53results about How to "Facilitate face recognition" patented technology

The invention relates to the entertainment equipment technical field, and especially relates to frame and mechanical motion synchronization simulation racing car equipment and a simulation method; the racing car equipment comprises a drive seat, a motion adjusting platform, a simulation control steering wheel, a simulation pedal, a virtual reality helmet, a game host, and a control circuit board; the virtual reality helmet and the motion adjusting platform can mutually cooperate, so the 3D video frames in the game and the drive seat mechanical motions can be synchronized, thus building more vivid visual effect; the simulation racing car equipment and simulation method are high in simulation level, vivid in visual effect, so participants can have more vivid, dynamic and excited racing car driving experiences, and the users can be personally on the scenes.

The invention provides a human face recognition method and apparatus. The method is improved on the basis of existing small sample supervised Laplace discriminant analysis, maximized inter-class scatter is integrated into an objective function of minimized inter-class scatter, Laplace discriminant analysis is used, a projection matrix is obtained by achieving the optimal objective function, and dimensionality reduction is performed on high dimensional human face data. The human face image recognition rate is higher than that of an existing SLDA (Stepwise Linear Discriminant Analysis) method for achieving better human face recognition after dimensionality reduction by means of the human face recognition method.

The invention relates to an image processing method and apparatus, an electronic device and a computer readable storage medium. The method comprises the steps of obtaining an image and basic information of the image, and according to the basic information of the image, compressing the image to generate a thumbnail; according to brightness and color distribution information of the thumbnail, performing region division on the thumbnail to obtain sub-regions, and performing priority ranking on the sub-regions according to the degree of closeness to a human face; and according to the priority ranking of the sub-regions, performing human face identification on the sub-regions in sequence to obtain a human face identification result of the thumbnail, and according to the human face identification result of the thumbnail, performing human face classification on the image corresponding to the thumbnail to generate a human face classification result. The thumbnail is relatively small in size, so that the human face identification can be performed efficiently in the subsequent process; the thumbnail is divided into the sub-regions, and the sub-regions are subjected to the human face identification, so that the human face in the whole thumbnail can be identified; and therefore, the efficiency of performing the human face classification on the image is greatly improved, the classificationerror rate is reduced, and the omission is avoided.

The invention discloses an intelligent monitoring and recognition method and device for the surrounding environment of a payee, and a medium. The method comprises the steps of video monitoring, targettracking, and interactive behavior detection and recognition. The target tracking comprises the following steps: when the video monitors that someone enters the periphery of the ATM, performing multi-target tracking by taking a human body in the monitoring video as a target by adopting Markov Monte Carlo to obtain a tracking video comprising a multi-target tracking track; the interactive behaviordetection comprises the steps of extracting features from a tracking video and constructing combined features to judge a face portrait and feature points thereof of a human body target through a convolutional neural network algorithm so as to judge whether a head posture and a sight angle are abnormal or not, and carrying out interactive behavior detection on the abnormal situation; the interactive behavior recognition is to further judge the type of the interactive behavior if the interactive behavior exists. According to the invention, people and objects in the withdrawal area can be monitored in real time, and the behaviors of people can be automatically detected and identified.

An apparatus for recognizing faces with different illuminations may include a processor and memory storing executable computer program code causing the apparatus to at least perform operations including detecting and extracting face data of a first candidate face of a first image and a second candidate face of a second image. The first image is associated with a first light intensity and the second image associated with a second light intensity different from the first light intensity. The computer program code may further cause the apparatus to analyze face data to determine whether the first candidate face corresponds to an area in the first image that is substantially the same as an area of the second candidate face and evaluate data of the first and second areas to determine whether the first and second candidate faces are valid or invalid faces. Corresponding methods and computer program products are also provided.

The invention relates to an antitheft door based on a face recognition technology. The antitheft door comprises a base, a door frame, a door sheet, a pedal, a recognition device, a manager, a lockingmechanism and two hinges, wherein the recognition device comprises a notch and tempered glass; a lifting mechanism, a lifting plate, a camera and two drying mechanisms are arranged in the notch; the lifting mechanism comprises a first motor, a roller, a tensioning assembly and two lifting assemblies; each lifting assembly comprises a rotating shaft, a driving wheel, a driven wheel and a conveyingbelt; each drying mechanism comprises an air inlet pipe, a drying chamber, an air outlet pipe, a direction adjusting assembly and a nozzle. According to the antitheft door based on the face recognition technology, the tempered glass protects the camera in the notch against damage, the lifting mechanism can drive the camera to move up and down to recognize faces of people at different heights, moreover, the drying mechanisms can remove water mist on the surface of the tempered glass in damp weather, the camera can shoot clear images, the face recognition accuracy can be guaranteed, and the equipment practicability is improved.

