63 results about "Tongue coat" patented technology

The invention discloses a method for automatic tongue coating segmentation based on deep learning. The method comprises the steps of S1, collecting and inputting an image comprising a tongue coating;S2, for the image including the tongue coating, adopting a Faster R-CNN deep learning method for tongue coating detection, and automatically obtaining a preliminary tongue coating region image; S3, calibrating the preliminary tongue coating region image with a VGG deep learning method to obtain a more accurate tongue coating region image; and S4, automatically segmenting a tongue coating image according to the calibrated tongue coating region image. The method in the invention realizes the more accurate tongue coating segmentation based on the deep learning method of big data, and solves the problem that the existing method has low accuracy of tongue coating segmentation.

An interactive oral cleaning tool set comprises a toothbrush head used for cleaning teeth, a tongue coating brush head used for cleaning tongue coatings, a clearance brush head used for cleaning gaps of trigona where the teeth and gingiva are connected, a bacterial plaque brush head used for cleaning bacterial plaque on the teeth and a brush handle which is detachably connected with the four brush heads in a clamping mode, and the lower end of each four brush head is arranged on an insertion column of a base in an inserted mode; a DMP module integrates a three-axis accelerometer and six-axis data provided by a three-axis gyroscope into Euler angles so as to directly reflect a moving posture of a current brush head, brush head moving data collected by an MPU6050 chip are read in an STM32L0 ARM microprocessor, when a tooth brushing gesture is incorrect, the STM32L0 ARM microprocessor enables a vibration motor to vibrate, APP application software of a mobile terminal gives out corresponding prompt words, and brush moving data in the mobile terminal are transmitted to a developer cloud database through WIFI. The interactive oral cleaning tool set has the advantages of being capable of conducting cleaning guidance and error correction and saving energy and environmentally friendly.

The invention discloses a graph theory-based Chinese medicinal tongue nature and tongue coat separation algorithm, which comprises the following steps of: converting an acquired tongue image into a hue, saturation and value (HSV) model, and dividing a tongue coat initial segmentation area by using an H value; dividing the tongue image into a set of areas; forming an initial segmentation result by using the initial segmentation area and an independent vertex in the image; sequentially stacking differences among area combination operator calculation areas; when valid elements are in the stack, separating the areas if the difference of the stack top areas is greater than one of the internal differences of two areas, determining that the stack top elements are invalid, repeating the step, otherwise, merging the two areas, and deleting the stack top elements and the differences between the related areas of the two areas; and calculating related contents of the newly merged areas, stacking the differences among the areas, and resetting the invalid elements in effect. According to the characteristic of the H value of the HSV space, the tongue coat initial segmentation area is determined, and segmentation efficiency and precision of the algorithm are improved; a threshold function adaptive algorithm is constructed, and the nature and coat crossing detail distinguishing capacity of the algorithm is improved; and the iterative algorithm of the segmentation process is improved by using area combination operators, and smooth nature and coat transition areas are segmented according to the human eye perceptiveness.

The invention discloses a tongue coating greasyness identification method based on texture and distribution characteristics. The method comprises steps that, (1), a training sample set is established by utilizing acquired tongue surface image samples in combination with Gabor textures, Tamura roughness and tongue coating distribution characteristics; (2), the training sample set is trained by utilizing a support vector machine to establish a tongue coating greasyness classifier; and (3), the established tongue coating greasyness classifier is utilized for identification to determine whether a to-be-identified tongue surface image belongs to a greasy tongue phenomenon type. Through the method, tongue surface image textures, roughness and tongue coating distribution characteristic vectors are acquired, the support vector machine is employed as the classifier to simulate tongue coating image identification of Chinese medical specialists, and repeatability is realized; in an identification stage through the method, artificial guidance and parameter setting are not necessary, the greasy tongue phenomenon determination mechanism is more visual and fairer; Chinese medical identification on the greasy tongue phenomenon is simulated, and problems of strong subjectivity and poor repeatability existing in traditional Chinese medicine visual observation about the greasy tongue phenomenon are solved.

