31 results about "Ear region" patented technology

A headset for detecting brain electrical activity may include a flexible substrate having first and second ends each configured to engage an ear of a subject and dimensioned to fit across the forehead of a subject. The headset may also include a plurality of electrodes disposed on the substrate and configured to contact the subject when the headset is positioned on the subject. First and second electrodes may contact top center and lower center regions of the forehead, respectively, third and fourth electrodes may contact front right and front left regions of the forehead, respectively, fifth and sixth electrodes may contact right side and left side regions of the forehead, respectively, and electrodes included within the securing devices may contact the ear regions. The third and fourth electrodes may be moveable in at least a vertical direction relative to the other electrodes.

An absorbent article includes a pair of front ear regions as part of a front waist region, a pair of back ear portions including a mechanical fastener as part of a back waist region, a crotch region connecting the front waist region and the back waist region, and a landing zone including a base material and a first discrete fastener element group embedded in the base material. The first discrete fastener element group includes at least one first discrete fastener element having a profile height. The base material has a profile height that is greater than the profile height of the first discrete fastener element. The landing zone may be associated with the outer cover in the front waist region between the front ear regions.

The invention relates to a method for detecting the phone holding violation of a driver in driving, and belongs to the technical field of machine vision. The method comprises the following steps of: acquiring a head image of an automobile driver, detecting a face in the head image of the driver by utilizing a face detection algorithm, and positioning a rectangular face region according to the detected face; positioning a left rectangular ear region and a right rectangular ear region according to the rectangular face region, and extracting characteristic indexes from the left and right rectangular ear regions; inputting the characteristic indexes into a mode identification algorithm, identifying whether the driver holds a phone or not in the head image, and storing an identification resultinto a phone holding result queue; and performing logic judgment on the phone holding result queue, and giving an early warning to the driver according to a logic judgment result. The method is high in real-time performance and identification accuracy; and the left-hand and right-hand phone dialing and answering behaviors of the driver can be detected and early warned, so that traffic accidents caused by the phone dialing and answering in driving can be effectively reduced, and driving safety is further improved.

An earbud includes a speaker driver, and a sensor módule secured to the speaker driver that is configured to detect and / or measure physiological information from a subject wearing the earbud. The sensor module includes a printed circuit board, an optical source secured to the printed circuit board, and an optical detector secured to the printed circuit board. A first light guide may be coupled to the optical source that is configured to deliver light from the optical source into an ear region of the subject via a distal end thereof. A second light guide may be coupled to the optical detector that is configured to collect light from the ear region via a distal end thereof and deliver collected light to the optical detector. One or more additional sensors may be secured to the speaker driver, such as accelerometers, humidity sensors, altimeters, and temperature sensors.

A headset for detecting brain electrical activity may include a flexible substrate having first and second ends each configured to engage an ear of a subject and dimensioned to fit across the forehead of a subject. The headset may also include a plurality of electrodes disposed on the substrate and configured to contact the subject when the headset is positioned on the subject. First and second electrodes may contact top center and lower center regions of the forehead, respectively, third and fourth electrodes may contact front right and front left regions of the forehead, respectively, fifth and sixth electrodes may contact right side and left side regions of the forehead, respectively, and electrodes included within the securing devices may contact the ear regions. The third and fourth electrodes may be moveable in at least a vertical direction relative to the other electrodes.

A system for adjusting blood glucose level including an insulin delivery device configured to release insulin into the body of a person, and an EEG monitor having an EEG sensing part including EEG electrodes. The EEG monitor can be arranged in the ear region of the person with the EEG sensing part arranged subcutaneously at the scalp or arranged in the ear canal. The EEG monitor includes an EEG signal processor arranged at the ear and adapted for identifying onset of hypoglycemia. The system further includes a wireless link between the EEG monitor and the insulin delivery device. The EEG monitor is configured to submit a warning signal to the insulin delivery device if an upcoming onset of hypoglycemia is identified. The warning message will cause the insulin delivery device to restrict insulin delivery for a predetermined time, and a warning is provided to the person or to a caregiver.

The invention discloses a bionic head model and system. The model is used for replacing a user to use a head-mounted article and collecting data, the model is provided with a bionic skull layer and a bionic head soft tissue layer, the bionic skull layer comprises a bionic neurocranium layer and a bionic face cranium layer, and the bionic head soft tissue layer forms a bionic eye region, a bionic mouth region, a bionic nose region and a bionic ear region. The model further comprises a processor, a transmitter, a camera device, a pressure sensor and a temperature and humidity sensor. The processor is separately connected with the transmitter, the camera device, the pressure sensor and the temperature and humidity sensor. According to the bionic head model, the adaptability and comfort of a user are obtained by detecting the head collection data when the user uses the head-mounted articles; various head-mounted articles can be tested; the bionic head model has higher compatibility; and more data support is provided for the design, development and inspection of the head-mounted articles.

