Hair removal instrument adaptive light output control method and hair removal instrument

CN122350864APending Publication Date: 2026-07-10ZHENGYIJIANG (GUANGXI) INTELLIGENT MANUFACTURING TECHNOLOGY CO LTD
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ZHENGYIJIANG (GUANGXI) INTELLIGENT MANUFACTURING TECHNOLOGY CO LTD
Filing Date
2026-04-10
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing hair removal devices lack real-time sensing and adaptive adjustment mechanisms, requiring a high level of user proficiency and easily leading to skin burns and discomfort.

Method used

By continuously acquiring skin image information, calculating skin color depth level and hair removal device displacement, and dynamically adjusting light intensity, frequency, and duration, uniform light illumination can be achieved.

Benefits of technology

It reduces uneven energy distribution, differences in hair removal results, and the risk of skin burns caused by uneven operation speed, thus improving user experience and safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122350864A_ABST
    Figure CN122350864A_ABST
Patent Text Reader

Abstract

This invention relates to the field of hair removal devices, specifically providing an adaptive light emission control method and a hair removal device. The method includes the following steps: continuously acquiring skin image information; performing grayscale processing on the acquired image information; calculating the skin tone depth level based on one frame of the image; performing feature point matching on the continuous images and calculating the displacement of the hair removal device by calculating the inter-frame displacement; controlling the light emission intensity, light emission frequency, and duration of the hair removal device based on the depth level and the displacement of the hair removal device to ensure uniform light exposure to the skin. This invention controls the light emission parameters during hair removal based on the user's skin tone depth and the movement trajectory of the hair removal device, achieving dynamic and coordinated adjustment of light intensity, frequency, and pulse width, effectively reducing uneven energy distribution, differences in hair removal effects, and the risk of skin burns caused by uneven operation speed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of hair removal devices, and more particularly to an adaptive light emission control method and a hair removal device. Background Technology

[0002] With the improvement of residents' living standards and increased awareness of skin beauty, laser and intense pulsed light (IPL) hair removal devices based on the principle of photothermal action have become one of the mainstream products in the home and commercial skin beauty field due to their advantages such as long-lasting hair removal effect and convenient operation. Existing IPL hair removal devices generally adopt a fixed parameter control mode, meaning that their light-emitting module emits light energy to the skin at a preset fixed frequency, fixed light intensity, and fixed duration during operation. Users need to manually hold the hair removal device and control its movement on the skin surface to complete the hair removal operation.

[0003] However, this type of fixed parameter control mode has obvious limitations and safety hazards: During operation, after irradiating one area, the distance the user moves the hair removal device depends on the user's own perception, which can result in the distance being too large or too short. When the moving distance is too large, there will be areas that are not irradiated. When the user moves the distance too short, the same area of ​​skin will continuously receive high-energy light for a short period of time, and the local skin temperature will rise rapidly and exceed the skin's safe tolerance range. This can cause discomfort such as redness and stinging, or even irreversible damage such as skin burns and pigmentation, seriously affecting the user experience and skin health.

[0004] Furthermore, existing technologies lack real-time sensing and adaptive adjustment mechanisms for user operation, and cannot dynamically adjust the luminescence parameters according to the movement of the hair removal device on the skin surface, resulting in a high requirement for user proficiency. Therefore, this application proposes an adaptive light emission control method for a hair removal device and a hair removal device in general. Summary of the Invention

[0005] The purpose of this invention is to provide an adaptive light emission control method and a hair removal device to solve the problem of poor usability of current hair removal devices.

[0006] To achieve the above objectives, the present invention provides the following technical solution: An adaptive light emission control method for a hair removal device includes the following steps: Continuously acquire skin image information; The acquired image information is converted to grayscale. Calculate the depth level of skin color based on one of the image frames; Feature point matching is performed on continuous images, and the displacement of the hair removal device is calculated by calculating the inter-frame displacement. The intensity, frequency, and duration of light emitted by the hair removal device are controlled based on the depth level and the displacement of the device to ensure that the skin receives uniform light.

