Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection
This addresses the problem of converting Arabic handwritten documents into text for users in digitization and archival fields, with incremental improvements in segmentation and recognition.
The paper tackles Arabic handwritten text recognition by developing an OCR pipeline with line segmentation using Differentiable Binarization and Adaptive Scale Fusion, achieving a Character Recognition Rate of 99.20% and Word Recognition Rate of 93.75% on single-word samples.
The problem of converting images of text into plain text is a widely researched topic in both academia and industry. Arabic handwritten Text Recognation (AHTR) poses additional challenges due to diverse handwriting styles and limited labeled data. In this paper we present a complete OCR pipeline that starts with line segmentation using Differentiable Binarization and Adaptive Scale Fusion techniques to ensure accurate detection of text lines. Following segmentation, a CNN-BiLSTM-CTC architecture is applied to recognize characters. Our system, trained on the Arabic Multi-Fonts Dataset (AMFDS), achieves a Character Recognition Rate (CRR) of 99.20% and a Word Recognition Rate (WRR) of 93.75% on single-word samples containing 7 to 10 characters, along with a CRR of 83.76% for sentences. These results demonstrate the system's strong performance in handling Arabic scripts, establishing a new benchmark for AHTR systems.