• español
    • English
    • Deutsch
  • English 
    • español
    • English
    • Deutsch
  • Login
View Item 
  •   PRCR Home
  • Polytechnic University of Puerto Rico
  • Design Project Articles Master Degree
  • Computer Engineering
  • View Item
  •   PRCR Home
  • Polytechnic University of Puerto Rico
  • Design Project Articles Master Degree
  • Computer Engineering
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Streak2O: Data Augmentation for Handwritten Text Recognition in Neural Networks

Thumbnail
View/Open
PUPR_SP21_MCpE_Eduardo J. Beltran Feliciano_Article (443.4Kb)
PUPR_SP21_MCpE_Eduardo J. Beltran Feliciano_Poster (1.011Mb)
Date
2021
Author
Beltran Feliciano, Eduardo J.
Metadata
Show full item record
Abstract
Streak2O is a machine learning data augmentation algorithm based on the combination of two other independent algorithms: Streak and Droplet. These three augmentations are implemented as non-trainable TensorFlow custom Keras layers to optimize execution time in a GPU based environment. They generate configurable random artifacts that imitate real life handwritten historical document or manuscript water damage and document mishandling. Testing this augmentation algorithm with small subsets of the NIST-SD19 dataset on a convolutional neural network architecture shows that they can help reduce neural network overfitting falling partially into the category of synthetic data generation. Key Terms ⎯ Handwritten Text Recognition, Machine Learning, Synthetic Data Augmentation, TensorFlow.
URI
http://hdl.handle.net/20.500.12475/1128
Collections
  • Computer Engineering

PRC Repository copyright © 2022  COBIMET, Inc.
Contact Us
Theme by 
Atmire NV
 

 

Browse

All of PRCRCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

LoginRegister

Statistics

View Usage Statistics

PRC Repository copyright © 2022  COBIMET, Inc.
Contact Us
Theme by 
Atmire NV