SUK · Third Year B.Tech. Computer Science and Engineering (Artificial Intelligence and Machine Learning) · NEP 2020
Image Processing and Computer Vision
AIML3203 · Semester VI · 3 credits · ISE 10 + mid-semester 30 + ESE 60
Unit 1: Basic Concepts of Image Formation
6 hoursGoals of image processing; image sensing, acquisition and formation; greyscale and colour representation; sampling and quantisation.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Digital image representation
- Sampling and quantisation
- Colour models
Unit 2: Image Enhancement and Processing
6 hoursImage transforms, enhancement, filtering, colour processing and segmentation; geometric primitives and transformations; plotting images, contours and histogram equalisation; interactive annotation.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Image transforms: DFT, DCT, Walsh-Hadamard and Haar
- Intensity transformations
- Histogram equalisation
- Colour image processing and transformations
Unit 3: Morphological Processing
6 hoursErosion, dilation, opening and closing; hole filling, connected components, thinning and skeletons; edge linking and boundary detection.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Morphological operations
- Hit-or-miss transform and morphological algorithms
- Binary shape analysis and skeletons
Unit 4: Introduction to Computer Vision
6 hoursComponents and applications of a vision system; image sources, structure and pixels; computer-vision frameworks.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Computer vision pipeline
- Camera models and calibration
Unit 5: Object Recognition and Motion Estimation
6 hoursViola-Jones, YOLO and deep-learning recognisers; optical flow and Gaussian mixture models; structure from motion, motion estimation and tracking; SIFT, SURF and HOG; Hough line detection, Harris corners and edge detection.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Object detection
- R-CNN family, SSD and YOLO
- Optical flow
- Structure from motion and bundle adjustment
- SIFT, SURF and BRISK features
- Corner detection
- Hough transform and RANSAC
Unit 6: Intelligent Vision Systems
6 hoursNeural networks for pattern classification; CNN layers, training and applications; autoencoders; gesture recognition; face detection and recognition.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- CNNs for image classification
- Autoencoders and VAEs
- Face detection and recognition
Unit contents are summarised from the official SUK syllabus . AiCanCode.org is not affiliated with Shivaji University, Kolhapur.