Search Results for author: Matthew Thomas Miller

Found 3 papers, 0 papers with code

Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription

no code implementations Findings (NAACL) 2022 Nikolai Vogler, Jonathan Parkes Allen, Matthew Thomas Miller, Taylor Berg-Kirkpatrick

We present a self-supervised pre-training approach for learning rich visual language representations for both handwritten and printed historical document transcription.

Language Modelling

BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts

no code implementations9 Jul 2019 Benjamin Kiessling, Daniel Stökl Ben Ezra, Matthew Thomas Miller

The application of handwritten text recognition to historical works is highly dependant on accurate text line retrieval.

Handwritten Text Recognition

Important New Developments in Arabographic Optical Character Recognition (OCR)

no code implementations28 Mar 2017 Maxim Romanov, Matthew Thomas Miller, Sarah Bowen Savant, Benjamin Kiessling

The OpenITI team has achieved Optical Character Recognition (OCR) accuracy rates for classical Arabic-script texts in the high nineties.

Optical Character Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.