The invention discloses a physique analysis method based on face and tongue image acquisition, which comprises the following steps: a doctor initially inputs personal information of a patient user andestablishes a personal electronic medical record for the patient user to archive; Under the standard illumination environment, the images of the patient's face and tongue were collected, and then theimages were preprocessed. The facial contour region is segmented to extract the color and luster information of the five internal organs feature regions, and then the tongue region of the front tongue image is segmented to extract the tongue quality and tongue coating information of the tongue body. Based on the YCbCr color space, the color and luster of the five internal organs characteristic regions were analyzed, and then the tongue quality and tongue coating information were analyzed, and the results of physique test were obtained synthetically. Generate and archive physique analysis reports. The method can improve the efficiency of physician's constitution diagnosis.

The invention belongs to the field of image processing and image analyzing and understanding, and particularly relates to a traditional Chinese medicine tongue body and tongue coating separation method based on a green monochromatic source. A tongue image acquisition system is established; tongue images acquired under a white light source and the green light source are collected; the tongue body portions of the tongue images extracted under the white light source and the green light source are respectively collected; image registration based on mutual information is performed on the two tongue body images; all the portions on a tongue body are totally aligned with one another; tongue body and tongue coating separation is performed on a tongue image acquired under the green light source; a tongue coating on the white light source is extracted in a masking mode through the tongue coating position information obtained through separation of the green light source. The method has the advantages that RGB images are converted into gray level images, then, histogram equalization is performed, image contrast is increased so that the tongue coating portion can be prominent, and stimulation on a tested person caused by light source changes and differences of two tongue images caused by tongue body shaking and tongue position changes are further reduced through an image registration method, wherein the tongue body shaking and the tongue position changes are caused by personal factors of the tested person.

The invention discloses a hyperspectral traditional Chinese medicine coated tongue quality classification method based on D-Resnet, and relates to the field of computer vision. Based on tongue coatingtongue quality classification of an RGB color space, the information amount is insufficient, a hyperspectral tongue image contains a large amount of spectral and spatial information, and the tongue coating tongue quality classification of a human body is realized by extracting the spectral reflectance change condition of a certain area of the tongue image and combining the spatial distribution information provided by the hyperspectral image. According to the method, an end-to-end D-Resnet network is provided to classify hyperspectral tongue images; the method comprises the following steps of:firstly, constructing a dense connection module to extract spectral information; then, a pre-activation bottleneck residual error module (pre-activation bottleneck residual error module) is constructed, so that space information can be extracted, and the spatial information of the pre-activation bottleneck residual error module can be obtained; according to the method, the coated tongue quality classification based on the hyperspectral image is realized.

The invention discloses a tongue coating tongue quality analysis method and system, computer equipment and a storage medium. The method comprises the following steps: acquiring an image of a tongue region from a face image comprising the tongue region according to a tongue positioning model; Separating the tongue part from the image of the tongue part area by using an elliptical template to form atongue part image; Dividing the tongue image into a tongue image and a tongue coating image according to a coating separation algorithm; And matching the tongue image with a pre-stored tongue color classification model, and matching the tongue coating image with the tongue coating color classification model to obtain tongue classification and tongue coating classification. By adopting the method,the speed and the accuracy of separating the tongue coating from the tongue in the image can be improved.

The invention discloses a tongue coat clearing device, relates to the field of medical care and aims at solving the problem that at present, part of devices capable of clearing tongue coat are arranged on the back sides of toothbrushes, but no electric clearing product good in use effect and convenient to carry is produced. A handle is arranged on one side of a body, an opening is formed in the other side of the body, a turning wheel is arranged in the opening, a rotary shaft of the turning wheel is sleeved with a spur gear, the spur gear is meshed with a worm wheel, the worm wheel is connected with an output shaft of a motor, a battery and a switch are arranged in the handle and used for controlling rotation of the motor. When the tongue coat clearing device is used, the effect of scraping off tongue coat can be played by attaching the turning wheel with a scraping sheet to tongue coat, then turning on the switch make the motor rotate and making the motor drive the worm wheel to rotate and thus drive the turning wheel to rotate. The tongue coat clearing device is ingenious in structure and convenient to operate and has a wide market prospect.

