84 results about "Color Skin" patented technology

A gesture recognition system using a skin-color based method combined with motion information to achieve real-time segmentation. A Kalman filter is used to track the centroid of the hand. The palm center, palm bottom, as well as the largest distance from the palm center to the contour from extracted hand mask are computed. The computed distance to a threshold is then compared to decide if the current posture is “open” or “closed.” In a preferred embodiment, the transition between the “open” and “closed” posture to decide if the current gesture is in “select” or “grab” state.

A method for detecting a facial area on a color image includes (a) placing a search window on the color image, (b) determining if a center pixel of the search window is a skin color pixel, indicating that the search window is a possible facial area candidate, (c) applying a 3-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (d) applying a 4-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (e) if steps (b), (c), (d) all determine that the search window is a possible facial area candidate, applying an AdaBoost filter to the search window to determine if the search window is a facial area candidate, and (f) if step (e) determines that the search window is a facial area candidate, saving the location of the search window.

A gesture recognition system and method that inputs videos of a moving hand and outputs the recognized gesture states for the input sequence. In each image, the hand area is segmented from the background and used to estimate parameters of all five fingers. The system further classifies the hand image as one of the postures in the pre-defined database and applies a geometric classification algorithm to recognize the gesture. The system combines a skin color model with motion information to achieve real-time hand segmentation performance, and considers each dynamic gesture as a multi-dimensional volume and uses a geometric algorithm to classify each volume.

The invention discloses a three-dimensional gesture estimation method and a three-dimensional gesture estimation system based on depth data. The three-dimensional gesture estimation method comprises the following steps of S1, performing hand region of interest (ROI) detection on photographed data, and acquiring hand depth data, wherein the S1 comprises the processes of (1), when bone point information can be obtained, performing hand ROI detection through single bone point of a palm; (2) when the bone point information cannot be obtained, performing hand ROI detection in a manner based on skin color; S2, performing preliminary estimation in a hand three-dimensional global direction, wherein the S2 comprises the processes of S21, performing characteristic extracting; S22, realizing regression in the hand global direction according to a classifier R1; and S3, performing joint gesture estimation on the three-dimensional gesture, wherein the S3 comprises the processes of S31, realizing gesture estimation according to a classifier R2; and S32, performing gesture correction. According to the three-dimensional gesture estimation method and the three-dimensional gesture estimation system, firstly cooperation of two manners is utilized for dividing hand ROI data; afterwards estimation in the hand global direction is finished according to a regression algorithm based on hand ROI data dividing; and finally three-dimensional gesture estimation is realized by means of the regression algorithm through utilizing the data as an aid. The three-dimensional gesture estimation method and the three-dimensional gesture estimation system have advantages of simple algorithm and high practical value.

A method for enhancing the color of an image to be displayed on a display includes receiving an image having a plurality of pixels where each of the pixels has a plurality of color components. The image is filtered using a spatial filter in such a manner that the lower frequency content of the image is enhanced in such a manner that the dynamic range of the lower frequency content is increased. The filtered image is modified such that the higher frequency content of the image to obtain a modified image that includes the higher frequency content and the lower frequency content.

A method and apparatus for recognizing a gesture in an image processing system. In the apparatus, an input unit receives an image obtained by capturing a gesture of a user using a camera. A detector detects a face area in the input image, and detects a hand area in gesture search areas. The gesture search areas being set by dividing the image into predetermined areas with reference to a predetermined location of the detected face area. A controller sets the gesture search areas, determines whether a gesture occurs in the detected hand area, and selects a detection area with respect to the gesture to generate a control command for controlling an image device. A calculator calculates skin-color information and differential-area information for checking a gesture in the detected hand area. Accordingly, a hand area can be accurately detected, and a gesture can be separated from peripheral movement information, so that mal-functioning caused by gesture recognition can be reduced.

A skin state analyzing method for analyzing the skin state of an examinee using an image of the skin of the examinee includes an analyzing step of analyzing at least one of texture / pores, spots, skin tone, and sebum of the skin from the image, a storing step of storing the image and an analysis result obtained from the analyzing step in association with skin examination date / time information and examinee information, a display screen generating step of generating a screen displaying the image and the analysis result of the examinee stored in the storing step, and an output step of outputting the information generated in the display screen generating step.

