I will build deep learning and computer vision models

Past Experience Highlights:

• ISRO Internship: Developed a satellite image segmentation pipeline to identify and classify terrain regions, improving model accuracy through data augmentation and optimized CNN architectures.
• Einfochips Internship: Built a real-time object detection model using YOLOv8 for industrial components, integrating live camera feeds for production monitoring.
• Academic Projects: Implemented handobject interaction detection using YOLOv11 and OpenCV to determine if a hand is holding an object, leveraging motion and texture analysis.

Services I Offer:

• Object Detection (YOLOv5/v8/v11, SSD, etc.)
• Image Classification with CNNs / Transfer Learning
• Image Segmentation (binary or multi-class)
• Frame-Based Analysis (e.g., hand holding object detection)
• Dataset Preprocessing, Annotation & Augmentation
• Model Evaluation and Fine-Tuning

Output Includes:

• Well-commented Python code (.ipynb / .py)
• Trained model weights + evaluation report
• Prediction visualizations (bounding boxes / masks)
• Easy guide to test or reuse your model

️ Tools I Use:

• YOLO (v5/v8/v11) · PyTorch · TensorFlow · Keras · OpenCV · LabelImg · Roboflow · Google Colab / Jupyter / Kaggle