The invention belongs to the medicine field, particularly relates to a pharmaceutical composite for curing colon cancer and a preparing method thereof. The technical problem solved by the invention is to provide a brand-new pharmaceutical composite for curing colon cancer and a preparation method thereof. The pharmaceutical composition comprises the following components: 5-11 parts of rucea javanica, 5-11 parts of common camptotheca fruit, 8-16 parts of semen coicis and/or sargentgloryvinestem, 8-16 parts of curcumaaromaticaSalisb, and 5-16 parts of gingseng and/or campanumaea pilosula. The pharmaceutical composition has efficacies of clearing away heat and toxic material, activating blood circulation, removing masses, benefiting vital energy and strengthening healthy energy and the like.Long-term clinic observation and series of experimental researches show that the pharmaceutical composition has good anti-cancer effect, especially has obvious curative effect. The parasitical composition mainly cures patients of colon cancer suffering from toxin and phlegm internal resistance and qi deficiency, has the symptoms of abdominal pain, fixed pain spot, unpalpable pain, abdominalmass, abdominal distention, acratia, anorexia, dark-purple tongue or tongue with blockage points or ecchymosises, white and greasy tongue coat, and pulse fine tart, and is used by patients of colon cancer or colon cancer postoperation dialectical species suffering from toxin and phlegm internal resistance and qi deficiency.

The invention discloses a traditional Chinese medicine tongue coating greasiness identification method. The method comprises the following steps: obtaining an image containing a tongue part; carryingout image preprocessing: segmenting a tongue body and smoothing the edge of a tongue image; extracting the texture features of the tongue coating image based on a Gabor wavelet algorithm; removing theedge effect of the tongue image; identifying the tongue coating greasy coating and obtaining an identification result; combining picture features with a traditional classifier, acquiring a tongue coating greasy recognition result accurately, and assisting traditional Chinese medicine diagnoses.

The invention discloses a shoe-tongue-coating jacquard elastic band forming a different-direction special pattern and a weaving technology thereof. The elastic band comprises a fabric body, the fabric body is interwoven by weft yarns and weft yarns to form wide-strip protruding areas and narrow-strip concave areas, and the wide-strip protruding areas and the narrow-strip concave areas are distributed in a staggered mode at intervals. In the product, according to different textures and different thickness degrees of fiber materials, different yarn discharging technologies and the designed pattern, computer jacquard typesetting is carried out; through the concave-convex view angle difference of the thickness of the yarns, a colored yarn of a lateral concave portion is concealed by a protruding portion, and the color of the other colored yarn can only be showed; the shown pattern effect is different when the constructed observing view direction is different, the pattern conversion effect is formed, and the using requirements are met.

The invention discloses a tongue coating image collection device which can photograph and video various tongue coatings and provide clear and accurate tongue coating images so as to promote normalization and standardization of traditional Chinese medicine diagnosis. The tongue coating image collection device comprises a photographing unit, a lighting circuit and a displaying unit, wherein the photographing unit is provided with a photographing shutter and photographs the tongue coatings when the photographing shutter is triggered; the lighting circuit is mounted around the photographing unit and provides light for the photographing unit; and the displaying unit is connected with the photographing unit through a data line and displays the tongue coatings to be photographed. The invention further provides a tongue image instrument comprising the tongue coating image collection device and a tongue coating detection method using the tongue image instrument.

The invention discloses a quantitative analysis method for traditional Chinese medicine tongue colors based on spectral information, and belongs to the field of objective researches on traditional Chinese medicine inspection diagnosis. Spectral reflectance of different types of tongues is collected to obtain a spectral reflectance data set of tongue colors and tongue coating colors, and a tongue color and tongue coating color classifier is established through a classification algorithm. For a certain tongue image, a tongue body part is separated by the classifier. The tongue body part is composed of tongue pigments, and an optical absorption scattering model of the tongue body is established according to the optical absorption and scattering principle of particles. Based on the model, thepigment concentration in the model is inversely determined according to the spectral reflectance of each pixel of the tongue body. The pigment concentration is utilized as a measurement means of the traditional Chinese medicine tongue colors to provide quantitative data reference related to syndrome degree for clinical treatment. By means of the method, number axes of red tongue and purple tonguemeasurement values can be established according to the formation mechanism of the traditional Chinese medicine tongue colors. For any tongue color, the measurement values on the number axes can be obtained by calculating the concentration of each pigment.

