Abstract: An apparatus that estimates a position of each object in image data in which a plurality of objects is imaged, the apparatus includes a first acquisition unit configured to acquire position information indicating positions of joints of the plurality of objects in the image data, a second acquisition unit configured to acquire a score map in which a feature for identifying each object is converted into a numerical value, the score map being output by a pre-trained model in response to input of the image data, and an identification unit configured to identify positions of joints belonging to each of the plurality of objects, based on the position information and the score map.

Abstract: The present disclosure relates to a handwritten text recognition method, including: acquiring an information sequence including a plurality of track points of handwritten text, wherein information on each track point comprises its abscissa, writing time and writing state value; dividing the plurality of track points into a plurality of strokes according to the writing state value of each track point, the writing state value including a first value representative of stroke pen-up and a second value representative of stroke pen-down, respectively; calculating a first segmentation threshold of the handwritten text; determining a first text segmentation point according to a result of comparison between an absolute value of a difference between abscissas of a start track point of one stroke and an end track point of its previous stroke and the first segmentation threshold; and performing text segmentation according to the first text segmentation point to obtain a text segmentation result.

Abstract: According to an embodiment, a reading system includes a first extractor and a reader. The first extractor extracts, from an image in which a meter is imaged, a first region surrounded with a first contour, and a second region surrounded with a second contour positioned outward of the first contour. The reader calculates a first indication based on the first region, calculates a second indication based on the second region, calculates a first score relating to the first indication based on the first region, and calculates a second score relating to the second indication based on the second region.

Abstract: The present disclosure provides a computer-implemented method, a device, and a computer program product using a user-guided domain adaptation (UGDA) architecture. The method includes training a combined model using a source image dataset by minimizing a supervised loss of the combined model to obtain first sharing weights for a first FCN and second sharing weights for a second FCN; training a discriminator by inputting extreme-point/mask prediction pairs for each of the source image dataset and a target image dataset and by minimizing a discriminator loss to obtain discriminator weights; and finetuning the combined model by predicting extreme-point/mask prediction pairs for the target image dataset to fool the discriminator by matching a distribution of the extreme-point/mask prediction pairs for the target image dataset with a distribution of the extreme-point/mask prediction pairs for the source image dataset.

Abstract: Embodiments discussed herein facilitate determination of whether lesions are benign or malignant. One example embodiment is a method, comprising: accessing medical imaging scan(s) that are each associated with distinct angle(s) and each comprise a segmented region of interest (ROI) of that medical imaging scan comprising a lesion associated with a first region and a second region; providing the first region(s) of the medical imaging scan(s) to trained first deep learning (DL) model(s) of an ensemble and the second region(s) of the medical imaging scan(s) to trained second DL model(s) of the ensemble; and receiving, from the ensemble of DL models, an indication of whether the lesion is a benign architectural distortion (AD) or a malignant AD.

Abstract: Ultrasound image devices, systems, and methods are provided. A clinical condition detection system, comprising a communication device in communication with an ultrasound imaging device and configured to receive a sequence of ultrasound image frames representative of a subject body across a time period; and a processor in communication with the communication device and configured to classify the sequence of ultrasound image frames into a first set of clinical characteristics by applying a first predictive network to the sequence of ultrasound image frames to produce a set of classification vectors representing the first set of clinical characteristics; and identify a clinical condition of the subject body by applying a second predictive network to the set of classification vectors.

Abstract: Systems and methods are provided for provided for automatic evaluation of a human embryo. An image of the embryo is obtained and provided to a neural network to generate a plurality of values representing the morphology of the embryo. The plurality of values representing the morphology of the embryo are evaluated at an expert system to provide an output class representing one of a current quality of the embryo, a future quality of the embryo, a likelihood that implantation of the embryo will be successful, and a likelihood that implantation of the embryo will result in a live birth.

Abstract: An information processing apparatus comprises a generating unit configured to generate supervised data relating to a topological invariant based on a topological property relating to supervised data corresponding to input data, and a training unit configured to perform, based on a geometric property relating to an output from a classifier to which the input data is input and the supervised data generated by the generating unit, training of the classifier.

Abstract: Embodiments relate to circuitry for temporal processing and image fusion. An image fusion circuit receives captured images, and generates corresponding image pyramids. The generated image pyramids are raster or tiled processed, and stored in memory. A fusion module receives a first and second image pyramids from the memory, and warps and fuses image pyramids to generate a fused image pyramid, which may be used for further processing, and may also be stored back into the memory. The image fusion circuitry is configurable to operate in a plurality of different configuration modes corresponding to different image fusion applications for fusing image pyramids of received images, including two-frame fusion, temporal filtering, infinite impulse response (IIR) temporal processing, and/or finite impulse response (FIR) temporal processing.

Abstract: A method of screening for a cancer in a patient, an integrated method of screening for a cancer in a patient, a computer program product for carrying out the methods, as well as a medical imaging apparatus for carrying out the methods are disclosed. Based upon the above, it is possible that the patient will obtain a more reliable result from a first medical imaging treatment.

