Abstract: A method of aligning images for 3D imaging of a sample includes, for each of multiple cameras located around a vessel, activating a respective light source that provides backlighting for the vessel, and capturing a respective 2D calibration image of the vessel. The method also includes, for each 2D calibration image, measuring a respective vertical position, horizontal position, and rotation of the image, in part by detecting edges of the vessel as depicted in the image. The method also includes generating calibration data based on the measured vertical positions, horizontal positions, and rotations for the respective 2D calibration images, capturing, by each camera, a respective set of 2D images of the sample in the vessel, and digitally resampling, using the calibration data, at least one of the respective sets of 2D images to correct for vertical offset, horizontal offset, and rotational offset of the set(s) of 2D images.

Abstract: Various techniques facilitate the development of an image library that can be used to train and/or validate an automated visual inspection (AVI) model, such an AVI neural network for image classification. In one aspect, an arithmetic transposition algorithm is used to generate synthetic images from original images by transposing features (e.g., defects) onto the original images, with pixel-level realism. In other aspects, digital inpainting techniques are used to generate realistic synthetic images from original images. Deep learning-based inpainting techniques may be used to add, remove, and/or modify defects or other depicted features. In still other aspects, quality control techniques are used to assess the suitability of image libraries for training and/or validation of AVI models, and/or to assess whether individual images are suitable for inclusion in such libraries.

Abstract: A method for 3D imaging of a sample, in a vessel having a longitudinal axis orthogonal to a horizontal plane, includes capturing, by at least three cameras located at different positions around the vessel, respective 2D images of the sample. Each image comprises pixels having associated pixel values. The optical axis of a first camera is inclined or declined at a first angle relative to the horizontal plane, with the first angle being greater than or equal to zero degrees. The optical axis of a second camera is inclined or declined at a second, larger angle relative to the horizontal plane. The method also includes generating a 3D image of the sample based on the pixel values associated with the 2D image pixels, and one or more look-up tables that collectively indicate, for pixels in each image, expected paths for light traversing the vessel and the sample.

Abstract: In a method for imaging a container holding a sample, the container is illuminated with a laser sheet of a first color, and one or more images of the container are capturing by a first imager configured to filter out colors other than the first color. Simultaneously with illuminating the container with the laser sheet of the first color, the container is illuminated with light of a second color different than the first color, wherein the light of the second color illuminates at least a majority of an entire volume of the container. One or more additional imagers of the container are captured by a second imager configured to filter out colors other than the second color. The one or more images and the one or more additional images are analyzed to detect particles within, and/or on an exterior surface of, the container.

Abstract: An apparatus for nondestructive detection of transparent or reflective objects in a vessel includes an imager configured to acquire data that represent light reflected from spatial locations in the vessel as a function of time, a memory operably coupled to the imager and configured to store the data, and a processor operably coupled to the memory and configured to detect the objects based on the data by (i) identifying a respective maximum amount of reflected light, over time, for each location in the spatial locations based on the data representing light reflected from the spatial locations as a function of time, and (ii) determining a presence or absence of the objects in the vessel based on the number of spatial locations whose respective maximum amount of reflected light, over time, exceeds a predetermined value.

Abstract: Techniques that facilitate the development and/or modification of an automated visual inspection (AVI) system that implements deep learning are described herein. Some aspects facilitate the generation of a large and diverse training image library, such as by digitally modifying images of real-world containers, and/or generating synthetic container images using a deep generative model. Other aspects decrease the use of processing resources for training, and/or making inferences with, neural networks in an AVI system, such as by automatically reducing the pixel sizes of training images (e.g., by down-sampling and/or selectively cropping container images). Still other aspects facilitate the testing or qualification of an AVI neural network by automatically analyzing a heatmap or bounding box generated by the neural network. Various other techniques are also described herein.

Abstract: In a method for imaging a container holding a sample, the container is illuminated with a laser sheet of a first color, and one or more images of the container are capturing by a first imager configured to filter out colors other than the first color. Simultaneously with illuminating the container with the laser sheet of the first color, the container is illuminated with light of a second color different than the first color, wherein the light of the second color illuminates at least a majority of an entire volume of the container. One or more additional imagers of the container are captured by a second imager configured to filter out colors other than the second color. The one or more images and the one or more additional images are analyzed to detect particles within, and/or on an exterior surface of, the container.

Abstract: In a method for imaging a container holding a sample, the container is illuminated with a laser sheet that impinges upon the container in a first direction corresponding to a first axis. A plane of the laser sheet is defined by the first axis and a second axis orthogonal to the first axis. The method also includes capturing, by a camera having an imaging axis that is substantially orthogonal to at least the first axis, an image of the container. The method further includes analyzing, by one or more processors, the image of the container to detect particles within, and/or on an exterior surface of, the container.

Abstract: An apparatus for nondestructive detection of transparent or reflective objects in a vessel includes an imager configured to acquire data that represent light reflected from spatial locations in the vessel as a function of time, a memory operably coupled to the imager and configured to store the data, and a processor operably coupled to the memory and configured to detect the objects based on the data by (i) identifying a respective maximum amount of reflected light, over time, for each location in the spatial locations based on the data representing light reflected from the spatial locations as a function of time, and (ii) determining a presence or absence of the objects in the vessel based on the number of spatial locations whose respective maximum amount of reflected light, over time, exceeds a predetermined value.