The invention discloses a tongue quality and tongue coating separation method based on an LGBM model, and relates to the technical field of tongue body image processing, and the method comprises the steps: dividing tongue quality pixel points and tongue coating pixel points into N types of different colors according to the color features of a tongue body image; then performing sampling to respectively obtain characteristic values of each channel component of the sample in the RGB color space, the HSV color space and the LAB color space, and combining the characteristics to obtain a characteristic vector; utilizing a PCA dimension reduction method to perform dimension reduction on the feature vector to obtain M types of features as input features of the LGBM model; performing training optimization on the LGBM model through the training set to obtain a trained LGBM tongue body color classifier; and preprocessing the tongue body images to be classified, and inputting the preprocessed tongue body images into the LGBM tongue body color classifier to obtain corresponding tongue quality images and tongue coating images respectively. The method has the advantages that the classification precision is greatly improved, the classification time is short, and few resources are occupied.

The invention discloses a traditional Chinese medicine tongue quality tenderness identification method based on image restoration and a convolutional neural network, and the method comprises the steps: obtaining an original tongue image, carrying out the tongue segmentation of the tongue image through a tongue semantic segmentation model, and obtaining a tongue segmentation image; performing tongue coating and tongue quality separation on the tongue body segmentation image by adopting a Gaussian mixture model; obtaining a tongue quality image; establishing a tongue quality image restoration model based on the generative image restoration network, and restoring the tongue quality image by using the tongue quality image restoration model to obtain a tongue quality restoration image with continuous texture features and color changes; carrying out feature extraction and classification on a data set of the tongue quality restoration image obtained after restoration by adopting an improved residual network, and establishing a tongue quality tenderness identification model; and identifying the tenderness of the tongue by using the tenderness identification model of the tongue. According to the method, the influence of the tongue coating on tongue quality tenderness recognition can be avoided, the characteristics obtained through self-learning can reflect richer tongue quality color and texture characteristics, and a good tongue quality tenderness recognition effect is achieved.

The invention is applicable to the technical field of respective tongue coating curdy and greasy identification, and provides a curdy and greasy coating classification algorithm based on a convolutional neural network; the convolutional neural network is used for performing feature extraction on curdy and greasy coating pictures, and can effectively combine the color, shape and texture of curdy and greasy coating to describe rich tongue coating image features; a possible curdy and greasy coating area is predicted through priori knowledge; the tongue picture is cut into a plurality of sub-images; therefore, the feature extraction method only needs to pay attention to the related sub-images instead of the whole image; because the multi-example classification decision is only decided by a minimum negative example in the normal tongue image and a maximum positive example in the curdy and greasy tongue image, and some overall information is obtained, the multi-example classification decision forces the positive packet (tongue image) to contain at least one curdy and greasy sub-image, and then whether the curdy and greasy coating is contained in the tongue image or not is judged by usinga multi-example learning method.

The invention discloses a cataplasm thermal patch. The cataplasm thermal patch comprises base cloth, wherein a paste layer is arranged on the base cloth, and drug components are arranged on the pastelayer and include the following components in parts by mass: 1-3 parts of raw rhubarb, 6-10 parts of cortex magnoliae officinalis, 6-10 parts of fructus piperis longi, 5-8 parts of fructus evodiae, 3-6 parts of radix aucklandiae, 3-5 parts of schisandra sphnanthera, 3-6 parts of rhizoma picrorhizae, 6-10 parts of rhizoma pinelliae, 3-6 parts of fructus aurantii immaturus, 6-10 parts of galangal, 6-10 parts of fructus chebulae, 3-6 parts of semen myristicae, 1-3 parts of radix sophorae flavescentis and 100-150 parts of deionized water. The cataplasm thermal patch has a specific formula and a reasonable preparation method; the cataplasm thermal patch is suitable for clearing damp, stopping diarrhea, regulating middle warmer and activating spleen and is suitable for treating treat child diarrhea (with the symptoms of diarrhea, thin sloppy or watery stool, abdominal distention, bellyache, anorexia, anabole or fever, pale tongue and white and greasy tongue coat) caused by dampness, encumbering spleen, soil as well as rotavirus enteritis and infectious diarrhea with the syndromes.

