determining whether the hair on the skin region has been treated with light pulses

Abstract

According to an aspect, there is provided an apparatus for use with a care device. The care device is configured to apply light pulses to a skin of a subject to perform a care operation on hair on the skin. The apparatus comprises a processing unit configured to receive one or more images of a first region of the skin from an imaging unit, wherein the imaging unit is arranged to acquire images of the skin of the subject; process the one or more images to determine whether the hair on the first region of the skin has been cared for with the light pulses based on a degree of at least one of carbonization and curling of the hair on the first region of the skin shown in the one or more images; and output a first signal indicative of whether the hair on the first region of the skin has been cared for with the light pulses.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to determining whether hair on a region of skin of a subject has been treated with light pulses. BACKGROUND

[0002] Techniques for removing unwanted hair include shaving, electrolysis, plucking, laser and light therapy, known as photoepilation, and injectable treatment with antiandrogens. Light-based techniques are also used for other types of skin treatment, including reducing hair growth and treating acne.

[0003] By using an appropriate configuration of light energy, i.e. in terms of wavelength, intensity and / or pulse duration if the light is pulsed, selective heating of the hair root and subsequent temporary or permanent damage to the hair follicle can be achieved. Domestic photoepilation devices, such as the Philips Lumea device, use intense pulsed light (IPL) from a high intensity light source, such as a xenon flash lamp, which can produce high output bursts of broad spectrum light.

[0004] Photoepilation treatment is characterized by the user of a photoepilation device treating a relatively small skin area for hair removal purposes. Photoepilation treatment uses strong light to heat the melanin in the hair and hair root, causing the hair follicle to enter a resting phase, preventing the hair from regrowing. For the technique to be used effectively for hair removal, the user must cover the skin area completely. Since the duration of this effect is limited, the treatment must be repeated regularly: typically after an initial phase of two weeks of treatment every two weeks, followed by a maintenance phase of treatment every 4 to 8 weeks.

[0005] US 2003 / 0023235 Al discloses a device for treating skin by light pulses. The device has a processor for determining from an image of the skin the color and size of a target object, such as a hair, to be treated. The processor determines a dose of light pulses based on said color and size.

[0006] US 2015 / 0032092 Al discloses a system for performing a cosmetic skin procedure using light. The system has a computer that utilizes information extracted from an image of the skin to determine an optimal treatment dose of light. Said information can include skin pigmentation, blemish thickness, hair pigmentation or hair length or thickness.

[0007] US 2002 / 0049432 Al discloses an apparatus for treating a patient's skin by a laser beam. The apparatus includes a detection unit that detects a color of the skin from an image of the skin taken by an imaging element. A control portion determines irradiation conditions of the laser beam based on the detected color.

[0008] EP 1 523 371 A1 discloses a hand-held device for treating skin tissue by means of a light beam. The hand-held device has a sensor, for example a CCD or CMOS camera, to generate information about a target region on the skin tissue, such as specific properties of the skin tissue, hair and skin diseases and irregularities, such as wrinkles, small marks or spots, and blood vessels. The information generated by the sensor is used to control the treatment.

[0009] US 6 267 771 B1 discloses a method of inhibiting hair growth on human skin. A contaminant including a dye is applied to the skin, allowing it to penetrate into the hair follicle and soil the follicle. Light having a wavelength absorbed by the dye is applied to the skin, thereby heating the follicle and the surrounding tissue that nourishes the follicle. The application of light is continued at least until the hair begins to curl.

[0010] In a typical light hair removal treatment, a user of a light hair removal device has to repeatedly manually position the light hair removal device on the skin and trigger light pulses to cover a full body area, such as an arm, a leg, etc. However, due to the fact that the light hair removal device typically does not provide any feedback to the user about the treated area and due to the fact that there is little or no user-perceptible change in the skin or hair shortly after applying a light pulse, it is difficult for the user to achieve full coverage of the body area and / or to avoid over-treating certain areas of the body area.

[0011] It is therefore desirable to be able to provide a method of determining whether hair on a skin area has already been treated with light pulses. SUMMARY

[0012] According to a first aspect, there is provided an apparatus for use with a treatment device. The treatment device is configured to apply light pulses to a skin of a subject to perform a treatment operation on hair on the skin. The apparatus comprises a processing unit configured to receive one or more images of a first area of the skin from an imaging unit, wherein the imaging unit is arranged to acquire images of the skin of the subject; process the one or more images to determine whether hair on the first area of the skin has already been treated with light pulses based on a degree of at least one of carbonization and curling of the hair on the first area of the skin shown in the one or more images; and output a first signal indicative of whether the hair on the first area of the skin has already been treated with light pulses. Thus, the apparatus is able to determine from the one or more images from an area of the skin whether hair on the area of the skin has already been treated with light pulses.

[0013] In some embodiments, the processing unit is configured to determine the degree of carbonization of the hair based on a color of the hair and / or a size of the hair determined from the one or more images. In some embodiments, the processing unit is configured to determine the degree of curling of the hair based on a degree of bending of the hair determined from the one or more images.

[0014] In some embodiments, the processing unit is configured to determine whether the hair on the first region of skin has been treated with the light pulses by: comparing the determined degree of said at least one of carbonization and curling of the hair on the first region of skin to a respective threshold value for the degree of carbonization and the degree of curling; or combining the determined degrees of carbonization and curling of the hair into a combined degree of carbonization and curling, and comparing the combined degree of carbonization and curling to a threshold value for the combined degree of carbonization and curling.

[0015] In further or alternative embodiments, the processing unit is configured to process the one or more images using a trained machine learning model to determine whether the hair on the first region of skin has been treated with the light pulses. The trained machine learning model can be an artificial neural network, such as a deep neural network.

[0016] In some embodiments, the processing unit is further configured to receive one or more further images of the first region of skin from the imaging unit, wherein the one or more further images are acquired by the imaging unit after the light pulses are applied to the first region of skin; and update the trained machine learning model using the one or more further images. These embodiments enable the performance of the machine learning model to improve or refine over time, in particular the use of images of the subject’s skin enables the machine learning model to be calibrated or tailored to the subject’s skin characteristics.

[0017] In some embodiments, the processing unit is further configured to analyze the one or more images to identify portions of the one or more images that include hair, and the processing unit is configured to process the identified portions of the one or more images to determine whether the hair on the first region of skin has been treated with the light pulses. These embodiments can make the processing of the one or more images more efficient.

