Amazon Technologies, Inc.

Frank Preiswerk

Timothy Stallman

Michael R Calder

Ali Can

Michael Robert Bocamazo

Armon Shariati

Joshua Nicholas Migdal

Techniques for optical lens characterization and calibration are described herein. In an example, a computer system receives a first image of a target captured by an image acquisition system having a camera and a lens and using first setting values in a setting space. The computer system inputs the first setting values and a first decode performance associated with image acquisition system having the first setting values for the barcode sets in the first image into a machine learning model and determines a representation of the setting space. The computer system inputs the machine learning model and one or more conditions into an algorithm and receives an output indicating second setting values in the setting space for the image acquisition system. The computer system sends the second setting values to the controller, which is configured to set the settings for the image acquisition system based on the second setting values.

Optical lens characterization and calibration

Techniques for optical resolution determination from barcode chart images are described herein. In an example, a computer system receives an image captured by an image acquisition system having a camera with a lens. The image is of a chart including barcode sets arranged in one or more orientations with respect to an optical axis of the camera, and individual barcodes of a barcode set have a barcode attribute. The computer system decodes the barcode sets in the image using a barcode decoder. The computer system determines, for individual barcode attributes and for individual orientations, a number of decoded barcodes in the barcode sets that match encoded information stored in a barcode manifest. The computer system determines a resolution metric of the image acquisition system for a target barcode decode rate based on a distribution of a decode rate associated with the barcode attribute for the decoded barcodes.

Optical resolution determination from barcode chart images

Systems and techniques for reading a structured identifier are provided. One technique involves obtaining a set of images of an item with a structured identifier. A region of interest (ROI) of the structured identifier within a first image of the set of images is determined. A second image comprising the ROI of the structured identifier is generated. An enhanced version of the second image is generated, based on processing the second image with at least one image restoration model. The structured identifier is decoded from the enhanced version of the second image to obtain data corresponding to the structured identifier.

Deep learning based image enhancement for barcode decoding

Systems and techniques for performing a scan-free reading of a structured identifier are provided. One technique involves obtaining a first set of images of an object within a scanning volume of an environment. The object is passed through the scanning volume without an explicit presentation of the structured identifier to an optical scanner within the environment. For each image of a plurality of the first set of images, an indication of a first region of interest of the structured identifier on the object within the image is obtained, based in part on a second set of images of the object having a lower quality than the first set of images. The first region of interest of the structured identifier is extracted from a first image of the plurality of the first set of images. The structured identifier within the first region of interest within the first image is decoded.

Scan-free barcode reading

Image data from a camera is used to identify one or more items in a dynamic field of view for item identification and tracking. The camera focus setting may be adjusted to different depth of field based on estimated distances to the items within the image data. After adjusting the focus setting, additional image data may be collected to capture a sharper image of the item and ensure sufficient clarity for item recognition based on item identifiers visible on the items within the image data.

Growing community of inventors

Brooklyn, NY, United States of America

Frank Preiswerk