A method of detecting defects in a composite layup includes capturing, using an infrared camera, reference images of a reference layup being laid up by a reference layup head. The method also includes manually reviewing the reference images for defects, and generating reference defect masks indicating defects in the reference images. The method further includes training, using the reference images and reference defect masks, a neural network, creating a machine learning model that, given a production image as input, outputs a production defect mask indicating the defect location and the defect type of each defect. The method also includes capturing, using an infrared camera, production images of a production layup being laid up by the production layup head, and applying the model to the production images to automatically generate a production defect masks indicating each defect in the production images.

A method of inspecting images on printed products by a computer in a printing machine. Printed products are recorded and digitized by an image sensor of an image inspection system in the course of the image inspection process, and the computer compares them to a digital reference image. If deviations are found, the defective printed products are removed. The computer analyzes the deviations found in the course of the image inspection process together with further data from other system parts and from the machine, determines specific defect classes and the causes thereof based on the defects by machine learning processes, assigns the defects found in the image inspection process to the defect classes in a corresponding way, and displays the classified detected defects with their defect classes and causes to an operator of the machine so that the operator can initiate specific measures to eliminate the defect causes.

A method for automatically reconstituting the architecture, along a reinforcing axis, of the reinforcement of a composite material, includes acquiring images of the reinforcement of the composite material, each image being acquired along a section plane perpendicular to the reinforcing axis; for each image acquired, detecting, using a neural network, barycentre and/or the circumference of each section of the reinforcing thread; for at least one acquired reference image, assigning a tag corresponding to a reinforcing thread, to each detected barycentre or circumference; for each other acquired image, assigning, to each detected barycentre and/or each detected circumference, the tag of the corresponding barycentre in the acquired reference image; reconstituting the architecture of each reinforcing thread from each detected barycentre and/or circumference having the tag of the reinforcing thread and the position on the reinforcing axis associated with the acquired image on which the barycentre and/or the circumference has been detected.

A method of identifying a defect in a wet film comprises conveying said wet film (20), in a wet state, on a conveyor (10), providing a laser projection (1511) onto the wet film, acquiring a series of images, each depicting an area of the wet film, wherein at least a portion of the laser projection is visible, and using at least some of said images to identify said defect. There is also disclosed a method and device for producing a film.

One aspect of the present disclosure relates to a generation method for a training dataset, comprising: capturing, by one or more processors, a target object to which a marker unit recognizable under a first illumination condition is provided; and acquiring, by the one or more processors, a first image where the marker unit is recognizable and a second image obtained by capturing the target object under a second illumination condition.

The disclosure described herein is directed to a computerized system and method of grading and authenticating collectibles utilizing digital imaging devices and processes to provide an objective, standardized, consistent high-resolution grading of collectible objects, such as but not limited to sport and non-sport trading cards. The disclosure eliminates the subjectivity present in the human grading process and overcomes the inherent limitations of the human eye.

A material data collection system allows capturing of material data. For example, the material data collection system may include digital image data for materials. The material data collection system may ensure that captured digital image data is properly aligned, so that material data may be easily recalled for later use, while maintaining the proper alignment for the captured digital image. The material data collection system may include using a capture guide, to provide cues on how to orient a mobile device used with the material data collection system.

A system and control method for determining an amount of paper product dispensed from a dispenser or remaining in the dispenser is provided. The paper product is initially loaded in the dispenser as a paper product formation, such as a roll or stack of the product. At defined intervals, a digital image of an aspect of the paper product formation in the dispenser is taken and transmitted to a digital imager processor. A feature of the digital image that changes as the paper product formation decreases in size as the paper product is dispensed is analyzed and compared with a predetermined value of the feature at a predefined size of the paper product formation to determine an amount of the paper product dispensed or remaining in the dispenser.

An integrated system for automatic forming, picking, and inspection of a grinding wheel mesh piece and a method thereof, including a visual inspection system (1), a conveying system (2), a cutting system (3), and a picking system (4); the conveying system (2) is used to precisely control a conveying action of a cutting section conveying platform (51) and a picking section conveying platform (52), and the visual inspection system (1) is used to acquire an image of a grinding wheel mesh cloth, establish virtual origin coordinates of a cutting layout and center coordinates of the grinding wheel mesh piece after cutting, recognize defects of the grinding wheel mesh cloth, and calibrate qualified center coordinates and unqualified center coordinates; the cutting system (3) is used to cut the grinding wheel mesh cloth moved to the cutting section conveying platform (51) to obtain a circular grinding wheel mesh piece.

A fiducial for use in the manufacture of a fabric article includes a hole through a layer of fabric. Another layer of fabric of the fabric article overlays and obscures the fiducial. The fiducial is detected by transmitting electromagnetic radiation through the fabric article. The electromagnetic radiation may make a single pass directly through the fabric article to a sensor, or may pass through the fabric article, be reflected off a surface, and pass back through the fabric article to the sensor.