SWATHI REDDY

Final-year Computer Science Engineering student with hands-on experience in deep learning for image and video analysis, including object detection, OCR, and medical image classification. Skilled in Python, PyTorch, TensorFlow, and end-to-end machine learning workflows, from data preprocessing and model training to testing and deployment. Experienced in building real-time AI pipelines, and conducting error analysis to derive insights for model improvement. Passionate about applying research-driven approaches, and persistent experimentation to solve complex, real-world problems in computer vision.

• AWS SAA, in progress
• Oracle AI Foundations
• Oracle OCI ML Foundations
• Google Data Analytics
• Java Programming - NPTEL
• Accenture Data Analytics Simulation

• Developed a deep learning pipeline using YOLOv5 for aircraft detection and EasyOCR for tail ID recognition in real-time video feeds.
• Implemented classification of runway events (take-off vs landing) and structured results for logging and analysis.
• Gained experience in end-to-end ML workflow, including data preparation, training, testing, and deployment in a real-world use case.

• Engineered a federated learning pipeline for retinal image analysis using MobileNetV2 and ResNet50, achieving 88.6% diagnostic accuracy while preserving patient data privacy.
• Designed end-to-end workflows (ETL, preprocessing, model training, benchmarking) across simulated hospital clients, ensuring reliable and scalable performance.
• Presented research at the 5th International Conference on Computer Vision and Robotics (CVR 2025). Link