Attention-based CNN-ConvLSTM for Handwritten Arabic Word Extraction

Word extraction is one of the most critical steps in handwritten recognition systems. It is challenging for many reasons, such as the variability of handwritten writing styles, touching and overlapping characters, skewness problems, diacritics, ascenders, and descenders' presence. In this work,...

Descripción completa

Detalles Bibliográficos
Autores: Ben Aïcha, Takwa|||0000-0002-3786-3649, Echi, Afef Kacem
Tipo de recurso: artículo
Fecha de publicación:2022
País:España
Institución:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:263998
Acceso en línea:https://ddd.uab.cat/record/263998
https://dx.doi.org/urn:doi:10.5565/rev/elcvia.1433
Access Level:acceso abierto
Palabra clave:Attention mechanism
ConvLSTM
CTC
Deep-learning
Handwritten Arabic word extraction
Descripción
Sumario:Word extraction is one of the most critical steps in handwritten recognition systems. It is challenging for many reasons, such as the variability of handwritten writing styles, touching and overlapping characters, skewness problems, diacritics, ascenders, and descenders' presence. In this work, we propose a deep-learning-based approach for handwritten Arabic word extraction. We used an Attention-based CNN-ConvLSTM (Convolutional Long Short-term Memory) followed by a CTC (Connectionist Temporal Classification) function. Firstly, the text-line input image's essential features are extracted using Attention-based Convolutional Neural Networks (CNN). The extracted features and the text line's transcription are then passed to a ConvLSTM to learn a mapping between them. Finally, we used a CTC to learn the alignment between text-line images and their transcription automatically. We tested the proposed model on a complex dataset known as KFUPM Handwritten Arabic Text (KHATT \cite{khatt}). It consists of complex patterns of handwritten Arabic text-lines. The experimental results show an apparent efficiency of the used combination, where we ended up with an extraction success rate of 91.7\%.