Transfer Learning for Multi-Script Identification: A Comparative Study
Year: 2025
Type: conference-paper
Abstract: Script identification is a critical step in document analysis and optical character recognition (OCR). This study evaluates the performance of transfer learning models for script identification in both handwritten and printed word images. We compare state-of-the-art pretrained models, including ResNet, EfficientNet, and VGG, on the imbalanced ICDAR 2021 Script Identificationin the Wild (SIW 2021) dataset. Our results demonstrate that transfer learning models achieve high classification accuracy, balanced accuracy, and ROC AUC scores, particularly when fine-tuned on mixed handwritten and printed data. Data augmentation and external data further enhance performance, highlighting the potential of transfer learning for real-world applications. All source code and dataset links are publicly available.
Authors: Abbas, faycel, MENASSEL, Yahia, Gattal, Abdeljalil, Hattabi, Hadil
Institutions: University of Boumerdes, Université Larbi Tébessi
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7104375655