[0018] In some embodiments, the processing unit is further configured to process the one or more images to determine further information about the hair on the first region of skin, and to include said further information in the first signal. In these embodiments, the further information can include at least one of: a hair density in the first region of skin; a hair intensity in the first region of skin; a hair thickness in the first region of skin; and a hair color in the first region of skin.

[0019] In some embodiments, the first signal includes the one or more images and an indication of a portion of the one or more images that has hair that has been treated with the light pulses. These embodiments provide feedback to the subject or other user of the treatment device, enabling them to identify where the light pulses should be applied, thereby improving the coverage of the treatment operation on the skin.

[0020] In some embodiments, the apparatus further comprises a user interface configured to receive the first signal, and the first signal is configured to cause the user interface to output feedback to a user of the treatment device regarding whether the hair on the first region of the skin has been treated with the light pulses. These embodiments also provide feedback to the subject or other user of the treatment device, enabling them to identify where light pulses should be applied, thereby improving the coverage of the treatment operation on the skin.

[0021] In some embodiments, the first signal is output to a control unit of the treatment device, and the control unit is configured to determine, based on the first signal, whether the treatment device should apply light pulses to the first region of the skin. These embodiments are therefore useful in the case of automatic control of the application of light pulses to the skin, thereby improving the coverage of the treatment operation on the skin.

[0022] According to a second aspect, there is provided a system comprising an imaging unit arranged to acquire images of the skin of a subject; and an apparatus according to the first aspect or any embodiment thereof.

[0023] In some embodiments, the imaging unit comprises at least a first imaging component for acquiring one or more images of the skin of the subject. In these embodiments, the imaging unit can further comprise a first polarizer arranged relative to the first imaging component such that light incident on the first imaging component passes through the first polarizer. The use of a polarizer can improve the depth of the skin visible in the images (i.e. the polarizer can observe light rays at different skin penetration depths).

[0024] In some embodiments, the system further comprises a treatment device configured to apply light pulses to the skin of the subject to perform a treatment operation on hair on the skin. In these embodiments, the treatment device comprises the imaging unit and / or the apparatus. In alternative embodiments, the treatment device is separate from the apparatus.

[0025] According to a third aspect, there is provided a computer-implemented method for determining whether hair on a region of the skin of a subject has been treated with light pulses from a treatment device. The treatment device is configured to apply light pulses to the skin of the subject to perform a treatment operation on hair on the skin. The method comprises receiving, from an imaging unit, one or more images of a first region of the skin, wherein the imaging unit is arranged to acquire images of the skin of the subject; processing the one or more images to determine whether hair on the first region of the skin has been treated with the light pulses based on a degree of at least one of carbonization and curling of the hair on the first region of the skin shown in the one or more images; and outputting a first signal indicative of whether the hair on the first region of the skin has been treated with the light pulses. This method is therefore able to determine from one or more images of a region of the skin whether hair on the region of the skin has been treated with light pulses.

[0026] In some embodiments, the processing step comprises determining a degree of carbonation of the hair based on the color of the hair and / or a size of the hair determined from the one or more images. In some embodiments, the processing step comprises determining a degree of curl of the hair based on a degree of bending of the hair determined from the one or more images.

[0027] In some embodiments, the processing step comprises comparing the degree of the at least one of carbonation and curl of the hair determined on the first region of the skin to a respective threshold value for the degree of carbonation and the degree of curl; or combining the determined degrees of carbonation and curl of the hair into a combined degree of carbonation and curl, and comparing the combined degree of carbonation and curl to a threshold value for the combined degree of carbonation and curl.

[0028] In further or alternative embodiments, the processing step comprises processing the one or more images using a trained machine learning model to determine whether the hair on the first region of the skin has been treated with the light pulses. The trained machine learning model can be an artificial neural network, such as a deep neural network.

[0029] In some embodiments, the method further comprises receiving one or more further images of the first region of the skin from the imaging unit, wherein the one or more further images are acquired by the imaging unit after the light pulses are applied to the first region of the skin; and updating the trained machine learning model using the one or more further images. These embodiments enable the performance of the machine learning model to improve or improve over time, in particular the use of images of the subject’s skin enables the machine learning model to be calibrated or tailored to the subject’s skin characteristics.

[0030] In some embodiments, the method further comprises analyzing the one or more images to identify portions of the one or more images that include hair, and the processing step comprises processing the identified portions of the one or more images to determine whether the hair on the first region of the skin has been treated with the light pulses. These embodiments can make the processing of the one or more images more efficient.

[0031] In some embodiments, the method further comprises processing the one or more images to determine further information about the hair on the first region of the skin, and including the further information in the first signal. In these embodiments, the further information can include at least one of: a hair density in the first region of the skin; a hair intensity in the first region of the skin; a hair thickness in the first region of the skin; and a hair color in the first region of the skin.

[0032] In some embodiments, the first signal comprises one or more images and an indication that a portion of the one or more images has hair on the skin that has been treated with light pulses. These embodiments provide feedback to a subject or other user of the treatment device that enables them to identify where light pulses should be applied, thereby improving coverage of the treatment operation on the skin.

[0033] In some embodiments, the user interface receives the first signal, and the first signal causes the user interface to output feedback to a user of the treatment device regarding whether hair on the first region of the skin has been treated with light pulses. These embodiments also provide feedback to a subject or other user of the treatment device that enables them to identify where light pulses should be applied, thereby improving coverage of the treatment operation on the skin.

[0034] In some embodiments, the first signal is output to a control unit of the treatment device, and the control unit determines, based on the first signal, whether the treatment device should apply light pulses to the first region of the skin. These embodiments are therefore useful in the case of automatic control of the application of light pulses to the skin, thereby improving coverage of the treatment operation on the skin.

[0035] According to a fourth aspect, there is provided an apparatus for training a machine learning model, MLM, for determining whether hair on a first region of the skin has been treated with light pulses. The apparatus comprises a processing unit configured to obtain a plurality of images of skin of one or more subjects, wherein each image is annotated with an indication of whether hair on the skin in the image has been treated with light pulses, wherein the plurality of images comprises at least one image annotated with an indication that hair on the skin in the image has been treated with light pulses, and at least one image annotated with an indication that hair on the skin in the image has not been treated with light pulses; and train the MLM using the plurality of images to distinguish between images in which hair on the skin has been treated with light pulses and images in which hair on the skin has not been treated with light pulses based on a degree of at least one of carbonization and curling of the hair shown in the image.

