Detection and reconstruction of east asian layout features in a fixed format document

• US 9,330,070 B2
• Filed: 03/11/2013
• Issued: 05/03/2016
• Est. Priority Date: 03/11/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Zaric, Drazen, Sesum, Milan, Lazarevic, Milos, Raskovic, Milos
• Primary Examiner(s): Reinier, Barbara
• Application Number:
  US13/794,541
• Publication Number:
  US 20140257789A1
• Time in Patent Office: 1,149 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 40/106 Display of layout of documents; Previewing
• CPC Class Codes: G06F 40/109 Font handling; Temporal or kinetic typography
• CPC Class Codes: G06F 40/129 Handling non-Latin characters, e.g. kana-to-kanji conversion
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

Detection of East Asian layout features and reconstruction of East Asian layout features is provided. Vertically written text in the fixed format document is detected and rotated for layout analysis. After layout analysis, the rotated text is rotated back and restructured in a flow format document. When a plurality of characters is written horizontally in a vertical line of text, vertically overlapping text runs are detected, designated as horizontal-in-vertical text, and are restructured as horizontal-in-vertical text in a flow format document. Lines of text are analyzed for attributes of a ruby line and are designated as ruby text, associated with corresponding text in a ruby base line, and restructured as ruby text in a flow format document. Text in a fixed format document is analyzed for detection of a particular East Asian language so that a font for the language is designated in a flow format document.

Claims

1. A method for detecting Chinese, Japanese, or Korean text in a fixed format document, method comprising:

receiving a fixed format document, the fixed document comprising one or more text runs on one or more pages;

analyzing the one or more text runs on a page for finding at least one Chinese, Japanese, or Korean character;

if at least one Chinese, Japanese, or Korean character is found on the page, analyzing the one or more text runs on the page for determining a text direction for the page, comprising;

analyzing the one or more text runs in a horizontal line and in a vertical line;

for each text run, determining if the text run fits a horizontal or a vertical sequence of text runs;

counting a number of characters in each horizontal text run and each vertical text run; and

if more characters are in the vertical text runs than in the horizontal text runs, determining the page comprises vertical text;

if the page comprises vertical text, rotating the page 90°

counterclockwise for layout analysis for reconstruction in a flow format document; and

reconstructing the fixed format document to a flow format document.

2. The method of claim 1, further comprising:

after rotating the vertical text 90°

counterclockwise, translating the vertical text down along a vertical axis by page width.

3. The method of claim 1, further comprising:

after layout analysis is performed, translating the previously rotated text runs up along a vertical axis by page height, and rotating the previously rotated text runs 90°

clockwise.

4. The method of claim 1, wherein analyzing the one or more text runs on a page for finding at least one Chinese, Japanese, or Korean character comprises determining if at least one character in the one or more text runs is a Unicode range for Chinese, Japanese, or Korean characters.

5. The method of claim 1, further comprising:

prior to analyzing the one or more text runs on a page for finding at least one Chinese, Japanese, or Korean character, separating a header or footer from a document body, the document body comprising the one or more text runs.

6. The method of claim 1, further comprising restructuring the vertical text as flow format vertical text in a flow format document.

7. The method of claim 1, further comprising:

analyzing the one or more text runs on a page for finding one or more text runs with vertical overlap;

if a text run has a vertical overlap with another text run, assigning the vertically overlapping text runs to a bucket;

if a text run does not have a vertical overlap with another text run, assigning the text runs to separate buckets;

analyzing buckets for finding multiple text runs; and

if a bucket comprises multiple text runs, designating the multiple text runs as horizontal-in-vertical text.

8. The method of claim 7, further comprising:

determining if one or more text runs comprise glyphs with vertical overlap; and

if one or more text runs comprise glyphs with vertical overlap, designating the one or more text runs as horizontal-in-vertical text.

9. The method of claim 7, further comprising reconstructing the horizontal-in-vertical text as flow format horizontal-in-vertical text in a flow format document.

10. A method for detecting Chinese, Japanese, or Korean text in a fixed format document, the method comprising:

receiving a fixed format document, the fixed document comprising one or more text runs on one or more pages;

analyzing the one or more text runs on a page for finding at least one Chinese, Japanese, or Korean character, wherein prior to analyzing the one or more text runs on a page for finding at least one Chinese, Japanese, or Korean character, separating a header or footer from a document body, the document body comprising the one or more text runs;

if at least one Chinese, Japanese, or Korean character is found on the page, analyzing the one or more text runs on the page for determining a text direction for the page;

if the page comprises vertical text, rotating the page 90°

counterclockwise for layout analysis for reconstruction in a flow format document; and

reconstructing the fixed format document to a flow format document.

11. The method of claim 10, further comprising:

after rotating the vertical text 90°

counterclockwise, translating the vertical text down along a vertical axis by page width.

12. The method of claim 10, further comprising:

after layout analysis is performed, translating the previously rotated text runs up along a vertical axis by page height, and rotating the previously rotated text runs 90°

clockwise.

13. The method of claim 10, further comprising restructuring the vertical text as flow format vertical text in a flow format document.

14. A method for detecting Chinese, Japanese, or Korean text in a fixed format document, the method comprising:

receiving a fixed format document, the fixed document comprising one or more text runs on one or more pages;

analyzing the one or more text runs on a page for finding at least one Chinese, Japanese, or Korean character;

if at least one Chinese, Japanese, or Korean character is found on the page, analyzing the one or more text runs on the page for determining a text direction for the page; and

if the page comprises vertical text, rotating the page 90°

counterclockwise for layout analysis for reconstruction in a flow format document;

after layout analysis is performed, translating the previously rotated text runs up along a vertical axis by page height, and rotating the previously rotated text runs 90°

clockwise; and

reconstructing the fixed format document to a flow format document.

15. The method of claim 14, further comprising:

after rotating the vertical text 90°

counterclockwise, translating the vertical text down along a vertical axis by page width.

16. The method of claim 14, wherein analyzing the one or more text runs on a page for finding at least one Chinese, Japanese, or Korean character comprises determining if at least one character in the one or more text runs is a Unicode range for Chinese, Japanese, or Korean characters.

17. The method of claim 14, further comprising restructuring the vertical text as flow format vertical text in a flow format document.

18. The method of claim 14, further comprising:

analyzing the one or more text runs on a page for finding one or more text runs with vertical overlap;

if a text run has a vertical overlap with another text run, assigning the vertically overlapping text runs to a bucket;

if a text run does not have a vertical overlap with another text run, assigning the text runs to separate buckets;

analyzing buckets for finding multiple text runs; and

if a bucket comprises multiple text runs, designating the multiple text runs as horizontal-in-vertical text.

19. The method of claim 17, further comprising:

determining if one or more text runs comprise glyphs with vertical overlap; and

if one or more text runs comprise glyphs with vertical overlap, designating the one or more text runs as horizontal-in-vertical text.

20. The method of claim 17, further comprising reconstructing the horizontal-in-vertical text as flow format horizontal-in-vertical text in a flow format document.