US 2018/0005029 A1Published application

Method for recognizing table, flowchart and text in document images

AssigneeKonica Minolta Laboratory U.S.A., Inc.

InventorWei Ming

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method for recognizing a binary document image as a table, pure text, or flowchart includes calculating a side profile of the image for each of the four sides, calculating a boundary removal size N corresponding to each side based on widths of lines or strokes closest to that side, and for each side, removing a boundary of size N from the document image, and re-calculating the side profile for each side after the removal. Then, based on a comparison of the side profiles and the re-calculated side profiles, the input document image is recognized as a table if all side profiles change from smooth to non-smooth, as pure text if the side profile changes are small, and as a flowchart if the original side profiles contain multiple sharp changes and wide flat regions and if the side profile changes significantly in the previously wide flat regions.

Claims20

Dependent claims

A method implemented in a data processing apparatus for recognizing an input document image as a table, pure text, or flowchart, the document image being a binary image where each pixel is a background pixel having a background pixel value or a content pixel having a content pixel value, the method comprising:

(a) calculating a side profile of the image for each of a top, bottom, left and right sides, each side profile being, for each pixel position along that side of the document image, a distance from that side to a first content pixel along a direction perpendicular to that side;
(b) calculating a boundary removal size N corresponding to each side based on line widths at a plurality of pixel positions along that side using content pixels closest to that side;
(c) for each side, removing a boundary of the size N from the document image by setting N consecutive pixels, starting from the first content pixel and going in the direction perpendicular to that side, to the background pixel value, to generate a boundary-removed image for that side;
(d) re-calculating a side profile for each of the top, bottom, left and right sides using the boundary-removed image for that side;
(e) based on a comparison of the side profiles and the re-calculated side profiles of some or all of the sides, recognizing the input document image as a table, pure text, a flowchart, or none of them.

2 more elements

A computer program product comprising a computer usable non-transitory medium having a computer readable program code embedded therein for controlling a data processing apparatus, the computer readable program code configured to cause the data processing apparatus to execute a process for recognizing an input document image as a table, pure text, or flowchart, the document image being a binary image where each pixel is a background pixel having a background pixel value or a content pixel having a content pixel value, the process comprising:

(a) calculating a side profile of the image for each of a top, bottom, left and right sides, each side profile being, for each pixel position along that side of the document image, a distance from that side to a first content pixel along a direction perpendicular to that side;
(b) calculating a boundary removal size N corresponding to each side based on line widths at a plurality of pixel positions along that side using content pixels closest to that side;
(c) for each side, removing a boundary of the size N from the document image by setting N consecutive pixels, starting from the first content pixel and going in the direction perpendicular to that side, to the background pixel value, to generate a boundary-removed image for that side;
(d) re-calculating a side profile for each of the top, bottom, left and right sides using the boundary-removed image for that side;
(e) based on a comparison of the side profiles and the re-calculated side profiles of some or all of the sides, recognizing the input document image as a table, pure text, a flowchart, or none of them.

2 more elements

Dependencies are inferred from the claim text.