Hewlett-Packard Development Company, L.p.

Jose Abad Peiro

Paolo Faraboschi

Sherif Yacoub

Daniel Ortega

Jordi Arnabat Benedicto

Luca Chiarabini

Petar Obradovic

Ignacio Ruiz De Conejo

Yacoub Sherif

Example methods for finding a text reading order in a document are described in which text zones are determined, the text zones are clustered using semantic measure and correlation and a reading order is found within each of the clusters.

Method for finding text reading order in a document

An automated document processing system is configured to normalize zones obtained from a document, and to extract articles from the normalized zones. In one configuration, the system receives at least one zone from the document, and applies at least one zone-breaking factor, thereby creating normalized sub-zones within which text lines are consistent with the at least one zone-breaking factor. The normalized sub-zones may be evaluated to obtain a reading order. Adjacent sub-zones are joined if text similarity exceeds a threshold value. Weakly joined sub-zones are separated where indicated by a topic vectors analysis of the weakly joined sub-zones.

Automated document processing system

A system for generating digital swatch books, comprising a simulation component for generating, based on a set of standard reference colors and based on at least one reproduction system profile representing a reproduction system's color reproduction characteristics, digital swatch book information representing a simulated set of reference colors associated with the original set of reference colors, as reproduced by the reproduction system; the system further comprising a portable document format generation component for generating, from said digital swatch book information, a multi-layer portable document format file comprising a first layer encoding first swatch book output information for viewing the digital swatch book on a display device, and a second layer encoding second swatch book output information for printing the digital swatch book on a printing device.

Digital swatch book

The analysis of graphic design material is discussed, and a system and adaptive method to automatically analyze graphic design material are disclosed. Aspects to be measured within a document containing the graphic design material are determined. Measurements of these aspects are performed. Output is prepared, wherein the output comprises an image of a page within the document and a view of measured aspects associated with the page, wherein the view is selected from among a group of views including a semantic view, a cluster view, a graphical view, or a poster view.

Analysis of graphic design material

A system and method of operation is configured to produce a PPML template from a PDF document. In one implementation, the system opens the PDF document and converts PDF elements within the PDF document into variable objects. A macro is generated, which contains rules governing use and reuse of the variable objects. The PPML template generated as final result is configured to include a definition of the variable objects, the macro and a version of the original PDF document, wherein at least portions of the PDF document are configured as a background element within the PPML document.

Growing community of inventors

Barcelona, Spain

Jose Abad Peiro