The invention provides a gesture identification method applied to control of a mobile service robot for the elder and disabled. Static gesture identification is combined with dynamic gesture identification, interference caused by complex background, large-area skin color or shielding during gesture segmentation can be eliminated, a man-machine interaction manner is natural and friendly, gesture instruction can be identified rapidly and accurately and a wheelchair is controlled safely when the method is applied to a mobile service robot system based on gesture identification, the movement range of a user is increased, and life quality of the user is improved effectively.

A gesture recognition system using a skin-color based method combined with motion information to achieve real-time segmentation. A Kalman filter is used to track the centroid of the hand. The palm center, palm bottom, as well as the largest distance from the palm center to the contour from extracted hand mask are computed. The computed distance to a threshold is then compared to decide if the current posture is “open” or “closed.” In a preferred embodiment, the transition between the “open” and “closed” posture to decide if the current gesture is in “select” or “grab” state.

The invention discloses a dynamic gesture recognition method based on Kinect depth information. Two static gestures for determining the start and end of a dynamic gesture are recognized through a depth image sequence obtained by a Kinect sensor. After the start gesture is detected, the position of a hand in a depth image is found through a depth threshold method, and then, the coordinates of the palm are found according to the palm features to carry out tracking. After the end gesture is recognized, tracking is stopped, and the track of the dynamic gesture is obtained. The gesture track is encoded using eight reference direction vectors, and the dynamic gesture is compared with reference dynamic gestures through an accelerated DTW (Dynamic Time Warping) method to get a recognition result quickly. By using Kinect depth information, the influence of external environments such as complex background, skin color and illumination can be eliminated. By adding the static gestures for determining the start and end and optimizing the DTW method, the efficiency and accuracy of dynamic gesture recognition are improved.

A color cosmetic composition containing color impregnated spherules where the color is expressed from the spherule upon application of the cosmetic to the keratinous surface and the expressed spherule serves an uptake function on the keratinous surface; a cosmetic composition containing a rupturable spherule filled with color, and a method for color skin using such compositions.

The invention provides a people stream counting system and a method thereof. The method comprises: firstly, recording the first face information at a first time point into a memory; then, identifying whether an image captured by a camera at the second time point is a complexion zone; if the complexion zone is real face, further judging that the face is frontal face or side face, and recording the judgement result into spurious face information; then, matching the similarity of the spurious face information and the first face information one by one; when the similarity matching reaches the set condition, taking the spurious face information as the first face information; when the similarity matching does not reach the set condition, recording the spurious face information as the second face information into the memory, and setting that the first face information is shaded; and finally, calculating the amount of people stream which passes through according to the face recorded by the memory.

An underwear garment is provided to give an illusion of a tattoo on the skin of the wearer above the pant line of an outer garment. The underwear garment has the shape of a panty with front and back panels formed of a sheer material, a crotch area connecting the lower portions of the front and back panels, and a waist area connecting the upper portions of the front and back panels. One or both of the front and back panels have a printed tattoo image formed on the sheer material. The sheer material is a single-ply, stretchable nylon material having a skin tone color. The tattoo image is applied to the sheer material by silkscreen printing.

The invention discloses a supermarket shopping cart hand identification method. The method comprises the following steps of (1) determining a hand position, taking a shopping cart opening as a reference surface H1, monitoring whether an object is located above the reference surface, and storing an image if the object is located above the reference surface; (2) carrying out image processing, and through establishing a skin color model, processing the image acquired from the step1; and (3) determining an object holding state, and carrying out secondary determination on the image acquired from the step2. In the invention, through steps of motion detection, skin color detection and hand and commodity determination, whether a hand holds a commodity can be accurately determined. By using the method, extra burdens and requirements to a user are not generated, and a whole determination process is automatically performed, which is very simple and convenient.

The invention discloses a gesture tracking method of any hand shape. The method comprises the following steps: (1), initializing a background model; (2), initializing a position area of a hand; (3), obtaining a statistical histogram of a target area according to the position area of hand; (4), according to the statistical histogram, carrying out histogram back projection on an image that is read in at the current time so as to obtain a skin color probability graph; (5), difference processing is carried out on a current frame, a previous frame, and the background model respectively so as to obtain a difference image; (6), on the basis of the difference image, all pixel points are marked with different types so as to obtain a foreground probability graph; (7), a motion skin color probability graph based on the foreground probability graph and the skin color probability graph; (8), carrying out clustering on the motion skin color probability graph and localizing a precise position of the human hand; and (9) updating the background model according to a tracking result. According to the invention, human hand tracking can be carried out simply and effectively; and the requirement of the hand shape of the user is low. Moreover, the computation complexity is low; and the humanization effect is realized.

