. 3B] shows an image of the scalp under cross-polarized light, and [Fig. 3C] shows an image of the scalp under UV light. In each lighting condition, different scalp conditions can be detected, such as dandruff, redness, irritation, acne, inflammation, and / or porphyrins.

[0057] For example, under white light, as shown in [Fig. 3A], hair segmentation algorithms can be applied to detect hair characteristics such as hair color (such as black and white hair), hair roots, hair root color, and the like. Under cross-polarized light, as shown in [Fig. 3B], acne, inflammatory dermatoses, redness, dandruff, and bruising can be detected. Under UV light, as shown in [Fig. 3C], porphyrins can be detected, as shown by the lighter spots (or "detected areas").

[0058] Figure 4A is a functional diagram of an example of a scalp condition detection system 4000, according to the present technology. In some embodiments, the system 4000 includes a device 100 (as shown in Figures IA in 1D), an intelligent device (or "scalp reader system") 1000, and an application 1040. In some embodiments, the application 1040 is downloaded onto the intelligent device 1000, but in other embodiments, it can be separate from the intelligent device, such as on a browser of another external device.

[0059] As shown in Figures IA in 1D, the device 100 can include a camera module (or optical device) 140, a lighting adjustment module (or light source) 135 and a transmission module (or processor) 120. As described here, in operation, the device 100 captures image data with the camera module 140 in a plurality of light conditions emitted by the lighting adjustment module 135 and transmits this image data to the intelligent device 1000 with the transmission module 120.

[0060] In some embodiments, the scalp reader system 1000 includes an image capture module 10, a feature notation module 20 and a result analysis module 30.

[0061] In some embodiments, the image capture module 10 is configured to receive a set of images of the scalp (or "image data") under three or more lighting conditions (as shown in Figures 3A to 3C).

[0062] In some embodiments, the feature scoring module 20 receives an image under a specific lighting condition as input and provides a corresponding score as output that reflects one or more scalp states (such as the level of dandruff or redness for an image under cross-polarized lighting). In some embodiments, the feature scoring module 20 applies a deep learning algorithm to the input to determine the score. For example, in some embodiments, the feature scoring module 20 applies deep learning models (such as a 3-layer convolutional neural network (CNN)) having the same structure but different weight sets to predict the dandruff level and redness level scores, respectively.

[0063] In some embodiments, the outcome analysis module 30 is configured to generate, based on the above score, a scalp and hair health analysis report to provide scores on scalp conditions such as dandruff, redness, hair fiber diameter, number of hair roots, risk level of hair loss, porphyrin level, etc. In some embodiments, the outcome analysis module 30 applies a deep learning algorithm to the input to determine the score. The intelligent device 1000 can include any number of additional modules, as shown in [Fig. 4B].

[0064] The application 1040 can be located on the intelligent device 1000. In some embodiments, the application 1040 includes a live streaming module 1041, a transmission module 1042 and one or more display modules 1043.

[0065] In some embodiments, the live streaming module 1041 is configured to display or show the image data received by the device 100. For example, if the image data is a video or a live stream, the live streaming module 1041 can display the image data in real time as an operator moves the device over an individual's scalp. In some embodiments, the image data is one or more photos. In such embodiments, the live streaming module 1041 can be omitted, or it can be configured to display the image data as photos.

[0066] The transmission module 1042 is configured to transmit information to a device operator and / or to one or more algorithms of the intelligent device 1000 for processing.

[0067] In certain embodiments, the display module 1043 is configured to display one or more overlays on the image data associated with a detected scalp condition, as explained in detail here.

[0068] In one example, the system in [Fig. 4A] is configured to detect dandruff and / or redness of the scalp. In such embodiments, the image capture module 10 obtains a set of images of the scalp at a location in three lighting modes. The feature scoring module 20 inputs one image of the image data in a specific lighting mode at a time and outputs the corresponding score that reflects the scalp conditions (for the level of dandruff or redness). Deep learning models (such as the 3-layer CNN) having the same structure but different sets of weights are used to predict the score for the level of dandruff and the level of redness, respectively.

