Picture for Matthew Thomas Miller

Matthew Thomas Miller

Advances and Limitations in Open Source Arabic-Script OCR: A Case Study

Add code
Feb 08, 2024
Viaarxiv icon

Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription

Add code
Dec 16, 2021
Figure 1 for Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription
Figure 2 for Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription
Figure 3 for Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription
Figure 4 for Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription
Viaarxiv icon

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

Add code
Jul 09, 2019
Figure 1 for BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts
Figure 2 for BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts
Figure 3 for BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts
Figure 4 for BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts
Viaarxiv icon

Important New Developments in Arabographic Optical Character Recognition (OCR)

Add code
Mar 28, 2017
Figure 1 for Important New Developments in Arabographic Optical Character Recognition (OCR)
Figure 2 for Important New Developments in Arabographic Optical Character Recognition (OCR)
Figure 3 for Important New Developments in Arabographic Optical Character Recognition (OCR)
Figure 4 for Important New Developments in Arabographic Optical Character Recognition (OCR)
Viaarxiv icon