US 11,758,071 B1
Identification and removal of noise from documents
Mohit Bansal, Hyderabad (IN); Rehan Ahmad, Hyderabad (IN); Harshita Srivastava, Hyderabad (IN); and Shrey Chirag Shah, Hyderabad (IN)
Assigned to HighRadius Corporation, Houston, TX (US)
Filed by HighRadius Corp., Houston, TX (US)
Filed on Jul. 26, 2022, as Appl. No. 17/873,954.
Int. Cl. H04N 1/58 (2006.01); G06V 30/40 (2022.01)
CPC H04N 1/58 (2013.01) [G06V 30/40 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, using a computing system, a document;
detecting, using the computing system and one or more machine learning algorithms, that noise exists in the document;
based on the detection that noise exists in the document, removing, using the computing system, the noise from the document, wherein removing the noise from the document comprises:
identifying, using the computing system, one or more contours of one or more continuous points in the document;
determining, using the computing system, one or more first contours of the one or more contours associated with potential noise;
detecting, using the computing system, whether there are one or more neighboring contours near the one or more first contours associated with potential noise; and
based on a detection of no, one, or more neighboring contours near the one or more first contours associated with potential noise, determining, using the computing system, whether each first contour of the one or more first contours associated with potential noise is not noise or is noise; and
generating, using the computing system, a copy of the document with each first contour that is not noise and without each first contour that is noise.