Courses/Computer Vision

Computer Vision

CSE471

Prof. Makarand Tapaswi + Prof. Charu Sharma•Spring 2025-26•4 credits

Revision Notes/Unit 2 — Digital Image Processing Recap

Unit 2 — Digital Image Processing Recap

Image fundamentals → point operations → spatial filters (mean / Gaussian / Sobel / Laplacian / LoG / unsharp / median / bilateral) → histograms (equalisation, stretching) → Fourier and DCT, JPEG pipeline → morphology (erosion / dilation / opening / closing / hit-or-miss, Otsu) → geometric transformations (affine, homography, forward vs inverse warping) → colour models → Hough transform → template matching. The DIP toolbox every CV student carries.

DIP — Filters, Histograms, Fourier/DCT, Morphology, Geometric Ops, Hough, Templates

24 min

DIP is the bag of operations that act *on* the pixels — before any 'learning'. Three big paradigms: **spatial** (operate on pixel neighbourhoods directly), **transform** (move to a different basis like Fourier/DCT, operate there, transform back), and **morphological** (set-theoretic operations on binary images via a structuring element). Every modern CNN op (conv, pooling, padding, BN) has a DIP ancestor; understanding the ancestor explains the descendant.