An End-to-End, Segmentation-Free, Arabic Handwritten Recognition Model on KHATT

TL;DR

This paper introduces a deep learning model for Arabic handwritten recognition that operates end-to-end without segmentation, achieving high accuracy on the KHATT database and facilitating applications like digitization and text retrieval.

Contribution

The work presents a novel segmentation-free, deep learning-based Arabic handwritten recognition model trained from scratch, with significant accuracy improvements on the KHATT dataset.

Findings

84% character recognition rate

71% word recognition rate

Effective line-level recognition without segmentation

Abstract

An end-to-end, segmentation-free, deep learning model trained from scratch is proposed, leveraging DCNN for feature extraction, alongside Bidirectional Long-Short Term Memory (BLSTM) for sequence recognition and Connectionist Temporal Classification (CTC) loss function on the KHATT database. The training phase yields remarkable results 84% recognition rate on the test dataset at the character level and 71% on the word level, establishing an image-based sequence recognition framework that operates without segmentation only at the line level. The analysis and preprocessing of the KFUPM Handwritten Arabic TexT (KHATT) database are also presented. Finally, advanced image processing techniques, including filtering, transformation, and line segmentation are implemented. The importance of this work is highlighted by its wide-ranging applications. Including digitizing, documentation, archiving, and text translation in fields such as banking. Moreover, AHR serves as a pivotal tool for making images searchable, enhancing information retrieval capabilities, and enabling effortless editing. This functionality significantly reduces the time and effort required for tasks such as Arabic data organization and manipulation.