[0007] Preferably, when acquiring image information of the skin, the skin is illuminated with auxiliary light of a preset intensity, and the calculation of skin color depth includes the following steps; Acquire a frame of RAW image and subtract the black level of that frame; Extract the average grayscale value of the red channel of the image; Based on the mapping relationship between the preset grayscale threshold range and the depth level, the depth level to which the obtained average grayscale value belongs is determined.

[0008] Preferably, before acquiring image information under auxiliary light, an ambient light image with the auxiliary light off is first acquired to subtract ambient light interference. The specific method includes the following steps: Acquire a RAW image with the auxiliary light off, calculate the average gray value of the image, and record it as the first gray value; Acquire a RAW image with auxiliary light on, calculate the average gray value of the image, and record it as the second gray value; Calculate the difference between the second gray value and the first gray value, and record it as the third gray value. Use the third gray value to determine the skin depth level.

[0009] Preferably, when acquiring a RAW image frame, the step of removing the black level of that frame is not performed.

[0010] Preferably, the method for calculating inter-frame displacement includes the following steps: The acquired images are converted to grayscale before being filtered and denoised. Divide the image into uniform blocks and extract the image's feature set; The displacement vectors of each sub-block between adjacent frames are calculated using a block matching algorithm, and blocks whose displacement vectors are less than a preset value are selected as valid blocks. Calculate the offset of the valid block; Based on the principle of global consistency, abnormal blocks are eliminated, and the real-time displacement of the hair removal device is calculated based on the offset of the remaining blocks.

[0011] Preferably, the image acquired first is designated as the first image, and the image acquired later is designated as the second image. The method for calculating the offset of the effective block includes the following steps: Select the valid block within the second image and denote it as the offset block; Search for a region with a radius of R around the block at the same position as the offset block in the first image; Calculate the difference between the searched block and the offset block, and select the block with the smallest difference as the original block; Calculate the vector difference between the offset block and the original block, which is the offset of the original block. Then, traverse all valid blocks in the second image. Remove valid blocks whose offset deviation exceeds the threshold, and calculate the average offset of the remaining blocks, which is the offset of the valid blocks.

[0012] The present invention also discloses an adaptive hair removal device, including a main body, wherein the main body is provided with a light emission hole, a light source module and a light control component, the light control component controls the light source module to generate light of a preset wavelength emitted from the light emission hole, and the method by which the light control component controls the light source module includes the above-described adaptive light emission control method for hair removal devices.

[0013] Furthermore, the adaptive hair removal device also includes: A detection light module is integrated on one side of the light output hole to generate auxiliary light of a preset intensity and irradiate the skin surface. The detection light module is electrically connected to the light control component. CMOS image sensor for continuously acquiring skin images; An image processing unit is used to receive image information from the CMOS image sensor and transmit it to the light control unit.

[0014] Furthermore, the adaptive hair removal device also includes: An infrared sensor is used to acquire skin temperature, and the light control device is electrically connected to the infrared sensor.

[0015] In summary, the present invention has the following advantages compared with the prior art: The adaptive light emission control method for hair removal devices disclosed in this invention controls the light emission parameters during hair removal based on the user's skin tone and the movement trajectory of the hair removal device. This achieves dynamic and coordinated adjustment of light intensity, frequency, and pulse width, effectively reducing uneven energy distribution, differences in hair removal effects, and the risk of skin burns caused by uneven operation speed. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the adaptive light emission control method for a hair removal device disclosed in Embodiment 1 of the present invention.

[0017] Figure 2 This is a schematic diagram of the process for calculating skin tone depth in the case of no auxiliary light in the adaptive light emission control method for hair removal devices disclosed in Embodiment 1 of the present invention.

[0018] Figure 3 This is a schematic diagram of the process for calculating skin tone depth in the adaptive light emission control method for hair removal devices disclosed in Embodiment 1 of the present invention when there is auxiliary light.

[0019] Figure 4This is a schematic diagram of the process for calculating the displacement of the hair removal device in the adaptive light emission control method for the hair removal device disclosed in Embodiment 1 of the present invention.

[0020] Figure 5 This is a flowchart illustrating the calculation of the offset of the effective block in the adaptive light emission control method for hair removal devices disclosed in Embodiment 1 of the present invention.