[0069] Figure 4B is another functional diagram of an example of a 4000 scalp condition detection system according to the present technology. In some embodiments, the 4000 system also includes one or more scoring modules, one or more segmentation modules, one or more post-processing modules, a statistical module, a segment tracking module, a scoring calculator, and a visualization module. In some embodiments, each of these modules is located on an intelligent device (such as the 1000 intelligent device). In some embodiments, one or more of these modules may be omitted.

[0070] At block 405, raw images are obtained. Generally, the 4000 system is configured to receive image data from a device (such as device 100). This image data can be called "raw images." Raw images can also be images taken by the device that have not been filtered or modified.

[0071] In block 410A, a scoring module applies an algorithm to the raw images based on the lighting conditions under which each image was captured, one or more colors in the image, or both. For example, if the raw image was taken in white light, the scoring module can generate a redness score, such as a percentage of redness present in the image, a shade of redness, or something similar. As another example, if the raw image was taken in UV light, the scoring module can detect porphyrins based on one or more colors in the raw image.

[0072] In block 415A, scores are generated by the scoring module. In some embodiments, only one score is generated, such as a redness score. In some embodiments, multiple scores are generated simultaneously, such as a dandruff score and a redness score.

[0073] Returning to block 405, in some embodiments, the raw images are also entered into one or more segmentation modules.

[0074] In block 410B, one or more segmentation modules receive the raw images as input and provide as output individual segments of hair and / or scalp features. In some embodiments, one or more areas of one or more features detected at a pixel level of the image are determined by the segmentation module.

[0075] In block 415B, individual segments of the detected features are output. In some embodiments, the features include dandruff, strands of hair (or "fibers"), hair roots, or the like. In some embodiments, blocks 410A and 410B occur either simultaneously or sequentially. In some embodiments, only block 410A or 410B is performed.

[0076] In block 420, one or more post-processing modules receive the scores and / or individual feature segments from blocks 415A and / or 415B, respectively. In some embodiments, the post-processing modules include a statistical module 425A, a segment tracking module 425B, a score calculator 425C, and / or a visualization module 425D.

[0077] In blocks 430A and 430B, the output of one or more of the post-processing modules is used to generate an analysis report (430A) and / or visualize one or more areas or regions in need of care (430B).

[0078] In block 435, products and / or treatments are recommended. In some embodiments, the products and / or treatments are recommended by application 1040.

[0079] In one example, the system 400 is configured to determine one or more scalp conditions, such as dandruff, hair quality, and / or hair roots. In such examples, the image capture module (such as the image capture module 10) is used to obtain a set of images of the scalp at a location under a plurality of lighting conditions. In some embodiments, the plurality of lighting conditions includes white light, UV light, and / or cross-polarized light. Then, the feature segmentation module 410B receives an input of image data under a specific light pattern at a time and outputs areas of detected features at a pixel level with a probability (between 0 and 1) in terms of scalp or hair conditions. In some embodiments, learning models Deep models (such as U-net) with the same structure and different weight sets are used to segment dandruff and hair fiber / root, respectively. For the dandruff segmentation model, the outputs are the dandruff class and scalp class per pixel. For the hair segmentation model, the outputs are five classes: black fiber, black fiber root, white fiber, white fiber root, and scalp, per pixel.

[0080] A segment tracking module (425B) is implemented specifically for capillary fiber detection. Within the segment tracking module, a fiber tracking function is configured to locate the position and direction of the fibers at a pixel level based on the segmented capillary fiber result.

[0081] In some embodiments, a statistical analysis module (425A) is implemented. For dandruff, the statistical analysis module locates the segmented dandruff class at a pixel level and calculates the number, size, and shape of the dandruff flakes. For dandruff, the dandruff types are classified based on the statistical data of the dandruff segments. For hair fibers, a diameter sampling function has been implemented to collect individual fiber diameters by sampling. For hair roots, a density estimation function can count the number of hair roots.

