853results about "Matching and classification" patented technology

Systems herein describe a secured transaction system for accessing a camera stream from a front-facing camera unit of a wearable computing device, identifying a visual marker in the camera feed associated with a payment application, in response to identifying the visual marker, transmitting a request to an operating system of the wearable computing device to isolate access of the camera stream to the payment application and in response to transmitting the request, initiating a transaction using the payment application.

The invention relates to the technical field of building design, and discloses an Internet-based building design dynamic process management system, which comprises a multi-factor identity verification module, a distributed data storage module, a process dynamic optimization engine, a behavior evaluation and intervention module and an intelligent audit tracking system. According to the building design dynamic process management system based on the Internet, through cooperative work of the process dynamic optimization engine and the behavior evaluation and intervention module, the problem that task optimization of a traditional process management system depends on a preset rule is solved; the flow dynamic optimization engine dynamically adjusts the task priority and resource allocation by using an improved ant colony algorithm based on the real-time task progress and the executor behavior data; meanwhile, the behavior evaluation and intervention module quantitatively evaluates the behavior of the executor according to a weighted scoring model, triggers an automatic intervention process when necessary, and can quickly adapt to sudden changes, so that the resource allocation efficiency is improved, and human errors are reduced.

Methods and systems are described for identity verification and deepfake prevention. A first video of a person is captured during an in-person interaction, the person's identity is verified, and the video is associated with the verified identity. In a subsequent electronic interaction, information about a second person is accessed, a second video of the second person is captured, and a trained neural network model is used to determine if the second person is attempting to identify as the first person. If the second person is not attempting to identify as the first person, the electronic interaction proceeds. If the second person is attempting to identify as the first person, the model determines if the first person is likely the same as the second person, transmitting a positive indicator if likely the same, and a negative indicator if not. Related networks, models, apparatuses, devices, techniques, and articles are also described.

This invention is directed to an electronic device with an embedded authentication system for restricting access to device resources. The authentication system may include one or more sensors operative to detect biometric information of a user, The sensors may be positioned in the device such that the sensors may detect appropriate biometric information as the user operates the device, without requiring the user to perform a step for providing the biometric information (e.g., embedding a fingerprint sensor in an input mechanism instead of providing a fingerprint sensor in a separate part of the device housing). In some embodiments, the authentication system may be operative to detect a visual or temporal pattern of inputs to authenticate a user. In response to authenticating, a user may access restricted files, applications (e.g., applications purchased by the user), or settings (e.g., application settings such as contacts or saved game profile).

A multi-port interface device for connecting multiple computing devices for data and power transfer includes a housing with an internal power source. A processor is electrically coupled to the internal power source. A power input port electrically coupled to the internal power source is designed to receive a power cord. The power cord is electrically couplable to an extrinsic power source to transfer power from the extrinsic power source to the internal power source. A plurality of ports electrically coupled to the processor is inset into the housing. Each port of the plurality of ports is exposed within the housing. The plurality of ports includes a plurality of universal serial bus ports and a memory card port.

Embodiments of the present application provide a fingerprint anti-counterfeiting neural network training method, a fingerprint anti-counterfeiting method and device, comprising: obtaining multiple sets of training data, each set of training data including: first native domain data, second native domain data and third native domain data; using the multiple sets of training data to train an initial classification network to obtain a target classification network, the initial classification network including a fusion subnetwork and a classification subnetwork, for each set of training data, the fusion subnetwork is used to generate a first fingerprint matching pair based on the feature description matrix of the first native domain data and the second native domain data, and generate a second fingerprint matching pair based on the feature description matrix of the first native domain data and the third native domain data, and the classification subnetwork is used for fingerprint classification and identification based on the first fingerprint matching pair and the second fingerprint matching pair. Through the present application, the problem of low identification accuracy of true and false fingerprints in related technologies is solved, and the effect of improving the identification accuracy of true and false fingerprints is achieved.

