Document Layout Analysis

From Wikipedia, the free encyclopedia

Document Layout Analysis is the process of identifying and categorizing the regions of interest in a document image. This is often performed before an image of text can be sent to an OCR engine. Typically a document is split up into "zones", which contain only one type of content (e.g. a column of text).

This process is similar to edge detection for images, though layout analysis must deal with many situations that are specific to text. For example, detecting embedded math symbols in a document requires a layout analysis that can differentiate between common letter symbols and common math symbols.

[edit] See also

• Optical character recognition

[edit] External links

• High Performance Document Layout Analysis by Thomas M. Breuel,at PARC, Palo Alto, CA, USA
• Geometric Layout Analysis Techniques for Document Image Understanding: a Review, ITC-irst Technical Report TR#9703-09