• Home
  • Search
  • Improving optical character recognition through efficient multiple system alignment
  • Cite Icon30
  • https://doi.org/10.1145/1555400.1555437Copy DOI Icon

Improving optical character recognition through efficient multiple system alignment

  • Jun 15, 2009
  • William B Lund +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Individual optical character recognition (OCR) engines vary in the types of errors they commit in recognizing text, particularly poor quality text. By aligning the output of multiple OCR engines and taking advantage of the differences between them, the error rate based on the aligned lattice of recognized words is significantly lower than the individual OCR word error rates. This lattice error rate constitutes a lower bound among aligned alternatives from the OCR output. Results from a collection of poor quality mid-twentieth century typewritten documents demonstrate an average reduction of 55.0% in the error rate of the lattice of alternatives and a realized word error rate (WER) reduction of 35.8% in a dictionary-based selection process. As an important precursor, an innovative admissible heuristic for the A* algorithm is developed, which results in a significant reduction in state space exploration to identify all optimal alignments of the OCR text output, a necessary step toward the construction of the word hypothesis lattice. On average 0.0079% of the state space is explored to identify all optimal alignments of the documents.

Similar Papers
  • Conference Article
  • Citations3

Okralact - a multi-engine Open Source OCR training system

  • Sep 20, 2019
  • Konstantin Baierer +2
  • Research Article
  • Citations3

Implementation of Tesseract OCR and Bounding Box for Text Extraction on Food Nutrition Labels

  • Dec 03, 2024
  • Building of Informatics, Technology and Science (BITS)
  • The Manuel Eric Saputra +2
  • Conference Article
  • Citations1

<title>Identification and correction of rejection and substitution errors in optical character recognition systems</title>

  • Apr 14, 1993
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Glenn S Himes +2
  • Research Article

IMPROVING THE IMAGE-TO-SPEECH SYSTEM ACCURACY THROUGH INTEGRATION OF OPTICAL CHARACTER RECOGNITION AND LANGUAGE PROCESSING TECHNIQUES

  • Jan 01, 2023
  • INFORMATION TECHNOLOGIES, ELECTRONICS, RADIO ENGINEERING
  • K.H Nikoghosyan +2
  • Conference Article
  • Citations10

Hybrid Approach to Adaptive OCR for Historical Books

  • Sep 01, 2011
  • Vladimir Kluzner +3
  • Conference Article
  • Citations2

On Raster Image Segmentation, Well Log Instance Detection, and Depth Information Extraction from Rasters Using Deep Learning Models

  • Oct 02, 2023
  • O A Gune +2
  • Research Article
  • Citations1

Text detection and recognition through deep learning-based fusion neural network

  • Sep 01, 2023
  • IAES International Journal of Artificial Intelligence (IJ-AI)
  • Sunil Kumar Dasari +1
  • Research Article
  • Citations8

Minimising Biasing Word Errors for Contextual ASR With the Tree-Constrained Pointer Generator

  • Jan 01, 2023
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • Guangzhi Sun +2
  • Research Article
  • Citations3

Methods for text segmentation from scene images

  • Jun 07, 2014
  • ELCVIA Electronic Letters on Computer Vision and Image Analysis
  • Deepak Kumar +1
  • Research Article

Advancement of Khmer Optical Character Recognition (OCR) Accuracy by Using Character Region Awareness (CRAFT) and Transformer-Based Models

  • Dec 01, 2025
  • Insight Cambodia Journal of Basic and Applied Research
  • Bunchhun Chhim +2
  • Research Article
  • Citations7

Balinese character recognition on mobile application based on tesseract open source OCR engine

  • Apr 01, 2020
  • Journal of Physics: Conference Series
  • I M D R Mudiarta +6
  • Research Article
  • Citations1

Mobile Text Reader for People with Low Vision

  • May 28, 2015
  • Jurnal Teknologi
  • Teng Ren Sin +4
  • Conference Article
  • Citations135

Towards Fast and Accurate Streaming End-To-End ASR

  • May 01, 2020
  • Bo Li +6
  • PDF
  • Research Article
  • Citations66

Improving the Accuracy of Tesseract 4.0 OCR Engine Using Convolution-Based Preprocessing

  • May 02, 2020
  • Symmetry
  • Dan Sporici +2
  • Conference Article
  • Citations30

Improved acoustic modeling for continuous speech recognition

  • Jan 01, 1990
  • C.-H Lee +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.