An artificial neuron unit and neural network for processing of input light are described. The artificial neuron unit comprises a modal mixing unit, such as multimode optical fiber, configured for receiving input light and applying selected mixing to light components of two or more modes within the input light and for providing exit light, and a filtering unit configured for applying preselected filter onto said exit light for selecting one or more modes of the exit light thereby providing output light of the artificial neuron unit.

Embodiments of the present disclosure pertain to extracting data corresponding to particular data types using neural networks. In one embodiment, a method includes receiving an image in a backend system, sending the image to an optical character recognition (OCR) component, and in accordance therewith, receiving a plurality of characters recognized in the image, sequentially processing the characters with a recurrent neural network to produce a plurality of outputs for each character, sequentially processing the plurality of outputs for each character with a masking neural network layer, and in accordance therewith, generating a first plurality of probabilities, wherein each probability corresponds to a particular character in the plurality of characters, selecting a second plurality of adjacent probabilities from the first plurality of probabilities that are above a threshold, and translating the second plurality of adjacent probabilities into output characters.

A method of tracking a gaze of an eye includes tracking the gaze of the eye in a first tracking mode. Glint data of at least one glint of the eye is obtained during at least a portion of tracking the gaze of the eye in the first tracking mode. The glint data is in a time domain and includes a time series of a spatial descriptor associated with the at least one glint. The glint data is transformed into a frequency domain to generate a glint frequency spectrum. A stability of the at least one glint is determined based on the glint frequency spectrum. If the at least one glint is determined to be unstable, tracking of the gaze of the eye is switched from the first tracking mode to a second tracking mode that is different from the first tracking mode.

A curved fingerprint recognizing device with a light-guiding component, a first reflecting layer, a second reflecting layer, light source and an image capturing component is disclosed. In the light-guiding component, a first surface has a curved surface, a second surface locates opposite to the first surface, an outer side wall inclinedly connects the first surface and the second surface, an inner side wall inclinedly connects to the second surface, and a bottom surface connects horizontally the outer side wall and the inner side wall. The light beam emitted from the light source is reflected by the first reflecting layer and the second reflecting layer after passing through the bottom surface to be transmitted to the first surface having the curved surface and thereby fingerprints of a bottom and sidewalls of an object to be recognized can be obtained by the image capturing component at the same time.

A method for authenticating an object, comprising determining a physical dispersion pattern of a set of elements, determining a physical characteristic of the set of elements which is distinct from a physical characteristic producible by a transfer printing technology, determining a digital code associated with the object defining the physical dispersion pattern, and authenticating the object by verifying a correspondence of the digital code with the physical dispersion pattern, and verifying the physical characteristic.

Techniques for generating magnetic resonance (MR) images of a subject from MR data obtained by a magnetic resonance imaging (MRI) system, the techniques including: obtaining input MR data obtained by imaging the subject using the MRI system; generating a plurality of transformed input MR data instances by applying a respective first plurality of transformations to the input MR data; generating a plurality of MR images from the plurality of transformed input MR data instances and the input MR data using a non-linear MR image reconstruction technique; generating an ensembled MR image from the plurality of MR images at least in part by: applying a second plurality of transformations to the plurality of MR images to obtain a plurality of transformed MR images; and combining the plurality of transformed MR images to obtain the ensembled MR image; and outputting the ensembled MR image.

A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

A computational imaging device and method are described, wherein the computational imaging device is operable to perform corner detection and other computer vision tasks more efficiently and/or more robustly than traditional imaging devices. In addition, methods are described operable to jointly optimize the computational imaging device and the corner detection task.

Systems and methods provide adapted content to a visitor to a physical environment. An example method receives an image of a visitor to an environment. A visitor portion of the image is distinct from an environment portion of the image. The method detects one or more shapes in the visitor portion of the image using an automatic shape detection technique and defines an approximate boundary of the one or more shapes using a mask. The one or more shapes can be shapes of the visitor's clothing items. The method then calculates an attribute for an area of the image within the mask and identifies electronic content based on the attribute for the area of the image within the mask. The attribute can be a color attribute for the area such as a median color or a dominant color. The method provides the identified electronic content for display in the environment.

A living body determination device includes: a light irradiation device that irradiates a measuring object with a first light including a plurality of spectrums; a spectroscopic device that disperses a light at intensity depending on a wavelength and outputs the light; an image acquisition device that receives the light output by the spectroscopic device and outputs image information representing brightness depending on the intensity of the light; and a control unit. The control unit, for each spectrum of the first light, acquires image information with respect to the measuring object from the image acquisition device, based on the image information, selects one or more areas, for each of the areas, acquires spectroscopic information, and based on whether the spectroscopic information satisfies a predetermined condition, determines whether the measuring object is a living body.