Author ORCID Identifier
Nicholas Howe: 0000-0002-4427-9985
Document Type
Technical Report
Publication Date
7-2025
Abstract
This paper proposes a novel approach to handwritten charac- ter recognition using convolutional non-recurrent deep neural networks. Such a network can run in parallel at every point of a document, offer- ing potential advantages in speed over recurrent approaches. The net- work’s output feeds into a beam search optimization for final decoding. Preliminary quantitative results show that the framework can achieve bootstrap training from labeled word images. It provides an alternative to sequential models that rely on connectionist temporal classification for alignment.
Keywords
character recognition, alignment, neural networks, deep learning
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Rights
Licensed to Smith College and distributed CC-BY 4.0 under the Smith College Faculty Open Access Policy
Recommended Citation
Howe, Nicholas, "Toward A Simplified Framework for Sequential Character Recognition" (2025). Computer Science: Faculty Publications, Smith College, Northampton, MA.
https://scholarworks.smith.edu/csc_facpubs/424
Comments
Author’s submitted manuscript.