69 results about "Face scale" patented technology

The invention belongs to the computer aided surgical technique and maxillofacial plastic medical treatment equipment field and relates to a computer simulation method for predicting soft tissue appearance change after a maxillofacial bone plastic surgery. The method comprises the following steps that: spiral CT scanning is performed on the maxillofacial of a patient before the surgery; data are led into maxillofacial surgery design simulation software, namely, CMF-pre CADS, so that a three-dimensional maxilla and skin surface model is re-constructed; a bone segment is reset/shifted to a preliminary location; and the similarity of a pre-surgery prediction model and a post-surgery true appearance is judged through comparison through Geomagic software. With the method adopted, the post-surgery appearance and stomatognathic system functions can be recovered excellently; the appearance of soft tissues are symmetrical, harmonious and beautiful; the post-surgery satisfaction degree of the patient reaches 95%; the effects of the plastic surgery are stable; and long-term satisfaction is also very high.

The invention belongs to the design of a surface model of a medical simulation human organ and a preparation method, in particular to a preparation method for an infant cleft lip facial simulation model, which comprises the following steps: (1) collecting three-dimensional original data of faces of cleft lip illness children; (2) rebuilding digital facial models of the faces of the cleft lip illness children; (3) automatically layering and scattering model files and forming processing files; (4) automatically processing resin part models of the faces of the cleft lip illness children; (5) duplicating silastic cleft lip facial models; and (6) coloring the silastic facial models. The invention can provide a personalized customization facial simulation model which is in high consistence withthe shape, color, texture and the like of the faces of the cleft lip illness children with three age of months; the simulation model not only provides the real reference for a surgeon before operation, causes the surgeon to know fairly well during the operation, and simultaneously provides postoperative facial esthetic effects for parents of cleft lip and palate patients.

An improved shock damper for building is composed of bottom base, top carrier, sliding groove consisting of upper and lower slide block and spherical receptor, and springs for connecting bottom base with top carrier. An arc recess is respectively made on the bottom surface of top carrier and top surface of bottom base for recepting upper and lower slide blocks which have a semi-spherical recess for containing the said spherical receptor. Its advantages are high shock damping effect, simple structure and low cost.

The invention discloses a scale estimation-based human face detection method. According to the method disclosed in the invention, a size of a human face on an image is estimated via human face scale estimation, the image is zoomed based on a human face scale, a suggestion frame extraction is performed rapidly via a full convolution network, and a human face detection result can be obtained via twotimes of cascaded classification and regression. According to the method, human face detection is performed based on combination of human face scale estimation and a cascaded convolution neural network, an overall calculation amount of human face detection can be reduced, overall time consumption for human face detection can be reduced, and human face detection effects can be ensured.

The invention discloses an anchor-point-free face detection method and a system. The method comprises the steps of inputting a to-be-detected face image into a trained face detection network for facedetection; performing face feature extraction on the trained face detection network, and outputting a face heat map, a face scale map and a face center offset map; regarding points greater than a preset threshold in the human face heat map as human faces; and extracting a face coordinate offset from a corresponding position on the face center offset map, adding the face coordinate offset to the coordinates of the face heat map to obtain a final face center position, and finally calculating the width and height of the face on the face scale map to obtain the coordinates of the face. According to the method, the human face is expressed as the central point of the human face frame, and then the size of the human face frame is directly returned according to the image features of the central position, so that the post-processing time of tedious anchor points is reduced, and a rapid and efficient human face detection task is realized.

The invention discloses a face detection and alignment method based on scale estimation. The face detection and alignment method comprises the steps of: inputting a picture into a scale estimation network, and outputting a scale with a scale probability vector greater than a preset threshold; when the scale estimation network is trained, allocating attention weights to faces in the picture in advance according to the face scales, wherein a loss function of the scale estimation network during training comprises binary classification loss of the face attention images; scaling a to-be-detected image through using the scale obtained by the scale estimation network to obtain a plurality of scale images; inputting the plurality of scale images into an anchor Pnet to obtain a plurality of candidate boxes, and removing non-face candidate boxes through adopting a non-maximum suppression algorithm to obtain a pre-processed candidate box; and cutting the preprocessing candidate box on the original image, zooming the preprocessing candidate box to a preset size, inputting the zoomed preprocessing candidate box into an anchor Rnet, removing a redundant box by using the non-maximum suppression algorithm to obtain a detection box, and extracting corresponding face feature points according to the detection box. The face detection and alignment method has the advantages of being high in adaptability and capable of detecting small-scale faces more efficiently.

