The technology disclosed relates to relates to providing command input to a machine under control. It further relates to gesturally interacting with the machine. The technology disclosed also relates to providing monitoring information about a process under control. The technology disclosed further relates to providing biometric information about an individual. The technology disclosed yet further relates to providing abstract features information (pose, grab strength, pinch strength, confidence, and so forth) about an individual.

A computer-implemented method for determining an output signal characterizing a first classification of an input image into a class from a plurality of classes. The output signal further characterizes a second classification of a robustness of the first classification against an attack with an adversarial patch.

A system comprising: a camera configured to capture one or more images of a user's hand; and a computer configured to: receive the one or more captured images, apply a mapping function to the received one or more images, thereby yielding one or more coordinates associated with at least one feature of the user's hand, wherein the mapping function is derived from a set of labeled images that are produced by applying a machine learning algorithm to training data which comprises images of a trainer's hand, wherein the images are labeled with coordinates obtained from multiple magnetic sensors attached to the trainer's hand.

An exemplary method includes a gesture recognition system determining, based on imagery of a user while the user touchlessly interacts with a user interface of a computer system, a configuration of a plurality of landmarks associated with the user and comparing the configuration of the plurality of landmarks to defined landmark configurations associated with a plurality of defined gestures. Each of the plurality of defined gestures may be associated with a different user input enterable by way of the user interface of the computer system. The method may further include the gesture recognition system selecting, based on the comparing of the configuration of the plurality of landmarks to the defined landmark configurations associated with the plurality of defined gestures, a defined gesture included in the plurality of defined gestures, and directing the computer system to enter a user input that is associated with the defined gesture.

In various examples, a background of an object may be modified to generate a training image. A segmentation mask may be generated and used to generate an object image that includes image data representing the object. The object image may be integrated into a different background and used for data augmentation in training a neural network. Data augmentation may also be performed using hue adjustment (e.g., of the object image) and/or rendering three-dimensional capture data that corresponds to the object from selected views. Inference scores may be analyzed to select a background for an image to be included in a training dataset. Backgrounds may be selected and training images may be added to a training dataset iteratively during training (e.g., between epochs). Additionally, early or late fusion nay be employed that uses object mask data to improve inferencing performed by a neural network trained using object mask data.

There is provided a recognition system adaptable to a portable device or a wearable device. The recognition system senses a body heat using a thermal sensor, and performs functions such as the living body recognition, image denoising and body temperature prompting according to detected results.

Systems and methods are provided for authenticating a user of a computing device. The system comprises one or more memory devices storing instructions, and one or more processors configured to execute the instructions to provide, to a computing device associated with a user, an indication of a prescribed authentication parameter. The system also receives image data including an image of the user of the computing device captured using an image sensor of the computing device. The system determines an identity of the user based on an analysis of the received image data, determines whether the received image data includes a feature corresponding to the prescribed authentication parameter, and authenticates the user based at least in part on whether the received image data includes the feature corresponding to the prescribed authentication parameter.

A system and method for computer vision based control of a device include a processor to track a human throughout a sequence of images of a space, to a location in the space, determine an identity of the human at the location in the space and if the human is at a predetermined location in the space, personalize operation of the device according to the identity of the human.

A method of preventing fraud and theft during automated teller machine (ATM) transactions includes recording a video stream using a camera mounted on or near the ATM, the camera being positioned to record the face of a user of the ATM and a background behind the user, providing a facial model database containing images of a large number of people taken from different angles, the facial model database containing images of unobscured faces as well as obscured faces, and receiving insertion of a bank card into the ATM. The method further includes comparing images captured from the recorded video stream with images contained in the facial model database, and producing a corresponding first face comparison result, and issuing a notice for the user to uncover the user's face when the first face comparison result indicates that the user's face is obscured.

A user interface device includes: a display unit which displays a two-dimensional or a three-dimensional display object in a display space; a sensor unit which measures 3D coordinates of fingers of a user in the display space; a motion detecting unit which detects motion of the fingers of the user relative to the display object based on the 3D coordinates of the fingers of the user measured by the sensor unit; and a display control unit which changes display content displayed by the display unit, according to a detection result obtained by the motion detecting unit.