Session-based character recognition for document reconstruction

摘要

Systems and methods are provided for sharing a screen from a mobile device. For example, a method includes receiving an image from a mobile device, performing recognition on the image to identify space-delimited strings, and generating a content graph for the image, the content graph having content nodes that represent at least some of the strings and the content graph having edges that represent a relative position of strings associated with the content nodes connected by the edges. The method may also include repeating the receiving, performing recognition, and generating for a plurality of images, the plurality of images belonging to a session, and generating a combined graph from the plurality of content graphs based on similarity of content nodes between content graphs, the combined graph representing text from the plurality of images in reading order.

主权项

1. A mobile device comprising:
at least one processor; and memory storing instructions that, when executed by the at least one processor, cause the mobile device to:
for a plurality of images associated with a session:
perform recognition on the image to identify space-delimited strings, andgenerate a content graph for the image, the content graph having content nodes that represent at least some of the strings, an edge in the graph representing a relative position of the content nodes the edge connects;generate a combined graph from the plurality of content graphs by clustering content nodes between the content graphs based on similarity metrics, wherein a cluster represents a node in the combined graph; andselect a best string from the cluster as a label for the node in the combined graph, wherein the combined graph represents text from the plurality of images in reading order.