• Home
  • Search
  • OCR enhancement through neighbor embedding and fast approximate nearest neighbors
  • https://doi.org/10.1117/12.928865Copy DOI Icon

OCR enhancement through neighbor embedding and fast approximate nearest neighbors

  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Generic optical character recognition (OCR) engines often perform very poorly in transcribing scanned low resolution (LR) text documents. To improve OCR performance, we apply the Neighbor Embedding (NE) single-image super-resolution (SISR) technique to LR scanned text documents to obtain high resolution (HR) versions, which we subsequently process with OCR. For comparison, we repeat this procedure using bicubic interpolation (BI). We demonstrate that mean-square errors (MSE) in NE HR estimates do not increase substantially when NE is trained in one Latin font style and tested in another, provided both styles belong to the same font category (serif or sans serif). This is very important in practice, since for each font size, the number of training sets required for each category may be reduced from dozens to just one. We also incorporate randomized k -d trees into our NE implementation to perform approximate nearest neighbor search, and obtain a 1000x speed up of our original NE implementation, with negligible MSE degradation. This acceleration also made it practical to combine all of our size-specific NE Latin models into a single Universal Latin Model (ULM). The ULM eliminates the need to determine the unknown font category and size of an input LR text document and match it to an appropriate model, a very challenging task, since the dpi (pixels per inch) of the input LR image is generally unknown. Our experiments show that OCR character error rates (CER) were over 90% when we applied the Tesseract OCR engine to LR text documents (scanned at 75 dpi and 100 dpi) in the 6-10 pt range. By contrast, using k -d trees and the ULM, CER after NE preprocessing averaged less than 7% at 3x (100 dpi LR scanning) and 4x (75 dpi LR scanning) magnification, over an order of magnitude improvement. Moreover, CER after NE preprocessing was more that 6 times lower on average than after BI preprocessing.

Similar Papers
  • PDF
  • Research Article
  • Citations7

An OCR Engine for Printed Receipt Images using Deep Learning Techniques

  • Jan 01, 2023
  • International Journal of Advanced Computer Science and Applications
  • Cagri Sayallar +2
  • Research Article
  • Citations7

Applicability of OCR Engines for Text Recognition in Vehicle Number Plates, Receipts and Handwriting

  • Dec 01, 2023
  • Journal of Circuits, Systems and Computers
  • Utsav Poudel +3
  • Conference Article
  • Citations1

Benchmarking commercial OCR engines for technical drawings indexing

  • Sep 10, 2001
  • J.C Lecoq +3
  • Research Article

Benchmarking open-source OCR engines on semantic slide regions in educational videos using a subset of FITVID dataset

  • Jan 01, 2025
  • i-manager’s Journal on Future Engineering and Technology
  • E Purushotham +2
  • Conference Article
  • Citations24

A Study on the Accuracy of OCR Engines for Source Code Transcription from Programming Screencasts

  • Jun 29, 2020
  • Abdulkarim Malkadi +2
  • PDF
  • Research Article
  • Citations73

Optical character recognition with neural networks and post-correction with finite state methods

  • Aug 20, 2020
  • International Journal on Document Analysis and Recognition (IJDAR)
  • Senka Drobac +1
  • Conference Article
  • Citations1

Coupled-layer neighbor embedding for surveillance face hallucination

  • Sep 01, 2013
  • Junjun Jiang +5
  • PDF
  • Research Article
  • Citations8

Optimizing OCR Performance for Programming Videos: The Role of Image Super-Resolution and Large Language Models

  • Mar 30, 2024
  • Mathematics
  • Mohammad D Alahmadi +1
  • PDF
  • Research Article

A hybrid approach to Bangla handwritten OCR: combining YOLO and an advanced CNN

  • Jun 21, 2025
  • Discover Artificial Intelligence
  • Aye T Maung +2
  • Research Article
  • Citations7

Enhanced portable text to speech converter for visually impaired

  • Jan 01, 2018
  • International Journal of Intelligent Systems Technologies and Applications
  • Chithra Selvaraj +1
  • Research Article
  • Citations101

Facial Image Hallucination Through Coupled-Layer Neighbor Embedding

  • Sep 01, 2016
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Junjun Jiang +4
  • Research Article
  • Citations10

Face super resolution based on parent patch prior for VLQ scenarios

  • May 25, 2016
  • Multimedia Tools and Applications
  • Liang Chen +4
  • Conference Article
  • Citations3

3D Rendering Framework for Data Augmentation in Optical Character Recognition : (Invited Paper)

  • Jul 15, 2021
  • Andreas Spruck +5
  • Research Article
  • Citations1

An Intelligent Semi-Automatic Workflow for Optical Character Recognition of Historical Printings

  • Apr 01, 2021
  • Christian Reul
  • Conference Article
  • Citations54

A hierarchical, HMM-based automatic evaluation of OCR accuracy for a digital library of books

  • Jun 11, 2006
  • Shaolei Feng +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.