Content

Hrs

00

Image Processing & Computer Vision :

Course Content

01

Introduction to Digital Image Processing & Computer Vision  

Digital Image, Image Processing origins;  Imaging in X-Rays, ultraviolet, visible infrared, visible, microwave, and radio bands; Fundamentals of image processing;  Components of image processing systems; Glossary of terms & definitions of Low level processing, Mid level analysis, High level understanding, Pattern recognition,  Computer vision, Computer graphics.

1-2

02

Digital Image Fundamentals

Visual perception – human eye, brightness adaptation and discrimination, Electromagnetic spectrum; Image sensing and acquisition – single, strip and array sensors, Image formation models; Image sampling and quantization – basic concepts, representation of image, special and gray level resolution, aliasing, zooming and shrinking; Relationships between pixels – nearest neighbor, adjacency, connectivity, regions, and boundaries; Distance measures; Image operations on a pixel basis; Linear and nonlinear operations.  

3-4

03

Image Enhancement in Spatial Domain

Gray level transformations - image negatives, log, power-law and piecewise linear transformation functions; Histogram processing – equalization,  matching; Enhancement operations - arithmetic, logic, subtraction and averaging; Spatial Filtering – linear & order-statistics for smoothing  and first & second derivatives/gradients  for sharpening. 

5-10

04

Image Enhancement in Frequency Domain

2-D Fourier transform, its inverse and properties; Discrete  and  Fast fourier transform; Convolution and Correlation theorems; Filtering in frequency domain - low pass smoothing, high pass sharpening, homomorphic filtering.

11-12

05

Image Restoration

Image degradation and restoration processes; Noise models - spatial properties, noise probability density functions, periodic noise, estimation of noise parameters; Restoration in the presence of noise - mean Filters, order-statistics filters, adaptive filters; Linear position-invariant degradations and estimation; Geometric Transformations - spatial transformation, gray-level interpolation.

13-16

06

Color Image Processing

Color fundamentals; Color models – RGB, CMY and HIS; Pseudocolor image processing; Full-color image processing - transformations, smoothing, sharpening, segmentation and compression.

17-18

07

Wavelets and Multiresolution Processing

Background - Image pyramids, sub-band coding, Haar transform; Multiresolution expansions - series expansions, scaling functions, wavelet functions; Wavelet transforms in one and  two dimensions; Wavelet packets.

19-20

08

Image Compression

Measuring information; Fundamentals of coding and inter-pixel redundancy; Image compression models – source and channel encoder/decoder;  Error-free compression using variable length, LZW, Bit-Plane, predictive lossless coding; Lossy compression using lossy predictive, transform and wavelet coding; Image compression standards.

21-24

09

Morphological Image Processing

Preliminaries - set theory and logic operations in binary images; Basic morphological operations - opening, closing operators, dilation and erosion;  Morphological algorithms - boundary extraction, region filling, extraction of connected components, convex hull, thinning, thickening, skeletons; Extension of  morphological operations to Gray-scale images.

25-28

10

Image Segmentation

Detection of discontinuities – point, line and edges; Edge linking and boundary detection - local processing, global processing using Hough transform; Thresholding - local, global and adaptive; Region-based segmentation - region growing, region splitting and merging; Motion detection.

29-36

11

Image Representation & Description

Representations - chain codes, polygonal approximations, signatures, boundary segments, skeletons; Boundary descriptors - shape numbers, statistical moments; Regional descriptors - topological, texture and moments of 2-D Functions.

37-39

12

Object Recognition

Patterns and pattern classes; Decision theoretic methods – matching, statistical classifiers, neural network; Structural methods - matching shape numbers, string matching, syntactic recognition of strings and trees; Need of intelligent processing and expert  systems.

40-42