The invention discloses an ear region rehabilitation massaging device for nursing of a department of otorhinolaryngology and relates to the field of medical appliances. The ear region rehabilitation massaging device comprises a holding rod, wherein a shell body is fixed to the upper end of the holding rod, two opposite vertical mounting plates are fixed to the top of the shell body, mounting grooves are separately formed in upper ends of the two mounting plates, a vertical fixed plate is fixed to the inner side of the shell body, a transverse threaded rod is rotatably mounted on the fixed plate, threads are separately formed in the two ends of the threaded rod, a first gear ring fixedly sleeves the middle part of the threaded rod and is in transmission connection with a driving motor fixedinto the shell body, and a vertical rotating vertical rod is rotatably mounted on the mounting plate. The ear region rehabilitation massaging device can be used for automatically carrying out periodic pressing on ears and then massaging the ears, a whole massaging process is carried out automatically and has no need of manual massaging, the use effect is good, and the entire device is simple in structure, small in size, convenient to carry and good in flexibility of operation.

The invention relates to a head-mounted display device and a method thereof. Embodiments relate to crosstalk cancellation to reduce crosstalk vibrations during use of multiple bone conduction transducers. A system, for example, a head-mounted display (HMD) for providing audio to a user, uses vibration sensors to detect vibrations caused by the bone conduction transducers. In particular, a vibration sensor may generate an error signal representing residual vibrations due to crosstalk at a given ear region of the user. The system uses estimated transfer functions for noise propagation paths through the user's head to generate an anti-crosstalk signal. In response to the anti-crosstalk signal, a bone conduction transducer transmits anti-crosstalk vibrations that reduce the error signal at thegiven ear region.

The invention discloses an ear area selection method for calling detection. Positioning a sensitive area by using the key points, wherein the sensitive area is divided into a left area and a right area; for the left sensitive area, setting the abscissa of the key point 5 as the right boundary, setting the abscissa of the key point 5 minus the 2 / 3 value of the face width as the left boundary, setting the ordinate of the key point 8 as the lower boundary, and setting the ordinate of the key point 17 as the upper boundary, thereby positioning the left sensitive area for making a call; for the right sensitive area, setting the abscissa of the key point 11 as the left boundary, setting the sum of the abscissa of the key point 11 and 2 / 3 of the width of the face as the right boundary, setting the ordinate of the key point 8 as the lower boundary, and setting the ordinate of the key point 26 as the upper boundary, thereby positioning the right sensitive area for making a call; substituting into an image to intercept a sensitive area; the sensitive area is selected on the basis of the face key points, stability is good, and accuracy is high.

An electrically conductive contact pin for press-fitting into a PCB in a Z-direction. The contact pin includes a press-fit zone with a central crosspiece area, and two wing areas adjacent to the crosspiece area, each crosspiece area having two ear areas. The crosspiece area is confined by a crosspiece rectangle and the ear regions are confined by ear rectangles. Corner points of the ear rectangles facing a center of the cross-sectional area coincide with corner points of the crosspiece rectangle. The crosspiece rectangle has a crosspiece width in an X direction of 9-29% of a starting thickness of the contact pin and a crosspiece thickness in a Y direction of 35-55% of the starting thickness. The ear rectangles have an ear width in the X-direction of 40-60% of the starting thickness and an ear thickness in the Y-direction of 15-35% of the starting thickness.

The present invention is directed to earmuffs, and is intended to allow for hot packs to be used, thereby improving the effect of protecting ear regions from cold and a cold wave in the winter season. In order to achieve this, the present invention provides earmuffs (10) including a pair of ear covers (11) and a band (12) configured to connect the ear covers (11), wherein reception slots (13) through which hot packs (20) configured to generate heat are inserted and stored are formed in the ear covers (11), respectively.

The invention discloses a live pig ear image segmentation method based on an active contour model. The method comprises steps that the algorithm is utilized to preprocess an image of a live pig, the quality of the image is improved, and grayscale difference between the ear region and surrounding pixels can be highlighted; the image area is reconstructed by randomly acquiring ear pixel points, andthe active contour model is utilized to perform preliminary segmentation of the ear image; the reconstructed active contour model is utilized to accurately extract the live pig ear image, and therebythe final segmented image is acquired. Compared with the traditional segmentation method, the live pig ear image segmentation method has advantages of fast speed and good effect, for the target area that may appear in the process of early warning of the blue ear disease of pigs, relatively good segmentation can be achieved.

The invention discloses an ear recognition and tracking method based on a convolutional neural network. Detect to obtain a face image including the ear area; build a second layered neural network for the ear data set and the ear labeling box label, and detect the ear area in the output image in step 1 through training; for the ear data set and ear feature points The label builds a third layered neural network, and automatically labels the ear feature points in the output image in step 2 through training. The present invention adopts a three-level cascaded architecture, which can effectively solve the problems of detection and feature point labeling when the existing ear data set is relatively small. Moreover, the multi-layer network can significantly compress the network size, the network structure parameters are relatively small, and the requirements for video memory in the training stage are not high, the training is easier to converge, and the performance is better under complex conditions.