[0082] In some embodiments, a scoring module (425C) may be implemented. In some embodiments, the scoring module determines the mean and median quarters of the dandruff and / or hair fiber size. The diameter may be calculated by a function. For hair fibers, the hair fiber diameter score is calculated based on the mean fiber diameter. Similarly, a hair loss risk score is calculated by a hair diversity function and, optionally, information collected by a questionnaire. The hair diversity function may classify the sampled fibers according to diameter into three classes ranging from fine to thick. A hair diversity score is calculated based on the result of comparing the mean diameter and the number of fibers for the three fiber classes.

[0083] In some embodiments, a viewing module (425D) is implemented. For film, the contours of the segmented film on the raw images are masked by viewing functions (as shown in Figures 6A to 6F). In some embodiments, for hair, the hair fibers and roots are masked with different colors against a black background of functionalized scalp. In some embodiments, for fine fibers with a diameter less than a threshold value, a pointer will be shown on the raw image by a viewing function.

[0084] In another example, the 4000 system can detect the presence / absence and / or a severity score of porphyrins. In such embodiments, the image capture module obtains a set of images of the scalp at a location in three lighting modes. The feature detection module receives one image at a time in a UV light mode. The feature detection module detects areas of a specific color that indicates porphyrins in the UV images. In some embodiments, a traditional image processing method based on a python-opencv package can be used to filter pixels whose color lies within the determined RGB value range. Then, the feature scoring module can determine the number, size, and shape of the detected porphyrins using a function. A porphyrin score can be calculated based on the fraction of the porphyrin area in the raw image.The visualization module can display the outlines of porphyrins detected on raw images masked by visualization functions.

[0085] Figure 4C is an example of the scalp condition detection system 4000, according to the present technology. As explained herein, in some embodiments, the system 4000 includes a device 100 and an intelligent device 1000. The intelligent device 1000 can host an application 1040 described herein. In some embodiments, the device 100 and the intelligent device 1000 are coupled communicatively, for example, by a wireless connection. Examples of wireless connections include Wi-Fi, Zigbee, and Bluetooth LTE.

[0086] Figure 5 is an illustration of an example of device 100 in use, In accordance with this technology, an operator, such as a hairdresser, pharmacist, dermatologist, or similar professional, can visualize an individual's scalp by placing the diffusion cone on the scalp. In certain embodiments, an operator can use the device and application to offer a more professional and personalized scalp and hair care service in hair salons. Highly accurate and quantitative results describing scalp and hair health based on multiple parameters can be delivered to help establish a scientifically based, diagnostic treatment product / service in the hair salon.

[0087] Figures 6A to 6J are examples of visualizations according to the present technology. In certain embodiments, after processing the raw image data and detecting one or more scalp states, the intelligent device 100, via an application, displays the image data including one or more overlays.

[0088] Figures 6A to 6F are visual representations of the visualizations used to clearly show concepts, while Figures 6G to 6J are photographs of examples of similar visualizations. Consequently, in Figures 6A to 6F, the intelligent device 1000, image data 1002, hair strands 1007A, 1007B, 1007C... and a score 1003 are represented.

[0089] For example, Figures 6A and 6G both show an image of the scalp without overlay. In such examples, no scalp conditions were detected. As shown in 6A, image data 1002 represents multiple hair strands 1007A, 1007B, 1007C... and no detection area, because no scalp conditions were detected. A score 1003 is provided as output depending on whether scalp conditions (and their severity) were detected.

[0090] On [Fig.6B], porphyrins 1008A, 1008B... are shown superimposed on image data 1002. Consequently, score 1003 would reflect the presence of porphyrins and / or porphyrin intensity based on the size, shape and / or number of porphyrins.

[0091] On [Fig.6C], films 1009A, 1009B... are shown superimposed on image data 1002. Consequently, score 1003 would reflect the presence of films, a classification of films, or both, based on the size, shape and / or number of films.

[0092] In [Fig. 6D], strands of hair are represented with different types of dashes to represent different thicknesses. [Fig. 6D] is a visual representation of the photograph in [Fig. 0J]. In some embodiments, the thickness of the hair strand is indicated by different colors. In some embodiments, the thickness of the hair strand can be classified in other ways, for example with labels as shown in [Fig. 0J]. The thickness of the hair strand, as explained here, is determined on the basis of the diameter of the hair strand. The score of 1003 in [Fig. 0D] would be based on a certain number of hair strands in each of the diameter categories. In some embodiments, a low score of 1003 is indicative of potential hair loss.

