Machine-learning based camera image triggering for quality assurance inspection processes
AssigneeElementary Robotics, Inc.
InventorsDat Do, Arye Barnehama
Life of this patent
Estimating the term…
Abstract
Data is received that includes a feed of images of a plurality of objects passing in front of an inspection camera module forming part of a quality assurance inspection system. Within each image, it is detected whether an object is present within the image. Instance identifiers are assigned to each object. A single image is identified in which the object is optimally represented for each object using the corresponding instance identifier. These identified images are provided to a consuming application or process for quality assurance analysis.
Claims29
A computer-implemented method for providing quality assurance comprising:
- receiving data comprising a feed of images of a plurality of objects passing in front of an inspection camera module forming part of a quality assurance inspection system;
- detecting, within each image, whether an object is present within the image;
- assigning an instance identifier to each object;
- identifying, for each object using the corresponding instance identifier, a single image in which the object is optimally represented;
- discarding images for each object other than the corresponding identified single image;
- and
- providing the identified images to a consuming application or process for quality assurance analysis.
A computer-implemented method for providing quality assurance comprising:
- receiving data comprising a feed of images of a plurality of objects passing in front of an inspection camera module forming part of a quality assurance inspection system;
- detecting, within each image, whether an object is present within the image;
- assigning an instance identifier to each object;
- identifying, for each object using the corresponding instance identifier, a single image in which the object is optimally represented;
- wherein the detecting, assigning, and identifying are constrained within a single region of interest of each image, the single region of interest being a subset of the corresponding image as a whole;
- and providing the identified images to a consuming application or process for quality assurance analysis.
Dependencies are inferred from the claim text.