ICFHR 2018 Competition on Recognition of Historical Arabic Scientific Manuscripts – RASM2018

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.