公开(公告)号：US20210049357A1

公开(公告)日：2021-02-18

申请号：US16539634

申请日：2019-08-13

Applicant: Adobe Inc.

Inventor： Mausoom Sarkar ,  Ameh Jain

IPC: G06K9/00 ,  G06N3/08 ,  G06K9/62 ,  G06T7/12

Abstract: Techniques for document segmentation. In an example, a document processing application segments an electronic document image into strips. A first strip overlaps a second strip. The application generates a first mask indicating one or more elements and element types in the first strip by applying a predictive model network to image content in the first strip and a prior mask generated from image content of the first strip. The application generates a second mask indicating one or more elements and element types in the second strip by applying the predictive model network to image content in the second strip and the first mask. The application computes, from a combined mask derived from the first mask and the second mask, an output electronic document that identifies elements in the electronic document and the respective element types.