Opaque document imaging: Building images of inaccessible texts

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

29 Scopus citations

Abstract

This paper introduces a method for building a readable image of an opaque, rolled or folded text from a volumetric, penetrating scan. The problem is framed by localizing, constructing, and manipulating an image induced by a surface embedded in a 3D voxel space. There are two central contributions that lead to the demonstrated results. First is an energy-based texture formation algorithm, which is a function of voxel intensities and the geometry of the embedded surface. Second is a regularization algorithm based on a constrained mapping of the embedded surface to a regularized image plane. The mapping preserves angles and lengths, which minimizes the distortion of text in the image. The experimental results show readable images derived from custom, high resolution (X-ray-based) CT scans of rolled papyrus and ink samples. These methods are significant for scholars seeking to study inaccessible texts, and may lead to viable techniques for scanning everyday opaque objects (books) without opening them.

Original languageEnglish
Title of host publicationProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Pages662-669
Number of pages8
StatePublished - 2005
EventProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, China
Duration: Oct 17 2005Oct 20 2005

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
VolumeI

Conference

ConferenceProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Country/TerritoryChina
CityBeijing
Period10/17/0510/20/05

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Opaque document imaging: Building images of inaccessible texts'. Together they form a unique fingerprint.

Cite this