Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196415,
        author = {Prabaharan P and Vaishnavi N and Priya dharshini K and Pavithra G},
        title = {Lightweight Hybrid OCR System for Handwritten Text with Energy-Aware Evaluation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {3767-3769},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196415},
        abstract = {The digitization of handwritten documents remains a challenging task due to variations in writing styles, noise, and image distortions. Traditional Optical Character Recognition (OCR) systems often fail to achieve high accuracy on handwritten text, while deep learning-based approaches, although effective, require significant computational resources. This paper presents a Lightweight Hybrid OCR System that combines traditional image processing techniques with deep learning-based models to improve recognition performance while maintaining efficiency. The proposed system includes preprocessing, segmentation, and a hybrid recognition module integrating a fine-tuned TrOCR model and a trained EasyOCR model using a dataset of over 10,000 handwritten text lines. The hybrid approach enhances recognition capability by leveraging both contextual understanding and character-level detection. The system achieves an accuracy of over 60% on complex handwritten inputs. Furthermore, an energy-aware performance evaluation is conducted to analyze computational efficiency in terms of execution time and resource utilization. Experimental results demonstrate that the proposed system provides a balanced trade-off between accuracy and performance, making it suitable for deployment in real-time and resource-constrained environments.},
        keywords = {Optical Character Recognition (OCR), Handwritten Text Recognition, Hybrid OCR, TrOCR, EasyOCR, Deep Learning, Image Preprocessing, Text Segmentation, Energy-Efficient Computing.},
        month = {April},
        }