US 10,095,677 B1 · Detection of layouts in electronic documents

Abstract

Disclosed are techniques and systems to detect a layout of a source document. A process may include receiving content from a first page and a second page of the source document, designating sections in each page along a first direction of the page, and assigning similar sections to a group. For the group, the process may proceed by dividing sections for each page into discrete portions associated with 2D coordinate areas, and identifying sets of 2D coordinate areas for the discrete portions that contain content. The number of times each portion contains some content may be compared to a threshold to determine a layout of the group of sections.

A method comprising:

extracting content from a first page and a second page of a source document, the first page and the second page each having a fixed layout;
determining a section break along a lengthwise direction of the first page;
designating a first section of the first page and a second section of the first page based at least in part on the section break of the first page;
determining a number of columns of the first section of the first page, including at least a first column and a second column;
determining a column width of the first column of the first section of the first page and a column width of the second column of the first section of the first page;
determining a section break along a lengthwise direction of the second page;
designating a first section of the second page and a second section of the second page based at least in part on the section break of the second page;
determining a number of columns of the first section of the second page, including at least a first column and a second column;
determining a column width of the first column of the first section of the second page and a column width of the second column of the first section of the second page;
determining whether the number of columns of the first section of the first page is a same as the number of columns of the first section of the second page;
determining that a difference in width between the column width of the first column of the first section of the first page and the column width of the first column of the first section of the second page is less than or equal to a predetermined width difference;
determining that a difference in width between the column width of the second column of the first section of the first page and the column width of the second column of the first section of the second page is less than or equal to the predetermined width difference;
assigning the first section of the first page and the first section of the second page to a first group based at least in part on determining that:
(i) the number of columns of the first section of the first page is the same as the number of columns of the first section of the second page;
(ii) the difference in width between the column width of the first column of the first section of the first page and the column width of the first column of the first section of the second page is less than or equal to the predetermined width difference, and (iii) the difference in width between the column width of the second column of the first section of the first page and the column width of the second column of the first section of the second page is less than or equal to the predetermined width difference;
dividing the first section of the first page into a first plurality of discrete portions to form a first grid having a defined density of discrete portions within a first area of the first section of the first page;
dividing the first section of the second page into a second plurality of discrete portions to form a second grid having the defined density of discrete portions within a second area of the first section of the second page;
identifying a first type of content and a second type of content within the extracted content, the first type of content being different than the second type of content;
assigning a first weight to the first type of content and a second weight to the second type of content based at least in part on a category of the source document, the first weight being greater than the second weight based at least part on a determination that the first weight is more indicative of a layout of the source document;
and
determining, based at least partly on at least one of the first weight or the second weight, a layout of the first group based at least in part on a determination of whether or not individual discrete portions of the first grid and the second grid would contain at least some of the extracted content within the first section of the first page or within the first section of the second page when the first page and the second page are respectively presented on a display.

18 more elements

Detection of layouts in electronic documents

Life of this patent

Detection of layouts in electronic documents

Life of this patent

Abstract

Claims20