A cleaning area estimation device (30) includes an estimation unit (33) that estimates dirt information (D2) about an inside of a cleaning area on the basis of image information (D1) obtained by imaging a cleaning area by an imaging device (10), and a generation unit (34) that generates map information (D3) indicating a map of the dirt information about the cleaning area on the basis of the estimated time-series dirt information (D2).

An image inspection device includes: an image acquisition unit to acquire an inspection target image; a geometric transformation processing unit to estimate a geometric transformation parameter for aligning a position of an inspection target in the inspection target image with a first reference image in which a position of the inspection target is known, and geometrically transform the inspection target image using the estimated geometric transformation parameter, thereby generating an aligned image in which the position of the inspection target is aligned with the first reference image; an image restoration processing unit to restore the aligned image, using an image generation network to receive an input image generated using the inspection target image and infer the aligned image as a correct image; and an abnormality determination unit to determine an abnormality of the inspection target using a difference image between the aligned image and the restored aligned image.

A novel disparity computation technique is presented which comprises multiple orthogonal disparity maps, generated from approximately orthogonal decomposition feature spaces, collaboratively generating a composite disparity map. Using an approximately orthogonal feature set extracted from such feature spaces produces an approximately orthogonal set of disparity maps that can be composited together to produce a final disparity map. Various methods for dimensioning scenes and are presented. One approach extracts the top and bottom vertices of a cuboid, along with the set of lines, whose intersections define such points. It then defines a unique box from these two intersections as well as the associated lines. Orthographic projection is then attempted, to recenter the box perspective. This is followed by the extraction of the three-dimensional information that is associated with the box, and finally, the dimensions of the box are computed. The same concepts can apply to hallways, rooms, and any other object.

Disclosed is a computer-implemented method of transmitting identification information of a medical instrument. The method encompasses comparing a digital image of an instrument tray and an instrument to a digital image of just the instrument tray to determine the identity of the instrument. A characteristic geometry such as its envelope is assigned to the instrument, and a characteristic quantity of the envelope such as its aspect ratio may be used to identify the instrument. Based on determining, from the image of the instrument and the instrument tray, the relative position between those two entities, the method determines whether the instrument has been taken from the instrument tray, and accordingly instructs a medical computing system about this determination. The medical computing system may then determine whether the correct instrument has been taken from the instrument has been taken from the instrument tray, for example by comparison with medical procedure planning data.

Provided is a cloud platform system for reading a medical image, the cloud platform system including: multiple image processing modules pre-programmed to perform preprocessing of the medical image and modularized; multiple artificial intelligence modules in which an artificial intelligence algorithm is pre-programmed and modularized; multiple layer modules in which layers applied to a configuration of the artificial intelligence algorithm are modularized by function; a learning model design unit providing a graphical user interface for designing an artificial intelligence-based learning model to a user terminal that has had access through a web browser; and a reading model generation unit generating a reading model by training the learning model designed by the learning model design unit.

Systems and methods are disclosed for detecting defects during manufacturing processes for materials and products. The provided systems may utilize imaging units and computer detection algorithms to determine the presence or absence of defects in manufactured materials or products. Detection of defects in material or products by the disclosed systems may prompt intervention in the manufacturing process to correct the source of the defects.

An analysis device for visualizing an accuracy of a trained determination device includes an acquisition unit acquiring an image pair of a non-defective product image and a defective product image, an extraction unit extracting an image region of a defective part of the defective product, a generation unit generating a plurality of image regions of pseudo-defective parts, a compositing unit synthesizing each of the image regions of the plurality of pseudo-defective parts with the non-defective product image to generate a plurality of composite images having different feature quantities, an unit outputting the plurality of composite images to the determination device and acquiring a label corresponding to each of the plurality of composite images from the determination device, and a display control unit displaying an object indicating the label corresponding to each of the plurality of composite images in an array based on the feature quantities.

A method of analyzing a product includes performing an anomaly detection on a received image using an autoencoder, wherein the autoencoder includes at least one first neural network trained based on a first set of training images, and the first set of training images includes a plurality of training images each showing a corresponding defect-free product; determining, using a binary classifier, whether or not a defect is present based on a result of the anomaly detection; performing defect detection on the received image using a defect detector, wherein the defect detector includes a third neural network trained based on a one third set of training images, and the third set of training images includes a plurality of training images each showing a corresponding defective product; and evaluating a result based on a weighting of the results of the anomaly detection, the defect detection, and the binary classifier.

A detection device detects a position of a leading end of a tip for executing an operation on a cell via the leading end, the tip including the leading end in a lower portion thereof. The detection device includes a light source that outputs light in a lateral direction such that the light has a width when viewed along an up-and-down direction, a movement mechanism that moves the tip, and a detector that detects the light output from the light source, wherein the light output from the light source until being detected by the detector includes first light and second light that advance in respective lateral directions that are different from each other, the movement mechanism moves the tip such that a part of the first light and a part of the second light are blocked by the leading end, and the detector detects the first light and the second light whose parts are blocked by the leading end.

An abnormality inspection system S1 according to an embodiment includes: an image acquisition unit configured to acquire a plurality of pieces of continuous pickup data of a component such that an identical spot of the component is contained in mutually different regions of the plurality of pieces of continuous pickup data; and a determination unit configured to detect presence or absence of abnormality in the plurality of pieces of continuous pickup data, and to determine that the component is abnormal, in a case where the abnormality is detected in all of the plurality of pieces of pickup data.