Based on a defective state of a structure, a degree of soundness that indicates how much the structure is sound is determined. Information about a defective state of the structure that provides grounds for this determination is outputted.

A leather defect detection system comprises a worktable, a conveying mechanism, an image capture module, a model training computing device and an embedded computing device, the worktable is used to place a to-be-detected leather; the conveying mechanism is movably disposed on the worktable; the image capture module is disposed on the conveying mechanism, when the conveying mechanism is actuated, relative positions of the image capture module and the to-be-detected leather change synchronously to capture a plurality of to-be-detected images respectively; the model training computing device uses a plurality of historical leather images captured by the image capture module to perform calculation to establish a defect identification model, and the defect identification model is transcoded into the embedded computing device, so that the embedded computing device is capable of directly using the transcoded defect identification model to perform defect identification on the to-be-detected images.

A system for inspecting and validating processes performed on a continuous web of fabric in an automated apparel manufacturing environment. The continuous web of fabric can move in a step wise fashion across a work area where tooling can perform one or more processes on the continuous web of fabric. At least one projector is provided to display an image onto the continuous web of fabric the image including a first image related to an article to be manufactured and a second image related to a reference grid. The continuous web of fabric and the first and second images are viewed by a camera, and data related to the viewed first and second images and the continuous web of fabric can be sent to a computer implemented control center which can analyze the data to determine whether a deviation or error exists regarding the manufacturing process.

An automated optical double-sided inspection apparatus includes a first image-capturing portion, a second image-capturing portion, a platform, a first light-blocking portion, a second light-blocking portion, and a processing portion. The platform carries an external object. When the processing portion operates in a first capturing mode, the second light-blocking portion blocks visible light from passing therethrough, while the first light-blocking portion allows visible light to pass therethrough, so that the first image-capturing portion shoots a first side of the external object through the first light-blocking portion to obtain a first image. When the processing portion operates in a second capturing mode, the first light-blocking portion blocks visible light from passing therethrough, while the second light-blocking portion allows visible light to pass therethrough, so that the second image-capturing portion shoots a second side of the external object through the second light-blocking portion to obtain a second image.

A first imaging unit 71 generates a first image a first image by taking an object to be inspected. A guide display unit 72 determines the object to be inspected from the first image by using a model for determining an object to be inspected from an image, and displays an illustration representing the object to be inspected as a guide. A second imaging unit 73 generates a second image by superimposing on the guide, and taking the object to be inspected with a recognizable marker regardless of color of an appearance of an object to be inspected, attached in a vicinity of a defect. A defect position determination unit 74 determines a position of the defect included in the object to be inspected based on a positional relationship between the illustration and the marker included in the second image. An information collecting unit 75 collects defect information associated with a type of the object to be inspected and the position of the defect.

A device to detect and analyze defects in magnified scale images of a surface of a finished product illuminated with a blue light source and viewed by multiple image-capturing devices each focused on their own spot includes a supporting mechanism, a transmitting mechanism, a detecting mechanism, and a processor. The transmitting mechanism carries and transmits the product. The detecting mechanism includes a detecting frame, a blue light source assembly. The processor is used to connect to a camera assembly, and preprocess the image of the front of the product to obtain a detection and analysis of any defects of the front of the product.

A system for taking high-resolution photographs from a vehicle-mounted camera, forming orthomosaics from video and/or multiple high-resolution photographs, and using artificial intelligence to detect and classify pavement flaws and defects in the imagery. Detection also includes the ability to capture quantifiable metrics for the defects and/or a region of interest. Three-dimensional imagery is produced from the same images as the orthomosaics. Surface and terrain map products made from the same source images capture additional details such as depth and volume. The highlighted orthomosaics and three-dimensional imagery can then be used as a basis to determine the pavement surface condition and subsequently support maintenance orders and manage pavement repairs. Further, metadata such as latitude, longitude, and altitude geo-location coordinates and sampling time can also be transferred to the output products to create a digital time history and enable analysis for preventative maintenance planning. Alternatively-sourced imagery may also be analyzed.

The present invention provides an image processing method for CDSEM for determining a measuring range of an image of a target pattern measured by a CDSEM machine. The image processing method of CDSEM comprises: obtaining a first gray scale image based on the image of the target pattern; performing Fourier transform to the first gray scale image to obtain a first frequency spectrum distribution; filtering out frequency spectrum components whose absolute values of ordinate are greater than preset threshold in the first frequency spectrum distribution to obtain a second frequency spectrum distribution, the preset threshold relates to the background noise and the signal frequency of SRAF features; and determining the measuring range based on the second frequency spectrum distribution.

A processing method includes obtaining a processing image of a apparatus and performing a second processing on the processing image to generate a target image to analyze the target image according to a target defect detection method to realize defect detection of the apparatus. The processing image is obtained by performing a first processing on an initial image of the apparatus. The first processing includes performing scale processing on the initial image according to defect parameters corresponding to the initial image.

A non-transitory computer-readable recording medium recording an image processing program that causes a computer to execute processing of: specifying a damaged portion by analyzing a captured image of a construction; and predicting, in the captured image, a range to which damage spreads based on the specified damaged portion and design data associated with the construction.