Tag-assisted Sentence Confabulation for Intelligent Text Recognition

Abstract

Autonomous and intelligent recognition of printed or hand-written text image is one of the key features to achieve situational awareness. A neuromorphic model based intelligent text recognition (ITR) system has been developed in our previous work, which recognizes texts based on word level and sentence level context represented by statistical information of characters and words. While quite effective, sometimes the existing ITR system still generates results that are grammatically incorrect because it ignores semantic and syntactic properties of sentences. In this work, we improve the accuracy of the existing ITR system by incorporating parts-of- speech tagging into the text recognition procedure. Our experimental results show that the tag-assisted text recognition improves sentence level success rate by 33% in average.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2012
Accession Number
ADA633691

Entities

People

  • Fan Yang
  • Morgan Bishop
  • Qing Wu
  • Qinru Qiu

Organizations

  • Syracuse University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Accuracy
  • Air Force Research Laboratories
  • Artificial Intelligence
  • Character Recognition
  • Cognition
  • Computer Science
  • Electrical Engineering
  • Feature Extraction
  • Models
  • Natural Language Processing
  • Neural Networks
  • Pattern Recognition
  • Personality
  • Probabilistic Models
  • Probability
  • Recognition
  • Situational Awareness

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Neural Network Machine Learning.