70 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.

The invention provides a building outer surface wind pressure measurement method. The method includes the steps that a rigid model is manufactured and pressure measurement points are set; a wind tunnel test is conducted on the rigid model in a single round, so that a point wind pressure coefficient independent peak value reserving sequence and a face average wind pressure coefficient independent peak value reserving sequence are acquired; maximum likelihood estimation is conducted on point scale parameters and point position parameters of the point wind pressure coefficient independent peak value reserving sequence and face scale parameters and face position parameters of the face average wind pressure coefficient independent peak value reserving sequence, so that the maximum design value and the minimum design value of point wind pressure coefficients and the maximum design value and the minimum design value of face average wind pressure coefficients are determined, wherein the point scale parameters, the point position parameters, the face scale parameters and the face position parameters submit to extreme value distribution; the most disadvantageous maximum design value and the most disadvantageous minimum design value of the point wind pressure coefficients and the most disadvantageous maximum design value and the most disadvantageous minimum design value of the face average wind pressure coefficients are determined; the wind pressure of the outer surface of a building is determined. The method has the advantages of being low in cost, high in safety and capable of being widely applied to the field of buildings.

The invention relates to the technical field of process and equipment for a new non-ferrous metal material and discloses a process and equipment for manufacturing a wide-width magnesium alloy plate. In the process, an as-cast rod material is subjected to milling face scaling, multi-axis forging, machining, high-temperature ageing, heating, extruding, flattening and coiling to finish the coiling production of the wide-width magnesium alloy plate. The equipment comprises a multi-axis forging machine, an extruding machine, a flattening machine and a coiling machine; the extruding machine, the flattening machine and the coiling machine are arrayed along a discharging axis of the magnesium alloy plate and are controlled by a synchronous control system, wherein the extruding machine is internally provided with a semi-circular or wavy arc-shaped extruding and distributing module; and a rod material heater is arranged at the inlet end of the extruding and distributing module. According to the invention, by utilization of the small-tonnage extruding machine and a mould in which an arc line between two points is longer than a straight line between the two points, the wide-width magnesium alloy plate which is larger than the size of the outlet of the extruding machine is produced in coils through an arc surface rolling and flattening machine for flattening an arc surface. The coiling production of the wide-width magnesium alloy plate can be finished with smaller investment.

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 provides a fish body growth character fast measuring device and a measuring method, and belongs to the field of aquaculture devices. When the device is used for measuring fish bodies, only few steps are needed. Besides, collecting of growth characters of one fish body can be finished in a short time, repeated contact with the fish body can be prevented, and stress responses caused by data collecting are reduced. A support on a measuring table of the device guarantees that a camera is kept to be fixed on the same height during growth data collecting of the fish bodies. Meanwhile, the face of the measuring table and a lens of the camera are provided with table face scales and lens scales respectively to guarantee that the camera is basically vertical to the fish bodies to be measured, and measuring errors are reduced.

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 vertical type fish scale-belly integrated machine. The vertical type fish scale-belly integrated machine comprises a machine frame, a fish inlet hopper, a side face scale scraping mechanism, a fish belly, fish back and scale scraping and fish belly opening mechanism and a toothed chain delivering mechanism which are arranged on the inner side of the machine frame from topto bottom, and a power mechanism is arranged on the side face of the machine frame. The opening width of the fish inlet hopper can be automatically adjusted according to the size of fish, and thus condition that the fish in different sizes do not tilt in the descending process is ensured; the side face scale scraping mechanism and the fish belly, fish back and scale scraping and fish belly opening mechanism can rapidly scrape the scales on the side face of the fish body and the fish belly, and open the fish belly simultaneously; the toothed chain delivering mechanism can send the fish out ofthe device after fish processing is completed; and the power mechanism provides power to each mechanism, so that normal operation of the mechanisms is guaranteed.

The embodiment of the invention discloses a face detection method and device. The concrete embodiment of the method comprises the steps that an image to be detected is acquired; the image to be detected is inputted to a first convolutional neural network trained in advance so as to obtain face feature information and body feature information, wherein the first convolutional neural network is usedfor extracting face features and body features; and the face feature information and the body feature information are inputted to a second convolutional neural network trained in advance so as to obtain the face detection result, wherein the second convolutional neural network is used for representing the corresponding relation of the face feature information, the body feature information and theface detection result. According to the method, the accuracy of the detection result under the condition of small face scale can be enhanced.

