US 11,869,258 B1
Classifying and segmenting characters within an image
Christian Kündig, Zürich (CH); Oliver Akermann, Zürich (CH); Bernd Schoner, New York, NY (US); and Luc Humair, Zürich (CH)
Assigned to Scandit AG, Zurich (CH)
Filed by Scandit AG, Zürich (CH)
Filed on Nov. 1, 2022, as Appl. No. 18/051,590.
Application 18/051,590 is a continuation of application No. 17/549,805, filed on Dec. 13, 2021, granted, now 11,495,036.
Claims priority of provisional application 63/143,269, filed on Jan. 29, 2021.
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 30/14 (2022.01); G06V 30/18 (2022.01); G06K 19/06 (2006.01); G06V 30/148 (2022.01)
CPC G06V 30/148 (2022.01) [G06V 30/1801 (2022.01); G06K 19/06028 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus for segmenting an image, the apparatus comprising:
a camera; and
one or more memory device comprising instructions that, when executed, cause one or more processors to perform the following steps:
receiving an image acquired by the camera, wherein the image comprises a first set of characters and a second set of characters;
classifying the first set of characters as an identifier;
classifying the second set of characters as data associated with the identifier;
dividing the image to create an image segment, after classifying the first set of characters and the second set of characters, wherein the image segment includes the first set of characters and not the second set of characters;
decoding the first set of characters in the image segment to generate a first character string;
decoding the second set of characters to generate a second character string; and
linking the first character string to the second character string based on classifying the first set of characters as the identifier and the second set of characters as the data associated with the identifier.