In various example embodiments, techniques are provided for training and/or using a semantic deep learning model, such as a segmentation-enabled CNN model, to detect corrosion and enable its quantitative evaluation. An application may include a training dataset generation tool capable of semi-automatic generation of a training dataset that includes images with labeled corrosion segments. The application may use the labeled training dataset to train a semantic deep learning model to detect and segment corrosion in images of an input dataset at the pixel-level. The application may apply an input dataset to the trained semantic deep learning model to produce a semantically segmented output dataset that includes labeled corrosion segments. The application may include an evaluation tool that quantitatively evaluates corrosion in the semantically segmented output dataset, to allow severity of the corrosion to be classified.

There are described herein methods and system for generating an inspection image of an object from radiographic imaging. The method comprises obtaining a plurality of digital images of the object positioned between a radiation source and a photon beam detector, the digital images taken at different object-detector distances or source-detector distances to create unique grain diffraction patterns in each one of the digital images, and forming the inspection image from image features common to the digital images at a common scale and removing the unique grain diffraction patterns.

A system is configured to receive an indication that an apparatus in a first assembled state should comprise a component with a first digital fingerprint and a component with a second digital fingerprint. The system is configured to receive video footage of apparatuses in the first assembled state. The system is configured to isolate an image of an apparatus in the first assembled state. The system is configured to split the image into a frame comprising a first component and a frame comprising a second component. The system is configured to generate first and second filtered images. The system is configured to identify feature points in the filtered images. The system is configured to determine that the first set of feature points matches the first digital fingerprint and that the second set of feature points matches the second digital fingerprint. The system is configured to update a component database.

Disclosed is a quaternion multi-degree-of-freedom neuron-based multispectral welding image recognition method, comprising: using three cameras having different wavebands to obtain multispectral weld pool images, and respectively performing pre-processing and edge extraction on the weld pool images having the different wavebands obtained at a same moment by the three cameras; establishing a quaternion-based multispectral weld pool image edge model; extracting low-frequency features after a quaternion discrete cosine transform; using a quaternion-based multi-degree-of-freedom neuron network to perform classification, training and recognition on edge features of the multispectral weld pool images. Compared to traditional means, the present invention has multiple recognition information sources, strong anti-interference capabilities and high recognition accuracy.

A non-destructive system for detecting anomalies in weldment of a pipeline is provided including an imaging apparatus, an anomaly detection unit, and a computing device. The imaging apparatus produces image segments corresponding to segments of the circumferential area of the weldment. The anomaly detection unit includes an artificial intelligence platform that processes and analyzes the image segments to identify at least one of a type, size, and location of a welding anomaly within the weldment using a database of truth data. The computing device includes a graphical user interface that displays the image segments with an overlay of information relating to at least one of the type, size, and location of the welding anomaly to the user.

A three-dimensional (3D) printer includes a nozzle and a camera configured to capture a real image or a real video of a liquid metal while the liquid metal is positioned at least partially within the nozzle. The 3D printer also includes a computing system configured to perform operations. The operations include generating a model of the liquid metal positioned at least partially within the nozzle. The operations also include generating a simulated image or a simulated video of the liquid metal positioned at least partially within the nozzle based at least partially upon the model. The operations also include generating a labeled dataset that comprises the simulated image or the simulated video and a first set of parameters. The operations also include reconstructing the liquid metal in the real image or the real video based at least partially upon the labeled dataset.

A fairing skin repair method based on measured wing data includes fairing skin registration. Data set P1 through denoising and filtering wing point cloud data is reorganized to obtain a key point set P. A histogram feature descriptor in a normal direction of any key point in set P and a skin point cloud data Q is calculated. Euclidean distance between feature descriptors of two points is calculated through K-nearest neighbor algorithm, and points with high similarity are added into a set M. A clustering is performed on set M using a Hough voting algorithm to obtain a local point cloud set P′ in set P. The method includes fairing skin repair. The boundary line of the point frame is projected onto Q, and a distance between a projection line on the point cloud and the boundary line is calculated to obtain an amount of skin to be repaired.

A hardness tester includes an image acquirer (controller) acquiring an image of a surface (surface image) of a sample captured by an image capturer, an identifier (controller) identifying, based on the surface image of the sample, a non-conformity region inside the image that is unsuitable for the hardness test using predetermined conditions, and a test position definer (controller) defining a test position in an area outside the non-conformity region identified by the identifier.

In an aspect, an image processing apparatus includes a processor and a memory in which a plurality of images obtained by capturing images of a building and a three-dimensional model of the building are stored in association with each other. The processor is configured to perform a development process to perform development of the three-dimensional model into a two-dimensional image, an extraction process to extract defect information of the building on the basis of the plurality of images, a mapping process to perform mapping of the defect information to the two-dimensional image, and an output process to output the two-dimensional image to which the mapping is performed.

A topographical identification and comparison system which converts other examples of the same kind or with parts of the examples of topographical structures having fixed references such as circular, rectangular and square, regular polygon to a digital data such as trace and wavy structural conditions of the surface areas and which carries out similarity comparison of this data by soft mathematical calculations.