Abstract: A method of balancing a dataset for a machine learning model includes identifying confusing classes of few-shot classes for a machine learning model during validation. One of the confusing classes and an image from one of the few-shot classes are selected. An image perturbation is computed such that the selected image is classified as the selected confusing class. The selected image is modified with the computed perturbation. The modified selected image is added to a batch for training the machine learning model.

Abstract: An endoscope image processing apparatus includes: an image acquisition unit that acquires endoscopic images; a detection unit that detects lesion images representing lesions in the endoscopic images acquired by the image acquisition unit; a clustering unit that groups the endoscopic images on the basis of a degree of correlation between the lesion images and generates, for each lesion, a group formed of corresponding ones of the endoscopic images; a representative image selection unit that selects, for each group, a representative image from among the endoscopic images in the group; a saving unit that saves, for each group, the representative image and the endoscopic images that form the group to which the representative image belongs, in association with each other; and a display unit that displays a list of the representative images saved in the saving unit.

Abstract: A computer-implemented method to improve scale consistency and/or scale awareness in a model of self-supervised depth and ego-motion prediction neural networks processing a video stream of monocular images, wherein complementary GPS coordinates synchronized with the images are used to calculate a GPS to scale loss to enforce the scale-consistency and/or -awareness on the monocular self-supervised ego-motion and depth estimation. A relative weight assigned to the GPS to scale loss exponentially increases as training progresses. The depth and ego-motion prediction neural networks are trained using an appearance-based photometric loss between real and synthesized target images, as well as a smoothness loss on the depth predictions.

Abstract: To provide an ultrasound imaging apparatus capable of displaying an ultrasound stitched image in which an analyte can easily grasp the state of the analyte, an ultrasound imaging apparatus is provided with an ultrasound image generation module which receives ultrasound waves transmitted from a plurality of mutually different positions on the surface of an analyte and reflected in the inside of the analyte and generates ultrasound images corresponding to the respective positions, an image stitcher module which synthesizes the ultrasound images at the respective positions and generates a stitched image of the cross section of the analyte, and a rotation angle adjusting module which adjusts the angle of the stitched image and orients a specific portion included in the stitched image in a predetermined direction.

Abstract: A system and method of processing a CT scan includes receiving a plurality of radiographs and determining an axis of rotation per scan from the plurality of radiographs prior to CT reconstruction.

Abstract: A method of determining a region of interest in an image of tissue of an individual by an apparatus including processing circuitry may include executing, by the processing circuitry, instructions that cause the apparatus to partition an image of tissue of an individual into a set of areas, identify a tissue type of each area of the image, and apply a classifier to the image to determine a region of interest, the classifier being configured to determine regions of interest based on the tissue types of the set of areas of the image.

Abstract: A method and system for processing thermal video images and thermal video images of patients, using a method of real-time demarcation of the macro aspect of the region of interest, generated by MIR and LIR electromagnetic wave emission and merging of the real image, with improvement of the image, also in real time, allowing for analysis of the micro aspect by means of NIR electromagnetic wave emission, for spectral identification of the sample by infrared vibrational spectroscopy. The method and system pertains to the fields of medicine, biomedicine, and electrical engineering.

Abstract: A computer-implemented method for predicting a cropland data layer (CDL) for a current year includes: retrieving a first set of records from a historical CDL database, where the first set corresponds to sampled areas of a region taken over a period for a number of years; retrieving a second set of records from a historical imagery database, where the second set corresponds to the sampled areas of the region, the period, and the number of years; employing the second set as inputs to train a deep learning network to generate the first set; retrieving a third set of records from a current imagery database, where the third set corresponds to a prescribed region, and where the third set corresponds to the time period and the current year; and using the third set as inputs and executing the trained deep learning network to generate a predicted CDL for the current year.

Abstract: Intelligent prediction systems and methods of use to train a neural network model to analyze images of property damage to detect and predict property damage of a property, the neural network model during training configured to (1) switch between one or more synthetic images comprising pixel-based masked annotations of damaged property from a synthetic engine and one or more real images comprising bounding box annotations of damaged property from a real database, and (2) freeze inactive class training to prevent learning on one or more inactive classes comprising one or more pre-determined missing annotated labels in the one or more synthetic images and/or the one or more real images.

Abstract: The present disclosure provides computer-aided diagnosis systems and methods. The method may include obtaining multiple medical images of one or more bones; for at least one of the multiple medical images, detecting one or more bone fracture regions of the one or more bones in the medical image; causing a management list to be displayed for managing the one or more bones; receiving an instruction related to selecting at least one of the one or more bones, the instruction being generated through the management list; and upon receiving the instruction, causing the following to be displayed: at least one of one or more reconstructed bone images related to the at least one selected bone; or a marker of the one or more detected bone fracture regions related to the at least one selected bone.

Abstract: The present invention relates to a breast image analysis method with four mammogram images which are input to a convolutional neural network as one input and a system therefor and the system includes an image receiving unit which receives four mammogram images; an image size adjusting unit which adjusts a size of a mammogram image received from the image receiving unit; a preprocessing unit which performs preprocessing on the mammogram image adjusted by the image size adjusting unit; a convolutional neural network (CNN)-based CNN learning unit which generates learning information by learning the mammogram image preprocessed by the preprocessing unit; and a CNN inference unit which receives the learning information learned from the CNN learning unit and a mammogram image to be classified from the image receiving unit to diagnose a breast abnormality.

