US 12,288,405 B2
Methods, systems, articles of manufacture and apparatus to extract region of interest text from receipts
Venkadachalam Ramalingam, Chennai (IN); Sricharan Amarnath, Chennai (IN); Raju Kumar Allam, Chennai (IN); Sreenidhi N. Upadhya, Chennai (IN); Kannan Shanmuganathan, Chennai (IN); and Hussain Masthan, Chennai (IN)
Assigned to NIELSEN CONSUMER LLC, Chicago, IL (US)
Filed by Nielsen Consumer LLC, Chicago, IL (US)
Filed on Aug. 26, 2022, as Appl. No. 17/822,664.
Claims priority of provisional application 63/292,973, filed on Dec. 22, 2021.
Prior Publication US 2023/0196806 A1, Jun. 22, 2023
Int. Cl. G06V 30/146 (2022.01); G06V 30/148 (2022.01); G06V 30/19 (2022.01)
CPC G06V 30/147 (2022.01) [G06V 30/153 (2022.01); G06V 30/19107 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium comprising instructions that, when executed, cause processor circuitry to at least:
improve region of interest detection efficiency by converting pixels of an input receipt image from a first format to a second format;
generate a binary representation of the input receipt image based on the converted pixels, the binary representation of the input receipt image corresponding to saturation values for respective ones of the converted pixels;
calculate mirror data from the binary representation of the input receipt image;
cluster the binary representation of the input receipt image to identify a first set of candidate regions of interest, the candidate regions of interest characterized by portions of the binary representation of the input receipt image having saturation values that satisfy a threshold value;
compute center coordinates of corresponding ones of the first set of candidate regions of interest of the binary representation of the input receipt image; and
cluster the mirror data to identify a second set of candidate regions of interest, the second set of candidate regions of interest used to measure an accuracy of the first set of candidate regions of interest.