Research by Jim Samuel et al. “Customized AI Readers: An Adaptive Framework for Flexible Human Handwriting Recognition of Numerical Digits with OCR Methods”

June 16, 2023

Abstract

Advanced artificial intelligence (AI) techniques have led to significant developments in optical character recognition (OCR) technologies. OCR applications, using AI techniques for transforming images of typed text, handwritten text, or other forms of text into machine-encoded text, provide a fair degree of accuracy for general text. However, even after decades of intensive research, creating OCR with human-like abilities has remained evasive. One of the challenges has been that OCR models trained on general text do not perform well on localized or personalized handwritten text due to differences in the writing style of alphabets and digits. This study aims to discuss the steps needed to create an adaptive framework for OCR models, with the intent of exploring a reasonable method to customize an OCR solution for a unique dataset of English language numerical digits were developed for this study. We develop a digit recognizer by training our model on the MNIST dataset with a convolutional neural network and contrast it with multiple models trained on combinations of the MNIST and custom digits. Using our methods, we observed results comparable with the baseline and provided recommendations for improving OCR accuracy for localized or personalized handwritten text. This study also provides an alternative perspective to generating data using conventional methods, which can serve as a gold standard for custom data augmentation to help address the challenges of scarce data and data imbalance.

Keywords

OCR; adaptive; custom; digits; MNIST; informatics; machine learning; deep learning

Citation

Jain, P.H.; Kumar, V.; Samuel, J.; Singh, S.; Mannepalli, A.; Anderson, R. Customized AI Readers: An Adaptive Framework for Flexible Human Handwriting Recognition of Numerical Digits with OCR Methods. Information202314, 305. https://doi.org/10.3390/info14060305

Recent Posts

Heldrich Center Releases New Work Trends Brief and Website

The Heldrich Center for Workforce Development is pleased to announce the availability of two new research products resulting from its long-running public opinion polling series, Work Trends. To better understand the public’s attitudes about work, employers, and the...

NJSPL Report: Analyzing the Use and Equity of ARPA Funds

Report Release: Analyzing the Use and Equity of ARPA Funds in NJ Local Governments and Beyond New Jersey State Policy Lab The American Rescue Plan Act’s Coronavirus State and Local Fiscal Recovery Funds (ARPA-SLFRF) represent a historic $350 billion investment to...

Dr. Grafova Presented Posters from the VSR Research

Dr. Irina Grafova recently returned from the AcademyHealth Research Meeting in Minneapolis, where she had the opportunity to present two posters from the Virtual Schwartz Rounds emotional support program for nurses, run by the New Jersey Nursing Emotional Well-being...

Heldrich Report: Analysis of NJ Life Sciences, Tech Sectors

The Heldrich Center, in conjunction with the New Jersey Economic Development Authority (NJEDA), is pleased to share a new workforce analysis of the life sciences and technology sectors in New Jersey, with a particular emphasis on the sectors’ intersection with...

Restrepo-Mieth Researches Tree Inventories in Galápagos, Ecuador

Who wants a tree inventory and why? The politics of inventorying urban forestry in Galápagos, Ecuador Abstract Trees make significant contributions to the urban experience by providing ecosystem services and aesthetic value. Considering these contributions, cities are...