Out of vocabulary word detection and recovery in Arabic handwritten text recognition. (September 2019)

• Record Type: Journal Article
• Authors: Jemni, Sana Khamekhem; Kessentini, Yousri; Kanoun, Slim
• Is Part Of: Pattern recognition. Volume 93(2019:Sep.)
• Page Start: 507
• Page End: 520
• Publication Date: 2019-09
• Subjects: Arabic Handwriting recognition -- Out of vocabulary detection and recovery -- Static lexicon -- Dynamic lexicon -- Statistical language model -- Deep learning -- Multi-dimensional long short term memory network; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.05.003
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel two-step OOV words detection and recovery method is proposed. The proposed method is generic and independent of the recognition engine. The proposed method uses various sub-lexical modeling to improve the detection step. The recovery process relies on dynamic lexicons built from large text corpora. The proposed method significantly improves the recognition results. Abstract: Today's Arabic Handwriting recognition systems are able to recognize arbitrary words over a large but finite vocabulary. Systems operating with a fixed vocabulary are bound to encounter so-called out-of-vocabulary (OOV) words. The aim of this research is to propose a two-step approach that tackles the problem of OOV words in Arabic handwriting. In the first step, we exploit different types of sub-word units to detect the potential OOVs. In the recovery stage, a dynamic dictionary is built to extend the initial static word lexicon in order to cope with the detected OOVs. The recovery includes a selection step in which the best word candidates extracted from the external resource are kept. Experiments were conducted on the public benchmarking KHATT and AHTID/MW databases. The obtained results revealed that sub-word modeling could give cues for improving the detection and that the use of a dynamic dictionary significantly improves the recognition performance compared to one-step approaches that are based on a large static dictionary or the combination of different sub-word units. We achieve the state of the art results on the KHATT dataset.