Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electronic and Information Engineering | en_US |
| dc.creator | Gao, Miao | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/3928 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Techniques for document layout analysis | en_US |
| dcterms.abstract | Document Layout Analysis (DLA) is the first step of document image understanding (DIU). DLA determines how the page is segmented and outputted in the reading order to the Optical Character Recognition (OCR) system for recognition. The false segmentation of a layout structure will lead to unacceptable document image understanding. In this study, a broadly speaking parameter-free approach for DLA is presented, which is based on a split-and-merge algorithm. The algorithm performs the segmentation in two steps: firstly, it divides up the image by an over-segmentation X-Y cut process. This step is to cut the page into blocks, generally blocks of two kinds: the proper segmented blocks and the over-segmented blocks; secondly, it selects the blocks that are more likely to be proper segmented ones by their sizes, usually the larger ones. The selected blocks will be recognized as pivots and then inputted to the maximal whitespace rectangle algorithm, which serves as a merging step. The final whitespaces derived are delimiters of the page segments. Experimental results on several images with different sizes, dpi's and layout structures have shown that our proposed method is insensitive to the parameters set and can produce high-quality results. | en_US |
| dcterms.extent | 76 leaves : ill. ; 30 cm. | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2009 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations. | en_US |
| dcterms.LCSH | Optical character recognition devices. | en_US |
| dcterms.LCSH | Optical pattern recognition. | en_US |
| dcterms.LCSH | Document imaging systems. | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b23218101.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 8.43 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/3928