Abstract: In an example embodiment, rather than a single calibration object, a plurality of calibration objects are placed within the field of view of an inspection camera at the same time. Each of the calibration objects is or includes a semi-spherical reflective object having known sizes. During a calibration process, the distance between a light source and camera may be determined by activating the light source and capturing an image of how the light source bounces off each of the calibration objects, and more particularly the location on each of the calibration objects that the light source appears to reflect from. This allows the angle that the light source strikes each calibration object to be calculated, and these angles can then be used to determine the distance between the light source and the camera.

Abstract: In an example embodiment, a reflective inclined surface is used as a calibration object. During a calibration process, the relative 3D position between a light source and a camera may be determined by activating the light source and capturing an image of how the light source bounces off the reflective calibration object. This may be repeated multiple times with the reflective inclined surface turned ninety degrees, along the z-axis, each time, essentially spinning the reflective inclined surface so that the highest edge is perpendicular to where it was previously with each capture of the camera. This allows the angle at which the light source strikes the reflective inclined surface in each repetition to be calculated, and these angles can then be used to determine the 3D position of the light source relative to the camera. The same technique with the same calibration object can be used to perform camera calibration.

Abstract: In an example embodiment, a calibration phase is performed where a calibration object is sent through the system and multiple images of the calibration object are taken. From these images, the direction and speed of the calibration object can be computed as well as the distance between the calibration object and the camera. From these three pieces of information, a three-dimensional offset vector is created. This three-dimensional offset vector can then be applied during a photometric stereo process to align the object in the different images so that the orientation and graduation of the surface can be accurately calculated.

Abstract: In an example, a light system is provided that allows for increased reliability in directly detecting defects in components by capturing multiple different images of the component under different lighting conditions and using a photometric stereo technique to reconstruct a three-dimensional (3D) model of the component, which can be used to perform additional operations to increase the reliability of defect detection, such as measuring the height of variations in a surface of the component.

Abstract: In an example embodiment, rather than a single calibration object, a plurality of calibration objects are placed within the field of view of an inspection camera at the same time. Each of the calibration objects is or includes a semi-spherical reflective object having known sizes. During a calibration process, the distance between a light source and camera may be determined by activating the light source and capturing an image of how the light source bounces off each of the calibration objects, and more particularly the location on each of the calibration objects that the light source appears to reflect from. This allows the angle that the light source strikes each calibration object to be calculated, and these angles can then be used to determine the distance between the light source and the camera.

Abstract: In an example, a light system is provided that allows for increased reliability in directly detecting defects in components by capturing multiple different images of the component under different lighting conditions and using a photometric stereo technique to reconstruct a three-dimensional (3D) model of the component, which can be used to perform additional operations to increase the reliability of defect detection, such as measuring the height of variations in a surface of the component.

Abstract: In an example embodiment, a uniform filtering technique is applied using photometric stereo to reduce or eliminate global defects in a scanned component. An image is taken of a component using a photometric stereo technique. A uniform filter then, for every point in the component, takes an average of heights of the points near it. This essentially “blurs” the image. The blurring may be repeated multiple times. The blurred image may then be subtracted from the original image, essentially flattening out the image in a manner that reduces or eliminated global inaccuracies. The post-filtered image can then be used for defect detection, with that defect detection being more accurate because of the reduction of the global inaccuracies.