Abstract: A method and system for performing semi or fully automatic data imbalance detection and correction in training a machine-learning (ML) model includes receiving a request to train the ML model, receiving access to a dataset for use in training the ML model, identifying a feature of the dataset for which data imbalance detection is to be performed, examining the dataset to determine a distribution of the feature across the dataset, determining if the distribution of the feature across the dataset indicates data imbalance, upon determining that the distribution of the feature across the dataset indicates data imbalance, identifying a desired distribution for the identified feature, selecting a subset of the dataset that corresponds with the selected feature and the desired distribution, and using the subset to train the ML model.

Abstract: A method for shadow and cloud masking for remote sensing images of an agricultural field using multi-layer perceptrons includes electronically receiving an observed image, performing using at least one processor an image segmentation of the observed image to divide the observed image into a plurality of image segments or superpixels, extracting features for each of the image segments using the at least one processor, and determining by a cloud mask generation module executing on the at least one processor a classification for each of the image segments using the features extracted for each of the image segments, wherein the cloud mask generation module applies a classification model including an ensemble of multilayer perceptrons to generate a cloud mask for the observed image such that each pixel within the observed image has a corresponding classification.

Abstract: A method, device, and computer readable medium for displaying a two-dimensional image of a viewed object simultaneously with an image depicting a three-dimensional geometry of the viewed object using a video inspection device is disclosed. The video inspection device displays a two-dimensional image of the object surface of a viewed object, and determines the three-dimensional coordinates of a plurality of surface points. At least one rendered image of the three-dimensional geometry of the viewed object is displayed simultaneously with the two-dimensional image. As measurement cursors are placed and moved on the two-dimensional image, the rendered image of the three-dimensional geometry of the viewed object is automatically updated.

Abstract: Techniques for implementing an efficient machine learning (ML) model for classification are provided. In one set of embodiments, a computer system can receive a query data instance to be classified. The computer system can then generate a first classification result for the query data instance using a first (i.e., primary) ML model, where the first classification result includes a predicted class for the query data instance and a confidence level indicating a likelihood that the predicted class is correct, and compare the confidence level with a classification confidence threshold. If the confidence level is greater than or equal to the classification confidence threshold, the computer system can output the first classification result as a final classification result for the query data instance. However, if the confidence level is less than the classification confidence threshold, the computer system can forward the query data instance to one of a plurality of second (i.e.

Abstract: A processor-implemented neural network method includes: determining a respective probability density function (PDF) of normalizing a statistical distribution of parameter values, for each channel of each of a plurality of feature maps of a pre-trained neural network; determining, for each channel, a corresponding first quantization range for performing quantization of corresponding parameter values, based on a quantization error and a quantization noise of the respective determined PDF; determining, for each channel, a corresponding second quantization range, based on a signal-to-quantization noise ratio (SQNR) of the respective determined PDF; correcting, for each channel, the corresponding first quantization range based on the corresponding second quantization range; and generating a quantized neural network, based on the corrected first quantization range corresponding for each channel.

Abstract: According to an aspect of an embodiment, a method may include obtaining a data set that includes categories (or features), and a target criteria. The method may further include obtaining a first decision tree model using the data set. The method may further include ranking the categories based on the first decision tree model and removing low-ranking categories from the data set. The method may further include generating a second decision tree model using the data set. The second decision tree model may include branch nodes. Each of branch nodes may represent a branch criteria. The method may further include pruning a branch node. The method may further include designating a remaining branch nodes as a rule node. The method may further include generating a rule based on the branch criteria of the rule node and presenting the rule in a graphical user interface.

Abstract: A method for estimating tightly enclosing bounding boxes by a computing system includes: controlling a scanning system including one or more depth cameras to capture visual information of the scene including one or more objects; detecting the one or more objects of the scene based on the visual information; singulating each the one or more objects from the frame of the scene to generate one or more 3D models corresponding to the one or more objects, the one or more 3D models including a partial 3D model of a corresponding one of the one or more objects; extrapolating a more complete 3D model of the corresponding one of the one or more objects based on the partial 3D model; and estimating a tightly enclosing bounding box of the corresponding one of the one or more objects based on the more complete 3D model.

Abstract: Aspects of the present disclosure involve systems, methods, devices, and the like for an end-to-end solution to auto-identifying features. In one embodiment, a novel architecture is presented that enables the identification of optimal features and feature processes for use by a machine learning model. The novel architecture introduces a feature orchestrator for managing, routing, and retrieving the data and features associated with analytical job request. The novel architecture also introduces a feature store designed to identify, rank, and store the features and data used in the analysis. To aid in identifying the optimal features and feature processes, a training system may also be included in the solution which can perform some of the training and scoring of the features.

Abstract: An optical imaging device for imaging a biometric input object is provided. The optical imaging device includes an optical sensor having an array of sensing elements. The optical sensor is configured to first read a first subset of sensing elements in the array of sensing elements; analyze the first read of the first subset of sensing elements to determine an ambient light condition; first alter an operating point of the optical imaging device based on the ambient light condition; and image the input object.

Abstract: A computer-implemented method of selecting a sequence of images of a user's eye for an eye tracking application wherein each image is captured when a stationary stimulus point is displayed to the user, the method comprising: for a plurality of different pairs of the images: comparing the pair of images with each other to determine an image-score that represents a degree of difference between the compared images; and calculating a sequence-score based on the image-scores for the plurality of pairs of images.

