Document compression with neighborhood biased pixel labeling

• US 10,133,712 B2
• Filed: 06/15/2016
• Issued: 11/20/2018
• Est. Priority Date: 05/26/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ahmed, Mohamed N.
• Primary Examiner(s): Carter, Aaron W
• Application Number:
  US15/183,032
• Publication Number:
  US 20160350266A1
• Time in Patent Office: 888 Days
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 40/146 Coding or compression of tree-structured data
• CPC Class Codes: G06T 9/20 Contour coding, e.g. using detection of edges
• CPC Class Codes: H04N 19/103 Selection of coding mode or of prediction mode
• CPC Class Codes: H04N 19/14 Coding unit complexity, e.g. amount of activity or edge presence estimation H04N19/146 takes precedence
• CPC Class Codes: H04N 19/176 the region being a block, e.g. a macroblock
• CPC Class Codes: H04N 19/182 the unit being a pixel
• CPC Class Codes: H04N 19/23 with coding of regions that are present throughout a whole video segment, e.g. sprites, background or mosaic
• CPC Class Codes: H04N 19/30 using hierarchical techniques, e.g. scalability H04N19/63 takes precedence

Abstract

To compress a document, a number of edges present in a selected portion of the document are counted to determine whether the number of edges exceeds a threshold. When the number of edges exceeds the threshold, a pixel is selected from the portion and a set of neighboring pixels is identified for the pixel. For each neighboring pixel in a subset of the neighboring pixels, a corresponding label of the neighboring pixel is identified. A mask layer contains labels of pixels in the portion where a label of the selected pixel is biased using labels of neighboring pixels in the subset of the neighboring pixels. The selected pixel is designated to a foreground or a background layer of the document according to the label of the selected pixel. A compressed document is constructed corresponding to the document using the mask layer, the foreground layer, and the background layer.

Claims

1. A computer system for compressing a document, the computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:

program instructions to count a number of edges present in a selected portion of the document;

program instructions to determine whether the number of edges exceeds a threshold number of edges;

program instructions to select, responsive to the number of edges exceeding the threshold number of edges, a pixel from the portion;

program instructions to identify, for the pixel, a set of neighboring pixels;

program instructions to identify, for each neighboring pixel in a subset of the set of neighboring pixels, a corresponding label of the neighboring pixel, wherein a mask layer corresponding to the document contains labels of pixels in the portion;

program instructions to bias, in the mask layer, a label of the selected pixel using labels of neighboring pixels in the subset of the neighboring pixels;

program instructions to designate, according to the label of the selected pixel, the selected pixel to one of a foreground layer corresponding to the document and a background layer corresponding to the document; and

program instructions to construct, corresponding to the document, a compressed document using the mask layer, the foreground layer, and the background layer.

2. The computer system of claim 1, wherein no intervening pixel is present between a neighboring pixel in the set of neighboring pixels and the pixel in the portion.

3. The computer system of claim 1, further comprising:

program instructions to receive the document; and

program instructions to divide the document into a set of blocks, each block in the set being of a specified size, wherein the portion is a block in the set of blocks.

4. The computer system of claim 3, further comprising:

program instructions to form the blocks in the set of blocks such that at least one block in the set of blocks overlaps at least one other block in the set of blocks.

5. The computer system of claim 1, further comprising:

program instructions to determine whether a second portion of the document includes the threshold number of edges; and

program instructions to label, responsive to the second portion not including the threshold number of edges, all pixels in the second portion as belonging in the background layer.

6. The computer system of claim 1, further comprising:

program instructions to detect an edge in the portion by determining whether a transition from a color of a first pixel in the portion to a color of a second pixel is greater than a threshold amount of transition.

7. The computer system of claim 6, further comprising:

program instructions to define a set of threshold amounts of transitions, wherein the threshold amount of transition is a member of the set of threshold amounts of transitions; and

program instructions to use a different threshold amount of transition from the set of threshold amounts of transitions to detect a different type of edge in the portion.

8. The computer system of claim 1, wherein the subset of the set of neighboring pixels is the entire set of neighboring pixels.

9. The computer system of claim 1, wherein a plurality of foreground layers correspond to the document, each foreground layer in the plurality of foreground layer corresponding to a different label value of pixels in the document.

10. The computer system of claim 1, wherein a plurality of background layers correspond to the document, each background layer in the plurality of background layer corresponding to a different label value of pixels in the document.

11. The computer system of claim 1, further comprising:

program instructions to complete constructing the mask layer, the foreground layer, and the background layer; and

program instructions to combine, as a part of constructing, the completed mask layer, the completed foreground layer, and the completed background layer to form the compressed document.

12. The computer system of claim 11, wherein the program instructions to combine uses a Portable Document Format (PDF), and the compressed document is a PDF document.

13. The computer system of claim 1, wherein the program instructions to identify, the program instructions to bias, and the program instructions to designate comprise a Piecewise Homogeneous Labeling (PHL) method, and the PHL method modifies a Fuzzy C-Means method of pixel classification.