[0093] In some embodiments, fine hairs are indicated by one or more indicators, as shown graphically in [Fig. 0E] and photographically in [Fig. 61]. In some embodiments, the one or more indicators 101 IA, 1011B, 1011C are pointers or arrows.

[0094] In [Fig. 0H], the hair roots are identified. In some embodiments, the superimposition visualizes the hair strands and / or the hair roots.

[0095] In [Fig. 6F], multiple overlays are shown on a single image 1002. In some embodiments, several of the visualizations shown in Figures 6A to 6J can be generated and overlaid on a single image. For example, Figure 6F shows multiple skin conditions, including detected porphyrins 1008A, 1008B..., dandruff 1009A, 1009B..., and fine hair indicators 101IA, 101IB, 101IC. In such cases, all these features can be shown on a single image 1002. Although the score 1003 can be a general hair or scalp health score, in some embodiments, an independent score 1003 is generated for each condition (i.e., a dandruff score, a porphyrin score, a hair diversity score, and the like).

[0096] Figure 7 is an example of a method 700 for detecting a scalp condition according to the present technology. In some embodiments, the method 700 can be carried out with a device (such as device 100) having an optical sensor (such as optical sensor 140) and a light source (such as light source 135). The device can be communicatively coupled to an intelligent device (such as intelligent device 1000) having an application (such as application 4000). The device, the intelligent device, and the application can be referred to herein as a system (such as system 4000). In some embodiments, the system includes one or more scoring modules, one or more segmentation modules, one or more post-processing modules, a statistical module, a segment tracking module, a scoring calculator, and a visualization module (as shown in Figures 4A to 4C).In some embodiments, each of these modules is located on an intelligent device. In some embodiments, one or more of these modules may be omitted.

[0097] In block 705, the device is placed on the user's scalp. In some embodiments, this can be done by a hairdresser, pharmacist, dermatologist, or similar professional.

[0098] In block 710, the light is emitted by the light source in a plurality of lighting modes (or conditions). In some embodiments, the plurality of lighting conditions includes white light, UV light, and / or cross-polarized light. In some embodiments, the light is emitted in one of a plurality of brightness modes (as shown in Figure 3).

[0099] In block 715, image data of the user's scalp is captured with the optical device. The image data (or "raw images") can be video or still images. In some embodiments, the image data is a live, real-time stream of the scalp. In some embodiments, the image data is captured during each lighting condition (or a subset of lighting conditions) of the plurality of lighting conditions. For example, an image of the image data can be captured in white light, cross-polarized light, and UV light.

[0100] At block 720, the image data is transmitted to the intelligent device. In some embodiments, this is facilitated by a processor (such as processor 120) over a wired or wireless connection (such as Wi-Fi, Bluetooth LTE or Zigbee).

[0101] In block 725, each image of the image data is analyzed with one or more algorithms as described herein. For example, in some embodiments, each image of the image data is analyzed with one or more scoring modules, one or more segmentation modules, one or more post-processing modules, the statistical module, the segment tracking module, the scoring calculator and / or the visualization module.

[0102] In block 730, areas of detected features are detected at a pixel level (as with the segmentation module described here). In some embodiments, the detected features include dandruff, redness, porphyrins, hair thickness, hair diversity, and the like.

[0103] In block 735, the detected areas (or features) are visually overlaid on the image data. Examples of this visual overlay are shown and described in Figures 6A to 6J. In some embodiments, the visual overlay is accompanied by a score (such as score 1003) and / or a report. In some embodiments, the score and / or report provide a diagnosis of one or more scalp conditions. In some embodiments, the report may also provide a treatment recommendation.

