US 12,469,320 B2
Method and system for electronic image analysis
David Lewis, Philadelphia, PA (US)
Assigned to Digital Legal Medical Records, LLC, Philadelphia, PA (US)
Filed by Digital Legal Medical Records, LLC, Philadelphia, PA (US)
Filed on Apr. 2, 2024, as Appl. No. 18/624,497.
Application 18/624,497 is a continuation of application No. 18/501,467, filed on Nov. 3, 2023, granted, now 11,983,948.
Application 18/501,467 is a continuation of application No. 17/855,495, filed on Jun. 30, 2022, granted, now 12,374,148.
Application 17/855,495 is a continuation of application No. 17/566,446, filed on Dec. 30, 2021, abandoned.
Claims priority of provisional application 63/422,275, filed on Nov. 3, 2022.
Claims priority of provisional application 63/240,333, filed on Sep. 2, 2021.
Claims priority of provisional application 63/195,598, filed on Jun. 1, 2021.
Prior Publication US 2024/0331433 A1, Oct. 3, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 30/414 (2022.01); G06F 40/109 (2020.01); G06F 40/169 (2020.01); G06F 40/197 (2020.01); G06N 20/00 (2019.01)
CPC G06V 30/414 (2022.01) [G06F 40/109 (2020.01); G06F 40/169 (2020.01); G06F 40/197 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system for transforming documentation, the system comprising:
a non-transitory computer readable storage medium for receiving a request from a user to transform a document;
a database for storing a copy of the document and at least one documentation detail associated with the document;
an extraction engine for identifying textual content from each page of the document and creating an information layer corresponding to each page of the document based on the textual content;
wherein each information layer is combed with each corresponding document page;
wherein each information layer provides searchable access to a portion of the textual content; and
wherein, for each letter string of the textual content and each page of the document, creating the information layer further comprises:
determining original bounding box size and bounding box coordinates for each letter string of the textual content based on information extracted from the textual content;
setting page transparency of the page to maximum;
reducing, gradually, a font size until the textual content fits within the original bounding box size; and
writing a word to the page based on the bounding box coordinates of the page.