[0036] According to a fifth aspect, there is provided an apparatus for using a machine learning model, MLM, the apparatus comprising a processing unit configured to: receive one or more images of a region of the skin from an imaging unit, wherein the imaging unit is arranged to obtain images of the skin of a subject; analyse the one or more images using the MLM trained according to the fourth aspect to determine whether hair on the region of the skin in the one or more images has been treated with light pulses; and output a first signal indicating whether hair on the region of the skin has been treated with light pulses.

[0037] According to a sixth aspect, a computer-implemented method for training a machine learning model (MLM) is provided for determining whether hair on a first region of skin has been treated with photopulse. The method includes: acquiring multiple skin images for one or more subjects, wherein each image is labeled with an indication of whether hair on the skin in the image has been treated with photopulse, wherein the multiple images include at least one image labeled with an indication that hair on the skin in the image has been treated with photopulse, and at least one image labeled with an indication that hair on the skin in the image has not been treated with photopulse; and training the MLM using the multiple images to distinguish between images where hair on the skin has been treated with photopulse and images where hair on the skin has not been treated with photopulse based on the degree of at least one of hair carbonization and curl shown in the images.

[0038] According to a seventh aspect, a computer-implemented method using a machine learning model (MLM) is provided, the method comprising: receiving one or more images of a skin region from an imaging unit, wherein the imaging unit is arranged to acquire images of a subject's skin; analyzing the one or more images using an MLM trained according to the method of a sixth aspect to determine whether hair on the skin region in the one or more images has been treated with light pulses; and outputting a first signal indicating whether hair on the skin region has been treated with light pulses.

[0039] According to an eighth aspect, a computer program product is provided, comprising a computer-readable medium containing computer-readable code configured to, when executed by a suitable computer or processing unit, cause the computer or processing unit to perform the method according to the third, sixth, seventh aspects, or any embodiment thereof. These and other aspects will become apparent from one or more embodiments described below. Attached Figure Description

[0040] Exemplary embodiments will now be described by way of example only with reference to the accompanying drawings, wherein:

[0041] Figure 1 This is an illustration of an exemplary nursing device that can be used with the present invention;

[0042] Figure 2 This is a block diagram of an exemplary system including an imaging unit and apparatus according to various embodiments;

[0043] Figures 3 to 5 Several examples of hair carbonization and curling before and after the application of light pulses are shown;

[0044] Figure 6 This is a flowchart illustrating an exemplary method for determining whether hair on a first area of ​​skin has been treated with light pulse therapy; and

[0045] Figure 7 is a flowchart illustrating a method of training a machine learning model for determining whether hair on a first region of skin has been treated with a light pulse. DETAILED DESCRIPTION

[0046] As described above, the techniques described herein can be used to determine whether hair on a region of skin has been treated with a light pulse from a treatment device. These techniques can be implemented by the treatment device (e.g., by a processing unit in the treatment device), or by a processing unit in a separate device. In order to acquire one or more images of a region of skin of a subject, an imaging unit (e.g., a camera) is needed. The imaging unit can be part of the treatment device, part of a separate device, or separate from both the treatment device and any device implementing the techniques described herein.

[0047] Figure 1 is an illustration of an exemplary treatment device 2 that can be used to apply a light pulse to a region of skin. It should be understood that, Figure 1 the treatment device 2 in is presented as an example of a handheld treatment device 2 that can be used with the present invention, and the treatment device 2 is not limited to Figure 1 the form shown or being a handheld treatment device. The treatment device 2 is used on a body of a subject (e.g., a human or an animal), and will be held in one or both hands of a user during use. When the treatment device 2 is in contact with a body part of the subject, the treatment device 2 performs some treatment operation on hair on the body of the subject using one or more light pulses. The treatment operation can be the removal of unwanted hair by laser and / or light therapy (referred to as photoepilation treatment or Intense Pulsed Light, IPL, treatment).

[0048] As described herein, the treatment device 2 is operated or used by a “user” and the treatment device 2 is used on the body of a “subject”. In some cases, the user and the subject are the same person, i.e., the treatment device 2 is held in the user’s hand and used by the user themselves (e.g., on the skin on their legs). In other cases, the user and the subject are different people, e.g., the treatment device 2 is handheld by the user and used on another person. In either case, it is difficult for the user to achieve full coverage of the body region and / or to avoid over-treating certain areas of the body region, as there is little or no user-perceptible change to the skin or hair shortly after the light pulse is applied.

[0049] The exemplary treatment device 2 includes a housing 4 that includes at least a handle portion 5 and a head portion 6. The handle portion 5 is shaped to enable the user to hold the treatment device 2 in one hand. The head portion 6 is located at a head end 8 of the housing 4, and the head portion 6 is in contact with the subject in order to perform a personal treatment operation on the body or skin of the subject at the location where the head portion 6 is in contact with the body or skin.

[0050] Nursing device 2 is used for nursing procedures using light pulses. Therefore, in Figure 1 In the device 2, the head portion 6 includes an aperture 10 disposed in or on the housing 4, such that the aperture 10 can be placed adjacent to or on the skin of the subject (i.e., in contact). The care device 2 includes one or more light sources 12 for generating light pulses, which are applied to the skin of the subject via the aperture 10 to perform the care procedure. The one or more light sources 12 are disposed in the housing 4 such that light pulses are provided from the one or more light sources 12 through the aperture 10. The aperture 10 may be in the form of an opening at the head end 8 of the housing 4, or it may be in the form of a window (including a waveguide) that is transparent or translucent to the light pulses (i.e., the light pulses can pass through the window).

[0051] exist Figure 1 In the exemplary embodiment shown, the orifice 10 has a generally rectangular shape, resulting in a generally rectangular skin care area on the skin. It should be understood that the orifice 10 can have any other desired shape. For example, the orifice 10 can be a square, ellipse, circle, or any other polygonal shape.

[0052] One or more light sources 12 can generate light pulses of any suitable or desired wavelength (or wavelength range) and / or intensity. For example, light source 12 can generate visible light, infrared (IR) light, and / or ultraviolet (UV) light. Each light source 12 can include any suitable type of light source, such as one or more light-emitting diodes (LEDs), (xenon) flash lamps, one or more lasers, etc. One or more light sources 12 can provide light pulses with a spectral content in the range of 560-1200 nanometers (nm) and a duration of approximately 2.5 milliseconds (ms), because these wavelengths prevent hair regrowth by absorbing and heating the melanin in the hair and hair root, putting the hair follicle into a dormant phase.

[0053] One or more light sources 12 are configured to provide light pulses. That is, one or more light sources 12 are configured to generate high-intensity light for a short period of time (e.g., less than 1 second). The intensity of the light pulses should be high enough to perform care procedures on the skin or body parts adjacent to the orifice 10.