[0104] Figure 8 is another example of a method 800 for detecting a scalp condition according to the present technology. In some embodiments, the method 800 can be carried out with a device (such as device 100) having an optical sensor (such as optical sensor 140) and a light source (such as light source 135). The device can be communicatively coupled to an intelligent device (such as intelligent device 1000) having an application (such as application 4000). The device, the intelligent device, and the application can be referred to herein as a system (such as system 4000).In some embodiments, the system includes one or more scoring modules, one or more segmentation modules, one or more post-processing modules, a statistical module, a segment tracking module, a scoring calculator, and a visualization module (as shown in Figures 4A to 4C). In some embodiments, each of these modules is located on an intelligent device. In some embodiments, one or more of these modules may be omitted. In some embodiments, process 800 is a subset of process 700.

[0105] At block 805, the films are segmented at a pixel level, as described in [Fig.4B]. In some embodiments, a 3-layer CNN algorithm is used to segment the films.

[0106] In block 810, the segmented film strips are classified. The classification may include film size, film shape, number of film strips and / or film type.

[0107] In block 815, an output score is provided regarding the severity / presence of dandruff. In some embodiments, the score is based on the classification in block 810. In some embodiments, the visual overlay is accompanied by a report. In some embodiments, the score and / or the report provide a diagnosis of one or more scalp conditions. In some embodiments, the report may also provide a treatment recommendation.

[0108] In block 820, the identified (or segmented) films are displayed superimposed on the image data, as shown in [Fig.6B].

[0109] Figure 9 is yet another example of a method 900 for detecting a scalp condition according to the present technology. In some embodiments, the method 900 can be carried out with a device (such as device 100) having an optical sensor (such as optical sensor 140) and a light source (such as light source 135). The device can be communicatively coupled to an intelligent device (such as intelligent device 1000) having an application (such as application 4000). The device, the intelligent device, and the application can be referred to herein as a system (such as system 4000).In some embodiments, the system includes one or more scoring modules, one or more segmentation modules, one or more post-processing modules, a statistical module, a segment tracking module, a scoring calculator, and a visualization module (as shown in Figures 4A to 4C). In some embodiments, each of these modules is located on an intelligent device. In some embodiments, one or more of these modules may be omitted. In some embodiments, process 900 is a subset of process 700.

[0110] In block 905, the hair strands are segmented at a pixel level, as described in [Fig.4B]. In some embodiments, a U-net algorithm is used to segment the hair strands.

[0111] In block 910, the segmented hair strands are measured to determine a hair strand diameter. In some embodiments, a hair strand direction and / or a hair strand color can also be determined.

[0112] In block 915, an average hair diameter is determined based on the measurements in block 910.

[0113] At block 920, a number of hair roots is estimated. This can be done by detecting the hair roots as shown in [Fig. 6H].

[0114] In block 925, a score is provided as output for hair. In some embodiments, the score is based on the measurements and metrics in blocks 910, 915, and 920. In some embodiments, the hair score includes hair thickness, probability of hair loss, number (or percentage) of gray hairs, hair diversity, and similar factors. In some embodiments, a visual overlay may also be displayed, as shown in Figures 6G and 6J. In some embodiments, the visual overlay is accompanied by a report. In some embodiments, the score and / or the report provide a diagnosis of one or more scalp conditions. In some embodiments, the report may also provide a treatment recommendation.

[0115] It should be understood that all processes 700, 800, and 900 should be interpreted as merely representative. In some embodiments, the process blocks of all processes 700, 800, and 900 may be carried out simultaneously, sequentially, in a different order, or even omitted, without departing from the scope of this disclosure. Examples

[0116] Figures 10A to 10E show an example of model training and validation for film scoring and segmentation. The algorithm development involves several steps, including data collection, manual labeling, algorithm training, algorithm validation, and so on.

[0117] Fig. 10A is an example of a method for the process of generating a film score.

[0118] At block 305, a raw image under a cross-polarized illumination condition (Xpol) is obtained.

[0119] At block 310, only one image of the raw images is read (as by system 400).

[0120] In block 315, a function (defined as img_matrice_norm_320) normalizes the image and determines the presence or absence of films by segmentation (as shown in [Fig.1OD]).

