Automatic Text Detection and Tracking in Digital Video

Abstract

Text which either appears in a scene or is graphically added to video can provide an important supplemental source of index information as well as clues for decoding the video's structure and for classification. In this paper we present algorithms for detecting and tracking text components that appear within digital video frames. Our system implements a scale-space feature extractor that feeds an artificial neural processor to extract textual regions and track their movement over time. The extracted regions can then be used as input to an appropriate Optical character Recognition system which produces indexible keywords.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1998
Accession Number
ADA458675

Entities

People

  • David S. Doermann
  • Huiping Li
  • Omid Kia

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Automatic
  • Character Recognition
  • Decoding
  • Detection
  • Digital Video
  • Feature Extraction
  • Information Operations
  • Language
  • Media
  • Neural Networks
  • Optical Character Recognition
  • Recognition
  • Universities
  • Video
  • Video Frames

Readers

  • Computational Linguistics
  • Computer Vision.

Technology Areas

  • Space
  • Space - Space Objects