AI is Math

Check out my course site: AIisMath.com

This is my CV course raw data git repo - you can see the raw .py/ .ppt files here.

Course TOC

Intro to CV and Python (slides)

• Python, VSCode & packages installation guide
• Course details
• What is computer vision (CV)?
• Course outline
• Intro to Python
  • Basic python tutorial notebook- part 1
  • Basic python tutorial notebook- part 2
  • NumPy tutorial notebook
  • Matplotlib tutorial notebook
  • OpenCV tutorial notebook
• Ex1: basic python, numpy & matplotlib, opencv

Basic image processing (slides)

• Image representation
• Pixel-wise operations
• Histogram equalization (notebook)
• Template matching
• Morphology operators
• Connected components
• Color space (notebook)
• Ex2: morphological operators and friends

Filtering and resampling (slides)

• Noise and filtering (notebook)
• Frequency representation
• Decimation
• Interpolation

Edge Detection (slides)

• Intro to edges
• Basic edge image (gradient filters notebook)
• Edge thinning
  • LoG
  • NMS
• Edge mask
• Canny edge detector (edge detection notebook)
• Other edge related topics
  • Frequency representation
  • Unsharp filter
• Ex3: Bilateral filter

Curve fitting (slides)

• Least squares
• Total least squares
• RANSAC (LS, TLS & RANSAC notebook)
• Ex4a: vignetting

Hough transform (slides)

• Hough transform (Hough transform notebook)
  • $(m,b)$ parameter space
  • $(\rho ,\theta )$ parameter space
• Ex4b: Hough circles

Image formation (slides)

• BRDF
• Pinhole camera
• Digital camera
• The human eye

Geometric transformation (slides)

• 2D->2D transformations (notebook)
• 3D->3D transformations
• 3D->2D transformations (3D projections)
  • Perspective projection
  • Orthographic projection

Camera calibration (slides)

• What is camera calibration?
• Camera extrinsics
• Perspective projection
• Camera intrinsics
• Full camera matrix
• Calibration methods and distortions (notebook)

Features (slides)

• What and why we need features detection?
• Feature detection
  • Blob detection
  • Harris corner detection (Harris notebook)
  • SIFT detector
• Feature description
  • Template matching
  • HOG
  • SIFT descriptor
• SIFT feature matching (SIFT notebook)
• Panoramas

Stereo (slides)

• Structure from motion
• Triangulation
• Stereo matching
• Camera rectification
• Epipolar geometry
  • Essential matrix
  • Fundamental matrix
  • Estimating the fundamental matrix
• Other 3D sensors

Neural networks basics (slides)

• The classification problem- again
• NN history
• Perceptron
  • Hyperplanes
  • Activation
• Dense layer
• Multi-layer perceptron (MLP)
• Optimization
  • Softmax + cross entropy + loss
  • Gradient descent
• Basic data preprocessing
  • Data normalization
  • Train, validation and test splits
• Fully connected net

Neural networks 2 (slides)

• ConvNets
  • Convolution layer
  • Pooling layer
• Overfitting