[0054] The illustrated care device 2 further comprises two skin contact sensors 14, 16, which are positioned on or in the head portion 6 for determining whether the head portion 6 is in contact with skin. The skin contact sensors 14, 16 measure a parameter indicative of whether the head portion 6 is in contact with skin and generate a respective measurement signal comprising a time series of measurements of the parameter. The measurement signal can be processed to determine whether the head portion 6 is in contact with skin. Typically, skin contact sensors are used for care devices 2, in particular for light epilators, to ensure that the care device 2 is in proper contact with the skin before generating light pulses to avoid that light pulses are directed into the eyes of the user or subject.

[0055] In some embodiments, the parameter can be a capacitance and thus the skin contact sensors 14, 16 can measure the capacitance via respective pairs of electrical contacts or electrodes on the surface of the head portion 6, wherein the measured capacitance is indicative of whether there is skin contact. In alternative embodiments, the parameter can be an intensity or level of light and thus the skin contact sensors 14, 16 can be light sensors measuring the intensity or level of light incident on the light sensor, wherein the measured intensity or level is indicative of whether there is skin contact (e.g. less / no light can indicate skin contact as the skin shields the light sensor 14, 16 and vice versa). In other alternative embodiments, the parameter can be a measurement of contact pressure and thus the skin contact sensors 14, 16 can measure the contact pressure via respective pressure sensors or mechanical switches, wherein the measured contact pressure is indicative of whether there is skin contact.

[0056] The illustrated care device 2 further comprises a skin color sensor 18 positioned on or in the head portion 6 for determining a skin color of the skin contacted by the head portion 6. The skin color sensor 18 measures a parameter indicative of the skin color of the skin and generates a measurement signal comprising a time series of measurements of the parameter. The measurement signal can be processed to determine the skin color of the skin contacted by the head portion 6. Typically, skin color sensors are used for care devices 2, in particular for light epilators, to ensure that the light pulses have an intensity suitable for the skin type being treated or even to prevent the generation of light pulses when the skin type is not suitable for light pulses (e.g. dark skin with much higher melanin content).

[0057] In some embodiments, the skin color sensor 18 can be a light sensor and the parameter measured by the light sensor can be an intensity or level of light of a particular wavelength or wavelengths reflected from the skin. The intensity or level of reflected light measured at one or more particular wavelengths can be indicative of the skin color. The measured intensity or level of reflected light can be based on a concentration of melanin in the skin and thus the measured intensity or level can be indicative of the melanin concentration. For example, the melanin concentration can be derived from light reflection measurements at 660 nm (red) and 880 nm (infrared) wavelengths.

[0058] The illustrated care device 2 further comprises a user control 20 which can be operated by a user to activate the care device 2 so that the head portion 6 performs the desired care operation on the subject's body (e.g. generates one or more light pulses by the one or more light sources 12). The user control 20 can be in the form of a switch, a button, a touchpad, etc.

[0059] Figure 2 is a block diagram of an exemplary system 40 comprising a device 42 for determining whether hair on a skin region has been treated with light pulses and an imaging unit 44. In some embodiments, the care device 2 can be considered as part of the system 40, although the care device 2 is not shown in Figure 2 . As mentioned above, the device 42 can be a device separate from the care device 2, so the device 42 can be in the form of an electronic device such as a smartphone, a smartwatch, a tablet computer, a personal digital assistant (PDA), etc. In other embodiments, the device 42, in particular the functionality according to the present application provided by the device 42, is part of the care device 2.

[0060] The imaging unit 44 is provided to generate one or more images (or video sequences) of one or more skin regions of the subject, in which regions light pulses can or can not have been applied. The imaging unit 44 can comprise any suitable components for capturing images, e.g. a charge-coupled device (CCD) and one or more lenses and / or mirrors. In some embodiments, the imaging unit 44 is a camera, such as a digital camera. In some embodiments, one or more further optical components are associated with the imaging unit 44, such as a polarizer placed in front of the imaging unit 44 so as to polarize light incident on the imaging unit 44. The use of a polarizer can improve the depth of the skin visible in the images (i.e. the polarizer can observe light rays at different skin penetration depths).

[0061] The imaging unit 44 is shown in Figure 2 separated from the device 42, but it will be appreciated that in other embodiments the imaging unit 44 can be integrated with or part of the device 42. In embodiments in which the imaging unit 44 is separate from the device 42, the imaging unit 44 can be part of the care device 2, or it can also be separate from the care device 2. In embodiments in which the imaging unit 44 is part of the care device 2, the imaging unit 44 can be arranged in the care device 2 close to the aperture 10 so that images can be acquired when the care device 2 is on or close to the skin.

[0062] The apparatus 42 includes a processing unit 46 that generally controls the operation of the apparatus 42 and enables the apparatus 42 to perform the methods and techniques described herein. Briefly, the processing unit 44 receives one or more images from the imaging unit 44, processes the one or more images to determine whether the hair on the skin region shown in the one or more images has been treated with light pulses, and outputs a signal indicative of whether the hair on the skin region has been treated with light pulses.

[0063] Accordingly, the processing unit 46 can be configured to receive the one or more images from the imaging unit 44, either directly, in embodiments in which the imaging unit 44 is part of the apparatus 42, or via another component, in embodiments in which the imaging unit 44 is separate from the apparatus 42. In either case, the processing unit 46 can include or incorporate one or more input ports or leads for receiving the one or more images (or signals carrying information representative of the one or more images) from the imaging unit 44 or other appropriate component. The processing unit 46 can also include or incorporate one or more output ports or leads for outputting the signal indicative of whether the hair on the skin region has been treated with light pulses.

[0064] The processing unit 46 can be implemented in a variety of ways, using software and / or hardware, to perform the various functions described herein. The processing unit 46 can include one or more microprocessors or digital signal processors (DSPs) that can be programmed using software or computer program code to perform desired functions and / or control components of the processing unit 46 to achieve desired functionality. The processing unit 46 can be implemented as a combination of dedicated hardware to perform some functions (e.g., amplifiers, pre-amps, analog-to-digital converters (ADCs), and / or digital-to-analog converters (DACs)) in combination with a processor, such as one or more programmed microprocessors, controllers, DSPs, and associated circuitry, to perform other functions. Examples of components that can be employed in various embodiments of the present disclosure include, but are not limited to, conventional microprocessors, DSPs, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), hardware for implementing neural networks, and / or so-called artificial intelligence (AI) hardware accelerators (i.e., one or more processors or other hardware designed specifically for AI applications that can be used in conjunction with a main processor).