The invention discloses a skin base liquid having a micro-ecological balance self-repairing function. The skin base liquid comprises, by weight, 0.05-0.1% of sodium hyaluronate, 0.05-0.2% of carbomer, 0.05-0.2% of triethanolamine, 0.05-0.1% of disodium ethylenediaminetetraacetate, 1.5-2.5% of lubrajel oil, 0.05-0.1% of methyl p-hydroxybenzoate, 2-3% of apple fruit cell culture extract, 0.5-1% of glycerol glucoside, 2-3% of ganoderma lucidum extract, 2-5% of palmitoyl tripeptide-5, 2-5% of alpha-arbutin, 0.5-1% of dendrobium officinale extract, 0.5-1% of caprylhydroxamic acid and 0.5-2% of azone. The skin base liquid can effectively repair cell damage, promote cell metabolism, make dark and uneven color skin bright and moist and make skin fine, soft and youthful.

The invention discloses a buffing algorithm suitable for an image shot by a mobile device. The algorithm comprises the steps of S100, acquiring the original image; S200, carrying out skin color detection on the original image, generating a Gaussian pyramid of a skin color probability graph, utilizing the original image to generate a Gaussian pyramid of a grayscale image, estimating global buffing intensity of the grayscale image, and calculating a stretching coefficient table of the buffing intensity; S300, calculating a similarity matrix through the Gaussian pyramid of the skin color probability graph, the Gaussian pyramid of the grayscale image and the stretching coefficient table of the buffing intensity; and S400, utilizing the similarity matrix to carrying out buffing operation on the original image, and synthesizing a final image. According to the algorithm, automatic buffing can be realized, and a user is enabled to complete buffing by one key; and the algorithm is simple and stable, is natural in a buffing effect, and runs smoothly on the mobile device.

The invention discloses a method for realizing a 360-degree turn-around real-time virtual fitting. Included is a virtual fitting system based on Kinect and gray prediction. The method comprises the steps of preparing a virtual person model, a clothing model and an accessory model in advance; wearing the clothing model on the virtual person model for corresponding binding; then subjecting the obtained skeleton joint point data through the Kinect and the virtual person model to cross corresponding binding; determining the front and back of a human body by using face detection of an elliptic skin color model; predicting the data change in left and right crotch joint points of the human body by using a gray prediction model in real time; and combining the results of the face detection and gray prediction to determine whether the skeleton joint data controlling the virtual person model are required to be corrected. For different cases, the virtual person model is driven to move by using different skeleton joint point data of the human body. The method of the invention can realize 360-degree fitting experience. A user can not only see the front fitting effect but also can see the fitting effects of the side and the back. The real-time performance is good and the stability is strong.

A method to detect anchorperson segment in news reporting by using visual characteristics to provide the basis to divide news into various categories includes steps of providing news image for skin color detection on the image with color space; applying morphology depending on whether the object in the image subject to skin color detection is moving to eliminate noise surrounding the image of the face to solve the region of the face of the anchorperson; and performing anchorperson detection once again by detecting the probable anchorperson segment.

A method for tinting, for coloring skin, or for increasing the tanned appearance of skin comprising the use of an extract of a plant from the family of Compositae or Asteraceae, preferably an extract of chicory (Cichorium intybus L.), and a method of screening a plant for the manufacture of a cosmetic composition for coloring, particularly for tinting, at least one part of skin.

The invention relates to the technical field of image processing, The invention discloses a method for realizing vehicle-mounted GUI skin removing by using shader, which comprises the following steps:a shader shader is programmed by using Opengl shading language GLSL, so that one shader shader runs on GPU in parallel to realize GUI color skin removing; Create two shaders in Opengl ES: Vertex shaders and fragment shaders, The invention adopts GPU to process data, realizes the skin real-time skin removing effect of any color of any figure based on Opengl ES, improves the speed of real-time drawing image for all pixels, vertices, texture position, hue, saturation, lightness and contrast, greatly improves the conversion efficiency, and achieves the requirement of small input and small modification.

Provided is a new type of virtual mouse driving method which is independent from individual skin color and capable of being implemented in general environments having a certain degree of disturbance. The virtual mouse driving method according to the invention in which a method of driving the virtual mouse is controlled by a change of hand shape includes an input step of receiving a plurality of images captured by an imaging camera at mutually different time points, a difference image extracting step of extracting a difference image among a plurality of images, and a virtual mouse driving step based on the extracted difference image.

