Abstract: A container inspection system is described herein. The container inspection system includes a camera and a computing system, wherein the camera is configured to capture multiple images of a transparent container as the transparent container is transported along a conveyor. Thus, the camera captures several images of the transparent container when the transparent container is at different positions relative to the camera. The container inspection system detects a defect in the transparent container based upon one or more images in the several images.

Abstract: A glass container inspection system including a diffuse illuminator configured to provide diffused light arranged to illuminate a portion of a glass container symmetrically about a central axis of the container. The inspection system further includes an image capture system that generates at least one image that includes a plurality of views of the glass container illuminated by the diffused light. The at least one image may include a view of the portion of the container reflected by a mirror. The glass container inspection system yet further includes a computing system in communication with the image capture system. The computing system can be configured to output an indication as to whether the container is defective based upon the data from the image capture system. The computing system can be further configured to output the indication responsive to detecting a check in the sidewall of the glass container.

Abstract: Described herein are various technologies pertaining to an automated light field illumination container inspection and manufacture system. The system includes a plurality of cameras that capture images of a container when the container is illuminated by way of light field illumination. Bands in images that include reflections in the exterior surface of the sidewall are identified, and a determination is made as to whether the container is defective based upon the identified bands.

Abstract: Described herein are various technologies pertaining to determining whether at least a portion of a sidewall of a glass container has insufficient thickness. A glass container inspection system comprises an infrared camera in communication with a computing system. The infrared camera is configured to capture an infrared image of an exterior of the sidewall of the glass container at long-wavelength infrared as the glass container undergoes a temperature change. The computing system receives the infrared image from the infrared camera and outputs an indication that at least the portion of the sidewall of the glass container has insufficient thickness based on the infrared image. The indication may also be based on a statistical model derived from infrared images of glass containers having sidewalls of known sufficient thickness.

Abstract: Described herein are various technologies related to inspecting transparent containers for both opaque and transparent defects. An emitter is configured to direct a color gradient through a sidewall of a transparent container, such that color of light that passes through the sidewall varies across the sidewall. A camera is configured to capture an image of the sidewall of the transparent container while the color gradient passes through the sidewall of the container. A computing system receives the image and determines whether the sidewall of the container includes either an opaque or a transparent defect based upon the image.

Abstract: A container inspection system is described herein. The container inspection system includes a light source that emits a flash of light when a container is detected as being in an inspection region. The container inspection system further includes a light director element that receives a portion of the flash of light and forms a tapering field of light that illuminates an exterior surface of a sidewall of the container when the container is in the inspection region. The container inspection system further comprises a camera that generates an image of the exterior surface when such surface is illuminated by the tapering field of light. A computing system receives the image and outputs an indication as to whether or not the container is defective based upon the image.

Abstract: Described herein are various technologies pertaining to an automated light field illumination container inspection. The container inspection system includes a plurality of cameras that capture images of a container when the container is illuminated by way of light field illumination. Bands in images that include reflections in the exterior surface of the sidewall are identified, and a determination is made as to whether the container is defective based upon the identified bands.

Abstract: Described herein are various technologies pertaining to automated container inspection. A region in an image of a container is labeled as being subject to depicting reflections. When determining whether or not the container is defective based upon the image of the container, values of pixels of the image are compared to corresponding statistics of such pixels, where the statistics can identify an acceptable distribution of values for a pixel. For pixels in the above-mentioned region, more variance in the values of the pixels is allowed (compared to allowed variance when analyzing values of pixels outside of the region) when determining whether or not the container is defective based upon the values of the pixels.

Abstract: Systems and methods for extracting topographic information from inspected objects to identify defects in the inspected objects. A part to be inspected is illuminated with at least two different colors emitted from an illuminator providing a gradient of light consisting of the at least two different colors. A single color image of the illuminated part to be inspected is acquired, providing a color-coded topographic mapping of the part to be inspected due, at least in part, to the gradient of light. Topographic monochrome views of the part to be inspected may be generated from the single color image. Each view of the topographic monochrome views may enhance a different type of feature or defect present in the part to be inspected which can be analyzed and detected.

Abstract: A machine for inspecting a rotating glass container for defects wherein the image evaluated for defects is a critical addition of a plurality of additions each defined by a plurality of time spaced images.

Abstract: Systems and methods for extracting topographic information from inspected objects to identify defects in the inspected objects. A part to be inspected is illuminated with at least two different colors emitted from an illuminator providing a gradient of light consisting of the at least two different colors. A single color image of the illuminated part to be inspected is acquired, providing a color-coded topographic mapping of the part to be inspected due, at least in part, to the gradient of light. Topographic monochrome views of the part to be inspected may be generated from the single color image. Each view of the topographic monochrome views may enhance a different type of feature or defect present in the part to be inspected which can be analyzed and detected.

