In one embodiment, a computing system may obtain a high-resolution X-ray image and a number of low-resolution X-ray images of an object of interest. The system may divide each of the low-resolution X-ray images into a number of low-resolution patches. Each low-resolution patch may be associated with a portion of the object of interest. The system may input a set of low-resolution patches associated with a same portion of the object of interest into a machine-learning model. Each low-resolution patch of the set may be from a different low-resolution X-ray image. The machine-learning model may output a high-resolution patch for the same portion of the object of interest. The system may compare the high-resolution patch outputted by the machine-learning model to a corresponding portion of the high-resolution X-ray image of the object of interest and adjust one or more parameters of the machine-learning model based on the comparison.

A method of detecting an anomaly in a crystallographic structure, the method comprising: illuminating the structure with x-ray radiation in a known direction relative to the crystallographic orientation; positioning the structure such that its crystallographic orientation is known; detecting a pattern of the diffracted x-ray radiation transmitted through the structure; generating the simulated pattern based on the known direction relative to the crystallographic orientation; comparing the detected pattern to a simulated pattern for x-ray radiation illuminating in the known direction; and, detecting the anomaly in the crystallographic structure based on the comparison.

A method for detecting defects in a product (10), such as food packaging, having a range of thicknesses of cross-section through which detection will take place; the method comprising: scanning the product (10), with for instance x-rays, to identify one or more light regions, and one or more dense regions of the product; and creating a first signal path and a second signal path from a single set of scanning data, and conditioning: the first signal path for detection of defects in the one or more dense regions; and the second signal path for detection of defects (14a, 14b, 14c) in the one or more light regions. Advantageously, detection of defects in the contents (dense region) of a product and the seal (light region) of the product is conducted simultaneously.

The disclosure provides an inspection method determining whether there is a defect in an electrode structural body including a cathode electrode layer, an electrolyte layer and an anode electrode layer electrode by an image processor. The inspection method includes a step of scanning the electrode structural body along a scanning direction to obtain a continuous transmission image, a step of digitizing a shade of each pixel of the transmission image, a step of calculating a difference value between a grayscale of a specific pixel and a median value of grayscales of comparison pixels located in front or rear of the specific pixel along the scanning direction, and a step of determining presence or absence of the defect according to the difference value and a predetermined threshold value.

The present disclosure directs to a system and method for CT imaging. The method may include acquiring computed tomography (CT) data, wherein the CT data is generated by scanning a subject using a CT scanner, the CT scanner including a focal spot and a detector, and the detector including a plurality of detector units. The method may also include obtaining a forward projection model and a back projection model, wherein the forward projection model and the back projection model are associated with sizes of the detector units and a size of the focal spot of the CT scanner. The method may further include reconstructing a CT image of the subject iteratively based on the CT data, the forward projection model, and the back projection model.

The invention relates to non-destructive imaging of the internal structure for safe and intuitive operator work. In the context of the invented method, electronic scanning first creates a virtual image of the surface of the object (5) whose internal structure is the subject of research. Part of the surface of the object (5) and the angle of scanning are set by voice or by movement of the operator's body (9). The virtual image of the surface of the object (5) is subsequently projected in the stereoscopic glasses (7), followed by creation of the virtual image of the internal structure of the object (5) for the same angle of scanning. The virtual image of the internal structure is projected in the virtual image of the surface of the object (5), or replaces the virtual image of the object (5).

The presently-disclosed technology improves the resolution of an x-ray microscope so as to obtain super-resolution x-ray images having resolutions beyond the maximum normal resolution of the x-ray microscope. Furthermore, the disclosed technology provides for the rapid generation of the super-resolution x-ray images and so enables real-time super-resolution x-ray imaging for purposes of defect detection, for example. A method of super-resolution x-ray imaging using a super-resolving patch classifier is provided. In addition, a method of training the super-resolving patch classifier is disclosed. Other embodiments, aspects and features are also disclosed.

A book digitization apparatus includes an emitter that applies an energy ray to a book, a detector that detects an energy ray radiated from the book in response to a material existing in the book, and a three-dimensional data generator that generates data of a plurality of space points in accordance with the detected ray. The data of the space points associates position information of a position in a three-dimensional space within the book with a physical property value used to identify a layout pattern of the material at the position in a direction of thickness of the book.

Constructing a computer image from raw imaging data or encoded imaging data by transforming a first data structure in which the raw imaging data or the encoded imaging data is stored into a second data structure storing reorganized imaging data. The raw imaging data or the encoded imaging data is received, stored in the first data structure. The computer reorganizes the raw imaging data or the encoded imaging data into the reorganized data and stores the reorganized data in the second data structure, which is a multi-dimensional array having subarrays containing local information needed by a convolutional neural network for processing the reorganized data. Other portions of the multi-dimensional array store other portions of the raw imaging data or the encoded imaging data. The computer also processes the reorganized data using the convolutional neural network to construct the image, whereby a constructed image is formed.

An image acquisition unit acquires first and second radiographic images acquired by irradiating a first radiation detector and a second radiation detector which overlaps the first radiation detector so as to deviate from the first radiation detector by a half pixel with radiation which has been emitted from a radiation source and transmitted through an object. A corresponding positional relationship acquisition unit acquires a corresponding positional relationship between the position of pixels of the first radiographic image and the position of pixels of the second radiographic image. A resolution enhancement unit estimates a pixel value corresponding to a position between the pixels of the first radiographic image, on the basis of the corresponding positional relationship, a pixel value of the first radiographic image, and a pixel value of the second radiographic image, and generates a processed radiographic image having a higher resolution than the first and second radiographic images.