SPPU · Third Year Electronics & Telecommunication Engineering · 2024 Pattern
Digital Image Processing
PEC-361B-ETC · Elective II · Semester VI · 3 credits · CCE 30 + end-semester 70
One of the Elective II options.
Unit 1: Fundamentals of Digital Image Processing
9 hoursSteps and components of image processing; image formation in the eye; sampling and quantisation; image types, histograms and file formats; pixel relationships, arithmetic and set operations; colour fundamentals, RGB, CMY and HSI models and the chromaticity diagram.
Marks: 14 in the end-semester exam · CCE: Unit test (12 marks, Units 1 & 2)
- Steps and components of image processing
- Image sampling and quantisation
- Image types, histograms and file formats
- Relationships between pixels
- Colour models: RGB, CMY and HSI
Unit 2: Spatial-domain Enhancement
9 hoursPoint and neighbourhood processing; negative, log, power-law, piecewise-linear, contrast stretching, grey-level and bit-plane slicing; mean, weighted, median filters; gradient, Laplacian and high-boost sharpening; Gaussian, salt-and-pepper and periodic noise and their removal.
Marks: 14 in the end-semester exam · CCE: Unit test (12 marks, Units 1 & 2)
- Grey-level transformations
- Contrast stretching and slicing
- Smoothing spatial filters
- Sharpening spatial filters
- Noise models and noise removal
Unit 3: Frequency-domain Enhancement and Segmentation
9 hoursFrequency-domain processing and spatial frequency; ideal, Butterworth and Gaussian low-pass and high-pass filters; edge detection with Roberts, Prewitt, Sobel and Canny; global and adaptive thresholding; region growing, splitting and merging.
Marks: 14 in the end-semester exam · CCE: Assignments or case study (12 marks, Units 3 & 4)
- Frequency-domain image processing
- Low-pass filters: ideal, Butterworth and Gaussian
- High-pass filters: ideal, Butterworth and Gaussian
- Edge detection operators
- Thresholding
- Region-based segmentation
Unit 4: Image Compression
8 hoursNeed for compression and the compression model; lossy and lossless compression; Huffman coding; DCT compression with 8×8 blocks; wavelet compression with the DWT; compression ratio, redundancy and quality trade-offs.
Marks: 14 in the end-semester exam · CCE: Assignments or case study (12 marks, Units 3 & 4)
- Image compression model and redundancy
- Huffman coding
- DCT-based compression
- Wavelet-based compression
Unit 5: AI-driven Computer Vision
9 hoursComputer vision and AI-assisted image processing; machine learning for images; object detection and face recognition; real-time video, embedded vision and edge AI; ethics; applications in vehicles, cities, healthcare and agriculture.
Marks: 14 in the end-semester exam · CCE: Seminar, open-book test or quiz (6 marks, Unit 5)
- Computer vision and machine learning for images
- Object detection and face recognition
- Embedded vision and edge AI
- Ethics and applications of computer vision
Unit contents are summarised from the official SPPU syllabus . AiCanCode.org is not affiliated with Savitribai Phule Pune University.