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


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.


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


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.

Recent Posts

Nikpour Receives Office of Disability Services Award

Professor Fereydoun Nikpour was selected for the Office of Disability Services Faculty Honor Roll. The Faculty Honor Roll is a new initiative to recognize instructors who go above and beyond to support the work of the Office of Disability Services (ODS). ODS staff...

Heldrich Report: NJ’s Energy-Efficiency Workforce Needs

New Jersey's Energy-Efficiency Workforce Needs, Infrastructure, and Equity Assessment New Jersey Governor Phil Murphy’s Energy Master Plan and Executive Order 315 set a goal to reduce fossil fuel usage to 100% clean energy by 2035. The Executive Order also called for...

Shaul Picker Receives 2024 Mortensen-Voorhees Award

Shaul Picker is the 2024 recipient of the Mortensen-Voorhees Award for Achievement in Transportation Studies. This award is granted annually to the highest-achieving student with a concentration in transportation at the Edward J. Bloustein School of Urban Planning and...

NJSPL – Key Insights from Early Offshore Wind Implementation

By Jessica Parineet Offshore wind development is in its early stages in the United States, with just under one gigawatt (GW) of utility scale capacity constructed. State decarbonization goals have catalyzed industry progress thus far, however the Biden administration...

EJB Talks: Political Update with Stuart Shapiro and Amy Cobb

Analyzing Trump's Guilty Verdict and the 2024 Election Outlook Stuart Shapiro welcomes back Amy Cobb MPAP '18 for a political update in the final EJB Talks episode of the spring 2024 season. They discuss the potential consequences of Trump's guilty verdict for...

Upcoming Events

Latest Past Events

Jersey City Alumni Mixer

Zeppelin Hall Biergarten 88 Liberty View Dr, Jersey City

Join us for an alumni mixer in #JerseyCity on Thursday, June 6th at Zeppelin Hall Biergarten. Parking for Zeppelin Hall is FREE - more information can be found here: This […]