Citation

Asmamaw Shiferaw, Natenaile and Lazarus Mayaluri, Zefree and Kumar Sahoo, Prabodh and Panda, Ganapati and Jain, Prince and Rath, Adyasha and Islam, Md. Shabiul and Tariqul Islam, Mohammad (2025) Handwritten Amharic Character Recognition Through Transfer Learning: Integrating CNN Models and Machine Learning Classifiers. IEEE Access, 13. pp. 52134-52148. ISSN 2169-3536

Text 8.pdf - Published Version Restricted to Repository staff only Download (2MB)

Abstract

Handwritten Amharic character recognition presents significant challenges due to the script’s syllabic nature and variations in handwriting styles. This study investigates a hybrid approach that integrates convolutional neural networks (CNNs) with machine learning classifiers to enhance recognition accuracy. Transfer learning is applied using four CNN architectures: AlexNet, VGG16, VGG19, and ResNet50 as feature extractors. Initially, their performance is evaluated with softmax classifiers. Subsequently, the softmax layer is replaced with machine learning classifiers, including Random Forest, XGBoost, and Support Vector Machine (SVM), while freezing the pretrained feature extractors. The Hybrid ResNet50 + SVM model achieves the highest accuracy of 91.89%, with a precision of 92.46%, recall of 91.15%, and an F1-score of 91.80%. These results indicate that SVM serves as a potential alternative to softmax, offering robust classification performance for complex handwritten scripts. This research contributes to advancements in handwritten character recognition systems for underrepresented languages.

Item Type:	Article
Uncontrolled Keywords:	Amharic script, handwritten character recognition, deep learning, convolutional neural networks (CNN), transfer learning.
Subjects:	L Education > LB Theory and practice of education > LB1060 Learning
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	30 Apr 2025 02:19
Last Modified:	30 Apr 2025 02:19
URII:	http://shdl.mmu.edu.my/id/eprint/13714

Downloads

Edit (login required)