Computer Vision
Posts and notes about computer vision.
Series & Posts
1
Computer Vision Roadmap: From Basics to Real Projects
2 What is Computer Vision? From Pixels to Decisions
3 A Short History of Computer Vision: 1545 to Now
4 Math for CV Beginners: Vectors, Matrices, Convolutions
5 Image Fundamentals: Color, Histograms, Noise, Filtering
6 How Images and Video Are Stored: Colour, JPEG, Frames
7 OpenCV Setup + First 10 Tasks in Python
8 Vision Metrics: Accuracy, Precision, Recall, mAP, IoU
9 CV Project Workflow: Dataset, Baseline, Error Iteration
10 Intensity Transforms and Frequency-Domain Filtering
11 Edge Detection and Thresholding That Actually Work
12 Morphology, Contours, and Shape Analysis for Real Images
13 Feature Matching (SIFT/ORB) and Image Stitching
14 Camera Calibration and Perspective Correction
15 Epipolar Geometry, Stereo Vision, and Depth Estimation
16 Optical Flow and Motion Tracking in Video
17 HOG, HOF and MBH: Descriptors Before Deep Learning
18 Your First Image Classifier (PyTorch + Transfer Learning)
19 Data Pipelines and Augmentation for Vision Models
20 CNN Architectures Explained: From LeNet to ResNet
21 YOLO Detection Pipeline: Data to Inference
22 Semantic and Instance Segmentation: U-Net to Mask R-CNN
23 Vision Transformers (ViT) and When to Use Them
24 CV Explainability: Grad-CAM, Failures, Bias Checks
25 3D Vision Basics: SfM, Point Clouds, and Pose Estimation
26 Multimodal Vision: CLIP, Embeddings, and Retrieval Systems
27 Video Understanding: Flow Networks, Interpolation, Stabilisation
28 Real-Time CV Systems: Tracking, Latency, Streaming
29 Deploying CV Models: ONNX, TensorRT, Edge, and APIs
30 Responsible CV: Privacy, Fairness, Security, Governance