Computer Vision & Deep Learning

I will develop deep learning pipelines for image classification, object detection, OCR, or real-time video analytics using state-of-the-art models.

Tech Stack:

    • Libraries: OpenCV, TensorFlow, YOLOv8, PyTorch, ultralytics

    • Architectures: CNN, SSD, ResNet, EfficientNet

    • OCR: Tesseract, EasyOCR

    • Deployment: ONNX, TensorRT, FastAPI, Flask, AWS Lambda

    • Annotation: Roboflow, CVAT

    • Edge Devices: Raspberry Pi, Jetson Nano

    • Data: Image augmentation, preprocessing

Deliverables:

    • Custom-trained or fine-tuned CV model

    • Inference script with confidence thresholds

    • Batch & real-time processing support

    • REST API or CLI tool

    • Deployment container or service

    • Model interpretability tools