Object description information that is transmitted by a biometric recognition apparatus is received, the object description information includes a biometric feature of a target object and location information of the target object. Identity information of the target object is obtained according to the biometric feature. A service information set in association with the identity information is obtained. From the service information set, one or more pieces of candidate service information are selected. The one or more pieces of candidate service information are transmitted to a terminal device associated with the identity information. At least a first piece of target service information returned by the terminal device is received. At least a first service corresponding to the first piece of target service information is processed. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

The invention relates to a fingerprint lock dynamic encryption authentication method and system and a medium. The method comprises a registration stage and an authentication stage. Wherein in the registration stage, lock body environment real-time physical parameters are collected, and a dynamic environment secret key is generated through a chaotic mapping function; acquiring a user fingerprint, identifying core and non-core feature regions, and encrypting the two types of regions by combining a dynamic environment key and a user key to generate registration encrypted fingerprint data; and dividing the data into two data fragments by using a quantum noise source true random sequence, storing the first data fragment in a local security chip, and encrypting the second data fragment and storing the encrypted second data fragment in a cloud server. In the authentication stage, environment parameters are collected in real time to generate a verification key, and the verification key is compared with a registration key; and when the two fragments are consistent, recombining the two fragments to restore the encrypted fingerprint data, authenticating the fingerprint input by the user, unlocking if the authentication succeeds, and triggering risk grading processing if the continuous failure reaches a threshold value. The overall safety and reliability of the fingerprint lock system are improved.

The invention provides a fingerprint signal processing method and device and electronic equipment, and can be applied to the technical field of fingerprint identification. Based on the method, before specific implementation, fingerprint pixel units in a fingerprint pixel unit array circuit can be connected with a preset gain amplifier with adjustable gain, and an improved fingerprint pixel unit array circuit is obtained. In specific implementation, when a fingerprint related signal is received, a matched target convolution kernel is determined in the fingerprint pixel unit array circuit; wherein the range of the target convolution kernel comprises a plurality of fingerprint pixel units; and traversing the fingerprint pixel unit array circuit by using a target convolution kernel, and processing the fingerprint related signal to obtain a target fingerprint signal. Therefore, the fingerprint pixel units in the fingerprint pixel unit array circuit can be fully utilized, the received fingerprint related signals are processed by constructing and using the corresponding target convolution kernels, the signal-to-noise ratio of the signals is effectively improved, and target fingerprint signals with high quality are obtained.

A medical imaging system including an optical identifier camera for imaging a medical device, a medical device packaging, a patient, or a technician. The system further includes an imaging probe for imaging of a target location, and a console with optical identifier logic to extract identifier markers or characteristics from the image of the medical device, packaging, patient or technician. A parameter logic determines the medical imaging parameters based on the identifiers or characteristics, and a medical imaging logic captures medical images of the medical device. The system enables efficient and accurate imaging of medical devices on the specific patient, by a specific technician, enhancing diagnostic capabilities and treatment planning in medical parameters.

Hierarchical patch-wise diffusion models (HPDMs) use a diffusion paradigm that learns a hierarchical distribution of patches instead of whole videos for efficient patch-wise training of diffusion models. To enforce consistency between the patches, deep context fusion may be used to propagate the context information from low-scale to high-scale patches in a hierarchical manner. To accelerate patch-wise training and inference, adaptive computation also may be used to allocate more computational resources and network capacity towards coarse image details and to cheapen synthesis of high-frequency texture details. All the processing stages are jointly trained to provide spatially aligned global context to the higher levels of the cascade. As a result, the model does not operate on the full-resolution inputs, which allows the model to be trained on high-resolution video datasets in an end-to-end fashion.

Embodiments of this application disclose a palm print recognition method, a method for training a feature extraction model, a device, and a storage medium, and belong to the field of computer technologies. The method includes: obtaining sample hand images for each of a plurality of sample user identifiers, at least two of the sample hand images associated with the each of the plurality of sample user identifier being acquired from image acquisition devices having different image acquisition characteristics; calling a feature extraction model to extract sample palm print features of the plurality of sample user identifiers; and adjusting the feature extraction model according to the sample palm print features of the plurality of sample user identifiers.

A driver monitoring (DM) computing device for monitoring driving behavior of a driver in real-time is provided. The DM computing device detects a user computer device associated with a driver inside the vehicle. The DM computing device collects state data of the user computer device. The state data includes data as to a state of the user computer device during a currently occurring trip. The DM computing device collects vehicle operation data of the vehicle while the driver and the user computer device are inside the vehicle. The DM computing device compares the collected vehicle operation data and the state data of the user computer device to determine whether the user computer device was activated during the currently occurring trip. The DM computing device causes a driving reward to be applied to an account associated with the driver for inactivity of the user computer device during the currently occurring trip.