Abstract: Assemblies (10), devices, and methods are described herein that allow an examiner to inspect a container (12) of liquid product (14) through a bottom wall (18) of the container using a line-of-sight diversion member (28, e.g. beam splitter, mirror or prism). In some forms, the assemblies described herein can be provided with mounts and connecting arms to couple the devices to inspection booths.

Abstract: In a method for replicating performance of an automated visual inspection (AVI) station, a mimic AVI station that performs one or more AVI functions of the AVI station is constructed. One or more container images are captured by an imaging system of the AVI station while a container is illuminated by an illumination system of the AVI station, and one or more additional container images are captured by a mimic imaging system of the mimic AVI station. The method also includes identifying, by one or more processors, one or more differences between the one or more additional container images and the one or more container images, generating, by the one or more processors, a visual indication of the difference(s) and/or one or more suggestions for modifying the mimic AVI station, and modifying the mimic AVI station based on the visual indication.

Abstract: An inspection system for a drug container is provided to identify foreign matter, such as particles or fibers, within the drug container prior to filling with a drug. The system includes a camera device aligned with an axis of the drug container and captures a series of images of an interior surface of a sidewall of the drug container while the robot causes relative movement between the drug container and the camera device along a linear path. Atypical lighting, which improves contrast between particles and the background in images is employed to aid detection. A control circuit then processes the series of images to identify foreign matter within the drug container.

Abstract: The apparati, methods, and computer program products disclosed herein can be used to nondestructively detect undissolved particles, such as glass flakes and/or protein aggregates, in a fluid in a vessel, such as, but not limited to, a fluid that contains a drug.

Abstract: An automated inspection system includes a sensor system that includes a sensor and is configured to generate a plurality of syringe scans by scanning each of a plurality of syringes. Each of the plurality of syringe scans is indicative of distance relative to the sensor. The automated inspection system also includes one or more processors configured to, for each of the plurality of syringes, analyze the respective syringe scan to determine (i) a first distance to a first portion (e.g., flange) of the syringe and (ii) a second distance to a second portion (e.g., plunger) of the syringe, and calculate a distance between the first and second portions based on the first distance and the second distance.

Abstract: A method for 3D imaging of a sample, in a vessel having a longitudinal axis orthogonal to a horizontal plane, includes capturing, by at least three cameras located at different positions around the vessel, respective 2D images of the sample. Each image comprises pixels having associated pixel values. The optical axis of a first camera is inclined or declined at a first angle relative to the horizontal plane, with the first angle being greater than or equal to zero degrees. The optical axis of a second camera is inclined or declined at a second, larger angle relative to the horizontal plane. The method also includes generating a 3D image of the sample based on the pixel values associated with the 2D image pixels, and one or more look-up tables that collectively indicate, for pixels in each image, expected paths for light traversing the vessel and the sample.

Abstract: In a method for imaging a container holding a sample, the container is illuminated with a laser sheet that impinges upon the container in a first direction corresponding to a first axis. A plane of the laser sheet is defined by the first axis and a second axis orthogonal to the first axis. The method also includes capturing, by a camera having an imaging axis that is substantially orthogonal to at least the first axis, an image of the container. The method further includes analyzing, by one or more processors, the image of the container to detect particles within, and/or on an exterior surface of, the container.

Abstract: A well plate cover includes a base defining a base plane, and a plurality of insertion elements. At least a portion of each of the insertion elements is transparent. Each of the insertion elements is coupled to the base, and extends, in a direction orthogonal to the base plane, from the base to a distal end surface of the insertion element. The distal end surface of each of the insertion elements includes an apex that, when the respective insertion element is inserted into a well of a well plate, extends further into the well than any other portion of the distal end surface. The apex is a point, a line, or a plane having a diameter that is less than one half of a maximum diameter of the distal end surface.

Abstract: A method for facilitating clone selection includes generating time-sequence images of a well containing a medium, including a first image and a later, second image. The method also includes detecting, by one or more processors analyzing the first image, one or more candidate objects depicted in the first image, and, for each of the candidate objects, determining whether the object is a single cell by analyzing an image of the object using a convolutional neural network. The method further includes detecting, by analyzing the second image with the processor(s), a cell colony depicted in the second image, and determining, by the processor(s), whether the colony was formed from only one cell based at least on whether each candidate object was determined to be a single cell. The method further includes generating, by the processor(s), output data indicating whether the colony was formed from only one cell.

Abstract: A system is described to facilitate the characterization of particles within a fluid contained in a vessel using an illumination system that directs source light through each vessel. One or more optical elements may be implemented to refract the source light and to illuminate the entire volume of the vessel. As the refracted source light passes through the vessel and interacts with particles suspended in the fluid, scattered light is produced and directed to an imager, while the refracted source light is diverted away from the imager to prevent the source light from drowning out the scattered light. The system can therefore advantageously utilize an imager with a large depth of field to accurately image the entire volume of fluid at the same time, facilitating the determination of the number and size of particles suspended in the fluid.

Abstract: The apparati, methods, and computer program products disclosed herein can be used to nondestructively detect undissolved particles, such as glass flakes and/or protein aggregates, in a fluid in a vessel, such as, but not limited to, a fluid that contains a drug.