[0021] Figure 6 This is a schematic diagram of the structure of the hair removal device disclosed in Embodiment 2 of the present invention.

[0022] Figure 7 This is an exploded view of the hair removal device disclosed in Embodiment 2 of the present invention.

[0023] Figure 8 This is a schematic diagram showing the connection of the infrared sensor, detection light module, and CMOS image sensor in the hair removal device disclosed in Embodiment 2 of the present invention.

[0024] Figure label: 100. Outer shell; 110. First shell; 120. Second shell; 130. Third shell; 131. Flexible sleeve; 132. Light emission hole; 133. Detection head; 200. Light source module; 210. Touch panel; 300. Control board; 400. Capacitor; 500. Heat sink; 600. Fan; 700. Detection module; 710. Detection light module; 720. CMOS image sensor; 730. Infrared sensor. Detailed Implementation

[0025] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0026] Example 1: As Figure 1 As shown, an embodiment of the present invention provides an adaptive light emission control method for a hair removal device, comprising the following steps: S10. Continuously acquire skin image information; S20. Grayscale processing of the acquired image information; S30. Calculate the depth level of skin color based on one of the frames of the image; S40. Perform feature point matching on continuous images and calculate the displacement of the hair removal device by calculating the inter-frame displacement. S50 controls the light intensity, frequency, and duration of the hair removal device based on the depth level and the displacement of the device, so as to ensure that the skin is evenly illuminated.

[0027] Specifically, in this embodiment, when the hair removal device is working, a CMOS image sensor integrated at the end of the device acquires images of the skin at a preset frequency (60fps) and transmits them to the processor of the device. The CMOS image sensor outputs RAW format images. After the processor acquires the image information of the skin, it performs grayscale processing on the RAW image. The processor takes out an image before the light is emitted and compares the grayscale value of the image with the grayscale value range of the preset depth level to obtain the depth level of the user's skin. Then, based on the feature point matching results of two consecutive frames, it calculates the instantaneous displacement vector of the hair removal device on the skin surface. The displacement vector includes the displacement magnitude and direction, and the light emission parameters are dynamically adjusted in combination with the displacement magnitude and depth level. For example, the light emission intensity is reduced for dark skin to prevent skin burns. For areas that have been irradiated, the light emission stops, and the displacement direction determines whether to enter a new irradiation area. The light emission continues only when the new irradiation area is entered. This method allows users to keep the hair removal device on their skin and control its movement. The device adjusts the light output parameters based on the speed (or distance) and depth of the skin, thereby improving the hair removal effect and reducing the chance of skin burns.

[0028] As a preferred embodiment of this example, Figure 2 As shown, when acquiring skin image information, the skin is illuminated with auxiliary light of a preset intensity. The calculation of skin color depth includes the following steps: S31. Acquire a frame of RAW image and subtract the black level of that frame; S32. Extract the average gray value of the red channel of the image; S33. Based on the mapping relationship between the preset grayscale threshold range and the depth level, determine the depth level to which the obtained average grayscale value belongs.

[0029] Specifically, in this embodiment, the CMOS sensor outputs a RAW format image. When the processor of the hair removal device acquires the RAW image, it first performs black level correction on the RAW image by subtracting a fixed value to eliminate noise caused by the dark current of the sensor. The fixed value to be subtracted is determined based on the actual measurement data of the sensor under no-light conditions or the calibration parameters preset at the factory. The corrected image then extracts the mean value of the red channel. After normalization, the mean value is mapped to the grayscale range of 0 to 255 and compared with the preset skin depth level threshold table to accurately determine the skin depth level. In this embodiment, the mapping relationship between the preset grayscale threshold range and the depth level is determined in the laboratory. The calibration method is to use artificial skin samples with standard skin color, collect RAW images of skin of various shades under constant light and temperature and humidity, statistically analyze the grayscale mean distribution of the red channel, and generate a grayscale threshold table according to the preset level classification standard. After verification by the Fitzpatrick six-type classification method, the grayscale mean ranges corresponding to types I to VI are defined as [210,255], [180,209], [150,179], [120,149], [90,119], and [40,89], with an error tolerance of ±3.

