Color and Layout-Based Identification of Documents Captured from Handheld Devices.

Ardhendu Behera, Denis Lalanne, Rolf Ingold

Research output: Contribution to conferencePaper

Abstract

This paper proposes a method, combining color and layout features, for identifying documents captured from low-resolution handheld devices. On one hand, the document image color density surface is estimated and represented with an equivalent ellipse and on the other hand, the document shallow layout structure is computed and hierarchically represented. Our identification method first uses the color information in the documents in order to focus the search space on documents having a similar color distribution, and finally selects the document having the most similar layout structure in the remaining of the search space.
Original languageEnglish
Pages51-54
Publication statusPublished - 2007
EventInternational Conference on Pattern Recognition and Computer Vision - Istanbul, Turkey
Duration: 25 Feb 200527 Feb 2005

Conference

ConferenceInternational Conference on Pattern Recognition and Computer Vision
CountryTurkey
CityIstanbul
Period25/02/0527/02/05

Fingerprint Dive into the research topics of 'Color and Layout-Based Identification of Documents Captured from Handheld Devices.'. Together they form a unique fingerprint.

Cite this