[0121] At block 320, the segmented image is modified with a function (defined as model_score_films) which compares the detected films to the model described here.

[0122] At block 325, a predicted film score is generated with approximately 0~5 as a base.

[0123] At block 330, this score is converted.

[0124] At block 335, a predetermined film score is generated with approximately 0-100 as a basis.

[0125] The model was trained on 4000 cross-polarized images of different individuals covering multiple types of scalp and hair problems in order to build a large dataset for algorithm development. Each image was labeled with an average Eurosyn dandruff score by experts, using the raw cross-polarized images. This data was then fed into a model having a 3-layer CNN network structure.

[0126] Figure 10B is a graph of the mean error (mean standard deviation for experts). The complete raw image dataset was collected from over 200 volunteers covering multiple scalp and hair tones / types of Asian, Caucasian, and African American individuals. The complete dataset consists of over 10,000 images. For the complete dataset, over 10 experts were engaged to rate the degree of dandruff on a single image. The labels are determined to be the mean of the experts' scores for model training, which serve as the real-world data for the dataset. The mean manual error (mean standard deviation) of the experts' scores is 0.49 (on a scale of 0 to 5) for the level of dandruff, which serves as the benchmark for evaluating the algorithm.For the film scoring prediction module, a 3-layer CNN model was trained on a training dataset consisting of 4000 cross-polarized light images. During the training process, the weights, hyperparameters, and neural network structure were tuned to obtain the best candidate. As shown in [Fig. 1OB], the mean error was 0.49 for the Eurosyn score.

[0127] Figure 100 is a graph of the mean absolute error (MAE) of the model on the test data. A test dataset, 10% the size of the training dataset (400 images for the film scoring model), was constructed to evaluate the trained model. For model evaluation, the predicted film score was compared to the actual field results (mean of the experts' scores), and the absolute error was recorded for each image. The mean absolute error of the trained model on the test dataset is 0.150, which is significantly lower than the manual error of the experts' scoring, as mentioned previously, thus demonstrating the performance of the trained algorithm.

[0128] Figure 10D is a representative image of a model training for film segmentation for visualization. Similarly, the film segmentation model was trained in a manner similar to the film scoring model. The structure of the segmentation model was chosen as a U-net model. The training dataset consists of hundreds of images with manually masked film edges (of various types). The test dataset also includes 10% of the training dataset.

[0129] Fig. 1OE shows a receptor efficiency (ROC) function graph. For a segmentation task, the Fl score or the ROC_AUC, which can be considered a combination of accuracy and recall, was used to evaluate the trained model. For film segmentation, the average ROC_AUC reached 0.959 for the test dataset, which is considered a high-accuracy model.

[0130] Figures 10F and 10G show an example of model training and validation for hair root scoring and segmentation. In [Fig. 10F], a representative method for scoring and segmenting hair roots for visualization is shown. The model was trained on 172 masked images of white light illumination conditions (124 from a hair reader and 48 from a scalp reader (such as Device 100)). Each image was manually labeled. In this case, a U-net structure model was used.

[0131] The model was validated for root detection (test on 20 images – 10 normal and 10 dark). An Fl score of 0.886 was determined. Table 1 presents the results of this validation.

[0132] [Table 1] Table 1 10 normal scalp test images, 10 dark scalp test images, 20 test images (10 normal + 10 dark). Fl Score: 0.94, 0.82, 0.88. Accuracy: 0.91, 0.82, 0.87. Recall: 0.98, 0.84, 0.91. Figure 100 is a graph showing a representative test of the predicted and actual test results. Accuracy is defined as shown in equation 1.

[0133]

[0134]

[0135]

[0136]

[0137]

[0138]

[0139]

[0140]

[0141]

[0142]

[0143] Precision = Equation 1 Where TP is the true positive and FP is the false positive. The recall is defined as shown in equation 2. TP Reminder — pp + p^ Equation 2 Where TP is the true positive and FN is the false negative. The Fl score is defined by equation 3. "n; clarifications-reminder H — y 1. Prediction + reminder Equation 3

[0144] The model was also validated for hair diameter. 85% agreed with the QNR response by HD (N = 66) in Quali @ JP.

