A medical image processing apparatus according to an embodiment includes processing circuitry configured to generate an output data set apparently expressing a second data set obtained by transmitting and receiving an ultrasound wave, for each scanning line, as many times as a second number that is larger than a first number, by inputting a first data set to a trained model that generates the output data set on a basis of the first data set obtained by transmitting and receiving an ultrasound wave as many times as the first number for each scanning line.

An example system includes a processor to receive an input and a model trained to classify inputs. The processor is to iteratively generate a perturbed input that optimizes a saliency metric including a classification term, a sparsity term, and a smoothness term, while keeping parameters of the model constant. The processor is to also detect that a predefined number of iterations is exceeded or a convergence of values of the perturbed input. The processor is to further generate a saliency mask based on a perturbation of the perturbed input in response to detecting the predefined number of iterations is exceeded or the convergence.

The disclosure discloses a cartoonlization processing method for an image, and relates to a field of computational vision, image processing, face recognition, deep learning technologies. The method includes: performing skin color recognition on a facial image to be processed to determine a target skin color of a face in the facial image; processing the facial image by utilizing any cartoonizing model in a cartoonizing model set to obtain a reference cartoonized image corresponding to the facial image in a case that the cartoonizing model set does not contain a cartoonizing model corresponding to the target skin color; determining a pixel adjustment parameter based on the target skin color and a reference skin color corresponding to the any cartoonizing model; and adjusting a pixel value of each pixel point in the reference cartoonized image based on the pixel adjustment parameter, to obtain a target cartoonized image corresponding to the facial image.

An image segmentation method according to an embodiment of the present invention is performed in a computing device having one or more processors and memory for storing one or more programs executed by means of the one or more processors, and includes the steps of: (a) receiving the input of an image; (b) generating a first-generation image segment set by dividing the input image in an overlapped manner; and (c) generating a second or higher-generation image segment set from the first-generation image segment set, wherein a subsequent-generation image segment set is generated by dividing in an overlapped manner at least one of a plurality of image segments included in the previous-generation image segment set.

An image segmentation method according to an embodiment of the present invention is performed in a computing device having one or more processors and memory for storing one or more programs executed by means of the one or more processors, and includes the steps of: (a) receiving the input of an image; (b) generating a first-generation image segment set by dividing the input image in an overlapped manner; and (c) generating a second or higher-generation image segment set from the first-generation image segment set, wherein a subsequent-generation image segment set is generated by dividing in an overlapped manner at least one of a plurality of image segments included in the previous-generation image segment set.

The technology disclosed relates to classification of process cycle images to predict success or failure of process cycles. The technology disclosed includes capturing and processing images of sections arranged on an image generating chip in genotyping process. Image description features of production cycle images are created and given as input to classifiers. A trained classifier separates successful production images from unsuccessful or failed production images. The failed production images are further classified by a trained root cause classifier into various categories of failure.

The technology disclosed relates to classification of process cycle images to predict success or failure of process cycles. The technology disclosed includes capturing and processing images of sections arranged on an image generating chip in genotyping process. Image description features of production cycle images are created and given as input to classifiers. A trained classifier separates successful production images from unsuccessful or failed production images. The failed production images are further classified by a trained root cause classifier into various categories of failure.

Disclosed herein is an apparatus for the real-time monitoring of construction objects. The apparatus for the real-time monitoring of construction objects includes: a communication unit configured to receive image data acquired by photographing a construction site, and to transmit safety information to an external device; and a monitoring unit provided with a prediction model pre-trained using binary image sequences of construction objects at the construction site as training data, and configured to detect a plurality of construction objects from image frames included in image data received via the communication unit and convert the detected construction objects into binary images, to generate future frames by inputting the resulting binary images to the prediction model, and to derive proximity between the construction objects by comparing the generated future frames with the resulting binary images and generate the safety information.

Disclosed is a method for recognizing a marine object based on hyperspectral data including collecting target hyperspectral data; preprocessing the target hyperspectral data; and detecting and identifying an object included in the target hyperspectral data based on a marine object detection and identification model, trained through learning of the detection and identification of the marine object. According to the present invention, the preprocessing and processing of the hyperspectral data collected in real time according to a communication state may be performed in the sky or on the ground.

Training deep neural networks requires a large amount of labeled training data. Conventionally, labeled training data is generated by gathering real images that are manually labelled which is very time-consuming. Instead of manually labelling a training dataset, domain randomization technique is used generate training data that is automatically labeled. The generated training data may be used to train neural networks for object detection and segmentation (labelling) tasks. In an embodiment, the generated training data includes synthetic input images generated by rendering three-dimensional (3D) objects of interest in a 3D scene. In an embodiment, the generated training data includes synthetic input images generated by rendering 3D objects of interest on a 2D background image. The 3D objects of interest are objects that a neural network is trained to detect and/or label.