SPPU · Third Year Artificial Intelligence and Data Science · 2024 Pattern
Computer Vision
PEC-321C-AID · Elective I · Semester V · 3 credits · CCE 30 + end-semester 70
One of the Elective I options.
Unit 1: Image Processing Fundamentals
9 hoursScope of computer vision; the CV pipeline; human versus machine vision; image representation, sampling and quantisation; RGB, CMY, CMYK and HSV models; point operations and intensity transformations.
Marks: 14 in the end-semester exam · CCE: Unit test (12 marks, Units 1 & 2)
- Computer vision pipeline
- Digital image representation
- Sampling and quantisation
- Colour models
- Intensity transformations
Unit 2: Enhancement and Spatial Filtering
9 hoursHistogram equalisation and specification; convolution; mean, Gaussian, median and bilateral smoothing; sharpening; Gaussian, salt-and-pepper, Poisson and speckle noise and their removal.
Marks: 14 in the end-semester exam · CCE: Unit test (12 marks, Units 1 & 2)
- Histogram equalisation
- Convolution and smoothing filters
- Sharpening filters
- Noise models and noise removal
Unit 3: Frequency Domain and Edge Detection
9 hoursFourier transform, DFT and FFT; magnitude and phase; low-, high- and band-pass filtering; the inverse DFT; Sobel, Prewitt, Roberts, Laplacian and LoG; the Canny detector.
Marks: 14 in the end-semester exam · CCE: Assignments or case study (12 marks, Units 3 & 4)
- Fourier transform of images
- Frequency domain filtering
- Gradient edge detectors
- Canny edge detector
Unit 4: Features and Segmentation
9 hoursHarris and Shi–Tomasi corners; texture features; global, adaptive and Otsu thresholding; region-based and clustering segmentation; morphology; boundary and region descriptors, moments and Fourier descriptors.
Marks: 14 in the end-semester exam · CCE: Assignments or case study (12 marks, Units 3 & 4)
- Corner detection
- Texture analysis
- Thresholding and Otsu's method
- Region-based segmentation
- Morphological operations
- Shape descriptors
Unit 5: Advanced Vision Applications
9 hoursSliding-window and region-proposal detection; modern detectors; Kalman tracking; optical flow; stereo and depth; activity recognition; face detection and recognition; vision in robots and vehicles.
Marks: 14 in the end-semester exam · CCE: Seminar, open-book test or quiz (6 marks, Unit 5)
- Object detection
- Object tracking with Kalman filters
- Optical flow
- Stereo vision and depth
- Face detection and recognition
Unit contents are summarised from the official SPPU syllabus . AiCanCode.org is not affiliated with Savitribai Phule Pune University.