A method including: receiving, as input, an image; providing a neural network structure including a plurality of multilayer multi-scale neural networks, wherein the plurality of multilayer multi-scale neural networks are arranged sequentially, by laterally connecting corresponding scale-level layers between each two adjoining multilayer multi-scale neural networks in the sequence; and at a training stage, training the neural network structure on a training dataset, to obtain a trained machine learning model configured to perform a computer vision task which includesoutputting at least one of: (i) a classification of the image into one class of a set of two or more classes, (ii) a segmentation of a least one object in the image, and (iii) a detection of at least one object in the image.

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.

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.

Artificial neural network systems involve the receipt by a computing device of input data that defines a pattern to be recognized (such as faces, handwriting, and voices). The computing device may then decompose the input data into a first subband and a second subband, wherein the first and second subbands include different characterizing features of the pattern in the input data. The first and second subbands may then be fed into first and second neural networks being trained to recognize the pattern. Reductions in power expenditure, memory usage, and time taken, for example, allow resource-limited computing devices to perform functions they otherwise could not.

Artificial neural network systems involve the receipt by a computing device of input data that defines a pattern to be recognized (such as faces, handwriting, and voices). The computing device may then decompose the input data into a first subband and a second subband, wherein the first and second subbands include different characterizing features of the pattern in the input data. The first and second subbands may then be fed into first and second neural networks being trained to recognize the pattern. Reductions in power expenditure, memory usage, and time taken, for example, allow resource-limited computing devices to perform functions they otherwise could not.

There is described herein a method and system for detecting, in a segmented image, the presence and position of objects with a dimension greater than or equal to a minimum dimension. The objects exhibit a property whereby a distance map of the object at a first scale and a distance map of the object at a second scale greater than the first scale differ by a constant value over a domain of the distance map of the object at the first scale. A distance map of a model object is compared to a distance map of a target object using a similarity score that is invariant to an offset.

Described are systems and methods for training a machine-learning model to generate image of biological samples, and systems and methods for generating enhanced images of biological samples. The method for training a machine-learning model to generate images of biological samples may include obtaining a plurality of training images comprising a training image of a first type, and a training image of a second type. The method may also include generating, based on the training image of the first type, a plurality of wavelet coefficients using the machine-learning model; generating, based on the plurality of wavelet coefficients, a synthetic image of the second type; comparing the synthetic image of the second type with the training image of the second type; and updating the machine-learning model based on the comparison.

MTF characteristics of a concavo-convex forming apparatus change depending on the amount of amplitude of input data, the operation condition of the apparatus, etc., and therefore, it is not possible to form a concavo-convex shape with good characteristics only by applying the MTF correction technique widely known in the image processing field. A concavo-convex forming apparatus including an input unit configured to input concavo-convex data representing concavo-convex of an object to be printed, and a correction unit configured to perform correction in accordance with a plurality of frequency band of the input concavo-convex data and whose intensity is made higher for the larger amplitude on the input concavo-convex data based on frequency response characteristics in a case where concavo-convex is formed on a printing medium.

Methods and apparatuses for authenticating communication devices and securely transmitting and/or receiving encrypted voice and data information. A biometric scanner, for example a fingerprint scanner, is utilized for authenticating the communication device and for generating the encryption key. The fingerprint scanner can be an area or swipe type of scanner is registered to a particular user and has unique intrinsic characteristics (the scanner pattern) that are permanent over time and can identify the scanner even among scanners of the same manufacturer and model. The unique scanner pattern of the scanner generates a unique encryption key that cannot be reproduced using another fingerprint scanner.

Disclosed herein is an improvement to prior art feature pyramids for general object detection that inserts a simple norm calibration (NC) operation between the feature pyramids and detection head to alleviate and balance the norm bias caused by feature pyramid network (FPN) and which leverages an enhanced multi-feature selective strategy (MS) during training to assign the ground-truth to one or more levels of the feature pyramid.