The invention relates to a multifunctional toothbrush which comprises a toothbrush handle and toothbrush head which is integrated with the toothbrush handle. Bristle planting holes with bristles inside are arranged on the toothbrush head. The multifunctional toothbrush is characterized in that a massage soft strip is disposed on each of the two sides of the front of the toothbrush head, each massage soft strip is provided with at least four cylindrical rubber massage columns, a tongue coating cleaning plate provided with silica gel particles is fixedly connected to the back of the toothbrush head, the bristles are arranged in three rows, the bristles in the middle row is of an inclined structure, the bristles on two sides are in a high-low stagger structure, and antislip strips are disposed on a thumb contact position and an index finger contact position of the toothbrush handle respectively. By the structural design of the bristles, tooth positions which are difficult to brush can be cleaned, dental plaque and stain can be removed, and gum sulcus can be cleaned. By the silica gel particles disposed on the tongue coating cleaning plate, tongue coating and mouth cavity can be cleaned. The rubber massage columns are capable of massaging gums and protecting teeth.

The invention discloses a special medical high-efficiency oral tongue coating detection instrument for making a user comfortable. The detection instrument comprises a base, wherein a support frame isfixedly arranged at the top of the base; a control box is fixedly arranged on one side of the support frame; a cavity I is formed inside the support frame; a motor I is fixedly arranged at the top inside the cavity I; the output end of the motor I is connected with a central shaft III; a rotating drum is fixedly arranged on the outer side of the central shaft III in a sleeving manner; a spiral chute is formed in the surface of the rotating drum; a sliding rod is arranged inside the spiral chute in a sliding connection manner; a limiting groove is formed in one side, which is far away from thecontrol box, of the cavity I; a sliding block I is arranged inside the limiting groove in a sliding connection manner; one side of the sliding block I is fixedly connected with the sliding rod; a mounting seat is fixedly arranged on the other side of the sliding block I; and a detection mechanism is arranged on the mounting seat. The detection instrument disclosed by the invention has the beneficial effects of being convenient to operate and high in intelligent degree, replacing the traditional manual detection and being capable of being widely applied to detection treatment of oral tongue coatings.

The invention discloses a rapid detection method of urease in tongue coating by using a pH value-ethanol method and a kit. The detection method comprises the following steps: A. measuring pH value of oral saliva with a pH test strip; B. dropwise adding 3-4 drops of 95% ethanol solution into a rapid urease reagent cup, and fully mixing reagent particles attached at the cup bottom and the ethanol solution with a toothpick; C. taking the tongue coating at the back of the tongue and placing the tongue coating in the reagent cup, fully mixing, dropwise adding additional 3-4 drops of dissolving solution into the reagent cup following standing for 5 minutes, fully mixing, standing for 5-10 minutes, and observing the color change; and D. measuring with the pH test strip if the color is changed into red, comparing the result with the pH value of the oral cavity, and thereby judging the result. The kit comprises a kit body, and the rapid urease reagent cup, a soft plastic bottle filled with 1-10ml of the dissolving solution and the 95% ethanol solution, pH precise test strips with detection range of 5.5-9.0, a packet of cotton swabs and a packet of toothpicks are arranged in the kit body. The detection method provided by the invention is simple and rapid, causes no wound and has low cost.

The invention provides an infant health status monitoring device and method. The method includes the following steps: using an oral tongue coating image acquisition device, a facial image acquisitiondevice, a first image processing device, a second image processing device, a first infrared temperature sensor, a second infrared temperature sensor, a third infrared temperature sensor, a heart rateblood oxygen sensor, a pressure sensor, an ultrasonic distance-measuring sensor, a microcontroller, a storage device, a display device, and a communication device; displaying a detection result through the display device, and meanwhile, transmitting the detection result of the infant health to a health big data cloud platform through the communication device; packaging and encrypting the health data detected by the microcontroller to generate encrypted data packets; controlling, by the microcontroller, the communication device to transmit the encrypted data packets to the health big data cloudplatform through a wireless transmission network, the cloud platform transmits the decrypted data to the cloud database; sending, by the cloud platform, the decrypted data to a cloud database; and comparing, by the cloud database, the data with standard data to analyze the infant health condition.