9 results about "Nose region" patented technology

The invention relates to the technical field of computer vision and biological feature recognition, and discloses an animal face recognition technology and device based on nose pattern and iris multi-dimensional features. Comprising the following steps: synchronously collecting a multi-modal image containing an animal nose region and at least one eye region, synchronously collecting a multi-modal image containing the animal nose region and at least one eye region, carrying out parallel processing on the multi-modal image, carrying out weighted fusion on a nose pattern feature vector FVnose and an iris feature vector FVris, and carrying out weighted fusion on the iris feature vector FVris and the nose pattern feature vector FVnose and the iris feature vector FVris; and carrying out animal individual identity recognition based on the fusion feature vector FVfused, and executing living body detection based on analysis of the eye region image. According to the method, attitude correction is carried out on the collected image, the image area is approximately in a regular rectangle shape by adopting affine transformation, small block shielding is processed by using a targeted AI image restoration algorithm when the image is shielded, and the recognition rate is improved by comparing the restored image with the original image.

The invention relates to the technical field of crossing of physiological signal monitoring and computer vision, in particular to a thermal infrared video respiration monitoring method and equipment based on a mask auto-encoder. According to the method, the affine transformation matrix is constructed through a small amount of RGB-thermal infrared face key points, and the key point tracking result of the RGB video is mapped to the thermal infrared video, so that mouth and nose region-of-interest tracking without large-scale thermal infrared video labeling is realized, a corresponding mouth and nose thermal infrared sub-graph sequence is obtained, and the sample acquisition cost is reduced; spatial partitioning and time stacking are carried out on the mouth and nose thermal infrared subgraph sequence, a thermal infrared space-time diagram facing the breathing task is constructed, and therefore space-time information of the sample is fully utilized; according to the method, the space-time diagram is subjected to self-supervision pre-training after being subjected to mask processing, secondary fine-tuning training is carried out through annotation data, and a mask auto-encoder after training is output, so that the accuracy and robustness of an output result are effectively improved.

The invention provides a soft tissue adaptive enhancement method and enhancement device for a skull side position film. The method comprises the following steps: extracting key anatomical points related to a mouth-nose area in the skull side position film by adopting a UNet-based feature point recognition model; extracting a mouth-nose area in the skull side position film according to the key anatomical points, and performing local enhancement; and carrying out weighted fusion on the enhanced mouth and nose area image and the original image of the skull side position film to form a soft tissue enhanced image of the skull side position film. According to the invention, through the feature point identification model, automatic and accurate positioning of key feature points is realized; independent image enhancement processing is carried out on the segmented mouth and nose areas, so that the contrast ratio, the definition and the detail visibility of the key areas can be remarkably improved on the premise of not influencing other areas of the image; and a fusion technology based on an adaptive weight map is adopted, so that smooth transition of the enhanced region and the original image at the boundary is ensured, and the overall consistency and visual authenticity of the image are ensured.

A mask assembly can include a mask seal. In some configurations, the mask assembly can be configured to be positioned entirely below a nasal bridge of a user's face and to leave the nasal bridge of the user exposed. The mask seal can include a nose region including at least one nose opening, a first flap on a first side of the nose region, and a second flap on a second side of the nose region. The first flap can be configured to contact one side of the nose of the user and the second flap can be configured to contact the other side of the nose of the user.

This invention discloses a nasal mask system. A nasal mask defines a breathing chamber for supplying positive pressure gas into a patient's airway, including sidewalls and a liner positioned posteriorly adjacent to the sidewalls. The posterior sealing surface of the liner has a contour with a concave curvature in the top lip region to have a shape complementary to the top lip region. The contour of the posterior surface of the liner is configured to extend from the bridge of the nose region to the respective left and right nasal corner regions along the corresponding left and right sides of the nose during use, and is adapted to extend from the left side of the nose to the right side of the nose along the top lip. The liner includes a relatively thick auxiliary band formed of an elastic flexible material and extending from the sidewalls to form corresponding cantilevered sections in the top lip region, corner region, and nasal side region of the liner. The top lip region cantilever has a C-shaped cross-section. It also includes a relatively thin facial flap that curves inward and extends along the periphery of the liner to define the posterior sealing surface of the liner, the inner edge of which defines an opening through which the patient's nose portion passes during use.

A mask assembly may include a mask seal. In some configurations, the mask assembly may be configured to be positioned entirely below a nose bridge of a user's face and expose the nose bridge of the user. The mask seal may include a nasal region including at least one nasal opening; a first flap located on a first side of the nose region; and a second flap on a second side of the nose region. The first flap is configured to contact one side of the nose of the user and the second flap is configured to contact the other side of the nose of the user.

The invention relates to the technical field of face recognition, and discloses a face recognition intelligent passage feedback system based on deep learning. A deep convolutional neural network module of the system receives original face image data collected by a camera, and extracts multi-dimensional feature vectors of an eye region, a nose region and a face contour through multi-level convolution operation fused with an attention mechanism; the infrared living body detection module runs in parallel, generates a living body verification result based on near infrared spectrum analysis, and outputs a biological activity index; the feature fusion module performs cross-modal alignment on the two features to generate a composite feature matrix; the dynamic feedback control module triggers a real-time interaction instruction according to a confidence coefficient threshold value of the composite feature matrix, and a display device is driven to output visual prompt information; and the decision engine module receives the composite feature matrix and the interaction state data, and outputs a final passing permission instruction through a weighted voting mechanism.

This invention discloses a head pose detection method, a mobile CT scanner, an electronic device, and a storage medium. The head pose detection method is applied to a mobile CT scanner, which includes a camera within its cavity. The method includes: acquiring a head image based on the camera and detecting the nose region within the head image to obtain a nose region image; performing ellipse recognition on the nose region image to obtain multiple elliptical regions; determining nose feature information based on the multiple elliptical regions; determining the degree of head offset based on the nose feature information; and detecting head pose based on the degree of head offset. This invention's head pose detection method performs ellipse detection on the nose region and extracts nose feature information, achieving head pose detection based on this nose feature information. This solves the problem of traditional head pose estimation methods heavily relying on complete facial key points, making the method simpler and more efficient.

This application discloses a non-contact heart rate monitoring and cardiac screening method based on 1300nm shortwave infrared light, belonging to the field of image processing technology. It includes: acquiring multiple frames of target face images captured by a 1300nm infrared camera; sequentially arranging the multiple frames of target face images to obtain a time-series signal; sending the time-series signal to a face nose region recognition and data acquisition module, locating the nose region in the time-series signal based on the Dlib algorithm, and collecting the average grayscale value of the pixels in the nose region to obtain the heart rate signal to be processed; sending the heart rate signal to be processed to a feature signal extraction module, sequentially performing detrending, mean removal, wavelet transform, and Kalman filtering to obtain a feature signal representing the heart rate; inputting the feature signal representing the heart rate to a heart rate status judgment module, obtaining the target heart rate through Fourier transform, and judging the target heart rate based on a two-level comparison strategy to obtain the target heart rate status. This method improves the accuracy and efficiency of cardiac screening.