The invention provides a half-body image three-dimensional reconstruction method and device which is used for solving the problems of high complexity and long reconstruction time. The method comprises the steps of obtaining an image of a front face including a half-body image of a target person, then performing texture expansion by adopting a head semantic mask of the front face to enable at least two organs in the expanded texture to be located at preset positions, and then complementing the texture of the back face according to the expanded texture image including the front face. In addition, a three-dimensional grid model can be constructed according to the front face, a pre-configured ear model is adopted to replace ears in the three-dimensional grid model, then the texture of the ear area is obtained from the replaced three-dimensional grid model and is fused to the texture of the complemented back face, and then the three-dimensional grid model is obtained, so that a professional modeling device is not needed, and the complexity is lower. Due to the fact that the front face texture and the back texture of the human body have certain correlation, the back texture is supplemented according to the front face texture, the constructed three-dimensional model better fits a figure, and a better effect is achieved.

The disclosure relates to an ear key point detection method, device and storage medium, and belongs to the field of image processing. The method includes: acquiring a human face image, the human face image includes key points of human face contour, and the key points of human face contour are used to determine the ear region in the human face image; acquiring the ear key point detection model, the The ear key point detection model is used to detect ear key points in any ear region; based on the ear key point detection model and the position of the human face contour key point in the human face image, the detection Ear key points in the face image. The ear area is determined by using the key points of the face contour, and the ear key points in the face image are detected by using the ear key point detection model, taking into account the positional relationship between the ear area and the face contour, and through the ear The key point detection model learns the way to detect ear key points in the ear area, which improves the accuracy of ear key points and reduces the error.

The invention discloses a method for conveniently positioning auricular points, which comprises the following steps of: establishing a three-dimensional human ear model library through three-dimensional scanning equipment and the like, and classifying ear models in the three-dimensional human ear model library through the approximation degree of the contour curvature and the internal curve curvature because the three-dimensional human ear model has the contour curvature and the internal curve curvature of the human ear; a plurality of similar ear shape databases are constructed, meanwhile, along with the increase of samples collected by ears, the similar ear shape databases are more perfect, and on the basis, the human auricular point positions in the similar ear shape databases are manually calibrated; then the computer matches the acupuncture points in the similar ear shape database through an ear region division method to form the similar ear shape database of the acupuncture point identification, and after a new patient comes, the ear mold acupuncture point identification graph of the patient can be obtained only by performing three-dimensional scanning on the ear of the patient; therefore, auricular point massage which is originally complex and inconvenient to popularize can be simplified, and the auricular point massage is easy to popularize.

An eye gaze detection method includes: acquiring image data of a face of a person; detecting, from the image data, a left eye region including a left eye of the person and a right eye region including a right eye of the person; detecting, from the image data of the face, at least one of an ear region including an ear of the person and a hair region including hair of the person, when only one eye region of the right eye region or the left eye region is detected; detecting information indicating an orientation of the face based on information indicating a position of one eye included in the one eye region and information indicating the at least one; and detecting information indicating an eye gaze of the person based on the information indicating the position of the one eye and the information indicating the orientation of the face.

The invention relates to a sports mask and a manufacturing method thereof, and relates to the technical field of textiles. The mask comprises a high-elasticity fabric area and a spacer fabric area. The high-elasticity fabric area is connected with the spacer fabric area in a sewing manner; the high-elasticity fabric area comprises a high-elasticity fabric, and the high-elasticity fabric is a fabric woven by yarns; the spacer fabric area comprises spacer fabric; when a user wears the mask, the spacer fabric region corresponds to at least one facial organ region of the user, the facial organ region including a facial skin region, an eye region, a nose region, a mouth region, and an ear region. When a user wears the mask, the high-elasticity fabric areas and the spacer fabric which are connected with each other are distributed at intervals, and the spacer fabric corresponds to the facial organ area of the user. In the exercise process of wearing the mask, a user can feel light and comfortable, the respiratory system cannot be stimulated by external cold air, and the exercise requirement can be better met.

The invention discloses a sound field sound effect control method, a terminal and a computer readable storage medium, and the method comprises the steps: obtaining user face data, and recognizing a user ear region according to the user face data; detecting the distance and the deflection angle of the ear region of the user, and obtaining corresponding sound effect parameters according to the detected distance and the deflection angle; and controlling a corresponding audio unit according to the acquired sound effect parameter, and switching the current sound field mode of the sound system to a corresponding sound field mode. According to the invention, the ear region of the user is recognized through the face recognition technology, and the ear of the user is tracked in real time by detecting the distance and the deflection angle of the ear region of the user, so that the sound effect parameters of the sound system are dynamically adjusted according to the change of the position of the ear of the user, the user can enjoy the best sound field and the best sound quality all the time, and the user experience is improved. And the sound effect of the sound system is improved.

The invention belongs to the technical field of medical image processing, and particularly relates to a left and right ear region segmentation method based on a temporal bone CT horizontal scanning image. The method is used for segmenting a left ear region and a right ear region in a head temporal bone CT image, so a computer can intensively perform subsequent processing on the ear regions. The method sequentially comprises the following steps: removing an invalid region of a head CT image; cutting out a left ear area and a right ear area in the image according to the proportion; sorting and storing the left ear area image and the right ear area image respectively. Experimental results show that for a horizontally scanned temporal bone CT image, the method can eliminate invalid black areas, discard information of other irrelevant parts and accurately extract left and right ear areas.