• Home
  • Search
  • Embedding Gravitational Search Algorithms in Convolutional Neural Networks for OCR applications
  • Cite Icon24
  • https://doi.org/10.1109/saci.2012.6249989Copy DOI Icon

Embedding Gravitational Search Algorithms in Convolutional Neural Networks for OCR applications

  • May 1, 2012
  • Lucian-Ovidiu Fedorovici +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper presents aspects concerning embedding Gravitational Search Algorithms (GSAs) in Convolutional Neural Networks (CNNs) for Optical Character Recognition (OCR) systems. The GSAs are used in combination with the Back Propagation (BP) algorithm as optimization algorithms in the training process of a specific CNN architecture for OCR applications. The new algorithm consists of applying first the GSA and next the BP in order to ensure performance improvements by avoiding the algorithms' traps in local minima. A performance analysis for a given benchmark application shows the advantages of our algorithm over the classical BP algorithm for a six layer CNN dedicated to OCR applications.

Similar Papers
  • Conference Article
  • Citations17

Evolutionary optimization-based training of convolutional neural networks for OCR applications

  • Oct 01, 2013
  • Lucian-Ovidiu Fedorovici +3
  • Conference Article

Nature-inspired optimization algorithms applied to fuzzy control, fuzzy modeling, mobile robots and optical character recognition

  • May 01, 2014
  • Radu-Emil Precup
  • Book Chapter
  • Citations2

GSA–Based Training of Convolutional Neural Networks for OCR Applications

  • Jan 01, 2012
  • Lucian-Ovidiu Fedorovici +3
  • Conference Article
  • Citations5

Robust pre-processing techniques for OCR applications on mobile devices

  • Jan 01, 2009
  • Loh Zhi Chang +1
  • Book Chapter
  • Citations7

A Hybrid Gravitational Search Algorithm and Back-Propagation for Training Feedforward Neural Networks

  • Jan 01, 2015
  • Quang Hung Do
  • PDF
  • Research Article
  • Citations38

Memetic algorithms for training feedforward neural networks: an approach based on gravitational search algorithm

  • Jul 06, 2020
  • Neural Computing and Applications
  • Ricardo García-Ródenas +2
  • Research Article
  • Citations32

ModPSO-CNN: an evolutionary convolution neural network with application to visual recognition

  • Sep 04, 2020
  • Soft Computing
  • Shanshan Tu +6
  • Conference Article
  • Citations19

A Generic OCR Using Deep Siamese Convolution Neural Networks

  • Nov 01, 2018
  • Ghada Sokar +2
  • Conference Article
  • Citations3

End-to-end system for printed Amazigh script recognition in document images

  • May 01, 2017
  • Nabil Aharrane +3
  • Conference Article
  • Citations8

Developing Automated Optical Character Recognition System Using Machine Learning Algorithm to Solve Payment Verification Issues

  • Oct 25, 2021
  • Michael Siek +1
  • PDF
  • Research Article
  • Citations35

A Finger-Worn Device for Exploring Chinese Printed Text With Using CNN Algorithm on a Micro IoT Processor

  • Jan 01, 2019
  • IEEE Access
  • Yu-Sheng Su +3
  • Conference Article
  • Citations1

Pre-processing for Improving the Recognition of Mobile based Gurmukhi Text Recognition System

  • Jul 06, 2021
  • Ravneet Kaur +1
  • PDF
  • Research Article
  • Citations33

Artificially Intelligent Readers: An Adaptive Framework for Original Handwritten Numerical Digits Recognition with OCR Methods

  • May 26, 2023
  • Information
  • Parth Hasmukh Jain +5
  • Book Chapter
  • Citations8

Soft Computing Techniques for Optical Character Recognition Systems

  • Dec 24, 2016
  • Arindam Chaudhuri +3
  • Book Chapter
  • Citations5

JPEG for Arabic Handwritten Character Recognition: Add a Dimension of Application

  • Oct 01, 2008
  • Abdurazzag Ali +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.