32 results about "Skin color change" patented technology

The invention relates to a gesture identification method based on depth information. The existing method has certain problems in the practical application environment and user experience. Firstly, a real-time depth image is acquired, a background image is acquired after background modeling, and a foreground area is detected by using the background image and the current image as a difference. Secondly, the built background image is updated and an independent human body area is extracted, then, a hand area and outline information are detected from each independent human body area, and the movement track of the hands tracking is obtained. Finally, the movement track is modeled by using a hidden Markov model to identify the gesture. The method can adapt to interference of skin color changes, is barely affected by factors such as distance, illumination, shading, movement and the like in the indoor environment, and is small in arithmetic calculation amount and high in real-time performance.

The invention relates to a non-contact physiological parameter detection method, system and device capable of detecting in real time and dynamically displaying human body physiological parameters. The preprocessing of trend term removal, filtering and normalization is carried out on each color component mean value matrix of a RGB (red, green, blue) image, the trend changes of data step property, upswept property, slantly downward property and longspan fluctuation, which are caused by background environment parameter changes are eliminated, and the antijamming capability of detection and the accuracy of the measured physiological parameters are improved. The consistency of positions and sizes of face images which are captured by front and rear frames is guaranteed, and noise interference produced by face image extraction is reduced to the greatest extent; through the amplification of skin color parameters when a RGB color component mean value is calculated, the difference value when the skin color changes along with the human body physiological activity is amplified, the loss of tiny useful signals in the data processing process is prevented, and the precision and the accuracy of extracting the human body physiological parameters are thus improved.

The invention provides a dynamic self-adaption skin color segmentation method and a device. The method comprises the following steps: a red green blue (RGB) image is obtained; colors and space of the RGB image are transformed to obtain a hue saturation value (HSV) image; a face of a person is tested to obtain a position and an area of the face; color values of a skin color pixels in the face area are collected to serve as a skin color sample, and color values of positions with intense light changes are recorded to serve as a skin color change sample; each chromatic value or saturation value of histograms of the skin color sample and the skin color change sample are polled and are combined with predetermined weight; through the covering rate of the pixel counts within the chrominance or saturation threshold ranges of the histograms to the total counts of the corresponding histograms, skin color segmentation threshold values are obtained; the skin colors are tested through the skin color segmentation threshold values. By means of the above method and device, the skin color dynamic and self-adaption segmentation can be achieved, and thereby the accuracy of the skin color testing and the adaptability of the skin color testing to light changes are improved.

The invention discloses a heart rate detection method based on a smart phone. The heart rate detection method is used for solving the technical problem that an existing heart rate detection method is poor in precision. According to the technical scheme, the heart rate detection method comprises the steps that a video recording human body skin color changes under irradiation of a stable light source is input to the smart phone, and human body volume pulse waves are calculated and captured by the smart phone; when main wave peaks are sought, an amplitude value of a current detection point is compared with an average amplitude value of multiple previous point near the current detection point, the volume pulse waves are located in a descending branch if the amplitude value of the detection point is small, the volume pulse waves are located in an ascending branch if the amplitude value of the detection point is large, alternation from the ascending branch to the descending branch serves as one main wave peak, and the heart rate is calculated by combining the interval time of the main wave peaks. According to the method, detection is always conducted along volume pulse wave signals, and therefore missing detection of the main wave peaks is avoided; the amplitude value of the current detection point is always compared with the average amplitude value of multiple previous points near the current detection point, therefore, double pulse peaks cannot change the descending state of the pulse waves, and false detection of the main wave peaks is avoided. Accordingly, the hear rate detection precision is improved.

The invention discloses a water-in-oil type liquid foundation composition form with a color mixing function as well as utilization and preparation methods thereof. The water-in-oil type liquid foundation composition form can be freely adjusted according to skin colors and tones of consumers, skin color changes caused by seasons or sunshine or skin color modification requirements (a T zone and a Vzone); the water-in-oil type liquid foundation composition form comprises the following products: a basic-color liquid foundation, a bright-color liquid foundation, a pink-color liquid foundation anda dark-color liquid foundation; the bright-color liquid foundation or the pink-color liquid foundation or the dark-color liquid foundation is compounded through the basic-color liquid foundation to obtain a liquid foundation suitable for skin colors of Asian women; a spectrocolorimeter is combined with an LCh color space to quantitatively describes that the brightness L value is 50 to 75 and the tone h value is 40 to 70.

The invention provides gene chips for skin gene detection and a kit thereof. The gene chips comprise the anti-sun-spot gene chip, the anti-freckle gene chip and the anti-sunburn gene chip. The kit comprises the gene chips, the anti-sun-spot capacity, the anti-freckle capacity and the anti-sunburn capacity of an individual can be quickly detected, genetic information of the spot generation resistance of the individual is obtained before generation of sun spots and freckles, the chips also help the individual to know about genetic information of skin color change of the individual, the individual is guided in taking related prevention measures, and the powerful support is provided for individualized medical beauty. The gene chips are adopted for detection, multiple detection genetic loci exist, in combination with questionnaires and actual observation, the sensitivity of a detection effect is good, the accuracy rate is high, the practicability is high, sampling is conducted conveniently,and the gene chips are conveniently popularized and applied to the beauty industry.