[0030] Preferred, such as Figure 3 As shown, before acquiring image information under auxiliary light, an ambient light image is first acquired with the auxiliary light off to subtract ambient light interference. The specific method includes the following steps: S33. Acquire a RAW image with the auxiliary light off, calculate the average gray value of the image, and record it as the first gray value; S34. Acquire a RAW image with the auxiliary light on, calculate the average gray value of the image, and record it as the second gray value. S35. Calculate the difference between the second gray value and the first gray value, and record it as the third gray value. Use the third gray value to determine the skin depth level.

[0031] Specifically, in this embodiment, to improve the grading accuracy, a two-frame difference method is used to eliminate ambient light disturbances. Before the auxiliary light is turned on, a frame of RAW image without auxiliary light is captured, and its red channel mean is extracted and recorded as the first gray value. Immediately after the auxiliary light is turned on, a second frame of RAW image is captured, and the corresponding red channel mean is extracted as the second gray value. The difference between the two is the pure auxiliary light response component. This difference is then normalized to the range of 0-255 and substituted into the aforementioned gray value threshold table for depth level determination. This difference strategy effectively removes the ambient light background, so that the response value only reflects the skin's true absorption characteristics of the auxiliary light, which conforms to the physiological law that the darker the skin color, the stronger the red light absorption, and the smaller the difference. Thus, it maintains the robustness and clinical consistency of type I-VI classification even in complex lighting scenarios.

[0032] It should be noted that when using the two-frame difference method to eliminate ambient light disturbances, the black level of the image is not removed when calculating the average gray value. Since the time difference between two consecutive frames is very small, the black level drift can be regarded as a constant bias, which is naturally canceled out in the difference calculation. Therefore, there is no need for an additional black level correction module, which simplifies the hardware design and avoids gray level deviation caused by black level estimation error.

[0033] As a preferred embodiment of this example, Figure 4 As shown, the method for calculating inter-frame displacement includes the following steps: S41. After grayscale processing, the acquired image is then filtered and denoised preprocessed. S42. Divide the image into uniform blocks and extract the image feature set; S43. Calculate the displacement vector of each sub-block between adjacent frames using the block matching algorithm, and select the block whose displacement vector is less than the preset value as the bit valid block. S44. Calculate the offset of the valid block; S45. Based on the principle of global consistency, abnormal blocks are removed, and the real-time displacement of the hair removal device is calculated based on the offset of the remaining blocks.

[0034] Specifically, in this embodiment, motion estimation is performed using two consecutive frames of images. First, the acquired images are converted to grayscale, and then noise is suppressed using a 3×3 mean filter (or median filter). The grayscale image is uniformly divided into 8×8 pixel local blocks, and the average grayscale value of the pixel blocks is used as the feature value. Subsequently, block matching is performed between two consecutive frames. Using the sum of absolute differences (SAD) criterion, all candidate positions are traversed within a local search window centered on the current block coordinates (e.g., radius R pixels, where R is a preset value, such as 16 pixels), and the position with the smallest SAD is selected as the initial offset estimate. The RANSAC algorithm is used to fit a translation model to the initial offset of all 8×8 blocks. After removing outliers, the median of the displacement vectors of all interior points is calculated. Finally, the real-time displacement of the hair removal device is characterized by the fitted rigid motion parameters.

[0035] Preferably, in this embodiment, such as Figure 5 As shown, the image acquired first is designated as the first image, and the image acquired later is designated as the second image. The method for calculating the offset of the effective block includes the following steps: S44.1 Select the valid block within the second image and denote it as the offset block; S44.2 Search for a region with a radius of R within the first image that is at the same position as the offset block; S44.3 Calculate the difference between the searched block and the offset block, and select the block with the smallest difference as the original block; S44.4 Calculate the vector difference between the offset block and the original block, which is the offset of the original block. Traverse all valid blocks in the second image. S44.5. Remove valid blocks whose offset deviation exceeds the threshold, and calculate the average offset of the remaining blocks, which is the offset of the valid blocks.