The invention relates to image processing, computer vision and machine learning fields, in particular to an online examination cheating judgment method based on Kinect color and depth information. Themethod comprises eight steps of face and trunk motion data acquisition, face and trunk motion data preprocessing, face and trunk motion data input, face and trunk motion training network construction, trunk motion training network construction, summary training network construction, network performance optimization by the training network and network performance test verification by a test network. According to the method, the advantages of rich, practical, real and reliable feature data returned by the Kinect to the human face and the trunk joint are fully utilized; combined with deep learning, the convenience of opening online courses on a large scale can be fully exerted, quality supervision can be carried out on online assessment, and the problem that a learner generally lacks credibility in society due to the fact that the learner is in a common unsupervised or limited supervised test environment before the computer of the learner is mainly solved.

The invention discloses a face recognition method, a device, equipment and a readable storage medium. According to the method, the face image which is successfully recognized and meets a certain condition can be screened out in the face recognition process; and the pre-stored face features of the registered user are updated according to the feature vector of the face image, so that continuous updating of the face features of the registered user is realized, the influence of face appearance change caused by age change or accidental conditions on a face recognition process is eliminated, and thereliability of a face recognition result is improved.

The invention relates to a system for acquiring and managing examinee information based on a three-dimensional face recognition system. The system comprises an examination table, a recognition control key, a three-dimensional face recognition device, a fingerprint recognition device, and ID card machine and a control system; the recognition control key, the three-dimensional face recognition device, the fingerprint recognition device and the ID card machine are embedded on the top of the examination table; a control system is positioned in the examination table, comprising a data processing circuit, a data storing chip, a driving circuit and a communication port circuit; the driving circuit is respectively electrically connected with the data processing circuit, the communication port circuit, the recognition control key, the three-dimensional face recognition device, the fingerprint recognition device and the ID card machine; the data processing circuit is electrically connected with the data storing chip. The system is simple in structure, and convenient to use; the examinee fingerprint, ID card information and face can be synchronously acquired and compared with the database and then stored, and therefore, the safety and fairness of examination can be improved.

The embodiment of the invention provides a face detection method and device. The method comprises: acquiring a to-be-detected image; Predicting the size of a human face in the to-be-detected image byusing a human face scale prediction network to obtain a predicted human face size; And positioning a face position in the to-be-detected image by using the predicted face size and the cascaded convolutional neural network, wherein the cascaded convolutional neural network comprises two sub convolutional neural networks. By implementing the embodiment of the invention, the face detection efficiencycan be improved.

The invention discloses a carbonate reservoir multistage alternating acid fracturing displacement optimization method. The optimization method comprises the following steps that (a) a surface-to-volume ratio of a reservoir to be subjected to acid fracturing is calculated, wherein S is the reaction area of reservoir rock, and V is the volume of an acid solution participating in a reaction; (b) themaximum construction displacement which can be borne by the reservoir is calculated in combination with the surface-to-volume ratio; (c) according to the bearing ability of a ground device, the actualconstruction displacement is determined; and (d) according to the acid pressure design scheme, the amount of each stage of prepad fluid and the acid solution is determined; and the amount of each stage of the prepad fluid and the acid solution is correspondingly divided by the actual construction displacement, and the injection time of each stage of the prepad fluid and the acid solution is obtained. According to the carbonate reservoir multistage alternating acid fracturing displacement optimization method, the problem that in the prior art, the displacement of multistage alternating acid fracturing is based on the performance of the ground device and lacks of consideration of reservoir factors is solved, the purposes that displacement parameters are optimized based on the surface-to-volume ratio of multistage alternating acid fracturing, and the effect of acid fracturing is improved are achieved.

The invention relates to a wardrobe, in particular to a novel special wardrobe for a student bathhouse. The novel special wardrobe comprises seats, a support, bottom boxes, shoe boxes, card swiping plates, clothes hooks and hot water pipes. The novel special wardrobe is improved on the basis of an existing bathroom wardrobe. Two layers of wardrobe bodies are arranged on the support of the wardrobe, the seats are arranged below the support, and each seat is sleeved with a sponge cover. The bottom boxes are arranged inside the wardrobe bodies and can contain keys, glasses, phones and other small objects. The shoe boxes are arranged close to the bottom boxes so that shoes can be separated from clothes and clothes can be prevented from being smudged. The number of contained clothes can be increased through the clothes hooks. The card swiping plates are arranged on corresponding wardrobe doors, when the wardrobe bodies are empty, it is displayed that the wardrobe bodies are empty, and after a card is swiped, a user name can be displayed just in case that the user forgets in which wardrobe body the clothes are placed. A mirror is installed on the back face of the corresponding wardrobe door, and therefore the user can make himself feel better after bathing.