[0065] The processing unit 46 can include or be associated with a memory unit 48. The memory unit 48 can store data, information, and / or signals (including one or more images) for use by the processing unit 46 in controlling the operation of the device 42 and / or in conducting or performing the methods described herein. In some embodiments, the memory unit 48 stores computer-readable code that can be executed by the processing unit 46 such that the processing unit 46 performs one or more functions, including the methods described herein. In particular embodiments, the program code can be in the form of an application of a smartphone, tablet computer, laptop computer, computer, or server. The memory unit 48 can include any type of non-transitory machine-readable medium, such as a cache or a system memory, including volatile and non-volatile computer memory such as random access memory (RAM), static RAM (SRAM), dynamic RAM (DRAM), read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), and electrically erasable PROM (EEPROM), and the memory unit can be realized in the form of a memory chip, an optical disc (such as a compact disc (CD), a digital versatile disc (DVD), or a Blu-ray disc), a hard disk, a tape storage solution, or a solid-state device (including a memory stick, a solid-state drive (SSD), a memory card, etc.).

[0066] In Figure 2In the illustrated embodiment, as the apparatus 42 is shown as separate from the imaging unit 44, the apparatus 42 also comprises interface circuitry 50 to enable the apparatus 42 to receive one or more images from the imaging unit 44. The interface circuitry 50 in the apparatus 42 can enable a data connection to and / or data exchange with other devices, including any one or more of the imaging unit 44, the care device 2, a server, a database, a user device, and a sensor. The connection to the imaging unit 44 (or any electronic device, such as the care device 2) can be direct or indirect (e.g. via the internet), and thus the interface circuitry 50 can enable a connection between the apparatus 42 and a network, or directly between the apparatus 42 and another device, such as the imaging unit 44 and / or the care device 2, via any desirable wired or wireless communication protocol. For example, the interface circuitry 50 can operate using WiFi, Bluetooth, Zigbee, or any cellular communication protocol, including but not limited to Global System for Mobile Communications (GSM), Universal Mobile Telecommunications System (UMTS), Long-Term Evolution (LTE), LTE-Advanced, etc. In the case of a wireless connection, the interface circuitry 50 (and thus the apparatus 42) can comprise one or more suitable antennas for transmission / reception over a transmission medium (e.g. air). Alternatively, in the case of a wireless connection, the interface circuitry 50 can comprise a means (e.g. a connector or plug) to enable the interface circuitry 50 to connect to one or more suitable antennas external to the apparatus 42 for transmission / reception over a transmission medium (e.g. air). The interface circuitry 50 is connected to the processing unit 46.

[0067] Although not shown in Figure 2 , the apparatus 42 can comprise one or more user interface components, including one or more components to enable a user of the apparatus 42 to input information, data and / or commands into the apparatus 42 and / or to enable the apparatus 42 to output information or data to a user of the apparatus 42. The user interface can comprise any suitable input component(s), including but not limited to a keyboard, a keypad, one or more buttons, switches or dials, a mouse, a touchpad, a touchscreen, a stylus, a camera, a microphone, etc., and the user interface can comprise any suitable output component(s), including but not limited to a display unit or screen, one or more lights or light elements, one or more speakers, a vibration element, etc.

[0068] It will be appreciated that a practical implementation of the apparatus 42 can comprise additional components to those shown in Figure 2 , for example. For example, the apparatus 42 can also comprise a power source, such as a battery, or components for enabling the apparatus 42 to be connected to a mains power supply.

[0069] As mentioned above, the technology described herein aims to provide a method of determining whether hair on a region of skin has been treated with a light pulse. In particular, it has been found that after the application of a suitable light pulse (i.e. at a suitable intensity and / or wavelength), the carbonization of the hair increases and / or the amount of curl in the hair increases. Hair is composed of keratin which is bound together by disulfide bonds. When a light pulse is applied, these disulfide bonds are broken. When these bonds break, the color appearance and structural integrity of the hair changes, causing the hair to "curl" and thus increasing the bend of the hair. This is the carbonization and curling effect.

[0070] Figures 3 to 5 A number of examples of hair carbonization and curling before and after the application of a light pulse are shown.

[0071] Figure 3 (a) is an image of a region of skin with some unshaven hair before the application of a light pulse. In Figure 3 Two hairs can be seen in (a). Figure 3 (b) is an image of the same region of skin after the application of a light pulse, and arrows 70, 72 show the correspondence between the hairs visible in Figure 3 (a) and the hairs in Figure 3 (b). It can be seen that after the application of a light pulse, the appearance of the two hairs has changed, Figure 3 the amount of carbonization visible in Figure 3 (a) has increased relative to Figure 3 (a). That is, the hairs in Figure 3 (b) look darker and thicker relative to their appearance in Figure 3 (a). Furthermore, compared to before the application of a light pulse, Figure 3 the hairs in (b) are more curled. The images in (a) and (b) are acquired using imaging unit 44 and a polarizer placed in front of imaging unit 44.

[0072] Figure 4 (a) is an image of a region of skin with some trimmed hair (i.e. the hair is short, but not cut at skin level) before the application of a light pulse. Two groups of hair are highlighted in Figure 4 (a) by boxes 74, 76. Figure 4 (b) is an image of the same region of skin after the application of a light pulse, and boxes 78, 80 (the correspondence between the hairs in the two images is shown by arrows 70, 72). It can be seen that after the application of a light pulse, the appearance of the hair has changed, Figure 4 the amount of carbonization visible in Figure 4 (a) has increased relative to Figure 4 (a). Furthermore, compared to before the application of a light pulse, Figure 4The images in (a) and (b) are acquired using imaging unit 44 and a polarizer placed in front of imaging unit 44.

[0073] Figure 5 (a) is an image of a region of skin with some shaved hair prior to application of a light pulse (i.e., the hair is short and cut to about the level of the skin). In this example, the hair is very short and the likelihood of curling of the hair is low. In (a), a hair is indicated by arrow 86. Figure 5 (a) is an image of a region of skin with some shaved hair prior to application of a light pulse (i.e., the hair is short and cut to about the level of the skin). In this example, the hair is very short and the likelihood of curling of the hair is low. In (a), a hair is indicated by arrow 86. Figure 5 (b) is an image of the same region of skin after application of a light pulse, the hair being indicated by arrow 86. It can be seen that the appearance of the hair has changed after application of the light pulse, Figure 5 (b) is an image of the same region of skin after application of a light pulse, the hair being indicated by arrow 86. It can be seen that the appearance of the hair has changed after application of the light pulse, Figure 5 (a) is increased. Since the hair is already short, the likelihood of curling of the hair is low and there is little visible difference in curling of the hair due to the light pulse. Since the hair is very short in this example, Figure 5 The images in (a) and (b) are acquired using imaging unit 44 with zoom or other form of magnification of the imaged region.

