A station device in a biometric pre-identification system uses identity to perform one or more actions. Identities are determined (such as via a backend) using biometric information. A biometric pre-identification device obtains biometric information and/or a digital representation thereof from a person approaching the station device. The biometric pre-identification device transmits such to the station device, facilitating the station to begin and/or perform various actions. The station device begins or performs the actions using the identity determined based on the biometric information before the person arrives at the station device.

A person authentication system is provided. The person authentication system includes one or more image capture devices. The person authentication system includes a computing system. The computing system includes one or more computing devices. The computing system is configured to obtain data indicative of a unique identifier associated with an earpiece worn by a person. The computing system is configured to obtain image data of an ear of the person via the one or more image capture devices. The computing system is configured to authenticate an identity of the person based, at least in part, on the image data and the data indicative of the unique identifier.

A facial recognition method using online sparse learning includes initializing target position and scale, extracting positive and negative samples, and extracting high-dimensional Haar-like features. A sparse coding function can be used to determine sparse Haar-like features and form a sparse feature matrix, and the sparse feature matrix in turn is used to classify targets.

Re-Identification of physical objects in an image background is made possible by the use of temporary data objects (i.e., video cookies). Image data including an image object representing a physical object in at least one of a plurality of backgrounds is pre-stored in a database. Identification data for the image object and image background data is extracted from the image object and a comparison is made to determine if the identification data matches identification data in the database. In the event no match is found, a temporary data object is created and stored in the database that links the identification data and the image background data. If an identification data match is found, it is determined whether a temporary data object exists in the database. If no temporary data object exists, one is created and stored in the database. If a temporary data object is determined to exist in the database, it is determined whether the temporary data object fulfills a predetermined condition(s). If the predetermined condition(s) is not fulfilled, a default action is executed and if the predetermined condition(s) are fulfilled, a specific action is executed.

Systems and methods for enhancing customer service are disclosed. The system can perform operations including detecting individuals and performing facial recognition on the individuals using visitor profiles stored by a local database. The operations can further include determining known visitors and unknown visitors among the individuals. The operations can further include generating new visitor profiles for the unknown visitors, obtaining identity information for the unknown visitors, and associating the identity information of the unknown visitors with the new visitor profiles. The operations can further include accessing identify information of the known visitors, obtaining personalized information for the known visitors from a central database, and providing the personalized information to the known visitors. The operations can further include updating the existing visitor profiles and new visitor profiles based on actions of the known visitors and actions of the unknown visitors and providing the updated visitor profiles to the central database.

The embodiments of the present disclosure provide a method of registering a face based on video data, including: receiving video data; acquiring a first image frame sequence from the video data, wherein each image frame in the first image frame sequence includes a face detection frame containing a complete facial feature; determining whether each image frame reaches a preset definition or not according to a relative position of the face detection frame in the image frame; extracting a plurality of sets of facial features based on an image information of the plurality of face detection frames in response to determining that the image frame reaches the preset definition, and determining whether the faces represent an object or not according to the plurality of sets of facial features; and registering the object according to the first image frame sequence in response to determining that the faces represent the object.

Technology disclosed herein provides an object tracking multi-camera system including a plurality of cameras to capture images of one or more objects and one or more pattern recognition modules, each of the pattern recognition modules configured to identify an object in a video frame using pattern recognition and assigning a tracking number to the identified object, collect a plurality of object frames related to the identified object and associating the plurality of object frames to the assigned tracking number, compare a newly obtained object frame with the plurality of object frames related to the identified object to determine if the newly obtained object frame is related to the identified object, and in response to the comparison determine that facial recognition does not need to be performed on the newly obtained object frame.

A user device transmit a natural language query with a request for a description of videos stored in a media repository. A query system receives the query and determines a command associated with obtaining the requested description of the videos stored in the media repository requested by the query. The determined command corresponds to an image analysis to perform on at least a portion of the stored videos. The query system determines, based at least in part on the determined command, an artificial intelligence model to execute on at least the portion of the stored videos. The query system determines, by executing the determined artificial intelligence model, a model output that includes the requested description of the videos stored in the media repository. The query system provides a response to the query. The response includes the requested description of the videos stored in the media repository.

Techniques are described for identifying and/or authenticating entities using a combination of independent identification technologies and/or platforms. In one embodiment, a system can comprising a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory.

The computer executable components can comprise a reception component that receives, from an entity, a request to authorize the entity based on image data of a person, wherein the request comprises the image data, and an authentication component that determines whether the person included in the image data corresponds to the entity.

The disclosure pertains to techniques for image processing. One such technique comprises a method for image selection, comprising: obtaining a sequence of images, detecting a first face in one or more images of the sequence of images, determining a first location for the detected first face in each of the images having the detected first face, generating a heat map based on the first location of the detected first face in each of the images of the sequences of images, determining a face quality score for the detected first face for each of the one or more images having the detected first face, determining a peak face quality score for the detected first face based in part on the face quality score and the generated heat map, and selecting a first image of the sequence of images, corresponding with the peak face quality score for the detected first face.