Computer Vision

Computer Vision

Image processing to deep learning. OpenCV, PIL, CNNs, transfer learning, object detection with YOLO, segmentation, OCR, and deploying vision models to production.

FundamentalsTopics 1–10

·What is Computer Vision?
·Images as Numpy Arrays
·OpenCV Basics
·Reading & Displaying
·Color Spaces (BGR/RGB/HSV)
·Image Transformations
·Convolution & Kernels
·Edge Detection
·Thresholding & Drawing
·PIL/Pillow & Image Pyramids

Start Fundamentals →

IntermediateTopics 11–20

·CNN Fundamentals
·Feature Maps & Pooling
·Backbones (ResNet, EfficientNet)
·Transfer Learning
·Data Augmentation
·Training a Classifier
·Batch Norm & Regularisation
·Object Detection (YOLO)
·Model Evaluation
·Datasets & Labels

Start Intermediate →

AdvancedTopics 21–30

·Modern Detection (YOLOv8+)
·Semantic Segmentation
·Instance & Panoptic Segmentation
·Pose Estimation & Keypoints
·Vision Transformers (ViT)
·Depth Estimation & 3D
·OCR & Document Understanding
·Multimodal Vision (CLIP & beyond)
·Tracking & Optical Flow
·Generative Vision (Diffusion & GANs)

Start Advanced →

ProductionTopics 31–40

·Model Optimisation & Quantisation
·ONNX & Runtime Engines
·Serving (FastAPI · Triton)
·Batch & Dynamic Batching
·GPU Inference at Scale
·Edge & Mobile Deployment
·Video & Streaming Pipelines
·Monitoring & Drift
·A/B Testing & Rollout
·Cost, Throughput & SLOs

Start Production →