[0074] Figure 5 (c) to (e) are images of other regions of skin after application of a light pulse, the hair being indicated by arrows 88, 90 and 92, respectively, in each image. In each image, it can be seen that the hair shows a relatively high degree of carbonization. In Figure 5 In (d) and (e), curling of the hair can be seen. As in Figure 5 (a) and (b), the hair in these examples is very short, so Figure 5 The images in (c) to (e) are acquired using imaging unit 44 with zoom or other form of magnification of the imaged region.

[0075] Thus, from Figures 3 to 5 It can be seen that the degree (i.e., amount) of carbonization and / or curling of the hair can be indicative of whether the hair on the region of skin has been treated with a light pulse and that proper processing of one or more images can determine whether the hair on the region of skin has been treated with a light pulse based on the degree of carbonization and / or the degree of curling.

[0076] Figure 6 The flowchart in FIG. 1 illustrates an exemplary method for determining whether hair on a region of skin has been treated with a light pulse according to the techniques described herein. One or more steps of the method can be performed as appropriate by processing unit 46 in device 42 in conjunction with memory unit 48 and interface circuitry 50 of device 42 and / or any of imaging unit 44. Processing unit 46 can perform one or more steps in response to executing computer program code that can be stored on a computer-readable medium such as, for example, memory unit 48.

[0077] In step 101, one or more images of the first region of skin are received. The one or more images can be received directly from the imaging unit 44, for example in real-time or near real-time as the images are generated by the imaging unit 44. Alternatively, the one or more images can have been previously generated by the imaging unit 44 and stored for subsequent analysis, for example in the memory unit 48, in a memory unit associated with the care device 2 or the imaging unit 44, or in a remote database, in which case step 101 can comprise the processing unit 46 retrieving or retrieving the one or more images from the storage location, for example from the memory unit 48 or the like.

[0078] In step 103, the one or more images are processed to determine whether the hair on the first region of skin has been treated with light pulses. The determination of whether the hair has been treated is based on the extent of at least one of carbonization and curling of the hair shown in the one or more images. Carbonization of the hair relates to the color and / or size of the hair shown in the one or more images. Curling of the hair relates to the bending of the hair shown in the one or more images.

[0079] In some embodiments, as part of step 103, the one or more images can be analyzed to identify portions of the one or more images that include hair, and the processing of the one or more images to determine whether the hair on the first region of skin has been treated with light pulses can operate on the identified portions of the one or more images. The output of this analysis can be a mask (image mask) or similar that highlights the one or more portions of the image that contain hair (or conversely do not contain hair). This analysis of the one or more images can include using contour detection and / or edge detection image processing techniques (known to those skilled in the art) to detect the hair in the image. For example, the edge detection technique can detect the contours of the hair in the image.

[0080] Then, in step 105, a signal is output indicating whether the hair on the first region of skin has been treated with light pulses. In some embodiments, the indication can be simply "the region of skin has been treated" or "the region of skin has not been treated". In other or further embodiments, the indication can include additional information relating to the skin, the hair, or the applied treatment.

[0081] The signal can be provided to a user interface component of the device 42 or the treatment apparatus 2, and the signal is configured to cause the user interface component to indicate whether the hair on the skin region has been treated with a light pulse. For example, if it is determined that the skin region that is currently in the field of view of the imaging unit 44 and that can be treated with a light pulse has been treated with a light pulse, the signal can cause a red light on the treatment apparatus 2 to be illuminated. Likewise, if it is determined that the skin region that is currently within the field of view of the imaging unit 44 has not been treated with a light pulse, the signal can cause a green light on the treatment apparatus 2 to be illuminated. A user of the treatment apparatus 2 will be able to use these indications to determine whether to trigger a light pulse at the current location of the treatment apparatus 2, which can help the user to improve the coverage of the treatment operation over the subject’s skin. As another example, the user can use the indication to determine whether a previous light pulse treatment of this part of the skin was successful. As a further example, where the device 42 is in the form of a smartphone or similar type of device, feedback about whether the skin region has been treated with a light pulse can be provided to the user or subject via an app (software application) executing on the device 42. The skilled person will appreciate other ways in which feedback about whether the skin region has been treated with a light pulse can be provided to the user, for example, including the use of a display screen, a loudspeaker, haptic feedback, and the like.

[0082] Alternatively (or additionally), if the conditions are suitable (e.g. the treatment apparatus 2 is in contact with the skin, the skin colour that the treatment apparatus 2 is in contact with is suitable to receive a light pulse, and the like), the treatment apparatus 2 can automatically trigger a light pulse, the signal can be provided to a control unit of the treatment apparatus 2, and the control unit can use the signal as part of the decision whether to treat the skin region that is currently adjacent to the orifice 10 with a light pulse.

[0083] The signal output in step 105 can also include information about the hair on the first region of skin. This information can be determined during one or more of the image processing in step 103. The user or a control unit in the treatment apparatus 2 can use this information as part of the decision whether to trigger a light pulse at the current location of the treatment apparatus 2 on the skin. The information can be provided as a value, a percentage, or a combination thereof. In some embodiments, the information includes at least one of a density of the hair in the first region of skin, an intensity of the hair in the first region of skin, a thickness of the hair in the first region of skin, and a colour of the hair in the first region of skin. The colour of the hair can be determined in response to the applied light pulse in terms of a degree of carbonisation of the hair and a degree of curling of the hair, as the amount of hair carbonisation and hair curling varies in response to the light pulse on different colour hair. The degree (amount) of carbonisation of an individual hair (e.g. 50% carbonised) can provide an indication of the thickness and / or intensity of the hair. Information about the density of the hair can be determined by analysing the amount of hair visible in the one or more images.

[0084] Any of these types of information can be used to determine suitable settings for the treatment device 2 to use to trigger the light pulses, for example the intensity setting can be adjusted based on the hair thickness, or the wavelength of the light pulses can be adjusted based on the colour of the hair.

[0085] In some embodiments, the signal output in step 105 can comprise the one or more images received in step 101. The one or more output images can comprise an indication (e.g. in the form of a mask on the image) of one or more portions of the one or more images having hair that has been treated with light pulses.

