US 11,960,966 B2
Decoding of two-dimensional barcodes under unfavorable conditions
Ivan Zagaynov, Dolgoprudniy (RU); Dmitry Zvonarev, Sarapul (RU); and Aleksandr Riashchikov, Samara (RU)
Assigned to ABBYY Development Inc., Dover, DE (US)
Filed by ABBYY Development Inc., Dover, DE (US)
Filed on May 16, 2022, as Appl. No. 17/745,026.
Prior Publication US 2023/0367983 A1, Nov. 16, 2023
Int. Cl. G06K 7/14 (2006.01); G06K 19/06 (2006.01); G06T 7/60 (2017.01)
CPC G06K 7/1417 (2013.01) [G06K 19/06028 (2013.01); G06T 7/60 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
estimating a module size of a barcode image (BI) based on geometric characteristics of a plurality of pixel groups, each of the plurality of pixel groups comprising one or more connected pixels of a first color;
rescaling the BI based on the estimated module size;
processing the rescaled BI using a neural network (NN) to obtain candidate locations of modules in the BI and a map of binarized pixel intensities of the BI;
identifying associations of grid positions in a grid of modules (GoM) with the candidate locations of modules in the BI, wherein an association of each of at least a subset of the grid positions in the GoM is identified based on one or more associations identified for other grid positions in the GoM; and
decoding the BI, using the GoM and the map of binarized pixel intensities.