Improving Right to Left Cursive Handwritten Text Recognition in Historical Manuscripts Using Learnable Edge Features and Channel Attention
TL;DR
An edge-aware line-level HTR framework that extends a CNN-Transformer baseline with a learnable edge-extraction channel and Squeeze-and-Excitation channel attention and shows that combining learnable structural cues with channel-wise attention has improved robustness for degradation-prone historical manuscript collections.
Abstract
Recent Handwritten Text Recognition (HTR) systems for Arabic and other right-to-left historical manuscripts have advanced exploration through convolutional neural network (CNN), recurrent, and Transformer-based models. However, degradation, weak diacritics, unstable baselines, and visually similar cursive letterforms still limit the recognition robustness. This paper presented an edge-aware line-level HTR framework that extends a CNN-Transformer baseline with a learnable edge-extraction channel and Squeeze-and-Excitation (SE) channel attention. The edge module emphasized stroke boundaries and character contours, while SE attention recalibrated feature responses to suppress background artifacts and preserve informative ink patterns. The resulting sequence was modeled by a Transformer encoder and trained using Connectionist Temporal Classification (CTC) with an auxiliary decoder cross-entropy loss. The experiments on the Kalima Arabic manuscript line-image dataset, using Books 1-8 with 86 pages and 1,759 annotated text lines, reduced character error rate from 6.40% to 4.10% and word error rate from 27.43% to 20.43%. These results show that combining learnable structural cues with channel-wise attention has improved robustness for degradation-prone historical manuscript collections.