Teaching AI visually and practically!
Welcome to the Computer Vision course! This syllabus outlines the lecture plan, core units, sub-topics, practical tasks, reference materials, and outcomes you’ll cover throughout the semester.
| Lec | Topic | Description | Tasks / Assignments |
|---|---|---|---|
| 0 | Introduction | Course Overview & Project Allotments | 35+ Projects in 10 Categories |
| Day | Topic | Sub-Topics | Tasks |
|---|---|---|---|
| 1 | Math Foundation | Linear Algebra, Prob & Stats, Geometry, Optimization, Calculus, Discrete Math, Signal Proc | Task 1: Jupyter Notebook on Math |
| 2 | Python Basics | Variables, Data Types, Loops, OOP, Modules, File I/O, Error Handling | Task 2: Summarize Python Course |
| 3 | NumPy | Array Ops, Shape Manipulation, Math Ops | Task 3: Selfie Image Processing |
| 4 | Matplotlib | Plotting Basics, Figures, Styling | Task 4: Implement Plotting Functions |
| 5 | OpenCV (cv2) | Basic Image/Video Ops, Transformations | Task 5: Video Processing with OpenCV |
| 6 | Scikit-image / Pillow | Image Transformations, Format Handling | Task 6: Pillow + OpenCV Use Cases |
| 7 | Flask / Django / FastAPI | Upload Images, API Calls, Video Streaming | Task 7: Deploy an API Model |
| Day | Topic | Sub-Topics | Tasks |
|---|---|---|---|
| 7 | Image Acquisition | Digital vs Analog, Cameras, CMOS vs CCD | Task 8-9: Sampling Theorem, Visualize Signal |
| 8 | Image Representation | Pixels, Color Spaces, Bits Per Pixel | Tasks 10–14: Color Space, Resolution, Size |
| 9 | Basic Image Ops | Color Conversion, Geometric Transforms, Bitwise Ops | Tasks 15–18: Draw Shapes, Transforms |
| 10 | Filtering Techniques | Convolutions, Morphology, Spatial/Non-Linear Filters | Tasks 19–24: Filters, Interpolation |
| 11 | Image Restoration | Degradation, Inverse Filtering, Wiener Filtering | Task 25: Noise Removal |
| 12 | Image Enhancement | Histogram Equalization, Intensity Transforms, Sharpening | Task 26–27: Enhance Details |
| 13 | Image Compression | JPEG, PNG, Lossy vs Lossless Compression | Task 28: Compress + Compare |
| 14 | Image Analysis | Edge Detection, Multi-Resolution Pyramids | Task 29–30: Sobel, Laplacian, Pyramids |
| Day | Topic | Sub-Topics | Tasks |
|---|---|---|---|
| 15 | Thresholding Techniques | Global, Adaptive, Otsu | Task 31 |
| 16 | Edge Detection | Sobel, Prewitt, Laplacian, Canny | Task 32 |
| 17 | Corner Detection | Harris, Shi-Tomasi, FAST, ORB | Task 33 |
| 18 | Texture Analysis | GLCM, LBP | Task 34 |
| 19 | Shape Analysis | Contours, Skeletons, Hu Moments | Task 35 |
| 20 | Segmentation | Watershed, Region Growing, K-means | Task 36 |
| 21 | Boundary Pattern Analysis | Chain Code, Polygon Approximation | Task 37 |
| 22 | Line Detection | Hough Transform, RANSAC | Task 38 |
| 23 | Circle / Ellipse Detection | Hough Circle Detection | Task 39 |
| 24 | The Hough Transform | Line, Circle, GHT | Task 40 |
| 25 | Pattern Matching | Template Matching, NCC, Feature Matching | Task 41 |
| Day | Topic | Sub-Topics | Tasks |
|---|---|---|---|
| 26 | The 3D World | Pinhole Model, Image vs World Coordinates | Task 42 |
| 27 | Image Transforms | Homography, Intrinsic/Extrinsic Params | Task 43 |
| 28 | 3D Reconstruction | Stereo Vision, Depth Maps | Task 44 |
| 29 | Introduction to Motion | Optical Flow, KLT Tracker | Task 45 |
| 30 | Kalman Filter | Tracking and Prediction | Task 46 |
| Day | Topic | Sub-Topics | Tasks |
|---|---|---|---|
| 31 | Automated Visual Inspection | Defect Detection, Template Matching | Task 47 |
| 32 | Surveillance Systems | Motion Detection, Object Tracking | Task 48 |
| 33 | In-Vehicle Vision | Lane Detection, Drowsiness Detection | Task 49 |
| 34 | Statistical Pattern Recog. | Bayes Classifier, k-NN, Decision Trees | Task 50 |
| 35 | Project Review + Viva | Mini Projects, Peer Assessment | Presentation + Evaluation |
| ID | Title | Author(s) |
|---|---|---|
| T1 | Computer Vision: Algorithms & Applications | Richard Szeliski |
| T2 | Computer & Machine Vision | E.R. Davies |
| T3 | Feature Extraction & Image Processing | Mark Nixon, A. Aquado |
| T4 | Linear Algebra and its Applications | Gilbert Strang |
| T5 | Probability & Statistics for Engineers and Scientists | Sheldon M. Ross |
| T6 | Operations Research: Theory and Applications | J.K. Sharma |
| T7 | Digital Signal Processing | Proakis, Manolakis |
| T8 | Discrete Mathematics | Seymour Lipschutz, Marc Lipson |
| T9 | Python Documentation | Python.org |
| T10 | NumPy Documentation | numpy.org |
| T11 | Matplotlib Tutorials | matplotlib.org |
| T12 | OpenCV Documentation | opencv.org |
| T13 | Scikit-Image Docs | scikit-image.org |
| T14 | Pillow Docs | python-pillow.org |
| T15 | Flask Documentation | flask.palletsprojects.com |
| T16 | Mathematics for Machine Learning | Deisenroth et al. |
| T17 | Data Science & ML (Mathematical + Statistical Methods) | Kroese et al. |
| T18 | Machine Learning: A Probabilistic Perspective | Kevin P. Murphy |
| T19 | Machine Learning: An Algorithmic Perspective | Stephen Marsland |
📬 For questions, assignments, and announcements: Check the Course GitHub Discussions
🧑🏫 Instructor: Purushotham Mailapalli – GitHub