A fingerprint recognition method and apparatus are provided. The method is applied to the field of fingerprint recognition technologies. The method includes: when a first fingerprint image is successfully matched, judging whether matching information of the first fingerprint image satisfies a first preset condition; when the matching information of the first fingerprint image satisfies the first preset condition, judging whether a cumulative update count of a second fingerprint template is greater than a first quantity threshold; when the cumulative update count of the second fingerprint template is greater than the first quantity threshold, judging whether priority information of the second fingerprint template satisfies a second preset condition; and when the priority information of the second fingerprint template satisfies the second preset condition, updating the second fingerprint template with the first fingerprint image. A high-quality fingerprint image is selected through a plurality of judgment conditions to update a fingerprint template library. Matching is performed based on an updated fingerprint template library. This can increase a fingerprint unlocking rate and an unlocking speed, so that user experience in unlocking is improved.

A fingerprint information processing apparatus includes: an output unit that outputs a certainty factor that is an index indicating probability in which fingerprints indicated by a fingerprint image correspond to at least one of a plurality of pattern types, by using the fingerprint image and a learning model constructed by machine learning using learning data including a sample image indicating fingerprints; and a processing unit that performs processing based on the certainty factor.

Disclosed is a method for providing a trained machine learning system for classifying images of fingerprints, the method comprising: providing a training data set, comprising sets of images of fingerprints, wherein each image in the training data set further comprises a binary label encoding a class designation; using the training data set to train a machine learning system, wherein the machine learning system comprises a classical machine learning model implemented on a classical processor and a quantum machine learning model implemented on a quantum processing unit (QPU); encoding the image data of each image in the training data set into a feature vector using the classical machine learning model, obtaining a family of feature vectors; using the family of feature vectors obtained from the images in the training data set to train the classical machine learning model and the quantum machine learning model, for providing the trained machine learning system, comprising a trained classical machine learning model and a trained quantum machine learning model.

Provided is a display device equipped with both a touch detection function and a fingerprint or vein shape imaging function. The display device includes a first light-emitting element, a second light-emitting element, a light-receiving element, and a light shielding layer. The first light-emitting element and the light-receiving element are arranged side by side on the same plane. The light shielding layer is provided above the first light-emitting element and the light-receiving element. The second light-emitting element is provided above the light shielding layer. The first light-emitting element has a function for emitting visible light upward. The second light-emitting element has a function for emitting invisible light upward. The light-receiving element is a photoelectric conversion element that is sensitive to visible light and invisible light. In addition, the light shielding layer has a part positioned between the first light-emitting element and the light-receiving element in a planar view, and the second light-emitting element overlaps with the light shielding layer in a planar view and is positioned further to the inside than the contour of the light shielding layer.

Disclosed in the present invention are a palmprint recognition method and apparatus, which relate to the technical field of palmprint recognition authentication, and solve the problem of low palmprint recognition accuracy caused by incapability of correcting palm postures in the prior art. The palmprint recognition method comprises: acquiring a palm image to be recognized; performing key point detection on the palm image on the basis of a preset first key point detection method, so as to obtain a first palm key point set; constructing an affine transformation matrix on the basis of the first palm key point set; on the basis of the first palm key point set and the affine transformation matrix, performing alignment and extraction on the palm image by means of a preset alignment and extraction method, so as to obtain first palmprint information, the first palmprint information comprising a palmprint attention region and a palm key point set; and inputting the first palmprint information and pre-stored second palmprint information into a preset first recognition model, and outputting a recognition result. The present invention can align palm images and correct palm postures, and can refine the granularity of palmprint features, thus improving the precision and accuracy of palmprint recognition.

An authentication guide device includes: one or more acquisition units configured to acquire ambient condition information at the time of acquisition of one or more pieces of biometric information of a person to be used for a plurality of types of biometric authentication; a guide determination unit configured to determine, based on ambient environment information, a guide method for presenting an execution order for preferentially executing the plurality of types of biometric authentication on a person; and a guide display unit configured to display the guide method on a display unit.