Abstract: Systems and methods for performing visual odometry more rapidly. Pairs of representations from sensor data (such as images from one or more cameras) are selected, and features common to both representations of the pair are identified. Portions of bundle adjustment matrices that correspond to the pair are updated using the common features. These updates are maintained in register memory until all portions of the matrices that correspond to the pair are updated. By selecting only common features of one particular pair of representations, updated matrix values may be kept in registers. Accordingly, matrix updates for each common feature may be collectively saved with a single write of the registers to other memory. In this manner, fewer write operations are performed from register memory to other memory, thus reducing the time required to update bundle adjustment matrices and thus speeding the bundle adjustment process.

Abstract: Monitoring the quality of sleep of an individual is essential for ensuring one's overall well-being. The existing methods for non-apnea sleep arousal detection are manual. A system and method for the non-apnea sleep arousal detection has been provided. The method uses a feature engineering based binary classification approach for distinguishing non-apnea arousal and non-arousal. A training data set is prepared using a plurality of physiological signals. A plurality of features are derived from the training data set. Out of those only a set of features are selected for training a plurality of random forest classifier models. A test sample is then provided to the plurality of random forest classifier models in the instances of fixed duration. This results in generation of prediction probabilities for each instances. The prediction probabilities are then used to predict the probabilities of non-apnea sleep arousal in the test sample.

Abstract: An electronic device and a model updating method are provided. The method includes: inputting a plurality of files to a first model and outputting a predicted result of each of the plurality of files; receiving a corrected result for correcting the prediction result of at least one first file in the plurality of files, and generating a first label file corresponding to the at least one first file according to the corrected result and the first file; training a plurality of models according to the first label file to generate a plurality of a trained model; testing the plurality of trained models using at least one test set; and replacing the first model with a first trained model when the predicting accuracy of the first trained model of the plurality of trained models is higher than the predicting accuracy of the first model.

Abstract: An information processing system configured to perform predetermined processing based on out-of-focus information corresponding to a first area of an image, the out-of-focus information corresponding to a difference in focus between the first area of the image and a second area of the image that is different from the first area of the image.

Abstract: A display panel including a display function layer displaying an image in a display area, a cover member including a first face and a second face disposed on an opposite side of the first face and faces the display panel, and a fingerprint sensor including a plurality of first detection electrodes disposed in a sensor base and configured to detect unevenness of an object brought into contact with or approaching the first face of the cover member, a shield electrode disposed to face the plurality of first detection electrodes and configured to suppress a change in capacitance between the first detection electrodes and the shield electrode, and switching elements disposed in correspondence with the first detection electrodes, the fingerprint sensor being arranged between the cover member and the display panel and arranged to overlap with the display area when viewed in a direction perpendicular to the first face are included.

Abstract: A method, system and computer-readable storage medium for performing a cognitive information processing operation.

Abstract: Techniques for efficiently identifying objects of interest in an environment and, thereafter, determining the location and/or orientation of those objects. As described below, a system may analyze images captured by a camera to identify objects that may be represented by the images. These objects may be identified in the images based on their size, color, and/or other physical attributes. After identifying these potential objects, the system may define a region around each object for further inspection. Thereafter, portions of a depth map of the environment corresponding to these regions may be analyzed to determine whether any of the objects identified from the images are “objects of interest”—or objects that the system has previously been instructed to track. These objects of interest may include portable projection surfaces, a user's hand, or any other physical object. The techniques identify these objects with reference to the respective depth signatures of these objects.

Abstract: A system and method include obtaining and authenticating image files from users such as insured users at the request of an entity such as an insurance provider. The requesting entity may supply an electronic address of the user and a unique identifier. The system may transmit a link to the electronic address. When selected, the link causes an image authentication application to be installed on a user device. The application takes the images securely and separately from a native camera application. Each image authentication application may be customized for each requesting entity. The authentication server may identify the requesting entity that made the request and identify a corresponding image authentication application to be provided to the electronic address. The images from the image authentication application may be authenticated via reverse image search, time, geolocation, and/or other information. The authenticated images and/or related data may be provided to the requesting entity.

Abstract: There is provided a video signal processing apparatus, including: a first interface configured to obtain a first video signal imaged within a first dynamic range; a second interface configured to obtain information for specifying a partial area of the obtained first video signal; and an arithmetic processing circuit configured to calculate a representative value of brightness of the first video signal of the partial area, to compress a dynamic range of the first video signal depending on the calculated representative value, and to generate a second video signal, a dynamic range of the second video signal being restricted to a second dynamic range narrower than the first dynamic range.

Abstract: A LUS robotic surgical system is trainable by a surgeon to automatically move a LUS probe in a desired fashion upon command so that the surgeon does not have to do so manually during a minimally invasive surgical procedure. A sequence of 2D ultrasound image slices captured by the LUS probe according to stored instructions are processable into a 3D ultrasound computer model of an anatomic structure, which may be displayed as a 3D or 2D overlay to a camera view or in a PIP as selected by the surgeon or programmed to assist the surgeon in inspecting an anatomic structure for abnormalities. Virtual fixtures are definable so as to assist the surgeon in accurately guiding a tool to a target on the displayed ultrasound image.