Image-based barcode detection
AssigneeZebra Technologies Corporation
InventorsDongqing Chen, Kui Liu, Neeharika Nelaturu, David S. Koch
Life of this patent
Estimating the term…
Abstract
A method includes: capturing an image; partitioning the image into sub-images; for each sub-image: providing the sub-image to a detection model, receiving, from the detection model, one or more sub-image regions of interest (SROIs), each SROI defined by (i) a position of the SROI, and (ii) one of a set of symbology categories, each symbology category encompassing a plurality of barcode symbologies; generating one or more regions of interest (ROI) from the SROIs, each ROI defined by a position of the ROI in the image, and a symbology category; and providing the ROIs to a decoder.
Claims12
A method, comprising:
- capturing an image;
- partitioning the image into sub-images;
- for a sub-image:
- providing the sub-image to a detector executing a detection model,
- receiving, from the detector, a sub-image region of interest (SROI) defined by (i) a position of the SROI within the sub-image, and (ii) a symbology category
- encompassing a plurality of barcode symbologies;
- generating a region of interest (ROI) from the SROI by converting the position of the SROI in the sub-image to a position in the image, the ROI defined by the position in the image and the symbology category;
- providing the ROI to a barcode decoder;
- and
- receiving, from the detector, a further SROI having a position within a further sub-image, wherein:
- generating the ROI from the SROI comprises:
- identifying SROIs with contiguous positions in the image, and merging the SROIs with contiguous positions.
A computing device, comprising:
- an image sensor;
- and
- a image pre-processor configured to:
- capture an image via the image sensor;
- partition the image into sub-images;
- and
- provide the sub-images to a detector;
- a detector configured to, for a sub-image:
- execute a detection model to obtain a sub-image region of interest (SROI) defined by (i) a position of the SROI within the sub-image, and (ii) a symbology category encompassing a plurality of barcode symbologies;
- generate a region of interest (ROI) from the SROI by converting the position of the SROI in the sub-image to a position in the image, the ROI defined by the position in the image and the symbology category;
- provide the ROIs to a barcode decoder;
- obtain a further SROI having a position within a further sub-image;
- and
- generate the ROI from the SROI by:
- identifying SROIs with contiguous positions in the image, and merging the SROIs with contiguous positions.
Dependencies are inferred from the claim text.