A method for improving face recognition from unseen domains by learning semantically meaningful representations is presented. The method includes obtaining face images with associated identities from a plurality of datasets, randomly selecting two datasets of the plurality of datasets to train a model, sampling batch face images and their corresponding labels, sampling triplet samples including one anchor face image, a sample face image from a same identity, and a sample face image from a different identity than that of the one anchor face image, performing a forward pass by using the samples of the selected two datasets, finding representations of the face images by using a backbone convolutional neural network (CNN), generating covariances from the representations of the face images and the backbone CNN, the covariances made in different spaces by using positive pairs and negative pairs, and employing the covariances to compute a cross-domain similarity loss function.

The present invention discloses a method for automatically replacing a reference photograph according to similarity concentration ratios. The method includes the following steps that: (1) a database is constructed in a system, a photograph archiving module, a photograph comparison module and a photograph replacement module are set in the database; (2) when a relevant person logins the system for the first time, the system takes a picture of the relevant person, wherein the picture is adopted as a reference photograph; (3) when the relevant person starts a process of multiple times of login; when the relevant person logins the system each time, the system identifies the face of the relevant person, an identified image is compared with the reference photograph, if the similarity of the identified image and the reference photograph reaches a specified value, the relevant person logins and enter the system; and (4) when the number of successful logins of the relevant person in the step 3 reaches a specified value of the system, images stored in the photograph comparison module are automatically compared, and a photograph with the highest similarity concentration ratio in all the images is identified and is adopted as a new reference photograph. With the method of the invention adopted, face recognition can be carried out more quickly, more accurately and conveniently.

The invention provides an adjusting device and method for face recognition equipment, and the method comprises the steps: enabling a camera to be started to carry out the shooting of a face biologicalfeature image of a user after the user is close to the face recognition equipment, and judging whether the face biological feature image is shot or not; if it is judged that the shooting does not exist, based on a plurality of preset definition data items which respectively define the installation base of the camera and correspondingly carry out different dynamic adjustment actions, informing a user of carrying out corresponding dynamic adjustment on the installation base by providing one or more instructions corresponding to the definition data items; and after an instruction provided by a user is received, enabling the mounting base to perform corresponding dynamic adjustment, so that the visual angle range of the camera mounted on the mounting base is adjusted to shoot a recognizable face biological characteristic image of the user. Therefore, under the condition that the user does not need to move forwards, backwards, leftwards and rightwards and/or change the face height, face recognition is rapidly and conveniently achieved, the use experience of the user is improved, and the recognition efficiency is improved.

The invention discloses a multifunctional touch display self-service terminal, relates to the technical field of self-service terminals, and aims to solve the problems that a chassis is mostly of an anti-slip fixed structure, so that the self-service terminal is very good in fixity, but the self-service terminal is difficult to carry, the self-service terminal cannot be flexibly carried as required, and the self-service terminal is inconvenient to carry. And the use effect of the self-service terminal is not good indirectly. The self-service terminal comprises a self-service terminal main body, a processing device is arranged in the self-service terminal main body, a touch display screen, a camera, a card slot and a USB interface are arranged on the self-service terminal main body, four moving wheels are arranged below the self-service terminal main body, and the four moving wheels are arranged at four corners of the self-service terminal main body. Buffering pieces are arranged between the four moving wheels and the self-service terminal body, the two ends of each buffering piece are connected with the corresponding moving wheel and the self-service terminal body to form an integrated structure, a fixing base is arranged outside the self-service terminal body, and electric telescopic rods are arranged on the two sides of the self-service terminal body.

The invention relates to a face recognition device convenient to adjust and used for vehicle access. The device comprises a mounting plate, a contraction mechanism, a connecting rod, a recognition plate, a recognition mechanism and two mounting components. The contraction mechanism comprises a driving component, a first bevel gear, a second bevel gear, a rotating rod, a connecting frame and two insertion tubes; the driving component comprises a translation unit, a first rack, a circular gear, a rotating shaft and a supporting unit; the recognition mechanism comprises a camera, a moving component, a moving plate and a direction adjusting component; and the moving component comprises a first motor, a frame and two moving units. According to the face recognition device convenient to adjust and used for vehicle access, the position of the recognition plate can be flexibly adjusted through the contraction mechanism according to the requirement, thus face recognition is convenient and the wide view field of a vehicle owner during driving is ensured, the recognition mechanism drives the camera to move and swing, thus a front face image of the vehicle owner is conveniently acquired, and the face recognition precision and the practicability of the equipment are improved.

The invention provides a Hog and Gabor feature efficient fusion fast face recognition method based on near-infrared face image, belonging to the technical field of pattern recognition and image processing. The method includes Hog feature extraction and Gabor feature extraction for near-infrared face image samples respectively. The non-negative matrix decomposition method is used to reduce the dimension of two kinds of eigenmatrices respectively. The Hog feature and Gabor feature are fused to obtain the fused feature. The linear discriminant analysis (LDA) was used to reduce the dimension of the fusion feature matrix, and the feature vectors of the training samples after the transformation matrix of the second projection and the second reduction are obtained. The nearest neighbor algorithmKNN is used to classify and recognize the test samples based on the distribution of training samples. The invention ensures the comprehensiveness of acquiring characteristic information, effectively improves the characteristic representation efficiency, reduces the cost of algorithm operation storage and time consumption, and improves the efficiency of face recognition process.