[0036] Specifically, in this embodiment, the current frame image is denoted as T, and the previous frame image is denoted as T-1. When calculating the average effective block offset, both images T and T-1 are divided into M×N 8×8 pixel blocks. For each sub-block in image T, block matching is performed in image T-1 within a region centered at the corresponding position and with a radius of R (e.g., 32 pixels). The similarity between the current block and each candidate block within the window is calculated. If the SAD criterion is used to quantify the similarity, the displacement vector corresponding to the position with the minimum SAD is taken as the initial estimated offset of the block. The candidate block with the highest similarity is selected as the matching block (the currently matched block in image T is denoted as the offset block, and the block with the highest similarity is denoted as the original block). The matching error (e.g., the minimum SAD value) and the displacement vector ( ,in, For displacement vector, ( , ) represents the coordinates of the offset block, ( , (The original block coordinates are used), and matching results with SAD values ​​less than 1.5 times the global median are retained; based on the spatial consistency assumption, the median of the orientation angle and the median of the magnitude of the displacement vectors of all matching blocks are calculated, and blocks with orientation angle deviations exceeding the threshold (e.g., 30°) or magnitude deviations exceeding the threshold (e.g., 50%) are removed; using the remaining valid matching blocks, a translation model (i.e., the average or median of all displacement vectors) is fitted, and the set of valid matching blocks and the fitted overall translation vector are output; the pixel translation vector is multiplied by the factory-calibrated pixel-physical conversion coefficient to obtain the actual physical displacement.

[0037] In this embodiment, when controlling the light emission parameters, the initial light intensity is determined based on the skin color depth level, with darker skin corresponding to a lower initial light intensity and lighter skin corresponding to a higher initial light intensity. Then, the light emission frequency and pulse width are adjusted according to the real-time displacement: when the displacement is less than a preset threshold (e.g., 0.5mm / frame), it is determined to be stationary or moving slowly, and the light emission frequency is appropriately reduced (e.g., from 5Hz to 3Hz) and the pulse width is extended (e.g., from 10ms to 15ms) to avoid excessive accumulation of local energy; when the displacement is greater than or equal to the preset threshold, the light emission frequency is increased (e.g., restored to 5Hz) and the pulse width is shortened (e.g., maintained at 10ms) to ensure that all areas of the skin receive uniform energy coverage during the movement.

[0038] Preferably, in this embodiment, when controlling the light emission frequency, skin temperature data collected by an infrared sensor is also used. If the temperature exceeds a safe threshold (e.g., 45°C), the light emission is immediately paused and a prompt is issued. The operation is resumed after the temperature drops back to a safe range, further ensuring the safety of use. Example 2: The present invention also discloses an adaptive hair removal device, including a body, wherein the body is provided with a light emission hole 132, a light source module 200 and a light control component, the light control component controls the light source module 200 to generate light of a preset wavelength emitted from the light emission hole 132, and the method by which the light control component controls the light source module 200 includes the above-described adaptive light emission control method for hair removal devices.

[0039] Specifically, in this embodiment, such as Figure 6 and Figure 7 As shown, the hair removal device includes a housing 100, one end of which is provided with a light outlet 132. The housing 100 integrates a light source module 200, a control board 300, a capacitor 400, a heat sink 500, and a fan 600.

[0040] The outer casing 100 includes a first casing 110, a second casing 120, and a third casing 130. The first casing 110 and the second casing 120 are both groove-shaped structures. The first casing 110 and the second casing 120 are fastened together to form a receiving cavity with an opening at one end. The third casing 130 is detachably connected to the opening of the receiving cavity by a snap-fit ​​connection to form a complete closed structure. The light emission hole 132 is provided on the third casing 130. The second casing 120 is provided with a control button. The control button is electrically connected to the control board 300 and is used to adjust the light intensity, frequency, and working mode.

