Work

Cooperative text and line-art extraction from a topographic map

Year: 1999

Type: conference-paper

Abstract: The black layer is digitized from a USGS topographic map digitized at 1000 dpi. The connected components of this layer are analyzed and separated into line art, text, and icons in two passes. The paired street casings are converted to polylines by vectorization and associated with street labels from the character recognition phase. The accuracy of character recognition is shown to improve by taking account of the frequently occurring overlap of line art with street labels. The experiments show that complete vectorization of the black line-layer bitmap is the major remaining problem.

Source: IAPR International Conference on Document Analysis and Recognition (ICDAR)

DOI: 10.1109/icdar.1999.791826

Authors: Luyang Li, G. Nagy, A. Samal, S. Seth, Yihong Xu

Institutions: Rensselaer Polytechnic Institute, University of Nebraska–Lincoln, Hewlett-Packard (United States)

Language: English

Topic: Handwritten Text Recognition Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2160215696

FWCI: 1.187

Cites: 11

Cited by: 22

Related to: 10