[0086] It will be appreciated that the image of the skin region can comprise a portion of skin that has been subjected to light pulse treatment and another portion of skin that has not been subjected to light pulse treatment. These different portions can be identified during the processing of step 103, for example by identifying a set of hairs or skin regions in the image that exhibit features consistent with the application of light pulses (e.g. carbonisation and curling), and a separate set of hairs or skin regions in the image that exhibit features consistent with the non-application of light pulses. In these embodiments, the signal output in step 105 can indicate (or comprise information indicative of) one or more portions of the skin region in the image that has been treated with light pulses and / or one or more portions that has not been treated with light pulses.

[0087] Step 103 can comprise processing the one or more images to determine a degree of carbonisation and / or curling of the hair on the first region of skin. It can be determined whether the hair on the first region of skin has been treated with light pulses based on the determined degree of carbonisation and / or curling of the hair in the first region of skin. The degree of carbonisation and / or curling of the hair can be represented as a respective score, for example a high score indicating high carbonisation or high curling, and vice versa. In some embodiments, the determined degrees of carbonisation and curling of the hair can be compared to respective threshold values. In some embodiments, the hair on the region of skin can be determined to have been treated with light pulses if both of the determined degrees exceed the respective threshold values. In other embodiments, the hair on the region of skin can be determined to have been treated with light pulses if at least one of the determined degrees exceeds the respective threshold value. Alternatively, the degree of carbonisation and the degree of curling of the hair in the first region of skin can be combined to form a single combined degree (e.g. a combined score), and this combined degree can be compared to a threshold value to determine whether the hair on the region of skin has been treated with light pulses.

[0088] In some embodiments, the degree of carbonation can be defined based on the color of the hair, the change in hair color relative to a known pre-treatment / pre-light pulse color, the size of the hair, and / or the change in size of the hair relative to a known pre-treatment / pre-light pulse size, and the degree of carbonation of the one or more images can be determined from the color, color change, size, and / or size change shown in the one or more images. The degree of carbonation of the hair can be determined from the number of pixels in the image that are related to the hair or to the carbonated portion of the hair (where the carbonated portion can be identified from the color of those pixels).

[0089] In some embodiments, the degree of curl can be defined based on the curl of the hair and / or the change in curl of the hair relative to a known pre-treatment / pre-light pulse curl, and can be determined from the one or more images from the hair curl and / or curl change shown in the one or more images.

[0090] In other embodiments of step 103, a trained machine learning model (MLM) is used to process the one or more images to determine whether the hair on the first region of skin has been treated with light pulses. The MLM can be any suitable type of MLM, e.g., a classical machine learning model that performs feature extraction such as using a support vector machine, decision tree, random forest, etc., or an artificial neural network such as a deep neural network that has multiple layers between an input layer and an output layer and identifies linear or non-linear relationships between the input layer and the output layer. The MLM evaluates each image to classify whether the hair on the region of skin shown in the image has been treated with light pulses. In some embodiments, the MLM receives the one or more images directly and performs all of the required analysis and processing of the images (e.g., determining the degree of carbonation and / or the degree of curl) to determine whether the hair on the region of skin visible in the image has been treated with light pulses. This is particularly true for MLMs that are artificial neural networks such as deep neural networks. In other embodiments, e.g., where a classical MLM is used, the one or more images can be processed prior to being provided to the MLM, e.g., to determine values for the degree of carbonation and / or the degree of curl, and these degree numbers can be provided to the MLM for analysis (optionally in addition to the one or more images) to determine whether the hair on the region of skin visible in the image has been treated with light pulses.

[0091] The MLM used in embodiments of step 103 will have been trained prior to use by the user / subject. Figure 7 The flowchart in FIG. 1 1 illustrates a method of training a MLM for determining whether hair on a region of skin has been treated with light pulses. Figure 7 The training method in FIG. 1 1 can be performed by any suitable device or apparatus including the apparatus 42, although it will be appreciated that, Figure 7 The method in FIG. 1 1 need not be performed by the apparatus 42 that performs Figure 6Performed by the same device or equipment. For example, Figure 7 The training method can be executed by a centrally located server or computer, and the trained MLM (or computer code representing the trained MLM) is distributed to various devices 42 for determining whether hair on skin areas conforms to... Figure 6 The method used in this study involves light pulse therapy.

[0092] Implemented in device 42 Figure 6 In embodiments of the method, one or more steps of the method may be performed by processing unit 46 in conjunction with any of memory unit 48 and interface circuitry unit 50 and / or imaging unit 44, depending on the circumstances. Processing unit 46 may perform one or more steps in response to executing computer program code that may be stored on a computer-readable medium such as, for example, memory unit 48.

[0093] To train an MLM, a training dataset is required. The training dataset consists of multiple skin images of one or more subjects (and may or may not include images using...). Figure 6 The method involves subjects. Each image in the training dataset is labeled with an indication of whether the hair on the skin in the image has been treated with light pulses. This labeling may be done manually by the user or someone else. The training dataset will include at least one image labeled with an indication that the hair on the skin in the image has been treated with light pulses, and at least one image labeled with an indication that the hair on the skin in the image has not been treated with light pulses. It is understood that the larger the training dataset, the more accurate the resulting MLM may be. In some embodiments, the images in the training dataset may be labeled with additional information, such as hair count (i.e., the number of hairs in the image), hair thickness or hair density, degree of carbonization (e.g., percentage), or any combination thereof. Preferably, in order to make the trained MLM accurate across a range of subjects and hair types, the training dataset should include hair images with different hair (e.g., hair of different colors) response levels to light pulses.

[0094] The training dataset is in Figure 7 The step 111 is used to obtain the images. This step may include collecting images and associated annotations (e.g., using imaging units and user interfaces) or retrieving images for the training dataset from a database or other electronic storage device.

[0095] Next, in step 113, the MLM is trained using the plurality of images in the training data set, such that the MLM is able to distinguish between images of hair on skin that has been treated with light pulses and images of hair on skin that has not been treated with light pulses. The MLM is trained to distinguish between images based on the degree of carbonization and the degree of curling of the hair shown in the images. Where the training data set includes annotations relating to hair count, hair thickness, hair density and / or percentage carbonization, the MLM can also be trained to provide an indication of these parameters for an input image. Techniques for training the MLM using the training data set are known to those skilled in the art, and details are not provided herein. However, as one example, the MLM can be trained using cross-validation, which trains the MLM using a subset of the images in the training data set and tests the accuracy of the trained MLM using one or more other images in the training data set. This training and testing can be repeated for different subsets of the images in the training data set to arrive at a final trained MLM. The trained MLM can then be used in step 103 of the method of Fig. 1. Figure 6

[0096] In some embodiments, once the MLM is deployed and used by a particular subject, the accuracy of the MLM can be improved or tailored to the particular subject's skin / hair characteristics by updating the MLM using images of the subject's skin that have been manually or automatically annotated to confirm whether light pulses have been applied. Alternatively or additionally, if the imaging unit 44 is part of the treatment device 2, the imaging unit 44 can be controlled to acquire images of the skin region after the treatment device has applied light pulses to that skin region.