The invention provides a visual access control for a building. The visual access control is characterized in that a storage device is arranged on a signal receiving and transmitting device and comprises a storage, a reading and writing chip and an SIM-card application module; an image pick-up device is connected with the storage by the reading and writing chip; the storage is connected with the SIM-card application module by the reading and writing chip; the SIM-card application module is connected with an alarming device; and the control type receiving and transmitting device is internally provided with a timed triggering device which is connected with the SIM-card application module. The visual access control provided by the invention has the advantage that when not in home, a user can still see the face of a guest ringing a doorbell and then carries out unlocking or alarming operation in sequence.

The invention discloses an angle measurer, and belongs to measuring devices. The angle measurer structurally comprises a horizontal movable ruler and an inclined locating ruler. The end portion of the horizontal movable ruler and the end portion of the inclined locating ruler are connected through a rotating shaft. The length of the horizontal movable ruler is equal to the length of the inclined locating ruler. Front-face scale marks are arranged on the front face of the horizontal movable ruler in an engraved mode. The front-face scale marks are gradually increased to 90 degrees at the front end of the horizontal movable ruler from 0 degree at the tail end of the horizontal movable ruler. Compared with the prior art, the angle measurer has the advantages of being convenient to operate, accurate in numerical reading, convenient to carry and the like, and therefore the angle measurer has good popularization and application value.

The invention discloses a multi-stage blind mating intelligent assembly device for a high-density component and a blind mating method thereof. The device comprises a three-dimensional servo motion platform, a precision optical platform, a TR component grabbing unit and a laser scanning unit, wherein the three-dimensional servo motion platform is arranged on the precision optical platform, the TR component grabbing unit and the laser scanning unit are both arranged on the three-dimensional servo motion platform, and the three-dimensional servo motion platform is used for controlling the motionof the TR component grabbing unit and the laser scanning unit in the three-dimensional space; an antenna structure is placed on the precision optical platform, and the TR component grabbing unit grabsTR components and realizes the blind mating of the antenna structure and the TR components under the positioning of the laser scanning unit and the movement of the three-dimensional servo motion platform. According to the multi-stage blind mating intelligent assembly device for the high-density component and the blind mating method thereof, the position and depth of a blind mating hole position of a connector can be automatically detected, in the blind mating assembly process of the blind mating connector, the blind mating hole position detection and positioning of different platforms and different array face scales are adapted, and references are provided for the blind mating assembly process.

The invention discloses a three-in-one 'dental body-dentition-face analysis' aesthetic ruler for dental restoration, which is formed by a long main ruler. A cross-shaped ruler is arranged on the leftend of the main ruler; a notch is formed above the middle part of the main ruler; the right end part of the main ruler is hinged with a root part of an arc-shaped pointer; the right part of the main ruler downwards extends to form a fan-shaped arc-shaped ruler; the tail part of the arc-shaped pointer fits to the arc-shaped ruler; an auxiliary ruler is perpendicularly embedded to the center of thenotch of the main ruler; a left sliding block is sleeved outside the left part of the main ruler; a right sliding block is sleeved outside the right part of the main ruler; vertical length pointers are slidably inserted into the rear sides of the left sliding block and the right sliding block; scales and corresponding marked lines are marked on the main ruler, the cross-shaped ruler and the auxiliary ruler. The aesthetic ruler not only can be used for analyzing a dental body, but also can be used for analyzing dentition, and can be also used for measuring face analysis; dental aesthetics measurement in dental aesthetics restoration is simpler and more convenient; measurement and analysis results are more objective and accurate; an effect of dental aesthetics restoration is further improved.

The invention relates to the technical field of makeup facilities, and discloses a vanity mirror with the function of adjusting the front and rear inclination angles. There are two L-shaped grooves on the inner surface of the left and right sides of the installation groove, the inner surface of the bottom of the installation groove is fixedly connected with a holding plate, and the top of the holding plate is provided with a runner. The vanity mirror with the function of adjusting the front and rear inclination angles can adjust the front and rear inclination angles of the upper mirror frame by setting the holding plate, the rotating wheel, the rotating rod and the bearing seat, so that users of different heights can adjust the Appropriate front and rear inclination angles of the vanity mirror achieve the effect of making up conveniently. By facilitating the operation of the user, the quality and efficiency of the make-up of the user are greatly improved, thereby saving the time of the user and improving the overall facial beauty.

A swing controller comprises three parts: an attachment part for attachment to the handle of the golf club, a main part including a main cylinder with spike and supporting three antifriction bearing rings and club face scale, and a telescope part including a telescoping cylinder with groove and O-ring disposed at a lower end of the telescope part and a positioning part for check points for indicating the position of the club and disposed at the upper end of the telescope part. The telescope part is extendable and allows adaptation to short golf clubs, to medium golf clubs and to long golf clubs. An extended axis of the club shank is produced by attaching the swing controller onto the end of the club handle. This renders possible and produces an effective, visual control for all axial planes.