The invention discloses an anti-interference non-contact heart rate detection method based on a face video. The method comprises the following steps: (1) acquiring a video image containing face information through a camera; (2) extracting a face area of interest; (3) calculating the mean value of the data of all pixel RGB channels for the area of interest, and converting the mean value into a color space with separable brightness and color; (4) detrending color components, and projecting the detrended color components to a color component plane to obtain an elliptical model of skin color change; (5) extracting the change of the skin color projected to the long axis of the elliptical model along with the heart rate by using an RANSAC algorithm; and (6) filtering the change, and extracting the heart rate of a testee by using a complete ensemble empirical mode decomposition method. The invention provides a quicker and more accurate non-contact heart rate detection algorithm, and the heartrate value of a head in a moving or static state can be measured more accurately.

The invention provides a composition for skin, application of the composition, a whitening and brightening cosmetic composition and a preparation method of the whitening and brightening cosmetic composition, and relates to the technical field of cosmetics. The skin composition comprises verbascoside, nicotinamide and a lactic acid bacteria fermentation lysate, wherein the verbascoside is mainly used for inhibiting formation of melanin particles, the nicotinamide is mainly used for inhibiting melanin from being transmitted to keratinocytes, and the lactic acid bacteria fermentation lysate is mainly used for accelerating shedding of melanin-containing cells in a cuticle. The verbascoside, the nicotinamide and the lactobacillus fermentation lysate are matched and have a synergistic effect, so the problems of melanin content, reduction and/or elimination of skin color change caused by hormone or environmental factors such as ultraviolet rays in a human body can be solved from a multi-dimensional and multi-channel target spot; therefore, the effects of effectively brightening the skin color and reducing the melanin content are achieved. The invention further provides application of the composition for skin and a whitening and brightening cosmetic composition.

The invention provides a production method of cellular structure tension change-based skin-color-changeable fluorescent fish. The production method comprises the following steps: selecting fluorescentprotein pairs, a cytoskeletal protein and a promoter to construct a recombinant transposon vector of a skin-color-changeable fluorescent protein, wherein the fluorescent protein pairs include a bluefluorescent protein and a green fluorescent protein, a cyan fluorescent protein and an orange fluorescent protein as well as a gold fluorescent protein and a cherry red fluorescent protein; simultaneously injecting the recombinant transposon vector and Tol2 mRNA into single-cell stage fertilized eggs of fish species to be treated so as to enable a target gene to be integrated into genome; screening and identifying the fish species which can stably express skin color change so as to obtain the fluorescent fish with changeable skin color caused by cellular structure tension change under light induction. The skin of the fluorescent fish obtained based on a fluorescence energy resonance transfer technology and a gene cloning technology changes the fluorescence color under light induction and in full and hungry conditions, so that the interaction between people and the fish is increased, the interestingness is improved, and the pattern of the ornamental fish market is greatly expanded.

The embodiment of the invention relates to the technical field of intelligent security, and discloses a drunk driving intelligent identification method, device and system. The method comprises the steps: receiving the first image of the driver face and the second image of the driver face collected by the high-definition camera in a parking lot; further judging whether the skin color of the secondimage and the first image changes if the first image of the driver face and the second image of the driver face match and determining that the driver is suspected to be drunk driving when the skin color change exceeds the preset skin color threshold; starting the toll station camera to collect the driving tracks of the vehicle; and determining that the driver is drunk driving if the driving tracksexceed the preset driving tracks. With application of the method, the technical problem of manually judging drunk driving at present can be solved so as to realize better confirmation of driver's drunk driving and provide one more guarantee for road traffic safety.

The invention discloses a non-contact heart rate variability feature extraction method based on a real application scene. The method comprises the following steps: 1) collecting an image containing a human face; 2) acquiring an image face area by using a face detection and tracking combined strategy; 3) enhancing skin color change through Euler amplification; 4) color space conversion and channel separation; 5) self-adaptive threshold skin detection; 6) extracting a source signal; (7) EEMD denoising; 8) carrying out five-point sliding smoothing filtering; 9) peak point detection and abnormal peak point correction; and 10) RR interval calculation and time domain, frequency domain and nonlinear HRV feature extraction. According to the method, the strategy for improving the feature extraction speed and the strategy for overcoming the influence of shaking and illumination and improving the feature extraction accuracy are integrated in the feature extraction method, the HRV features can be rapidly extracted in a non-contact mode in a real application environment, and it is guaranteed that the HRV features are consistent with contact type extraction results.