The invention discloses a palm image recognition method and system based on fusion of a convolutional neural network and an image neural network, and belongs to the technical field of crossing of biological feature recognition and artificial intelligence. The problems that in the prior art, local texture features and a global topological relation are separated, dynamic scene adaptability is poor, and multi-modal features are not fully fused are solved. The method comprises the following steps: 1) designing a dual-path hybrid network architecture (DPHGCN), extracting multi-scale local texture features through a lightweight CNN, constructing an adaptive graph structure by using a dynamic graph generator (DGG), and modeling a topological relation between key points in combination with a graph attention network; 2) developing a cross-modal feature alignment module (GIPL), and realizing dimension mapping and semantic alignment of CNN feature graph and graph node embedding; and 3) providing a layered attention fusion mechanism, and combining space attention, topological attention and cross-modal attention to dynamically weight and fuse heterogeneous features. According to the method, 98.7% of recognition accuracy is achieved on a public data set, the reasoning speed reaches 32 ms / frame, 76.2% of robustness is still kept in a 50% shielding scene, and the method can be widely applied to the fields of financial payment identity authentication, medical palmprint pathological analysis, real-time security verification and the like.

The invention relates to the technical field of palmprint recognition, and discloses a palmprint recognition method based on multi-feature fusion, and the method comprises the steps: collecting a palmprint image, carrying out the preprocessing of the palmprint image, and generating a palmprint ROI image; extracting a multi-scale feature vector of the palmprint ROI image and a histogram feature vector of the palmprint image; splicing the multi-scale feature vector and the histogram feature vector to generate a target feature vector; and calculating the similarity between the target feature vector and the feature vector of the palmprint in a preset database, and outputting a palmprint recognition result according to the similarity. A hierarchical multi-scale filtering mechanism is utilized to process features of different scales layer by layer, and rich texture features are effectively captured; the importance of different scale features is dynamically adjusted by using a multi-scale channel attention mechanism, so that the network pays more attention to feature information beneficial to a recognition task; the histogram features are extracted and fused with the multi-scale features, so that the recognition result is more effective, the accuracy of the recognition result is improved, and the robustness of the recognition result is enhanced.

The invention discloses a data processing method and device and a program product. Relates to the field of artificial intelligence or financial science and technology, and the method comprises the steps: collecting face feature data in a face image or a face video when a financial service is handled, inputting the face feature data into a target recognition model, and obtaining a recognition result, the recognition result is used for indicating whether a target object in the face image or the face video is a moving object; under the condition that the recognition result indicates that the target object in the face image or the face video is a moving object, collecting static biological characteristics of the target object to obtain static characteristic data, and collecting dynamic behavior characteristics of the target object to obtain dynamic characteristic data; and performing anomaly detection on the static feature data and the dynamic feature data to obtain a target detection result. According to the method and the device, the problem of low security of security verification in a financial business handling process in the prior art is solved.

A computerized method is provided for user authentication using hand gestures. Multiple points on a user's hand can be tracked using cameras or various sensors and the motion of those points in space and relative to each other can used to create gesture-based passwords. Such user authentication techniques have advantages in augmented and virtual reality applications where traditional text-based passwords may be difficult. Gesture-based user authentication can be augmented with physical characteristics of the specific user's fingers and hands including size, shape, and distinguishing marks to enhance security.

An apparatus may include a display stack, an ultrasonic sensor stack and a high-impedance stack including one or more high-impedance layers. The ultrasonic sensor stack may include an ultrasonic transceiver layer and an ultrasonic transceiver circuitry (UTC) layer. Each of the high-impedance layers may have an acoustic impedance that is higher than an acoustic impedance of the UTC layer. The high-impedance stack and the ultrasonic sensor stack may form an acoustic resonator bounded by the UTC layer and the high-impedance stack. The acoustic resonator may be configured to enhance the ultrasonic waves transmitted by the ultrasonic sensor stack at a peak frequency of the ultrasonic sensor stack. The peak frequency may be a frequency used by the ultrasonic sensor stack for obtaining fingerprint images. An apparatus stack portion that includes the ultrasonic sensor stack may have a thickness corresponding to a multiple of a quarter wavelength at the peak frequency.