The invention relates to a static gesture recognition method based on a bounding box. The method comprises the following steps: segmenting a gesture region in a scene image according to skin color information, and obtaining a gesture image; secondly, considering the geometrical characteristics of the gestures from multiple aspects aiming at the influence of deformation on the geometrical characteristics of the gestures, proposing an idea of utilizing a layering strategy, and realizing recognition tasks of various gestures in two steps; firstly, the number of fingers in a gesture image is detected; on the basis, gesture modeling is carried out by utilizing the relative positions of fingers, multi-type gesture classification is converted into classification of two gesture types in the current step, the problem of complex calculation caused by feature data fusion is avoided, gesture modeling and classification are carried out by utilizing gesture geometrical features, and the gesture recognition rate is improved.

The invention discloses a dynamic gesture recognition system and a dynamic gesture recognition method using a hidden Markov model fused with hand shapes and motion characteristics. The method comprises the following steps of extracting a hand region, tracking the hand region, extracting gesture characteristics, training a classifier and recognizing a gesture. In the scheme, a new hand region extraction algorithm based on image edges and hand skin colors is provided; the hand region, new dynamic gesture characteristic extraction manners and characteristic processing manners are segmented from each frame of image of a gesture video; a dynamic gesture classifier is constructed by use of hidden Markov model; the classifier is trained in combination with hand shape characteristics and hand motion characteristics; and finally, the trained classifier can be used for recognizing new gestures except a training sample set in real time. According to the dynamic gesture recognition system and thedynamic gesture recognition method using the hidden Markov model fused with hand shapes and motion characteristics, the dynamic gesture can be recognized with low calculation complexity, and thus thesystem and the method can be practically applied.

A method for detecting a facial area on a color image includes (a) placing a search window on the color image, (b) determining if a center pixel of the search window is a skin color pixel, indicating that the search window is a possible facial area candidate, (c) applying a 3-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (d) applying a 4-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (e) if steps (b), (c), (d) all determine that the search window is a possible facial area candidate, applying an AdaBoost filter to the search window to determine if the search window is a facial area candidate, and (f) if step (e) determines that the search window is a facial area candidate, saving the location of the search window.

The invention discloses a dynamic display real-time three-dimensional virtual fitting system and method. The system comprises an information acquisition unit, a data storage unit, a digital human construction unit, a virtual fitting unit and a pushing unit. The information acquisition unit is used for acquiring information of user body data, user face images and man-machine interaction instructions; the data storage unit is used for constructing and storing a human body model database, a hair style and skin color chartlet database, a clothing template database, a skeleton animation database and a three-dimensional scene database; the digital human construction unit is used for reconstructing the human body model in the data storage unit according to the information obtained by the information acquisition unit; the virtual fitting unit is used for performing sewing and cloth simulation on the garment sample and completing fitting display; and the pushing unit is used for rendering the display animation of the digital human in the three-dimensional scene in real time to complete a three-dimensional virtual fitting process, and uploading the display animation to a cloud end or a client for storage. According to the invention, personalized requirements of users can be met.

The invention discloses a training sample generation method and device, a storage medium and electronic equipment. The training sample generation method comprises: acquiring an object identifier of ato-be-trained object and a model file corresponding to the object identifier, wherein the model file comprises a three-dimensional model and a skin map set, and the skin map set comprises a pluralityof pure-color skin maps and a plurality of colored skin maps; determining corresponding transformation models of the three-dimensional model under different orientation angles, wherein each orientation angle corresponds to one transformation model; generating a plurality of sample image groups according to the plurality of color skin maps and the transformation model; generating a labeling graph of each sample graph group according to the object identifier, the plurality of pure-color skin chartlets and the transformation model; and generating the training sample of the to-be-trained object according to the annotation image and the sample image group, so that the sample image and the annotation image can be automatically generated, manual screenshot and annotation are not needed, and the sample generation efficiency is high.

The invention provides an accessory recommendation method, an accessory virtual try-on method and device, and electronic equipment, and relates to the field of artificial intelligence. The method comprises the steps of obtaining a target face image of a to-be-recommended accessory; extracting face feature data of the target face image; wherein the face feature data comprises one or more of face feature data, five-sense-organ feature data and skin color feature data; and inputting the face feature data in the target face image into an accessory recommendation model obtained by pre-training, andobtaining recommendable suitable accessory style information through the accessory recommendation model. According to the invention, proper accessories can be directly recommended to the user quicklyand effectively according to the condition of the user, the user does not need to try on for many times with time and labor wasted, and the user experience is better improved.