This repository contains an Optical Character Recognition (OCR) model developed as part of a Deep Learning university course. The model learns to recognize and extract text from images using neural networks.
- Built using PyTorch and Google Colab
- Trained on a labeled image-text dataset
- Handles printed and synthetic characters
- Includes pre-processing, model training, and evaluation
- Final results documented in a structured PDF report
code.ipynb– Main notebook for training and evaluation
- Python
- PyTorch
- torchvision
- OpenCV
- Google Colab
This project was completed as part of my coursework in Computer Science, with a focus on Deep Learning and Computer Vision.
I'm currently seeking an internship opportunity to apply and grow my skills in OCR, vision, and AI research.
Feel free to connect or reach out if you’re hiring or open to collaboration!
This project is released under the MIT License.