Abstract: An approach for a computer program to receive image data of a subject including at least a portion of a spine of the subject and a chronological age of the subject. The approach includes the computer program pre-processing the image data including at least a portion of a spine. The approach includes determining an apparent age of the spine or a portion of the spine of the subject using a trained artificial intelligence deep learning algorithm.

Abstract: This document generally describes systems, methods, devices, and other techniques related to speaker verification, including (i) training a neural network for a speaker verification model, (ii) enrolling users at a client device, and (iii) verifying identities of users based on characteristics of the users' voices. Some implementations include a computer-implemented method. The method can include receiving, at a computing device, data that characterizes an utterance of a user of the computing device. A speaker representation can be generated, at the computing device, for the utterance using a neural network on the computing device. The neural network can be trained based on a plurality of training samples that each: (i) include data that characterizes a first utterance and data that characterizes one or more second utterances, and (ii) are labeled as a matching speakers sample or a non-matching speakers sample.

Abstract: This application describes a medical image classification method, a model training method, and a server. The medical image classification method includes: obtaining, by a device, a medical image data set. The device includes a memory storing instructions and a processor in communication with the memory. The method includes performing, by the device, quality analysis on the medical image data set, to extract feature information of a medical image in the medical image data set; and classifying, by the device, the medical image data set based on the feature information and by using a pre-trained deep learning network for performing anomaly detection and classification, to obtain a classification result.

Abstract: Systems for and methods of monitoring and analyzing deposit in an industrial water system are provided. The methods comprise heating a substrate while the substrate contacts industrial water in the industrial water system to form deposit on the substrate. A series of digital images of the substrate while the substrate contacts the industrial water in the industrial water system is created. A region of interest in the series of digital images of the substrate is defined. A deposit feature in the region of interest in the series of digital images of the substrate is identified. The deposit feature in the region of interest in the series of digital images of the substrate is analyzed to determine a deposit trend of the substrate in the industrial water system. Generally, the systems are configured so as to be capable of carrying out one or more of the methods.

Abstract: A neural network system leverages dual attention, specifically both spatial attention and channel attention, to jointly estimate heart rate and respiratory rate of a subject by processing images of the subject. A motion neural network receives images of the subject and estimates heart and breath rates of the subject using both spatial and channel domain attention masks to focus processing on particular feature data. An appearance neural network computes a spatial attention mask from the images of the subject and may indicate that features associated with the subject's face (as opposed to the subject's hair or shoulders) to accurately estimate the heart and/or breath rate. Channel-wise domain attention is learned during training and recalibrates channel-wise feature responses to select the most informative features for processing. The channel attention mask is learned during training and can be used for different subjects during deployment.

Abstract: A method of analyzing a substrate contacting a fluid present in an industrial system is provided. The method comprises creating a series of digital images of the substrate while contacting the fluid present in the industrial system. A region of interest in the series of digital images of the substrate is defined. A corrosion feature in the region of interest in the series of digital images of the substrate is identified. The corrosion feature in the region of interest in the series of digital images of the substrate is analyzed to determine a corrosion trend of the industrial system. In certain embodiments of the method, the fluid is industrial water, and the industrial system is an industrial water system.

Abstract: In one aspect, the present application provides a computer-implemented method for generating a digital data set representing a target tooth arrangement, comprising: obtaining a first 3D digital model representing an initial tooth arrangement; extracting at least one feature from each tooth of the first 3D digital model; generating a feature vector based on the extracted features; and aligning the first 3D digital model using a Statistical Shape Model based on the feature vector to obtain a second 3D digital model representing a target tooth arrangement.

Abstract: Disclosed herein is a system and method of identifying new products on a retail shelf using a feature extractor trained to extract features from images of products on the shelf and output identifying information regarding the product in the product image. The extracted features are compared to extracted features in a product library and a best-fit is obtained. A new product is identified if the distance between the features of the product on the shelf and the features of the best-fit product from the product library are above a predetermined threshold.

Abstract: This application discloses a traffic light recognition method and apparatus in the field of artificial intelligence that relate to an automated driving technology. The recognition apparatus determines location information of n first traffic lights in a first image based on current positioning information of a vehicle, a calibration parameter of an image sensor, and prestored map data; and detects the first image by using an image detection method, to obtain location information of m second traffic lights in the first image and indication information of the m second traffic lights. This effectively reduces a traffic light recognition error, and improves recognition accuracy.