The invention discloses a coal mine working face gas geological risk evaluation method. A working face gas geological evaluation index system comprising coal seam basic characteristics, coal seam structure characteristics, gas emission characteristics and gas outburst characteristics, and a grading standard are constructed, wherein the indexes specifically comprise secondary indexes such as coal seam burial depth, thickness, fault fractal dimension, structural curvature, absolute / relative gas emission amount, gas content, coal body structure and local outburst prediction indexes; a working face scale gas geology grading evaluation method system is determined, and the method specifically comprises the steps of evaluation parameter system establishment and grading, membership function and weight determination, multi-level fuzzy mathematical evaluation model construction, and geology mapping and zoning evaluation. The working face gas geology grading evaluation standard and method meet the actual geological conditions of the Korean mining area, the grading and zoning result is reliable, the potential of being popularized to other high-gas mines and tectonic coal development areas is achieved, and a basic basis can be provided for accurate, safe and efficient coal mining geology guarantee.

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 mainly relates to a reverse-osmosis and ultra-filtration scale inhibitor with the wide suitable salinity range. The inhibitor has the good scale inhibition effect within the wide ionic strength range, and is prepared from one or more of amino trimethylene phosphonic acid (ATMP), phosphono-carboxylic acid (POCA), polyaspartic acid (PASP) and polyamino polyether methylene phosphonate (PAPEMP); by means of the reverse-osmosis and ultra-filtration scale inhibitor, membrane face scaling can be effectively prevented, fouling of a membrane is prevented, and the service life of a membrane system is prolonged. The working pressure and the water production efficiency of the membrane system are kept, and it is prevented that due to fouling, energy consumption of the system is increased. According to the reverse-osmosis and ultra-filtration scale inhibitor with the wide suitable salinity range, the reverse-osmosis scale inhibitor can be suitable for the wide water-quality salinity range (electric conductance is 0 microsecond to 30,000 microseconds) through compounding, and the using effect of the reverse-osmosis inhibitor can be guaranteed within the range.

The invention discloses a face detection method based on convolution neural network cascade for large-scale scene monitoring images. The specific operation steps of the method are as follows: (1) collecting and sorting large-scale scene monitoring image data and making detailed labeling; (2) designing a cascading convolution neural network structure by fusing the face region and its semantic information, that is, the face and its surrounding shoulder region; (3) training the cascading convolution neural network model which fuses face region and its semantic information. The invention effectively solves the problem of poor face detection effect caused by small face scale, large scale change and blurred face details in the large-scale scene monitoring image, and the detection performance isgreatly improved compared with the existing face detection algorithm.

The invention belongs to the technical field of bicycle parking equipment, and particularly relates to a bicycle parking device. The main body structure of the bicycle parking device comprises a parking hall, a vertical lifting unit, a vertical lifting mechanism, a horizontal rotating unit, a mechanical gripper unit, a rotation parking unit and an electrical control unit. Six radial parking platforms are adopted to solve the problem of insufficient parking space utilization rate. Bicycles are conveyed by use of lead screws, so that the control accuracy is improved. Through ingenious combination of the vertical lifting unit, vertical lifting mechanism, horizontal rotating unit, mechanical gripper unit, rotary parking unit and electric control unit, stable, rapid, accurate and smooth code scanning type full-automatic bicycle storing and taking is achieved, the problems of city face appearance damage and theft prevention and damage prevention caused by disorderly parking and disorderly placing of shared bicycles are solved, the bicycle parking system is suitable for traffic stations such as residence communities and railway station bus stations, and the space utilization rate is greatly increased under a limited parking area.

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 relates to an intelligent disease diagnosis and treatment system, which is composed of a server, a mobile phone application and a household detection instrument. The intelligent diseasediagnosis and treatment system is based on the server provided with the latest medical theories and a large number of diagnostic data updated at any time, adopts data sharing as a basic mode, takes the household detection instrument as a means, and performs diagnosis through querying the state of illness and facial condition of a patient, more importantly, the intelligent disease diagnosis and treatment system suggests the patient to diagnose the state of illness by means of a portable detection instrument communicated with a mobile phone, and finds out the optimal suggestion and the optimal treatment scheme according to the massive diagnosis and treatment cases. The intelligent disease diagnosis and treatment system can help doctors in work and can eventually replace general work of the doctor.

The invention adopts postoperative photos similar to the preoperative facial appearance of a cosmetic operation accepter to evaluate the postoperative effects of the accepter before cosmetic operation, thereby ensuring that the accepter can know postoperative effects before cosmetic operation. Moreover, the evaluation can be taken as a contract engagement with a plastic surgeon. By comparing the similarity between the photos of a recipient and the adopted postoperative photos, the cosmetic operation accepter can select a plastic surgeon who realizes the expectation of the recipient. Preoperative and postoperative photos of similar facial appearance are difficult to obtain through video recording, and the usability of the photos needs to be acquired and affirmed through the technical flows of the novel method. Through the internet, the system adopts the flows to set membership, photo privacy protection and photo usability affirmance, and establishes a database to store a great number of photos and video recordings of different faces before and after cosmetic operations.

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.

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.