Abstract: Embodiments relate to circuitry for temporal processing and image fusion. An image fusion circuit receives captured images, and generates corresponding image pyramids. The generated image pyramids are raster or tiled processed, and stored in memory. A fusion module receives a first and second image pyramids from the memory, warps the first image pyramid based upon the second image pyramid, and fuses the warped first image pyramid with the second image pyramid to generate a fused image pyramid, which may be used for further processing, and may also be stored back into the memory. Because pyramid generation occurs prior to warping and fusion, and by allowing fused image pyramids to be stored back into memory, the image fusion circuitry is configurable to implement a variety of temporal processing functions involving different image fusion combinations.

Abstract: A preoperative survival prediction method and a computing device applying the method include constructing a data seta according to a plurality of enhanced medical images and a resection margin of each enhanced medical image and obtaining a plurality of training data sets from the constructed data set. For each training data set, multi-task prediction models are trained. A target multi-task prediction model is selected from the plurality, and a resection margin prediction value and a survival risk prediction value are obtained by predicting an enhanced medical image to be measured through the target multi-task prediction model. The multi-task prediction model more effectively captures the changes over time of the tumor in multiple stages, so as to enable a joint prediction of a resection margin prediction value and a survival risk prediction value.

Abstract: A system and method for facilitating DBS electrode trajectory planning using a machine learning (ML)-based feature identification scheme configured to identify and distinguish between various regions of interest (ROIs) and regions of avoidance (ROAs) in a patient's brain scan image. In one arrangement, standard orientation image slices as well as re-sliced images in non-standard orientations are provided in a labeled input dataset for training a CNN/ANN for distinguishing between ROIs and ROAs. Upon identification of the ROIs and ROAs in the patient's brain scan image, an optimal trajectory for implanting a DBS lead may be determined relative to a particular ROI while avoiding any ROAs.

Abstract: A system for performing remote artificial intelligence-assisted electronic warranty verification including at least one processor configured to transmit an instruction to capture at least one product image of a specific product, receive and perform product image analysis on the product image to identify at least one product-distinguishing characteristic, transmit an instruction to capture an image of a purchase receipt, receive and perform receipt image analysis on the purchase receipt image to identify product purchase information, access a universal data structure containing data on products offered by suppliers, use the at least one product-distinguishing characteristic and product purchase information to identify in the universal data structure the specific product, identify in the universal data structure a link to a warranty data structure of the supplier, access the link to lookup the specific product and receive a warranty coverage indication from the supplier data structure, and transmit an indicatio

Abstract: Controls within images of a user interface of a computer application are detected by way of region-based R-FCN and Faster R-CNN engines. Datasets comprising images containing application control, wherein the application controls include images of application where width is greater than height, width is equal to height and height is greater than width are retrieved. Each of the datasets is processed with the R-FCN and Faster R-CNN engines to generate a software configured to recognize, from an input image, application controls wherein the application controls are characterized by dimensions where width is greater than height, where width is substantially equal to height, and where height is greater than width.

Abstract: A non-transitory computer-readable recording medium storing a training data generation program for causing a computer to execute processing including: identifying, from among meta-analysis literatures stored in a memory, a plurality of meta-analysis literatures in which a first literature is cited; determining a degree of similarity between the plurality of identified meta-analysis literatures based on feature information of the plurality of identified meta-analysis literatures; and in response to the degree of similarity being equal to or higher than a threshold, generating training data for machine learning including the first literature.

Abstract: A method of pipelining inference of a neural network, which includes an i-th layer (i being an integer greater than zero) and an (i+1)-th layer, includes processing, for a first input image, first i-th values of the i-th layer to generate first (i+1)-th values for the (i+1)-th layer, processing, for the first input image, the first (i+1)-th values of the (i+1)-th layer to generate output values, and concurrently with processing, for the first image, the (i+1)-th values, processing, for a second input image, second i-th values of the i-th layer to generate second (i+1)-th values.

Abstract: The disclosure relates to methods and systems for detecting the orientation of an oocyte and its polar body. Examples include an automated method for detection of an orientation of an oocyte, the method including: i) acquiring an image of the oocyte; ii) defining first and second elliptical features in the image based on edges detected in the image; iii) calculating an orientation of the second elliptical feature relative to the first elliptical feature; and iv) outputting a relative orientation of a polar body of the oocyte based on the orientation of the second elliptical feature relative to the first elliptical feature.

Abstract: A method for generating simulated point cloud data, a device, and a storage medium includes: acquiring at least one frame of point cloud data collected by a road collecting device in an actual environment without a dynamic obstacle as static scene point cloud data; setting, least one dynamic obstacle in a coordinate system matching the static scene point cloud data; simulating in the coordinate system, a plurality of simulated scanning lights emitted by a virtual scanner located at an origin of the coordinate system; updating the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle; and at least one of adding a set noise to the simulated point cloud data, and, deleting point cloud data corresponding to the dynamic obstacle according to a set ratio.

Abstract: Various embodiments are described that relate to classification of an unknown object. A time series signal associated with an unknown object can be obtained from a sensor. The time series signal can be subjected to a transform set, such as a Fourier transform and a discrete cosine transform, to produce a transform outcome. Based, at least in part, on the transform outcome, the unknown object can be classified.