[0097] The updating (or retraining) of the MLM can be achieved by adding images of the subject to the training data set and retraining the MLM using the updated training data set. In some embodiments, this updating or retraining can be performed as part of the MLM calibration procedure when the subject first starts using the apparatus 42.

[0098] An improvement is therefore provided in determining whether hair on a skin region has been treated with light pulses.

[0099] ​Variations to the disclosed embodiments can become apparent to those of ordinary skill in the art upon reading the foregoing description and understanding the principles and the details of the methods and techniques described herein. In the claims, the term comprising does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude a plurality. A single processor or other unit can fulfil the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. A computer program can be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state storage medium supplied together with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. An apparatus (42) for use with a care device (2), wherein the care device is configured to apply light pulses to the skin of a subject to perform a care operation on hair on the skin, the apparatus comprising a processing unit (46) configured to: Receive one or more images of a first region of the skin from an imaging unit (44), wherein the imaging unit is arranged to acquire images of the subject's skin; Its features are, The processing unit (46) is further configured to: The one or more images are processed to determine whether the hair in the first region of the skin has been treated with light pulses based on the degree of at least one of carbonization and curling of the hair in the first region of the skin shown in the one or more images. as well as Output a first signal indicating whether the hair on the first area of ​​the skin has been treated with light pulses.

2. The apparatus (42) of claim 1, wherein the processing unit (46) is configured to determine the degree of carbonization of the hair based on the color and / or size of the hair determined from the one or more images.

3. The apparatus (42) according to claim 1 or 2, wherein the processing unit (46) is configured to determine the degree of curl of the hair based on the degree of curvature of the hair determined from the one or more images.

4. The apparatus (42) according to any one of claims 1 to 3, wherein the processing unit (46) is configured to determine whether the hair on the first region of the skin has been treated with light pulses by: The degree of at least one of carbonization and curling of the hair on the first region of the skin is determined and compared with corresponding thresholds for the degree of carbonization and the degree of curling; or The determined degree of carbonization and curliness of the hair are combined into a combined degree of carbonization and curliness, and the combined degree of carbonization and curliness is compared with a threshold value for the combined degree of carbonization and curliness.

5. The apparatus (42) according to any one of claims 1 to 4, wherein the processing unit (46) is configured to process the one or more images using a trained machine learning model to determine whether the hair on the first region of the skin has been treated with light pulses.

6. The apparatus (42) according to claim 5, wherein the processing unit (46) is further configured to: Receive one or more additional images of the first region of the skin from the imaging unit (44), wherein the imaging unit acquires the one or more additional images after a light pulse is applied to the first region of the skin; and The trained machine learning model is updated using one or more additional images.

7. The apparatus (42) according to any one of claims 1 to 6, wherein the processing unit (46) is further configured to analyze the one or more images to identify portions of the one or more images including hair, and the processing unit is configured to process the identified portions of the one or more images to determine whether the hair on the first region of the skin has been treated with light pulses.

8. The apparatus (42) according to any one of claims 1 to 7, wherein the processing unit (46) is further configured to process the one or more images to determine additional information about the hair on the first region of the skin, and to include the additional information in the first signal.

9. The apparatus (42) according to claim 8, wherein the additional information includes at least one of the following: The density of the hair in the first region of the skin; The intensity of the hair in the first region of the skin; The thickness of the hair in the first region of the skin; and The color of the hair in the first region of the skin.

10. The apparatus (42) according to any one of claims 1 to 9, wherein the first signal includes the one or more images and an indication of one or more portions of the one or more images having been treated with light pulses.

11. The apparatus (42) according to any one of claims 1 to 10, wherein the apparatus further comprises a user interface configured to receive the first signal, and wherein the first signal is configured to cause the user interface to output feedback to a user of the care device (2) regarding whether the hair on the first area of ​​the skin has been treated with light pulses.

12. The apparatus (42) according to any one of claims 1 to 11, wherein the first signal is output to a control unit of the care device (2), and wherein the control unit is configured to determine, based on the first signal, whether the care device should apply a light pulse to the first area of ​​the skin.

13. A system comprising: Imaging unit (44), the imaging unit being arranged to acquire images of the subject's skin; as well as The device (42) according to any one of claims 1 to 12.

14. A computer-implemented method for determining whether hair on a region of a subject's skin has been treated with light pulses, the light pulses originating from a treatment device (2), wherein the treatment device is configured to apply light pulses to the subject's skin to perform a treatment on the hair on the skin, wherein the method comprises: Receive one or more images of a first region of the skin from the imaging unit (44), wherein the imaging unit is arranged to acquire images of the subject's skin; The method is characterized in that it further comprises: Processing (103) the one or more images to determine whether the hair in the first region of the skin has been treated with light pulses based on the degree of carbonization and curling of the hair in the first region of the skin shown in the one or more images; and The output (105) is a first signal indicating whether the hair on the first area of ​​the skin has been treated with light pulses.

15. The method of claim 14, wherein the processing (103) step comprises: The method further includes using a trained machine learning model (MLM) to analyze the one or more images to determine whether hair on a region of skin in the one or more images has been treated with light pulses, and the method further includes: Acquire (111) multiple images of the skin of one or more test subjects, wherein each image is labeled with an indication of whether the hair on the skin in the image has been treated with photopulse, wherein the multiple images include at least one image labeled with an indication that the hair on the skin in the image has been treated with photopulse, and at least one image labeled with an indication that the hair on the skin in the image has not been treated with photopulse; and The MLM is trained (113) using the plurality of images to distinguish between images of skin hair that have been treated with light pulses and images of skin hair that have not been treated with light pulses, based on the degree of carbonization and curling of the hair shown in the images.

16. A computer program product comprising a computer-readable medium containing computer-readable code configured to cause the computer or processing unit (46) to perform the method of claim 14 or 15 when executed by a suitable computer or processing unit (46).

Images