Abstract: Apparatuses, systems, and techniques to train a generative model based at least in part on a private dataset. In at least one embodiment, the generative model is trained based at least in part on a differentially private Sinkhorn algorithm, for example, using backpropagation with gradient descent to determine a gradient of a set of parameters of the generative models and modifying the set of parameters based at least in part on the gradient.

Abstract: According to various embodiments, a system and method for processing an image of a biological specimen stained for a presence of at least one lymphocyte biomarker is disclosed. The system and method are configured to detect lymphocytes in the image and compute a foreground segmentation mask based on the lymphocytes detected within the image. Outlines of the detected lymphocytes are identified in the image by filtering the image with the computed foreground segmentation mask. A shape metric may be derived for each of the detected lymphocytes based on the identified lymphocytes outlines. The derived shape metric may be associated with location information for each of the detected lymphocytes and a value of each of the derived shape metric may be compared to a predetermined threshold value. A predictive cell motility label may be assigned to each of the detected lymphocytes based on the comparison.

Abstract: Correction content is made learnable based on a correction operation performed by a user on an attribute setting screen in setting attribute information, such as a filename, based on a character string obtained by character recognition processing on a scan image.

Abstract: In implementations of systems for generating occurrence contexts for objects in digital content collections, a computing device implements a context system to receive context request data describing an object that is depicted with additional objects in digital images of a digital content collection. The context system generates relationship embeddings for the object and each of the additional objects using a representation learning model trained to predict relationships for objects. A relationship graph is formed for the object that includes a vertex for each relationship between the object and the additional objects indicated by the relationship embeddings. The context system clusters the vertices of the relationship graph into contextual clusters that each represent an occurrence context of the object in the digital images of the digital content collection.

Abstract: A printing apparatus includes a reception unit configured to receive a print job, and an execution unit configured to execute printing of the print job received by the reception unit. The execution unit has a function of, in a case where a setting time or more elapses with a particular cause preventing the printing of the print job not being removed, canceling the printing of the print job. The execution unit has a function of canceling printing of a new print job received by the reception unit in a state where the setting time or more elapses with the particular cause not being removed.

Abstract: An example system may include a processor and a non-transitory machine-readable storage medium storing instructions executable by the processor to determine, during an imaging operation by an imaging component of a printing device, whether a print queue, supplied by the imaging component, will be depleted by a printing component of the printing device prior to a completion of the imaging operation; and adjust, based on the determination, a media feed rate of the printing component.

Abstract: An image forming apparatus includes a controller configured to obtain PJL data via a data interface, obtain filter data via the data interface, store the obtained filter data in a non-volatile memory, the filter data associating non-target PJL data with target PJL data, the non-target PJL data being PJL data not intended for causing the image forming apparatus to a particular process, the target PJL data being PJL data intended for causing the image forming apparatus to perform the particular process, and when the obtained PJL data is the non-target PJL data associated with the target PJL data in the filter data stored in the non-volatile memory, convert the obtained PJL data into the target PJL data associated with the non-target PJL data in the filter data stored in the non-volatile memory.

Abstract: A three-dimensional reconstruction method based on half-peak probability density distribution, including: slicing three-dimensional point cloud along Z-axis direction to obtain N spatial layers; extracting the scatter information in i-th spatial layer and projecting information to Zi plane; constructing membership function of each grid and scatter in the Zi plane and drawing a three-dimensional probability density plot; making a plane parallel to XOY plane through half-peak wmax/2 of three-dimensional probability density plot, parallel intersecting a three-dimensional probability density plot to obtain a contour LXY; superimposing radioactive source reconstruction contours corresponding to N spatial layers sequentially to obtain a three-dimensional reconstruction model of a radioactive source.

Abstract: A system and method for rich content transformation are provided. The system and method allow rich content transformation to be separately processed on a client device and on a cloud-based server. The client device downsizes a rich content and transmits the downsized rich content to the cloud-based server via a network. The cloud-based server calculates function parameters based on the downsized rich content using one or more machine learning models included in the server. The calculated function parameters are transmitted to the client device via the network. The client device then applies these function parameters to the rich content on the client device to obtain the transformed rich content.

Abstract: An image forming apparatus includes an image forming portion configured to form an image on a sheet; and an operating portion including a display screen which includes at least numeric keys, a start key configured to cause the image forming portion to start image formation, and a stop key configured to stop the image formation by the image forming portion, and including a hardware key provided on a back side of the display screen and configured to start a maintenance mode of the image forming apparatus.

