A knowledge-based approach to deriving logical structure from document images
Debashish Niyogi · 1995
An important application of artificial intelligence is knowledge-based document image understanding, specifically the analysis of document images to identify and logically classify objects in an image. The object classification problem is particularly interesting in the domain of document images, where the problem becomes that of segmenting the different regions, or blocks, of printed matter using standard image processing techniques, and then using spatial domain knowledge to first classify these blocks (e.g., text paragraphs, photographs, etc.), then group these blocks into logical units (e.g., newspaper stories, magazine articles, etc.), and finally determine the reading order of the text blocks within each logical unit. This essentially translates to the problem of converting the physical structure of the document into its logical structure with the use of domain knowledge about document layout. The objective of this work is to develop a computational model for the derivation of th...