[0041] The light source module 200 is existing technology. The light source module 200 includes a light-emitting cavity, which is a hollow shell structure. A light source and a reflector are fixedly connected inside the light-emitting cavity. The light source is a xenon lamp, and the reflector has a circular groove structure. The light source is located inside the reflector. A light-emitting end is provided on the light-emitting cavity, and the light-emitting end is coaxially aligned with the light-emitting hole 132 to ensure that the light is focused by the reflector and emitted vertically. A lens structure made of quartz glass is provided on the light-emitting end. A touch piece 210 is integrated on the light-emitting end. The touch piece 210 is a ring-shaped thin-film pressure sensor used to detect the user's pressure and contact area, and provides real-time feedback to the control board 300. The light source module 200 is only allowed to start when effective contact is detected (pressure ≥ 0.3N and contact area ≥ 80% of the area covered by the light-emitting hole 132), preventing false triggering due to suspension. The touch piece 210 is electrically connected to the control board 300.

[0042] Preferably, the third housing 130 is provided with a flexible sleeve 131 at the light outlet 132. The flexible sleeve 131 is made of medical silicone material and is embedded in the edge of the light outlet 132. After deformation, it closely fits the contour of the skin, which not only buffers the impact of pressing but also enhances the sealing of the light path.

[0043] The control board 300 is existing technology, and it is equipped with a light control component, which is a main control chip in the prior art. This main control chip has a built-in control algorithm, which controls the light emission parameters of the xenon lamp during operation, such as dynamically adjusting the pulse energy and pulse width based on skin temperature, skin tone depth level, real-time displacement of the hair removal device, and real-time fit. The control method described in Embodiment 1 is integrated into the firmware of the main control chip. The control board 300 also integrates a display screen, and the first housing 110 has a transparent structure, such as a transparent plate, at the corresponding position of the display screen to allow the display content to pass through and to protect the display screen.

[0044] The control board 300 integrates a power module, such as a charging and discharging structure, which is electrically connected to a capacitor 400. The capacitor 400 is connected in parallel with the xenon lamp and is used to release high-energy pulses instantaneously to ensure that the energy of a single flash is stable and the peak power meets the standard. The power module is powered by AC mains. After the xenon lamp completes one firing, the power module charges the capacitor 400 in preparation for the next firing.

[0045] The heat sink 500 is existing technology. It employs a copper-based aluminum fin composite structure and is in close contact with the heat source areas of the light source module 200 and the control board 300. The fan 600 works in conjunction with the heat sink 500 through intelligent temperature control logic. It automatically starts and stops when the temperature sensor detects a local temperature exceeding 55°C, ensuring that the light source module 200 remains within a safe thermal range under continuous pulse output. The heat sink 500 is fixedly connected to the control board 300 with screws, and the fan 600 is fixedly connected to the heat sink 500 with bolts.

[0046] In a preferred embodiment of this invention, the adaptive hair removal device further includes a detection light module 710, a CMOS image sensor 720, and an image processing unit. The detection light module 710 is integrated on one side of the light outlet 132 and is used to generate auxiliary light of a preset intensity and irradiate the skin surface. The detection light module 710 is electrically connected to the light control component. The CMOS image sensor 720 is used to continuously acquire skin images. The image processing unit is used to receive the image information from the CMOS image sensor 720 and transmit it to the light control component.

[0047] Specifically, the third housing 130 is provided with a detection head 133 at the end of the light outlet 132. The detection head 133 is a groove-shaped structure disposed inside the third housing 130. The detection head 133 is provided with an optical window adapted to the detection light module 710 and the CMOS image sensor 720 to ensure that the detection light and the imaging path do not interfere with each other. The detection light module 710 is an LED lamp that generates white light of a specific wavelength and intensity to uniformly illuminate the target area. The CMOS image sensor 720 is prior art. The CMOS image sensor 720 and the detection light module 710 are electrically connected to the light control component. The image processing unit can be a dedicated image processing coprocessor embedded in the light control component or an image processing program.

[0048] Preferably, the adaptive hair removal device further includes an infrared sensor 730 for acquiring skin temperature, and the light control component is electrically connected to the infrared sensor 730. The infrared sensor 730 collects skin surface temperature data in real time, is electrically connected to the light control component, and feeds back the temperature data to the light control component.

[0049] In this embodiment, as Figure 8 As shown, the detection optical module 710, CMOS image sensor 720, and infrared sensor 730 are integrated on a single circuit board, forming a replaceable detection module 700. The detection module 700 is connected to the main control chip via a standard interface and is fixed to the inside of the detection head 133 with hot melt adhesive. The detection head 133 is also provided with a temperature measurement window corresponding to the infrared sensor 730.

