Paper Info
Title
ICFHR 2018 Competition on Recognition of Historical Arabic Scientific Manuscripts – RASM2018
Abstract
This paper presents an objective comparative evaluation of page analysis and recognition methods for historical scientific manuscripts with text in Arabic language and script. It describes the competition (modus operandi, dataset and evaluation methodology) held in the context of ICFHR2018, presenting the results of the evaluation of six methods - three submitted and three baseline systems. The challenges for the participants included page segmentation, text line detection, and optical character recognition (OCR). Different evaluation metrics were used to gain an insight into the algorithms, including new character accuracy metrics to better reflect the difficult circumstances presented by the documents. The results indicate that, despite the challenging nature of the material, useful digitisation outputs can be produced.
Year
DOI
Venue
2018
10.1109/ICFHR-2018.2018.00088
2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)
Keywords
Field
DocType
performance evaluation, page analysis, optical character recognition, OCR, layout analysis, recognition, datasets
Arabic,Segmentation,Computer science,Optical character recognition,Natural language processing,Artificial intelligence,Machine learning
Conference
ISSN
ISBN
Citations 
2167-6445
978-1-5386-5876-5
2
PageRank 
References 
Authors
0.40
5
4
Name
Order
Citations
PageRank
Christian Clausner1448.49
Apostolos Antonacopoulos237836.45
Nora McGregor320.40
Daniel Wilson-Nunn420.40