A sample palm print image generation method includes generating a major palm print line according to a preset major palm print line distribution pattern, determining a palm print distribution region in which the major palm print line is located, generating a minor palm print line in the palm print distribution region based on a preset minor palm print line distribution pattern, generating a candidate palm print image based at least on the major palm print line and the minor palm print line, labeling the candidate palm print image with a candidate image label that represents a palm print distribution of the candidate palm print image including at least one of a major palm print line distribution or a minor palm print line distribution, and inputting the candidate palm print image to a palm print generation model to obtain a sample palm print image.

In a biometric identification system, a transparent body can have a curved platen surface. The curved platen surface can be removably contacted by an anatomy of a user. The anatomy can have an anatomical pattern. An illumination source can illuminate the curved platen surface with an illumination beam. The illumination beam can propagate away from the curved platen surface as a return beam having a beam pattern shaped to correspond to the anatomical pattern. An imaging lens can focus the return beam to form a real image of the beam pattern at an image location. Field-curvature-correcting sensor optics can include a sensor. The sensor can sense the real image of the beam pattern at the image location. The field-curvature sensor optics can include a planar sensor and an image-flattener lens. The field-curvature sensor optics can include a curved, convex sensor.

A system of enhancing biometric analysis matching utilizes an image sensor, such as a digital camera, to capture an image of a face of a person. The system may perform image enhancement, such as edge and contrast enhancement, prior to performing face matching. The enhancement may be localized to a given image region based on determined region illumination. The system may perform image processing and analysis comprising face detection, alignment, feature extraction, and recognition. A biometric recognition confidence indicator may be generated using the results of the image enhancement and analysis. At least partly in response to the biometric recognition confidence indicator falling below a threshold enhancing recognition confidence using an image of visual indicia captured using the image sensor.

The invention discloses a passenger getting-on confirmation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the initial riding information of a target vehicle in response to a first starting instruction for the target vehicle; if it is detected that the target vehicle is in the parking state, obtaining positioning information of the target vehicle; comparing the positioning information with the destination information of each initial passenger, and obtaining the identity feature of the target passenger from the initial riding information to obtain a target identity feature set; in response to a restart instruction for the target vehicle, obtaining identity features of actual passengers in the target vehicle, and obtaining an actual identity feature set; if the actual identity feature set is not matched with the target identity feature set, prompt confirmation information is sent to a driver of the target vehicle, and the prompt confirmation information is used for prompting that the passenger does not get on the vehicle. By combining the positioning information, whether all the passengers get on the vehicle again can be accurately judged, and the situation that the passengers are missed at the midway parking points is effectively avoided.

The invention discloses a novel graph contrast learning framework with mutual information maximization, and relates to the technical field of graph contrast learning, multi-modal learning and mutual information maximization. The framework comprises the following steps: constructing a nearest neighbor graph, spreading similar samples to data of a missing mode, optimizing a loss function, and performing clustering optimization. The existing method has two main problems: (1) the existing method is mostly suitable for complete data and has a poor processing effect on data of a missing mode; and (2) the current palmprint and palm vein fusion recognition technology does not completely capture the complex relationship between the palmprint and palm vein features, resulting in inaccurate clustering result. According to the method, the modal loss in the incomplete palm print and palm vein fusion recognition task is effectively reduced, and the clustering performance is enhanced. According to the method, the mutual information maximization loss function is introduced, the adaptability and robustness of the model to incomplete data are effectively enhanced, and the method has high recognition precision and clustering performance when processing incomplete multi-modal data.

The embodiment of the invention provides a fingerprint identification method and device, electronic equipment and a storage medium. The fingerprint identification method comprises the following steps: acquiring a to-be-identified fingerprint image; the to-be-identified fingerprint image is identified through a plurality of seed templates, the plurality of seed templates are spliced into at least one first virtual puzzle, and the adjacent seed templates in the first virtual puzzle have overlapping areas; if the identification of the fingerprint image to be identified by the plurality of seed templates fails, determining at least one reference area from the first virtual puzzle according to the similarity between the fingerprint image to be identified and the plurality of seed templates; determining the auxiliary template, of which the overlapping rate with any reference region is greater than an overlapping rate threshold value, in the plurality of auxiliary templates as a supplementary template; and identifying the fingerprint image to be identified through the supplementary template.