Date of Award
5-2025
Culminating Project Type
Starred Paper
Styleguide
apa
Degree Name
Computer Science: M.S.
Department
Computer Science and Information Technology
College
School of Science and Engineering
First Advisor
Dr. Maninder Singh
Second Advisor
Dr. Jie H. Meichsner
Third Advisor
Dr. Jalal Khalil
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Keywords and Subject Headings
Optical Character Recognition, Text Detection, Text Recognition, Entity Recognition, Convolutional Neural Networks, Recurrent Neural Networks
Abstract
The integration of optical character recognition (OCR) technology with indoor positioning systems marks a significant advancement in innovation, poised to revolutionize various aspects of daily life by enhancing safety, navigation, and efficiency within indoor environments. This research project stems from a critical use case focusing on precise localization in emergency scenarios within indoor environments. The research aims to generalize this capability across buildings, facilitating user navigation and entity localization through application-based directions. Central to this paper is the extraction of entity information from image frames using OCR technology, presenting challenges in efficient image data processing in terms of both accuracy and computation during inference especially over extended periods of time. The primary objective of this research project is to explore deep learning methodologies and deduce a method for simplistic OCR which minimizes computational overhead without compromising accuracy. A set of standardized entities relevant to building environments is defined to ensure selective identification and prioritization based on relevance and importance. The study later pivoted to a comparative analysis of existing models as a consequence of model training setbacks.
Recommended Citation
Syed, Ashhad W., "An OCR Application for Location-Based Indoor Entity Recognition" (2025). Culminating Projects in Computer Science and Information Technology. 59.
https://repository.stcloudstate.edu/csit_etds/59
Comments/Acknowledgements
I am sincerely grateful to my advisor, Dr. Maninder Singh, who introduced me to this problem and provided unwavering guidance throughout the completion of this paper. I am also thankful to my committee members, Dr. Jie H. Meichsner and Dr. Jalal Khalil, whose support, particularly during the early stages, was critical. My appreciation goes to Dr. Ramnath Sarnath, my advisor in the initial phase of my program, whose mentorship helped me settle well. I likewise recognize all the CSIT faculty for their commitment to student success, especially Dr. Andrew Anda, Dr. Jayantha Herath, Dr. Adriano Cavalcanti, and Dr. Omar Al-Azzam, from whose courses I drew numerous ideas that greatly shaped this work. I extend my thanks to Mr. Chris Stanley, Director of ETI – SCSU, under whose supervision I honed my professional skills through a multitude of engaging projects. I am also thankful for the continuous assistance provided by Mr. Clifford Moran throughout the program. Finally, I cannot overstate my gratitude to my family for their unwavering encouragement, which laid the foundation for me to pursue my goals.