An automatic labeling method for assigning labels to unlabeled point clouds among a set of labeled and unlabeled point clouds includes preparing an initial machine learning classification model, selecting a labeled point cloud for each of the unlabeled point clouds based on similarities between a feature vector of each of the unlabeled point clouds output through the model and feature vectors of the labeled point clouds output through the model and assigning a cluster label to each of the unlabeled point clouds based on a label of the selected labeled point cloud, assigning pseudo labels to the unlabeled point clouds to which the cluster labels are assigned based on a confidence score obtained through the model, and updating the model by training the model with the labeled point clouds and the unlabeled point clouds to which the pseudo labels are assigned.

An automated learning system of a content provider includes a database, an image processing unit, and a server. The database stores data related to visual marks, features of the visual marks, a set of discriminating instances, a position of a region of interest, and pre-defined threshold values. The image processing unit includes a detection module, a determination module, and a feature generation module. The detection module detects frames from a primary display device. The determination module extracts a static visual area, and determines a visual mark. The feature generation module generates discriminating features of the visual mark. The server maps the discriminating features with the stored data, identifies at least one closest visual mark, and transmits the updated visual mark and the discriminating features to secondary display devices.

The technology disclosed processes input data through a neural network and produces an alternative representation of the input data. The input data includes per-cycle image data for each of one or more sequencing cycles of a sequencing run. The per-cycle image data depicts intensity emissions of one or more analytes and their surrounding background captured at a respective sequencing cycle. The technology disclosed processes the alternative representation through an output layer and producing an output and base calls one or more of the analytes at one or more of the sequencing cycles based on the output.

A system and method for defect detection. In some embodiments, the method includes: identifying, by a first neural network, a suspicious area in a first image; selecting, from among a set of defect-free reference images, by a second neural network, a defect-free reference image corresponding to the first image; identifying, by a third neural network, in the defect-free reference image, a reference region corresponding to the suspicious area; and determining, by a fourth neural network, a measure of similarity between the suspicious area and the reference region.

The present application relates to an image processing method and system. The method may include: acquiring a sequence of input images containing a target object; and performing multi-resolution fusion on the sequence of input images to generate a single fused image, where pixels of the fused image may include a pixel at a corresponding position of an input image in the sequence of input images, and each pixel of the fused image containing the target object may include a pixel at a corresponding position of an input image in the sequence of input images in which part of the target object is focused.

Systems, methods and computer program products for sample efficient training of machine learning models are provided. A process may proceed, starting with an initial set of labeled examples and the initial set of unlabeled examples, to label unlabeled examples in an iterative manner, with the input dataset for a next iteration comprising an augmented set of labeled examples from a current iteration and selected unlabeled examples, until a final set of labeled examples is created. The final set of labeled examples is used to train a machine learning model. Each iteration includes mapping the input dataset to a reduced dimension space and using the reduced dimension space to identify high value examples to label.

An Edge encapsulated method and system for real-time detection of a double parking vehicle blocking parked vehicles by capturing images using a mounted monocular camera then processing using two Semi-Supervised Object Detection (sSOD) stages, that is trained with partly labeled and mostly unlabeled data to optimize the model parameters for the detection problem, gathered by capturing video from moving vehicle passing through multiple different vehicle types and parking systems with unconfined location.

An information processing system creates a teacher database configured to train an analysis model from an observation image and labeling information corresponding to the observation image using an information processor. This system includes a storage unit, an image processing unit, and a teacher database creating unit. The storage unit stores image processing data formed of information showing a relationship between an observation condition and a parameter relating to the observation image. Further stores a first observation image, a first observation condition, and first labeling information. The image processing unit accepts the first observation image and the first observation condition as inputs, performs image processing corresponding to the parameter to the first observation image based on the image processing data, and creates a second observation image corresponding to a second observation condition. The teacher database creating unit creates the teacher database from the second observation image and the first labeling information.

A computer-implemented method is disclosed. The method includes a) accessing a first image, b) accessing a second image, c) from an adversarial pattern generating system, generating a face recognition adversarial pattern for display from a specified region of a face corresponding to the second image, the face recognition adversarial pattern operable to minimize a measure of distance as determined by a face recognition system, between the face and a class of the first image, or to maximize a probability of the misclassification of the second image by the face recognition system, d) providing a face mountable device, that is mounted on the face, access to the face recognition adversarial pattern in real time via a communications component, and e) controlling light patterns on the face mountable device according to the face recognition adversarial pattern.

Methods and apparatus for the application of machine learning to radiographic images of animals. In one embodiment, the method includes receiving a set of radiographic images captured of an animal, applying one or more transformations to the set of radiographic images to create a modified set, segmenting the modified set using one or more segmentation artificial intelligence engines to create a set of segmented radiographic images, feeding the set of segmented radiographic images to respective ones of a plurality of classification artificial intelligence engines, outputting results from the plurality of classification artificial intelligence engines for the set of segmented radiographic images to an output decision engine, and adding the set of segmented radiographic images and the output results from the plurality of classification artificial intelligence engines to a training set for one or more of the plurality of classification artificial intelligence engines. Computer-readable apparatus and computing systems are also disclosed.