In a first defect candidate area detected on the basis of a difference between a value of each pixel in a picked-up image and a value of a corresponding pixel in a reference image and a second defect candidate area detected on the basis of a ratio between a value of each pixel in the picked-up image and a value of a corresponding pixel in the reference image, an overlapping area is detected as a defect area. It is thereby possible to suppress detection of a false defect and detect a defect with high accuracy. In a preferable defect detection part, a shaking comparison part detects a defect candidate area on the basis of a difference in the pixel value between the picked-up image and the reference image, and a false information reducing part limits pixels to be used for obtaining the above ratio to those included in the defect candidate area.

Provided herein is an apparatus, including a photon emitter configured to emit photons onto a surface of an article, a photon detector array configured to receive photons from surface features of the article; and a processing means configured for processing photon-detector-array signals corresponding to photons scattered from the surface features and photons fluoresced from the surface features, wherein the processing means is further configured for classifying the surface features of the article.

Provided is a defect review technique that can accurately correct coordinate differences with respect to unusual defects in which it is difficult to accurately correct coordinate misalignments by conventional automatic fine alignment. If it is impossible to correct a coordinate misalignment on the basis of a first optical microscope image acquired by a first light source, a defect review apparatus acquires a second optical microscope image using a second light source, and determines whether it is possible to correct the coordinate misalignment on the basis of the second optical microscope image.

There is provided a system and method of inspecting a specimen. The method includes obtaining a first image of an inspection area of a die of a semiconductor specimen and a group of reference images corresponding to a group of candidate reference units, obtaining a second image informative of one or more partitions of the inspection area respectively associated with one or more inspection algorithms, for each given pixel of the first image, determining location of one or more reference pixels thereof based on information of the second image, selecting, from the group of candidate reference units, one or more specific reference units actually required for inspecting the inspection area based on the determined location, and using one or more reference images corresponding to the selected reference units to inspect the first image, thereby providing an inspection result of the inspection area.

The method can include obtaining a digital image of a wood board having a defect, the digital image including a representation of the defect; using a computer: mapping the position and shape of the representation of the defect, and generating blasting instructions based on the mapped position and shape; positioning the wood board in a given position in a cleaning station, the cleaning station having a blasting nozzle and holding the wood board in its coordinate system; and the cleaning station automatically moving the blasting nozzle relative to the wood board and blasting the defect based on the blasting instructions, including moving at least one of the blasting nozzle and the wood board relative to a frame of the cleaning station.

An apparatus according to the present disclosure acquires a display condition for displaying at least a part of target data as a display image on a display device, determines, in a case where the display image is changed, whether to store the display condition according to a changed display image in a storage device, based on an index relating to the change of the display image, and stores, in a case where the display condition is determined to be stored, the display condition according to the changed display image in the storage device.

A detection apparatus that detects a mark formed on a substrate is provided. The detection apparatus comprises a detection optical system that irradiates light on the mark on the substrate held by a stage and detects an image of the mark, and a processor that performs a detection process of the mark based on the image of the mark. The processor finds a detection value indicating a position of the mark in an observation field of the detection optical system based on the image of the mark, finds a subregion in which the mark is located among a plurality of subregions in the observation field, and corrects the detection value based on a correction value corresponding to the found subregion among correction values predetermined for the plurality of subregions, respectively.

Systems and methods for detecting cracks in a surface by analyzing a video, including an full-HD video, of the surface. The video contains successive frames, wherein individual frames of overlapping consecutive pairs of the successive frames have overlapping areas and a crack that appears in a first individual frame of a consecutive pair of the successive frames also appears in at least a second individual frame of the consecutive pair. A fully convolutional network (FCN) architecture implemented on a processing device is then used to analyze at least some of the individual frames of the video to generate crack score maps for the individual frames, and a parametric data fusion scheme implemented on a processing device is used to fuse crack scores of the crack score maps of the individual frames to identify cracks in the individual frames.

A method of measuring a gas turbine engine component of a gas turbine engine according to an example of the present disclosure includes, among other things, providing at least one gas turbine engine component including a coating on a substrate, detecting infrared radiation emitted from at least one localized region of the coating at a first wavelength in a first electromagnetic radiation frequency range, detecting infrared radiation emitted from the substrate corresponding to the at least one localized region at a second, different wavelength in a second electromagnetic radiation frequency range that differs from the first electromagnetic radiation frequency range, and determining a heat flux relating to the at least one localized region based upon a comparison of the first wavelength and the second wavelength.

Disclosed is a method for estimating twin defect density in a single-crystal sample, including: (A) etching the observed surface of a single crystal to form etch pits; (B) selecting bar-shaped etch pits caused by twin defect; (C) from the long-axis direction lengths of the etch pits caused by twin defect, estimating the twin defect density by using the following equation: twin defect density=Σkx′.sub.i/area of sample, wherein 2≤k≤3, and x′.sub.i is the long-axis direction length of an etch pit caused by the i-th twin.