[0145] Although illustrative embodiments have been shown and described, it will be appreciated that various changes may be made to them without departing from the spirit and scope of the invention.

[0146] This application may refer to quantities and numbers. Unless otherwise specified, such quantities and numbers shall not be considered restrictive but representative of the possible quantities or numbers associated with this application. Similarly, in this regard, this application may use the term "plurality" to refer to a quantity or number. In this regard, the term "plurality" is understood to mean any number greater than one, for example, two, three, four, five, etc. The terms "about," "approximately," "near," etc., mean plus or minus 5% of the stated value. For the purposes of this disclosure, the expression "at least one of A, B, and C," for example, means (A), (B), (C), (A and B), (A and C), (B and C), or (A, B, and C), including all other possible permutations when more than three items are listed.

[0147] The embodiments disclosed herein may employ circuitry to implement the technologies and methodologies described herein, functionally connect two or more components, generate information, determine operating conditions, control an apparatus, device, or process, and / or the like. Any type of circuitry may be used. In one embodiment, the circuitry includes, among other things, one or more computing devices such as a processor (e.g., a microprocessor), a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or the like, or any combination thereof, and may include elements or electronics of separate digital or analog circuits, or combinations thereof.

[0148] An embodiment includes one or more data stores that, for example, store instructions or data. Non-limiting examples of one or more data stores include: volatile memory (e.g., random access memory (RAM), dynamic random access memory (DRAM), or the like), non-volatile memory (e.g., read-only memory (ROM), electrically erasable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), or the like), persistent memory, or the like. Other non-limiting examples of one or more data stores include erasable and programmable read-only memory (EPROM), flash memory, or the like. The one or more data stores may be connected, for example, to one or more computing devices by one or more instructions, data, or power buses.

[0149] In one embodiment, the circuitry includes a computer-readable media player or a memory slot configured to accept a signal-carrying medium (for example, computer-readable memory storage, computer-readable recording storage, or the like). In one embodiment, a program intended to cause a system to perform any of the disclosed processes may be stored, for example, on computer-readable recording storage (CRMM), a signal-carrying medium, or the like.Non-limiting examples of signal-carrying media include recordable media such as any form of flash memory, magnetic tape, floppy disk, hard disk drive, compact disc (CD), digital video disc (DVD), Blu-Ray disc, digital tape, computer memory, or the like, and transmission media such as digital and / or analog communication media (e.g., fiber optic cable, waveguide, wired communication link, wireless communication link (e.g., transmitter, receiver, transceiver, transmission logic, receiving logic, etc.).Other non-limiting examples of signal carrier media include, but are not limited to, DVD-ROM, DVD-RAM, DVD+RW, DVD-RW, DVD-R, DVD+R, CD-ROM, Super Audio CD, CD-R, CD+R, CD+RW, CD-RW, compact video discs, super video discs, flash memory, magnetic tape, magneto-optical disc, MINIDISC, non-volatile memory card, EEPROM, optical disc, optical storage, RAM, ROM, system memory, web server, or similar.

[0150] The detailed description presented above in relation to the accompanying drawings, where similar numbers refer to similar elements, is intended to be a description of various embodiments of this disclosure and is not intended to represent the only embodiments. Each embodiment described in this disclosure is offered solely by way of example or illustration and should not be construed as being preferred or advantageous over other embodiments. The illustrative examples provided herein are not intended to be exhaustive or to limit the disclosure to the specific forms disclosed. Similarly, all the steps described herein may be interchangeable with other steps, or combinations of steps, to achieve the same or substantially similar result.In general, the embodiments disclosed here are not limiting, and the inventors contemplate that other embodiments within the scope of this disclosure may include structures and features from more than one specific embodiment shown in the Figures and described in the patent memorandum.

[0151] In the preceding description, specific details are presented to provide a thorough understanding of examples of embodiments of the present Disclosure. However, it will be apparent to those skilled in the art that the embodiments described herein can be implemented without incorporating all the specific details. In some cases, well-known process steps have not been described in detail so as not to unnecessarily obscure various aspects of this disclosure. Furthermore, it should be noted that the embodiments of this disclosure may employ any combination of the features described herein.