[0050] The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms “a,” “the,” and “the” used in this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0051] It should be understood that although the terms first, second, third, etc., may be used in this invention to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of this invention, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0052] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An adaptive light emission control method for a hair removal device, characterized in that, Includes the following steps: Continuously acquire skin image information; The acquired image information is converted to grayscale. Calculate the skin depth level based on one of the image frames; Feature point matching is performed on continuous images, and the displacement of the hair removal device is calculated by calculating the inter-frame displacement. The intensity, frequency, and duration of light emitted by the hair removal device are controlled based on the depth level and the displacement of the device to ensure that the skin receives uniform light.

2. The adaptive light emission control method for hair removal devices according to claim 1, characterized in that, When acquiring skin image information, the skin is illuminated with auxiliary light of a preset intensity. The calculation of skin color depth includes the following steps: Acquire a frame of RAW image and subtract the black level of that frame; Extract the average grayscale value of the red channel of the image; Based on the mapping relationship between the preset grayscale threshold range and the depth level, the depth level to which the obtained average grayscale value belongs is determined.

3. The adaptive light emission control method for hair removal devices according to claim 2, characterized in that, Before acquiring image information under auxiliary light, an ambient light image with the auxiliary light off is first acquired to subtract ambient light interference. The specific method includes the following steps: Acquire a RAW image with the auxiliary light off, calculate the average gray value of the image, and record it as the first gray value; Acquire a RAW image with auxiliary light on, calculate the average gray value of the image, and record it as the second gray value; Calculate the difference between the second gray value and the first gray value, and record it as the third gray value. Use the third gray value to determine the skin depth level.

4. The adaptive light emission control method for a hair removal device according to claim 3, characterized in that, When acquiring a RAW image frame, the step of removing the black level of that frame frame is not performed.

5. The adaptive light emission control method for a hair removal device according to claim 1, characterized in that, The method for calculating inter-frame offset includes the following steps: The acquired images are converted to grayscale before being filtered and denoised. Divide the image into uniform blocks and extract the image's feature set; The displacement vectors of each sub-block between adjacent frames are calculated using a block matching algorithm, and blocks whose displacement vectors are less than a preset value are selected as valid blocks. Calculate the offset of the valid block; Based on the principle of global consistency, abnormal blocks are eliminated, and the real-time displacement of the hair removal device is calculated based on the offset of the remaining blocks.

6. The adaptive light emission control method for a hair removal device according to claim 5, characterized in that, The method for calculating the offset of the effective block, denoted as the first image acquired first and the second image acquired later, includes the following steps: Select the valid block within the second image and denote it as the offset block; Search for a region with a radius of R around the block at the same position as the offset block in the first image; Calculate the difference between the searched block and the offset block, and select the block with the smallest difference as the original block; Calculate the vector difference between the offset block and the original block, which is the offset of the original block. Then, traverse all valid blocks in the second image. Remove valid blocks whose offset deviation exceeds the threshold, and calculate the average offset of the remaining blocks, which is the offset of the valid blocks.

7. An adaptive hair removal device, comprising a body, wherein the body is provided with a light emission hole, a light source module, and a light control component, the light control component controlling the light source module to generate light of a preset wavelength emitted from the light emission hole, characterized in that, The method by which the light control device controls the light source module includes the adaptive light emission control method for the hair removal device according to any one of claims 1-6.

8. The adaptive hair removal device according to claim 7, characterized in that, The adaptive hair removal device also includes: A detection light module is integrated on one side of the light output hole to generate auxiliary light of a preset intensity and irradiate the skin surface. The detection light module is electrically connected to the light control component. CMOS image sensor for continuously acquiring skin images; An image processing unit is used to receive image information from the CMOS image sensor and transmit it to the light control unit.

9. The adaptive hair removal device according to claim 8, characterized in that, The adaptive hair removal device also includes: An infrared sensor is used to acquire skin temperature, and the light control device is electrically connected to the infrared sensor.