The invention relates to a face recognition device. The face recognition device comprises a screen structure module, a recognition assembly and a height regulating device, wherein the recognition assembly is arranged on the top of the screen structure module; the height regulating device comprises an upper bracket, a lower bracket and a lifting mechanism; the upper bracket is matched with the lower bracket; the upper bracket can slide up and down relative to the lower bracket; the lifting mechanism is arranged on the lower bracket; the lifting mechanism is used for controlling the upper bracket to ascend or descend in a sliding direction; and the screen structure module is fixedly arranged on the upper bracket. The face recognition device disclosed by the invention can effectively regulateheight of the recognition assembly, facilitates application of face recognition, and improves user experience.

The invention discloses an application system based on a face recognition technology for replacing the aged bus card annual inspection, and the system comprises a first housing, a second housing, a positioning assembly, and an adjusting assembly, one side of the first housing is provided with a display panel, the head part of the side, provided with the display panel, of the first housing is provided with a camera, and the second housing is provided with a control panel; and the positioning assembly is used for fixing the positions of the first shell and the second shell after movement and comprises a second telescopic rod, and the output end of the second telescopic rod is fixedly connected with a positioning block making contact with the ground. The adjusting assembly is used for adjusting the height of the first shell so that users of different heights can use the device conveniently, and the adjusting assembly comprises two first telescopic rods. Through the arrangement of the positioning assembly and the adjusting assembly, the position of the device after movement can be fixed, face recognition can be conveniently conducted on old people of different heights, and the use requirements of different users are met; and the structure is simple, and a user can conveniently maintain and replace.

The invention discloses an office paper file management system. The system comprises a tool cabinet. The tool cabinet comprises a plurality of layers. An RFID card reader is arranged at the upper partof each layer of the tool cabinet. A plurality of paper files provided with RFID electronic tags are arranged in the tool cabinet. The RFID electronic tag is placed upwards and corresponds to the RFID card reader. A control panel is arranged on the side surface of the tool cabinet. The RFID electronic tag is connected with the control panel. The control panel is provided with a display module used for displaying and a face recognition module used for recognizing the face. The control panel is electrically connected with an electric door of the tool cabinet. The number and positions of files in the cabinet can be well recorded through the RFID label and the RFID card reader, face recognition is conducted, the taking safety of the files is improved, the files are not placed in the originalplace, the alarm lamp gives an alarm for prompting, and file management can be more standard.

The invention discloses a visitor machine which comprises a supporting mechanism, a host box body, a thermal printer, a display mechanism and an input keyboard, the supporting mechanism is fixedly mounted on the lower side surface of the host box body, and a microprocessor, a memory, a wireless communication module and a power supply module are arranged in the host box body; the display mechanism comprises a display backboard, a display screen and an upper camera. According to the visitor machine, face recognition of visitors can be facilitated by using the upper camera so that rapid paperless registration of the visitors is facilitated, and the personnel entering efficiency is improved; identity information of the visitors can be conveniently printed by utilizing the thermal printer so that the visitors can conveniently prepare for reference at any time after entering; wireless communication with a monitoring center can be realized by utilizing the wireless communication module so that visitor information is uploaded.

The invention discloses an intelligent management and control system and method applied to power plant safety management. In a power plant high-risk area, due to the limited working period and different staff technical levels, management staff monitoring is needed in an operation field, thus the number of staff in the working field is large, and the risk is high. The intelligent management and control system for the power plant safety management comprises an access control system (1), the access control system is internally provided with a control and management system, the control and management system are connected with an LED screen (3), a trumpet (2), an alarm apparatus (9) and a face recognition system correspondingly through guide lines, the LED screen is connected with a hard disk video (4) through a reticle, the hard disc video is connected with a computer (5) through a data line, the hard disc video is connected with the alarm apparatus through a signal line, the computer is connected with a power amplifier (7) through a data line, the power amplifier is connected with the trumpet through an audio cable, the computer is connected with a liquid crystal display (6) through areticle, and the liquid crystal display is provided with an information real-time display system. The intelligent management and control system and method for the power plant safety management are applied to an intelligent management and control system on power plant safety management.

The invention discloses an intelligent air conditioning method and device based on Internet of Things signal transmission. The method comprises the steps that a sensing unit collects initial parameters through sensing equipment; the artificial intelligence unit supplements fresh air and oxygen for the human body through an air supply volume adjusting algorithm; the artificial intelligence unit supplements physical energy to the human body through an energy beverage supplementation algorithm or a manual mode. According to the intelligent air conditioning device, automatic ventilation, oxygen supply and energy supply can be provided for wearers who work for a long time in indoor and outdoor environments, the intelligent air conditioning device based on Internet of Things signal transmission does not need to be picked up in the whole process, and the intelligent air conditioning device is particularly suitable for medical staff and current increasingly severe epidemic situations.