Abstract: The present invention relates to a method and an apparatus for estimating a user pose using a three-dimensional virtual space model. The method of estimating a user pose including the position and orientation information of a user for a three-dimensional space includes a step of receiving user information including an image acquired in a three-dimensional space, a step of confirming a three-dimensional virtual space model constructed based on spatial information including depth information and image information for the three-dimensional space, a step of generating corresponding information corresponding to the user information in the three-dimensional virtual space model, a step of calculating similarity between the corresponding information and the user information, and a step of estimating a user pose based on the similarity.

Abstract: An image processing method includes searching for a next pixel of a skeleton branch of a target image based on an already-searched current pixel of the skeleton branch, and determining whether the skeleton branch is a burr branch based on a number of already-searched pixels of the skeleton branch.

Abstract: Systems and methods for digitized document image text contouring are provided. One or more memories may be coupled to one or more processors, the one or more memories including instructions operable to be executed by the one or more processors. The one or more processors may be configured to receive a digitized document image. The one or more processors may be configured to preprocess the digitized document image to generate a plurality of contours. The one or more processors may be configured to adjust a plurality of bounding boxes of the plurality of contours; analyze the adjusted plurality of bounding boxes; create one or more clips based on the analysis; dynamically threshold the one or more clips; perform optical character recognition of the one or more clips; and receive output responsive to the optical character recognition.

Abstract: One variation of a method includes, at a sensor block: detecting a set of objects within a region-of-interest in a frame; detecting an object type of each object; detecting a location of each object within the region-of-interest; and storing object types and object locations of the set of objects in a set of containers. The method further includes, at the computer system: accessing a database of commissioning images; extracting a commissioning image annotated with boundaries from the database; initializing a visualization layer of a set of pixels representing the region-of-interest; and calculating a frequency of presence of the object type intersecting each pixel based on the set of containers; calculating a color value for each pixel based on the frequency of presence; and assigning the color value to each pixel in the visualization layer; and generating a heatmap of the region-of-interest based on the visualization layer and the commissioning image.

Abstract: An example virtual reality (VR) system includes a VR headset, a plurality of monitoring stations, and an image processing device. Each of the monitoring stations includes an image sensor to capture images of the VR headset and an environment in which the VR headset is used. The image processing device is to process the images captured by the monitoring stations to detect an object in the environment, and to transmit, to the VR headset, information that includes notification of the object detected.

Abstract: There is provided an abnormal communication detection apparatus capable of reducing over-detection.

Abstract: To efficiently determine learning data for estimating an unknown behavior by a machine, an information processing device according to the present invention is provided with: an information acquisition means for acquiring an image including a person; and a feature conversion means for converting skeleton information extracted from the image into a feature vector which indicates elements constituting a behavior of the person and is a lower dimension than the skeleton information.

Abstract: A drill hole inspection method for using a drill hole inspection system to inspect a drill hole of a printed circuit board (PCB) is provided. The drill hole inspection method includes: scanning the PCB to obtain 3-dimensional (3D) image voxel data of the PCB; determining a first-dimension interval corresponding to the PCB along one direction of the 3D image voxel data; determining, in a plane of the 3D image voxel data which is orthogonal to the direction, a 2-dimensional (2D) position corresponding to the drill hole; extracting a portion of the 3D image voxel data as drill hole voxel data according to the first-dimension interval and the 2D position; analyzing the drill hole voxel data to obtain an inspection result of the drill hole; and outputting the inspection result through an output component. In addition, a drill hole inspection system and an inspection device using the same are also provided.

Abstract: Provided herein are systems and related methods of performing solar field and receiver inspections based on polarimetric-enhanced imaging.

Abstract: Methods and systems for modification of electronic system operation based on acoustic ambience classification are presented. In an example method, at least one audio signal present in a physical environment of a user is detected. The at least one audio signal is analyzed to extract at least one audio feature from the audio signal. The audio signal is classified based on the audio feature to produce at least one classification of the audio signal. Operation of an electronic system interacting with the user in the physical environment is modified based on the classification of the audio signal.

Abstract: A method of predicting cancer recurrence risk for an individual includes receiving patient spatial multi-parameter cellular and sub-cellular imaging data for a tumor of the individual, and analyzing the patient spatial multi-parameter cellular and sub-cellular imaging data using a prognostic model for predicting cancer recurrence risk to determine a predicted cancer recurrence risk for the individual, wherein the joint prognostic model is based on spatial correlation statistics among features derived for a plurality of intra-tumor spatial domains from spatial multi-parameter cellular and sub-cellular imaging data obtained from a plurality of cancer patients.