One or more example embodiments of the present invention relates to a computer-implemented method for providing an outline of a lesion in digital breast tomosynthesis includes receiving input data, wherein the input data comprises a reconstructed tomosynthesis volume dataset based on projection recordings, a virtual target marker within a lesion being in the tomosynthesis volume dataset; applying a trained function to at least a part of the tomosynthesis volume dataset to establish an outline enclosing the lesion, the part of the tomosynthesis volume dataset corresponding to a region surrounding the virtual target marker in the tomosynthesis volume dataset; and providing output data, wherein the output data is an outline of a two-dimensional area or a three-dimensional volume surrounding the target marker.

An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

A system and a method for automatic video redaction are provided herein. The method may include: receiving, an input video comprising a sequence of frames captured by a camera, wherein the input video includes live video obtained directly from the camera, wherein recordation of the video directly from the camera is disabled; performing visual analysis of the input video, to detect portions of the frames of the input video in which one of a plurality of predefined objects or a descriptor thereof is detected; generating a redacted input video by replacing the portions of the frames with new portions of another visual content; and recording the redacted input video on a data storage device, wherein the generating of thethe redacted input video, is carried out by a computer processor, after the input video is captured by the camera and before the recording of the redacted input video on the data storage device.

Systems and methods for detecting a waste receptacle, the system including a camera for capturing an image, a convolutional neural network, and processor. The convolutional neural network can be trained for identifying target waste receptacles. The processor can be mounted on the waste-collection vehicle and in communication with the camera and the convolutional neural network configured for using the convolutional neural network. The processor can be configured for using the convolutional neural network to generate an object candidate based on the image; using the convolutional neural network to determine whether the object candidate corresponds to a target waste receptacle; and selecting an action based on whether the object candidate is acceptable.

Systems and methods for providing a universal platform for at-home health testing and diagnostics are provided herein. In particular, a health testing and diagnostic platform is provided to connect medical providers with patients and to generate a unique, private testing environment. In some embodiments, the testing environment may facilitate administration of a medical test to a patient with the guidance of a proctor. In some embodiments, the patient may be provided with step-by-step instructions for test administration by the proctor within a testing environment. The platform may display unique, dynamic testing interfaces to the patient and proctor to ensure proper testing protocols and accurate test result verification.

Provided is a contour shape recognition method, including: sampling and extracting salient feature points of a contour of a shape sample; calculating a feature function of the shape sample at a semi-global scale by using three types of shape descriptors; dividing the scale with a single pixel as a spacing to acquire a shape feature function in a full-scale space; storing feature function values at various scales into a matrix to acquire three types of feature grayscale map representations of the shape sample in the full-scale space; synthesizing the three types of grayscale map representations of the shape sample, as three channels of RGB, into a color feature representation image; constructing a two-stream convolutional neural network by taking the shape sample and the feature representation image as inputs at the same time; and training the two-stream convolutional neural network, and inputting a test sample into a trained network model to achieve shape classification.

Provided is a contour shape recognition method, including: sampling and extracting salient feature points of a contour of a shape sample; calculating a feature function of the shape sample at a semi-global scale by using three types of shape descriptors; dividing the scale with a single pixel as a spacing to acquire a shape feature function in a full-scale space; storing feature function values at various scales into a matrix to acquire three types of feature grayscale map representations of the shape sample in the full-scale space; synthesizing the three types of grayscale map representations of the shape sample, as three channels of RGB, into a color feature representation image; constructing a two-stream convolutional neural network by taking the shape sample and the feature representation image as inputs at the same time; and training the two-stream convolutional neural network, and inputting a test sample into a trained network model to achieve shape classification.

Example embodiments allow for training of encoders (e.g., artificial neural networks (ANNs)) to generate a color palette based on an input image. The color palette can then be used to generate, using the input image, a quantized, reduced color depth image that corresponds to the input image. Differences between a plurality of such input images and corresponding quantized images are used to train the encoder. Encoders trained in this manner are especially suited for generating color palettes used to convert images into different reduced color depth image file formats. Such an encoder also has benefits, with respect to memory use and computational time or cost, relative to the median-cut algorithm or other methods for producing reduced color depth color palettes for images.

Example embodiments allow for training of encoders (e.g., artificial neural networks (ANNs)) to generate a color palette based on an input image. The color palette can then be used to generate, using the input image, a quantized, reduced color depth image that corresponds to the input image. Differences between a plurality of such input images and corresponding quantized images are used to train the encoder. Encoders trained in this manner are especially suited for generating color palettes used to convert images into different reduced color depth image file formats. Such an encoder also has benefits, with respect to memory use and computational time or cost, relative to the median-cut algorithm or other methods for producing reduced color depth color palettes for images.

A human-object interaction detection method, a neural network and a training method therefor is provided. The human-object interaction detection method includes: extracting a plurality of first target features and one or more first motion features from an image feature of an image to be detected; fusing each first target feature and some of the first motion features to obtain enhanced first target features; fusing each first motion feature and some of the first target features to obtain enhanced first motion features; processing the enhanced first target features to obtain target information of a plurality of targets including human targets and object targets; processing the enhanced first motion features to obtain motion information of one or more motions, where each motion is associated with one human target and one object target; and matching the plurality of targets with the one or more motions to obtain a human-object interaction detection result.