| CPC G06F 40/186 (2020.01) [G06V 30/18105 (2022.01); G06V 30/412 (2022.01); G06V 30/416 (2022.01)] | 21 Claims |

|
1. A computer-implemented method for automated visual analysis of documents to generate digital templates, the method comprising:
accessing a digital image of a document page;
accessing a background color definition;
tracking a current content state for analyzing the digital image, the current content state having a plurality of potential states comprising:
a first state indicating a collision with a non-background; and
a second state indicating no collision with the non-background;
testing a first plurality of test lines of pixels from the digital image against the background color definition to identify, from the first plurality of test lines of pixels, a first plurality of content state transition lines, each line in the first plurality of test lines of pixels extending in a first direction;
testing a second plurality of test lines of pixels from the digital image against the background color definition to identify, from the second plurality of test lines of pixels, a second plurality of content state transition lines, each line in the second plurality of test lines of pixels extending in a second direction;
identifying intersections between the first plurality of content state transition lines and the second plurality of content state transition lines;
determining an area of interest bounded by intersecting lines from the first plurality of content state transition lines and the second plurality of content state transition lines;
processing the area of interest to determine that the area of interest represents content; and
based on a determination that the area of interest represents content, storing the area of interest as a design element of a digital page template.
|