Dissertations and Theses

Date of Award

2025

Document Type

Thesis

Department

Computer Science

First Advisor

Michael Grossberg

Keywords

Deep Learning, Writer identification, Writer attributes, Individual word images, Historical fragments analysis, Multi-label classification.

Abstract

This thesis focuses on developing automated deep learning methods for writer identification and writer attribute prediction from handwriting. It introduces two novel architectures: Convolutional Transformer Encoder (CTE) and Convolutional Swin Encoder (CSE). CTE is designed for determining authorship from handwritten text, be it modern or historical handwriting. CTE tracks subtle features and cues from handwriting strokes to distinguish authorship. It is the first of its kind capable to operate on historical handwritten fragments, setting it apart from existing methods that rely on entire document pages. CSE is designed to determine multiple attributes of an author such as authorship, gender, age and handedness. It achieves competitive performance compared to traditional page-level methods that typically rely on separate classifiers. While CTE is an exclusive classifier using a Transformer block, CSE is a multi-label classifier leveraging Swin Transformer blocks.

Included in

Data Science Commons

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.