Provided is a line displacement evaluation method of evaluating line displacement occurring in a press-formed article in press forming of forming a character line. This method includes acquiring a cross section profile of the press-formed article measured so as to traverse the character line formed in the press-formed article; calculating a 4th order differential coefficient of the acquired cross section profile; and evaluating the line displacement, on the basis of the calculated 4th order differential coefficient of the cross section profile.

A workpiece inspection and defect detection system includes a light source, a lens that inputs image light arising from a surface of a workpiece, and a camera that receives imaging light transmitted along an imaging optical path. The system utilizes images of workpieces acquired with the camera as training images to train a defect detection portion to detect defect images that include workpieces with defects. Anomaly detector classification characteristics are determined based on features of the training images. Run mode images of workpieces are acquired with the camera, and based on determined features from the images, the anomaly detector classification characteristics are utilized to determine if the images of the workpieces are classified as anomalous. In addition, the defect detection portion determines if images are defect images that include workpieces with defects and for which additional operations may be performed (e.g., metrology operations for measuring dimensions of the defects, etc.)

Technologies for producing training data for identifying degradation of physical components include a system. The system includes circuitry configured to apply an accelerated degradation process to a physical component of an industrial plant. Additionally, the circuitry of the system is configured to obtain measurement data indicative of visual characteristics of the physical component at each of multiple phases of degradation, wherein the measurement data is usable to train a neural network to identify a phase of degradation of another physical component.

An electronic device for optically checking an appearance of a product for defects includes a first checking device checking a plane of a product and a second checking device checking side surfaces of the product. The first checking device includes a first camera device, a second camera device, and first white and red light sources. The second checking device includes a third camera device, at least one second white light source, and at least one second red light source. When the first white light source or the first red light source are activated, the first and second camera device capture at least one image of a plane. When the second white light source or the second red light source are activated, the third camera device captures at least one image of a side surface.

A learned model generation method includes: using a teacher image including a defect map that is an image indicating a distribution of a defect portion of a surface of steel and having an equal image size, and presence/absence of periodic defects assigned in advance to the defect map; and generating a learned model by machine learning, the learned model for which: an input value is a defect map that is an image indicating a distribution of a defect portion of a surface of steel and having an image size of the equal image size; and an output value is a value concerning presence/absence of periodic defects in the defect map.

A method of evaluating quality of a wafer or an apparatus of evaluating quality of a wafer may include: performing a copper-haze evaluation on a piece of wafer or a single crystal ingot; collecting copper-haze map data and a copper-haze evaluation score based on a result of the copper-haze evaluation; training an artificial intelligence model based on the copper-haze map data and the copper-haze evaluation score; and performing crystal defect evaluation on the piece of the wafer or the single crystal ingot using the learned artificial intelligence model that outputs the copper-haze evaluation score when the copper-haze map data is input.

An image view angle conversion method includes: model training data are obtained, the model training data including planar images of a training object at a plurality of different view angles and labels corresponding to respective view angles, where the labels corresponding to the different view angles are different. A pre-designed generative adversarial network model is trained according to the model training data to obtain a view angle conversion network model. A planar image of a target object and labels corresponding to one or more expected view angles of the target object are input into the view angle conversion network model, so that the view angle conversion network model generates planar images of the target object at the expected view angles.

A method for monitoring species of algae for stress comprises growing a test set of algae of a given species, applying a stress of a predetermined kind to some of the algae, and irradiating the algae at a predetermined first set of wavelengths. The algae are then monitored at a predetermined second set of wavelengths to detect fluorescence and/or absorbance carried out on the first set of wavelengths by the stressed algae. The detected fluorescence and/or absorbance is compared for each irradiation wavelength between the stressed algae and unstressed algae to find signs indicating the applied stress. There is then a stage of searching through combinations of respective irradiation wavelengths and detected wavelengths to find a minimal set of irradiating and detected wavelengths that detects the stress. The smallest size set is then used in irradiating further sets of algae of the tested species to detect the given stress.

An electronic apparatus including a display and one or more processor is disclosed. The one or more processor is configured to: divide a first error value of each of a plurality of first components with respect to a mounting position acquired through inspection of a plurality of substrates of a first type, into a plurality of error values, generate a graph of a tree structure including a plurality of nodes corresponding to the plurality of first components, component types of each of the plurality of first components and a plurality of components included in a mounter, adjust attributes of each of the plurality of nodes using the plurality of error values divided from the first error value of each of the plurality of first components, and display the graph in which the attributes of each of the plurality of nodes are adjusted, on the display.

A product defect detection method and apparatus, an electronic device, and a storage medium are provided. A method includes: acquiring a multi-channel image of a target product; inputting the multi-channel image to a defect detection model, wherein the defect detection model includes a plurality of convolutional branches, a merging module and a convolutional headbranch; performing feature extraction on each channel in the multi-channel image by using the plurality of convolutional branches, to obtain a plurality of first characteristic information; merging the plurality of first characteristic information by using the merging module, to obtain second characteristic information; performing feature extraction on the second characteristic information by using the convolutional headbranch, to obtain third characteristic information to be output by the defect detection model; and determining defect information of the target product based on the third characteristic information.