US 12,387,517 B1
Graph-based document layout detection
Yair Kittenplon, Raanana (IL); Shai Mazor, Binyamina (IL); Ron Litman, Tel-Aviv (IL); Niv Berchi Nayman, Shoham (IL); and Shahar Tsiper, Haifa (IL)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Dec. 13, 2022, as Appl. No. 18/065,541.
Int. Cl. G06V 30/414 (2022.01); G06V 10/82 (2022.01); G06V 30/10 (2022.01); G06V 30/413 (2022.01); G06V 30/416 (2022.01)
CPC G06V 30/414 (2022.01) [G06V 10/82 (2022.01); G06V 30/10 (2022.01); G06V 30/413 (2022.01); G06V 30/416 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
one or more processors; and
a memory storing instructions that, when executed on or across the one or more processors, cause the one or more processors to:
receive a document comprising text;
apply an optical character recognition (OCR) technique to identify the text in the document;
generate a graph representation of the document, wherein the graph representation comprises a plurality of nodes and a plurality of edges that connect different ones of the plurality of nodes, wherein individual ones of the nodes correspond to different portions of the text identified according to the OCR technique;
apply a graph convolutional network (GCN) machine learning model to the graph representation to identify a layout of different sections of the document according to respective merge inferences generated by the GCN for individual ones of the plurality of edges; and
provide the layout of different sections of the document.