US 8,788,930 B2Granted

Automatic identification of fields and labels in forms

AssigneeRicoh Company, Ltd.

InventorJohn W. Barrus

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system and method for processing form images including strokes. A controller receives a plurality of form images including a plurality of strokes. A stroke identification module identifies the position of each stroke in each of the form images. A geometry engine generates an overlay of the plurality of form images and identifies a group of overlapping strokes from the overlay. The geometry engine generates a field bounding box encompassing the group of strokes, the field bounding box representing a field in the plurality of form images. The geometry engine crops a field image from each form image based on the size and position of the field bounding box. A label detector analyzes an area around the field image in the form image to determine a label and generates a label image.

Claims20

Dependent claims

A computer-implemented method for identifying a field in each of a plurality of form images, the method comprising:

receiving, at one or more processors, the plurality of form images, each form image including a plurality of strokes;
generating, with the one or more processors, a stroke bounding box for each set of strokes identified in the plurality of form images based on a distance between strokes being within a threshold, each stroke bounding box encompassing a corresponding set of strokes and having associated size and position information;
generating, with the one or more processors, an overlay of the plurality of form images;
identifying, with the one or more processors, a group of overlapping strokes from the overlay of the plurality of form images by identifying sets of strokes that overlap each other in the overlay based on stroke bounding box size and position information;
generating a field bounding box based on an average size and position of stroke bounding boxes associated with the group of overlapping strokes, the field bounding box representing the field in each of the plurality of form images;
and
generating a plurality of field images from the plurality of form images based on the field bounding box.

4 more elements

A system for identifying a field in each of a plurality of form images, the system comprising:

one or more processors;
a stroke identification module stored on a memory and executable by the one or more processors, the stroke identification module for receiving the plurality of form images, each form image including a plurality of strokes, and generating a stroke bounding box for each set of strokes identified in the plurality of form images based on a distance between strokes being within a threshold, each stroke bounding box encompassing a corresponding set of strokes and having associated size and position information;
a geometry engine coupled to the stroke identification module, the geometry engine for generating an overlay of the plurality of form images, identifying a group of overlapping strokes from the overlay of the plurality of form images by identifying sets of strokes that overlap each other in the overlay based on stroke bounding box size and position information, generating a field bounding box based on an average size and position of stroke bounding boxes associated with the group of overlapping strokes, the field bounding box representing the field in each of the plurality of form images and generating a plurality of field images from the plurality of form images based on the field bounding box.

A computer program product comprising a non-transitory computer useable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

receive a plurality of form images, each form image including a plurality of strokes;
generate a stroke bounding box for each set of strokes identified in the plurality of form images based on a distance between strokes being within a threshold, each stroke bounding box encompassing a corresponding set of strokes and having associated size and position information;
generate an overlay of the plurality of form images;
identify a group of overlapping strokes from the overlay of the plurality of form images by identifying sets of strokes that overlap each other in the overlay based on stroke bounding box size and position information;
generate a field bounding box based on an average size and position of stroke bounding boxes associated with the group of overlapping strokes, the field bounding box representing a field in each of the plurality of form images;
and
generate a plurality of field images from the plurality of form images based on the field bounding box.

4 more elements

Dependencies are inferred from the claim text.