Segmentation-based hybrid compression scheme for scanned documents
First Claim
1. A method for compressing digital data, comprising the steps of:
- generating an edge-map representation from an input representation; and
applying a color test to the input representation based on it and the edge-map representation to determine the type of content contained in the input representation, then if the input representation contains only text, only line drawing, or only text and line drawing, applying a first photo compression algorithm to the input representation to compress it, or if the input representation contains at least one of a photo or image and at least one of text or line drawing, (i) applying a segmentation operation to the input representation based on it and the edge-map representation to separate a background portion from a foreground portion of the input representation, the foreground portion containing at least one of a text or a line drawing region, (ii) applying a bi-level compression algorithm to a mask of each text and line drawing region in the foreground portion, and (iii) applying a second photo compression algorithm to the background portion.
2 Assignments
0 Petitions
Accused Products
Abstract
A hybrid compression scheme in which one or more compression schemes are applied to a scanned document depending on its content. Based on the scanned document data itself and edge-map version thereof, a color test is performed to determine if the document is text or a drawing. If only a few colors are detected, the entire document is compressed by a photo compression technique at full resolution. If more than a few colors are present, the document is most likely a mixed mode document, in which case the entire document undergoes segmentation, a process in which text and drawing regions are separated from the background. The mask of the text and/or drawing regions are coded by a bi-level compression technique, whereas background is down-sampled, if necessary, and then compressed by a photo compression technique. A wrapper module is used to wrap the compressed stream(s) into a single file for easy browsing or transmitting.
178 Citations
16 Claims
-
1. A method for compressing digital data, comprising the steps of:
-
generating an edge-map representation from an input representation; and
applying a color test to the input representation based on it and the edge-map representation to determine the type of content contained in the input representation, then if the input representation contains only text, only line drawing, or only text and line drawing, applying a first photo compression algorithm to the input representation to compress it, or if the input representation contains at least one of a photo or image and at least one of text or line drawing, (i) applying a segmentation operation to the input representation based on it and the edge-map representation to separate a background portion from a foreground portion of the input representation, the foreground portion containing at least one of a text or a line drawing region, (ii) applying a bi-level compression algorithm to a mask of each text and line drawing region in the foreground portion, and (iii) applying a second photo compression algorithm to the background portion. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. An apparatus for compressing digital data, comprising:
-
an edge detector configured to generate an edge-map representation from an input representation;
color test module configured to apply a color test to the input representation based on it and the edge-map representation to determine the type of content contained in the input representation;
a first photo compression module configured to apply a first photo compression algorithm to the input representation to compress it, if the input representation contains only text, only line drawing, or only text and line drawing;
a segmentation module configured to apply a segmentation operation to the input representation to separate a background portion from a foreground portion of the input representation, the foreground portion containing at least one of a text or a line drawing region, if the input representation contains at least one of a photo or image and at least one of text or line drawing;
a bi-level compression module configured to apply a bi-level compression algorithm to a mask of each text and line drawing region in the foreground portion; and
a second photo compression module configured to apply a second photo compression algorithm to the background portion. - View Dependent Claims (9)
-
-
10. A device-readable medium carrying a program of instructions configured to direct a device to compress digital data, the program of instructions comprising:
-
instructions for generating an edge-map representation from an input representation;
instructions for applying a color test to the input representation based on it and the edge-map representation to determine the type of content contained in the input representation;
instructions for applying a first photo compression algorithm to the input representation to compress it, which are executed if the input representation contains only text, only line drawing, or only text and line drawing; and
instructions for (i) applying a segmentation operation to the input representation based on it and the edge-map representation to separate a background portion from a foreground portion of the input representation, the foreground portion containing at least one of a text or a line drawing region, (ii) applying a bi-level compression algorithm to a mask of each text and line drawing region in the foreground portion, and (iii) applying a second photo compression algorithm to the background portion, which are executed if the input representation contains at least one of a photo or image and at least one of text or line drawing. - View Dependent Claims (11, 12, 13, 14, 15, 16)
-
Specification