Abstract: Systems and methods to identify defects of a surface coating treatment in a beverage can. One or more image suspects are acquired, including at least a portion of a surface treated by a coating. A coating characteristic detection process is performed on the one or more image suspects. At least one coating characteristic is determined based at least in part on the coating characteristic detection process.

Abstract: A method and configuration to estimate the dimensions of a cuboid. The configuration includes two image acquisition units offset from each other with at least one of the units positioned at a defined acquisition height above a background surface. Image processing techniques are used to extract a perimeter of a top surface of the cuboid, placed on the background surface, from pairs of acquired images. A height estimation technique, which corrects for spatial drift of the configuration, is used to calculate an absolute height of the cuboid. The absolute height of the cuboid is used, along with the extracted perimeter of the top surface of the cuboid, to calculate an absolute length and an absolute width of the cuboid. The height, length, and width may be used to calculate an estimated volume of the cuboid.

Abstract: Systems and methods to estimate the height profile of an object using tomosynthesis-like techniques. A plurality of raw images of an object to be characterized are acquired, where the plurality of raw images are representative of a plurality of spatial shifts of an imaging device relative to the object to be characterized. The raw images are processed to generate composite images, where each composite image corresponds to a unique image shift between spatially adjacent raw images. A volatility parameter value is calculated within a neighborhood of a same image pixel location for each composite image. The composite image having the largest volatility parameter value for the image pixel location is determined. A unique image shift, corresponding to the composite image having the largest volatility parameter value, is transformed into a height value representative of a height dimension of the image pixel location.

Abstract: A system and method to detect defects in ink blankets of a decorator wheel. An image of each of a plurality of ink blankets of a decorator wheel is acquired using an optical inspection device of the system as the decorator wheel rotates past the optical inspection device during an inking process. Each acquired image is correlated to a unique ink blanket of the plurality of ink blankets. Each acquired image is further matched to a unique standard image of a correlated unique ink blanket. Each acquired image is also compared to a matching unique standard image to determine any defects.

Abstract: A method and configuration to estimate the dimensions of a cuboid. The configuration includes two image acquisition units offset from each other with at least one of the units positioned at a defined acquisition height above a background surface. Image processing techniques are used to extract a perimeter of a top surface of the cuboid, placed on the background surface, from pairs of acquired images. A height estimation technique is used to calculate an absolute height of the cuboid. The absolute height of the cuboid is used, along with the extracted perimeter of the top surface of the cuboid, to calculate an absolute length and an absolute width of the cuboid. The height, length, and width may be used to calculate an estimated volume of the cuboid.

Abstract: A machine for inspecting glass containers which are being rotated at an inspection station. A light source illuminates a selected area on a rotating glass container while the container rotates through a selected angle and a camera is triggered to capture an image while the bottle rotates through that angle. A plurality of sequential images are recorded and a critical addition is made to be inspected.

Abstract: Apparatus, systems, and methods to recognize features on bottom surfaces of containers on a container production line, detect defects in the containers, and correlate the defects to specific production equipment of the container production line, based in part on the recognized features. The system includes imaging apparatus, programmable processing devices, and encoders. The methods include synchronization techniques and correlation techniques.

Abstract: Systems and methods to estimate the height profile of an object using tomosynthesis-like techniques. A plurality of raw images of an object to be characterized are acquired, where the plurality of raw images are representative of a plurality of spatial shifts of an imaging device relative to the object to be characterized. The raw images are processed to generate composite images, where each composite image corresponds to a unique image shift between spatially adjacent raw images. A volatility parameter value is calculated within a neighborhood of a same image pixel location for each composite image. The composite image having the largest volatility parameter value for the image pixel location is determined. A unique image shift, corresponding to the composite image having the largest volatility parameter value, is transformed into a height value representative of a height dimension of the image pixel location.

Abstract: A method and system to monitor randomly oriented objects on a process line are disclosed. A color camera is used initially to collect a set of reference images of at least one reference object. The reference images represent various spatial orientations of the reference object. The reference object serves as the standard for the process. The reference images are stored in a computer-based platform. The color camera is then used to capture images of monitored objects as the monitored objects pass by the color camera on a process line. The monitored objects may have a random spatial orientation with respect to the color camera as the monitored objects pass through the field-of-view of the color camera. The captured images of the monitored objects are processed by the computer-based platform and compared to the reference images in order to determine if certain characteristic parameters of the monitored objects have deviated from those same characteristic parameters of the reference object.