Abstract: An image processing device includes: one or more processors including hardware. The one or more processors are configured to: calculate, on a basis of a reference image acquired by capturing an image of a reference subject which has an optical characteristic that is equivalent to at least a part of a living body, image transformation parameters through congruence transformation that transforms a coordinate corresponding to a color of target region included in the reference image defined in a color space into a coordinate corresponding to an achromatic color in the color space; and perform, in the color space on a basis of the calculated image transformation parameters, the congruence transformation of colors of a color image acquired by capturing an image of the living body, the color image being constituted by at least two monochromatic image corresponding to different illumination having different center wavelengths.

Abstract: In classifying images by machine learning, provided are an image classification method, device, and program for classifying the image from which the feature difference is hardly detected, in particular, classifying the interference fringe image of tear fluid layer by the dry eye types. The method includes a step of acquiring a feature value from an interference fringe image of tear fluid layer for learning, a step of constructing a model for classifying an image from the feature value acquired from the interference fringe image of tear fluid layer for learning, a step of acquiring the feature value from an interference fringe image of tear fluid layer for testing, and a step of performing classification processing for classifying the interference fringe image of tear fluid layer for testing by types of dry eye using the model and the feature value acquired from the interference fringe image of tear fluid layer.

Abstract: This application provides a method for transmitting face image data and transferring value, apparatuses, an electronic device, and a storage medium, which belongs to the field of network technologies. The method for transmitting face image data includes acquiring a face data stream through the sensor, and transmitting the face data stream to the first processor; performing image screening on a face image in the face data stream by the first processor to obtain at least a target face image, the target face image meeting a target condition; retrieving a target web address from the memory by the first processor; and transmitting the target face image to the target web address by the first processor.

Abstract: A first communication device may execute an output control process of externally outputting output information, the output information obtained using a public key of the first communication device, receive an authentication request from a second communication device that has obtained the public key, send a first authentication response to the second communication device via a wireless interface in a case where it is determined that a wireless connection has been established between the first communication device and a first access point, the first authentication response including first role information indicating that the first communication device is to serve a first role which is a role of sending first wireless setting information to the second communication device, and send the first wireless setting information to the second communication device.

Abstract: According to at least one embodiment, an image forming apparatus includes a processor configured to cause forming an image with a decolorable color material on a tagged paper sheet with an RFID tag, reading data of the RFID tag attached to the tagged paper sheet before the image is formed, and promoting information related to reuse of the tagged paper sheet based on the data read from the RFID tag before the image is formed on the tagged paper sheet.

Abstract: An apparatus and method for a printing system is provided which determines whether image data input by execution of an input job is a blank and, in a case where the image data is determined to be a blank, the printing system records information indicating the determination of a blank as history information of the input job. Thus, in a case where image data input by execution of an input job is not output by execution of an output job, the user is able to easily confirm the cause of the output failure of the input image data.

Abstract: A program creation device includes training data including image data, a setting unit configured to set information of a frame specifying a region for each cell for detecting the presence or absence of the object from the image, and a learning unit configured to execute machine learning of the training data and to create a learned program for extracting the object from the image. The setting unit acquires information on a target region of the training data and on aspect ratios of the anchor, calculates a degree of matching between the anchor and the target region for each aspect ratio while changing a size of the anchor, and calculates an adoption rate of the target region whose degree of matching is a proportion no less than a threshold, and determines, based on a result of the calculation, the size of the anchor used in the learned program.

Abstract: A method, user device, and a printing device for manufacturing one or more customized products are provided. The method involves capturing one or more three-dimensional (3-D) images of one or more objects, transmitting the captured one or more 3D images to a printing device, converting the transmitted one or more 3D images into a predefined format; wherein the predefined format is a format read by the printing device. The method further comprises printing the converted one or more 3D images using the printing device to create one or more 3D objects, wherein the one or more 3D objects are a replica of the one or more objects in the one or more captured 3D images, and manufacturing one or more customized products using the created one or more 3D objects.

Abstract: In some example embodiments, a computer-implemented method may include training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.

Abstract: A method for magnetic resonance imaging and plaque recognition includes: obtaining magnetic resonance undersampled K-space data; transforming the magnetic resonance undersampled K-space data to an image domain through inverse Fourier transform to obtain a preprocessed image; reconstructing the preprocessed image through a pre-established deep learning reconstruction model to obtain a high-resolution imaging image of a blood vessel wall; and recognizing plaques in the high-resolution imaging image of the blood vessel wall through a pre-established deep learning plaque recognition model. A neural network corresponding to the pre-established deep learning reconstruction model is a dense connection network. The magnetic resonance undersampled K-space data is head-and-neck combined magnetic resonance undersampled K-space data of the blood vessel wall.