Computer--Vision-Lectures

This is a series of Jupyter notebooks that attempts to cover computer vision from its origins to the present day.

Lecture 1 (How vision works)

• How vision works
  • How does eyes work
  • How do we process light?
  • How the brain sees 3D
  • One eye
  • Two eyes
  • Brain
  • So what are we looking at?
  • where does light come from?
  • so what makes visible light special, then?
  • How do we perceive colors?
  • CIE 1931 and Color Matching (William Wright and John Guild Experiment)
  • Experiment
  • Restrictions on viewing conditions
  • Practical example
  • From CIE-RGB to CIE-XYZ
  • sRGB
  • Linear sRGB
  • CIELAB

  Lecture 2 (How the cameras work)

  • How the cameras work
    • Camera operation
    • Pinhole camera
    • Bayer Pattern
    • Reading Images on the Computer
    • Pixel Grid
    • Pixel read types
    • HWC (Height, Width, Channel)
    • CHW (Channel, Height, Width)
  • Getting started with OpenCV
    • Read an Image
    • Show an Image
    • Save an Image
    • Read from the camera (video)
    • Read from a video
    • Draw in a frame
    • Draw a line
    • Draw an arrow
    • Draw a rectangle
    • Draw a circle
    • Draw a Polygon
    • Draw text
    • Print day and time on video
    • Event Handlers in OpenCV
  • Representation of information in tensors
  • Object Detection and Object Tracking Using HSV

  Lecture 3 (Image interpolation and scaling)

  • Image interpolation and scaling
    • Image size scaling
    • Nearest neighbor
    • Triangle interpolation
    • Bilinear interpolation
    • Bicubic Interpolation
    • Summary and some others
    • Image size reduction
    • Box filter
    • Gaussean filter
    • Filters for Images on OpenCV (summary and some others)
    • Image De-noising - Non-Local Means Denoising
    • Low-pass/High-pass Filters
    • Simple Image Thresholding (With Global Value)
    • Adaptive Thresholding (With Dynamic Value)
    • Otsu's Binarization
    • Histograms
    • One-dimensional
    • Multidimensional
    • Morphological Transformations
    • Dilation
    • Erosion
    • Opening
    • Closing
    • Gradiant
    • Tophat
    • blackhat
    • Structuring Elements
    • Thinning
    • Thickening
    • Skeletonization (Medial Axis Transform)
    • Bitwise Operations
    • AND
    • OR
    • XOR
    • NOT - square
    • Find Edges
    • Properties of convolutions
    • Commutative property
    • Associative property
    • Distribution property over addition
    • Scalable property
    • Sobel filters
    • Sobel X
    • Sobel Y
    • Sobel XY
    • Sobel Combined
    • Laplacian
    • Gaussian difference (DoG)
    • Sharpen
    Sharpen
    • Identity Kernel
    • Sharpen Kernel
    • Canny Edge Detector