The invention discloses a dynamic skin changing method and device for a chart following user interface and computer equipment. The dynamic skin changing method for the chart following the user interface comprises the steps: monitoring display parameters of the user interface in real time; judging whether the display parameters of the user interface are changed or not; and if the display parametersof the user interface are changed, running the chart skin changing function to change the skin of the chart. According to the dynamic skin changing method and device for a chart following a user interface and computer equipment, by monitoring the display parameters of the user interface in real time, when it is monitored that the display parameters of the user interface change, the chart skin changing function is operated to change the skin of the chart, the chart skin color can change along with the skin color change of the user interface in real time, the refreshing effect of the user interface is avoided, and the user experience is improved.

The invention provides a beauty skin color change method and apparatus. The method comprises the steps of obtaining an original image, sending an operation instruction to the original image and judging the operation instruction; if the operation instruction is a ruddy operation instruction, obtaining an image red hue region in an RGB space of the original image; calculating HSV space chroma, an offset weight and an actually required offset angle of each pixel point in the red hue region; converting each pixel point to a YUV space, and according to the actually required offset angle, performinghue offset operation on the pixel point through matrix operation, and increasing the saturation through the matrix operation; and converting each pixel point subjected to the saturation increment inthe YUV space into a pixel point of the RGB space through the matrix operation, thereby obtaining a ruddy image corresponding to the original image. The image skin color beauty change effect and efficiency can be improved.

The invention discloses an in-vivo detection method based on skin color change, which comprises the following steps: providing a camera to take frame sequential user images; and providing a detectionsystem to detect whether the green component of the skin color in frame sequential user images is changed or not, if the change occurs, then the in-vivo detection passes, if no change occurs, the in-vivo detection fails. The invention also discloses another in vivo detection method based on skin color change, which includes the following steps: providing a camera to take frame sequential user images; and providing a detection system to detect whether the gray value of the skin in the frame sequential user images changes or not, if the gray value of the skin in the frame sequential user imageschanges, the in-vivo detection passes; If the gray value of the skin in the frame sequential user images does not change, the in-vivo detection fails.

The invention relates to the field of artificial intelligence, and particularly discloses a heart rate estimation method, device and equipment based on image recognition and a storage medium. The method comprises the steps: acquiring multiple frames of scene images, determining multiple frames of skin images according to the multiple frames of scene images, and extracting skin color change signalsfrom the multiple frames of skin images; obtaining a current scene corresponding to the multiple frames of scene images, and selecting a filtering interval corresponding to the current scene according to the current scene; filtering the skin color change signal in the filtering interval to obtain a filtered skin color change signal; and determining the heart rate according to the wave crest of the filtered skin color change signal. According to the invention, the half-frequency phenomenon can be inhibited, and the heart rate identification accuracy is improved. In addition, the invention alsorelates to the blockchain technology, and the scene image can be stored in a blockchain node.

The invention relates to the field of traditional Chinese medicine physiotherapy and treatment and particularly relates to a method for measuring cupping situations based on skin image recognition situations. An initial skin image can be shot by a camera; a skin image in a cup is shot by the camera at a time interval of 30 s and automatically uploaded to a central control system; skin color changes are measured according to time serial numbers; and cupping is stopped immediately when the skin image has a too dark color and is analyzed to be purplish red and dripping occurs.

The invention relates to the field of biological recognition and blockchain, and particularly discloses a feature wave extraction method, device and equipment and a storage medium, and the method comprises the steps: obtaining multiple frames of skin images of a preset region, and extracting a skin color change signal from the multiple frames of skin images; performing interference removal on theskin color change signal to obtain a processed skin color change signal; carrying out signal decomposition on the processed skin color change signal to obtain a plurality of intrinsic mode functions;performing Fourier transform on each intrinsic mode function to obtain frequency information corresponding to each intrinsic mode function; and determining a target feature wave according to the frequency information corresponding to each intrinsic mode function. In addition, the invention also relates to a blockchain technology, and the skin image, the skin color change signal and the target feature wave can be stored in the blockchain node. The integrity and the accuracy of the obtained target feature wave are improved.

The invention discloses a lower limb arterial embolism monitoring device, and relates to the technical field of medical instruments, the lower limb arterial embolism monitoring device comprises a movable base and a fixed base, the sides, close to limbs, of the movable base and the fixed base are cambered surfaces, a sensor collection belt is arranged on the cambered surfaces, and the sensor collection belt is composed of a temperature sensor and a piezoelectric sensor; The distance between the movable base and the fixed base is adjustable, the fixed base is provided with a measuring scale, the top end of the fixed base is provided with an arc-shaped support, the arc-shaped support is provided with a sliding support, the bottom end of the sliding support is provided with an arc-shaped block, and the bottom end of the arc-shaped block is provided with a sensor for monitoring arterial pulse of limbs. Automatic clamping and attaching are carried out through electric driving, too tight pressing can be effectively avoided, the comfort is improved. Meanwhile, multiple indexes are detected, and the swelling degree, the pulse condition, the skin color change and other problems of limbs of a patient are accurately measured.