Abstract: A learning data generation apparatus includes an object extraction unit configured to extract an object image from an image; a classification evaluation unit configured to evaluate the object possireimage based on a learned model, and to calculate reliability indicating a degree of posibility that the object image is classified as a candidate label; a classification determination unit configured to, if the reliability is smaller than a first threshold and equal to or larger than a second threshold which is smaller than the first threshold, associate a temporary label different from the candidate label with the object image; and a learning data generation unit configured to generate learning data based on the object image that is associated with the temporary label.

Abstract: Commercial interactions with non-discretized items such as liquids in carafes or other dispensers are detected and associated with actors using images captured by one or more digital cameras including the carafes or dispensers within their fields of view. The images are processed to detect body parts of actors and other aspects therein, and to not only determine that a commercial interaction has occurred but also identify an actor that performed the commercial interaction. Based on information or data determined from such images, movements of body parts associated with raising, lowering or rotating one or more carafes or other dispensers may be detected, and a commercial interaction involving such carafes or dispensers may be detected and associated with a specific actor accordingly.

Abstract: There is provided an inspection device, an inkjet printing apparatus, and an inspection method capable of accurately inspecting a printed image printed on a surface of a transparent base material. A first light-emitting unit (61) emits light from one side of a transparent base material (9) toward the transparent base material (9). An imaging unit (63) images the transparent base material (9) from the other side of the transparent base material (9). As described, the first light-emitting unit (61) and the imaging unit (63) are disposed on the opposite sides of the transparent base material (9). As a result, it is possible to suppress generation of the shadow of a printed image itself in a captured image (D1). Therefore, the printed image can be accurately inspected based on the captured image (D1) obtained.

Abstract: A method of adaptive neural image compression with rate control by meta-learning includes receiving an input image and a hyperparameter; and encoding the received input image, based on the received hyperparameter, using an encoding neural network, to generate a compressed representation. The encoding includes performing a first shared encoding on the received input image, using a first shared encoding layer having first shared encoding parameters, performing a first adaptive encoding on the received input image, using a first adaptive encoding layer having first adaptive encoding parameters, combining the first shared encoded input image and the first adaptive encoded input image, to generate a first combined output, and performing a second shared encoding on the first combined output, using a second shared encoding layer having second shared encoding parameters.

Abstract: A convolution calculation apparatus applied for convolution calculation of a convolution layer includes a decompression circuit, a data combination circuit and a calculation circuit. The decompression circuit decompresses compressed weighting data of a convolution kernel of the convolution layer to generate decompressed weighting data. The data combination circuit combines the decompressed weighting data and non-compressed data of the convolution kernel to restore a data order of weighting data of the convolution kernel. The calculation circuit performs calculation according to the weighting data of the convolution kernel and input data of the convolution layer.

Abstract: System and method for measuring dyslipidemia condition of a subject using thermal imaging is disclosed. The disclosed system and method includes thermal sensors for capturing thermal images and/or videos of a body part; and a processing engine to detect a predefined region of the body part in each frame of the captured images and/or videos. The processing engine segments one or more portions from the predefined region in each frame of the captured images and/or videos to identify a ROI comprising arteries in the segmented portions. Based on the identified region of interest, the engine extracts pixel values, representing biosignals, from each frame of the captured images and/or videos to determine parameters associated with a rate of atherosclerotic, levels of lipids and lipoproteins, and hemodynamic factors of the subject. Further a risk score for the dyslipidemia condition based on the determined parameters using computational models is measured.

Abstract: An artificial intelligence system for analyzing imagery, the system comprising a computing device, the computing device designed and configured to receive a plurality of photographs related to a human subject; analyze the plurality of photographs to identify a conditional indicator contained within the plurality of photographs; generate a classification algorithm utilizing the conditional indicator, wherein the classification algorithm utilizes the conditional indicator as an input and outputs a conditional profile; and determine a conditional status of the human subject utilizing the conditional profile.

Abstract: An optical communication system includes an optical transmitter and one or more processors. The optical transmitter is configured to output an optical signal, and includes an average-power-limited optical amplifier, such as an erbium-doped fiber amplifier (EDFA). The one or more processors are configured to receive optical signal data related to a received power for a communication link from a remote communication system and determine that the optical signal data is likely to fall below a minimum received power within a time interval. In response to the determination, the one or more processors are configured to determine a duty cycle of the optical transmitter based on a minimum on-cycle length and a predicted EDFA output power and operate the optical transmitter using the determined duty cycle to transmit an on-cycle power that is no less than the minimum required receiver power for error-free operation of the communication link.

Abstract: Techniques for tracking eye movement in an augmented reality system identify a plurality of base images of an object or a portion thereof. A search image may be generated based at least in part upon at least some of the plurality of base images. A deep learning result may be generated at least by performing a deep learning process on a base image using a neural network in a deep learning mode. A captured image may be localized at least by performing an image registration process on the captured image and the search image using a Kalman filter model and the deep learning result.