Computer Vision and AI projects, I'm the one!
- Computer Vision & Deep Learning solutions for complex visual recognition problems
- Object Detection: YOLO v5/v8/v11, Detectron2, Faster-RCNN
- Object Tracking: DeepSORT, ByteTrack, OC-SORT, StrongSORT
- Image Segmentation: Mask-RCNN, U-Net, Segment Anything (SAM), DeepLab
- OCR: Tesseract, PaddleOCR, Azure Document Intelligence, Aws Textract, MistralOCR
- Facial Recognition: FaceNet, DeepFace, Dlib, ArcFace, RetinaFace
- Image Classification: ResNet, EfficientNet, Vision Transformer (ViT), InceptionV3
- Pose Estimation: OpenPose, MediaPipe, YOLO-Pose, AlphaPose
- Real-time Video Analytics: Live streaming, video processing, frame analysis
- Custom Model Training: Fine-tuning, transfer learning, data augmentation
- Model Optimization: TensorRT, ONNX, TensorFlow Lite for edge deployment
- Cloud Integration: Aws Rekognition, Google Vision, AzureML
- Edge Deployment: Jetson Nano/Xavier, Raspberry Pi
Platforms/Realtime Inference: Web, Mobile, Desktop, API
Tools, Frameworks and Platforms:
- Deep Learning: PyTorch, TensorFlow, Keras, OpenCV, sklearn, Roboflow, Ultralytics
- Cloud Platforms: AWS, Azure, GCP, Huggingface
- Databases: MongoDB, Postgres, Mysql, Redis