Segmental Rescoring in Text Recognition

Abstract

A method for text recognition includes generating a number of text hypotheses for an image, for example, using an HMM based approach using fixed-width analysis features. For each text hypothesis, one or more segmentations are generated and scored at the segmental level, for example, according to character or character group segments of the text hypothesis. In some embodiments, multiple alternative segmentations are considered for each text hypothesis. In some examples, scores determined in generating the text hypothesis and the segmental score are combined to select an overall text recognition of the image.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 04, 2014
Accession Number
ADA597567

Entities

People

  • Krishnakumar Subramanian
  • Premkumar Natarajan
  • Richard Schwartz
  • Rohit Prasad

Organizations

  • RTX

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Character Recognition
  • Computer Programming
  • Computer Programs
  • Computer Vision
  • Computers
  • Feature Extraction
  • Hidden Markov Models
  • Instructions
  • Local Area Networks
  • Machine Learning
  • Memory Devices
  • Neural Networks
  • Pattern Recognition
  • Probability
  • Recognition
  • Supervised Machine Learning

Readers

  • Computational Linguistics
  • Regression Analysis.
  • Speech Processing/Speech Recognition.