[0152] This application may include references to directions, such as "vertical", "horizontal", "front", "back", "left", "right", "above" and "below", etc. These references, and other similar references in this application, are intended to help describe and understand the particular embodiment (such as when the embodiment is positioned for use) and are not intended to limit this disclosure to those directions or locations.

[0153] This application may also refer to quantities and numbers. Unless specifically stated, these quantities and numbers are not to be considered restrictive, but rather as examples of the possible quantities or numbers associated with this application. Similarly, in this respect, this application may use the term "plurality" to refer to a quantity or number. In this respect, the term "plurality" is understood to mean any number greater than one, for example, two, three, four, five, etc. The terms "about," "approximately," etc., mean within 5% of the stated value. The term "based on" means "based at least partially on."

[0154] The principles, representative embodiments, and modes of operation of this disclosure have been described in the preceding description. However, aspects of this disclosure that are intended to be protected should not be interpreted as being limited to the particular embodiments disclosed. Furthermore, the embodiments described herein should be considered illustrative rather than restrictive. It should be understood that variations and changes may be made by other means, and equivalents employed, without departing from the spirit of this disclosure. Accordingly, it is expressly intended that all such variations, changes, and equivalents fall within the spirit and scope of this disclosure as claimed.

Claims

Demands

1. Device for detecting a scalp condition, a hair condition, or both, wherein the scalp condition includes at least the presence or absence of dandruff, and the hair condition includes the presence or absence of hair, comprising: at least one camera configured to view a user's scalp; a scattering cone disposed around the at least one camera; a lighting module comprising at least one light source, wherein the at least one light source is configured to emit light in a plurality of lighting conditions; and a processor configured to: - receive image data from the at least one camera captured during at least one lighting condition from the plurality of lighting conditions; and - transmit the image data to an intelligent device for detecting the scalp condition, the hair condition, or both.

2. Device according to claim 1, wherein the image data comprises a set of images at a location on the user's scalp in each lighting condition of the plurality of lighting conditions.

3. Device according to claim 1, wherein the plurality of lighting conditions includes a white light condition, a cross-polarized light condition, an ultraviolet (UV) light condition, or a combination thereof.

4. Device according to claim 1, wherein at least one camera is a three-lens camera, and wherein each lens of the three-lens camera has a different focal length.

5. A system for detecting a scalp condition, a hair condition, or both, wherein the scalp condition includes at least the presence or absence of dandruff, and the hair condition includes the presence or absence of hair growth, the system comprising: the device of claim 1; and an intelligent device, wherein the intelligent device includes an intelligent device processor, and wherein the intelligent device processor is configured to: - receive image data from the device; - input an image from the image data into one lighting condition of the plurality of lighting conditions; - determine one or more areas of one or more detected features at a pixel level of the image; and - display the one or more areas superimposed on the image data.

6. A system according to claim 5, wherein the intelligent device processor is further configured to: - segment image data at a pixel level; - locate the segmented films; - classify the segmented films based on film number, film size and film shape based on statistical film data; - provide output a score for film severity; and - display film outline segments superimposed on the image data.

7. A system according to claim 5, wherein the intelligent device processor is further configured to: - segment hair strands in image data on the basis of color; - determine a position and direction of hair strands; - measure individual diameters of one or more of the hair strands; - determine an average hair diameter; and - provide as output a hair score based on the hair condition, wherein the hair score includes an average diameter of the hair strands, a percentage of white or gray hair, root color detection, or a combination thereof.

8. System according to claim 5, wherein a 3-layer convolutional neural network (CNN) having the same structure with different weight sets is used to predict the severity of the dandruff score and a level of scalp redness.

9. A system according to claim 5, wherein the intelligent device processor is further configured to: - detect one or more colors on a pixel level in the porphyrin-indicative image data; - determine a number, size, shape, or combination thereof, of porphyrins; - output a porphyrin score; and - display outlines of the detected porphyrins superimposed on the image data.

Images