Xerox Palo Alto Research

Researchers at the Fuji Xerox Palo Alto Laboratory (FXPAL) recently demonstrated the Seamless Documents project, mobile phone technology that can store a scanned document in a database and analyze its structure and content. The analysis is used to identify sections and paragraphs to automatically extract key phrases that summarize sections, enabling users to jump to a section labeled with a key word, or skip to the last paragraph on a page, when reading the document on a mobile phone. The software also automatically resizes images, section headers, and plain text when a user is scrolling through the document. The first part of the Seamless Documents project focuses on converting analog documents into digital information that can be stored in a database and accessed using the Internet and cell-phone networks. FXPAL software analyzes the document's structure to find paragraph breaks, pictures, and section titles. The software then automatically summarizes text and chooses key words and concepts from each section to highlight for the user. The second part of the project involves software that runs on mobile phones. The software opens the document and displays extracted information. The user can see a view of the document with key phrases in a large font, overlaid on top of paragraphs and segments.