18001025661 / 8527794500

Syllabus | B.Tech-Computer Science & Engineering | Image processing and Pattern Recognition

  Image processing and Pattern Recognition Learning Schedule
Pre-requisites: AI 3 0 0 3


This course is a graduate-level introductory course to the fundamentals of digital image processing and the theory of pattern recognition. It emphasizes general principles of image processing, rather than specific applications. Lectures will cover topics such as point operations, color processing, image thresholding/segmentation, morphological image processing, image filtering and DE convolution, noise reduction and restoration, scale-space techniques, feature extraction and recognition, image registration, and image matching. This course includes foundations of pattern recognition algorithms and machines, including statistical and structural methods. Data structures for pattern representation, feature discovery and selection, classification vs. description, parametric and non-parametric classification.


The objective of this course is to

  1. imparts knowledge in the area of image and image processing
  2. understand fundamentals of digital image processing
  3. provide knowledge of the applications of the theories taught in Digital Image Processing
  4. learn the fundamentals of Pattern recognition and to choose an appropriate feature
  5. classification algorithm for a pattern recognition problems and apply them properly using modern computing tools such as Matlab, C/C++ etc.


On completion of this course, the students will be able to

  1. understand Basics of Image formation and transformation using sampling and quantization
  2. understand different types signal processing techniques used for image sharpening and smoothing
  3. perform and apply compression and coding techniques used for image data
  4. understand the nature and inherent difficulties of the pattern recognition problems
  5. understand concepts, trade-offs, and appropriateness of the different feature types and classification techniques such as Bayesian, maximum-likelihood, etc
  6. select a suitable classification process, features, and proper classifier to address a desired pattern recognition problem.


Unit I: Introduction to Image Processing

Image formation, image geometry perspective and other transformation, stereo imaging elements of visual perception. Digital Image-sampling and quantization serial & parallel Image processing.

Unit II: Image Restoration

Image Restoration-Constrained and unconstrained restoration Wiener filter , motion blur remover, geometric and radiometric correction Image data compression-Huffman and other codes transform compression, predictive compression two tone Image compression, block coding, run length coding, and contour coding.

Unit III: Segmentation Techniques

Segmentation Techniques-thresh holding approaches, region growing, relaxation, line and edge detection approaches, edge linking, supervised and unsupervised classification techniques, remotely sensed image analysis and applications, Shape Analysis – Gestalt principles, shape number, moment Fourier and other shape descriptors, Skelton detection, Hough trans-form, topological and texture analysis, shape matching.

Unit IV:  Pattern Recognition

Basics of pattern recognition, Design principles of pattern recognition system, Learning and adaptation, Pattern recognition approaches, Mathematical foundations – Linear algebra, Probability Theory, Expectation, mean and covariance, Normal distribution, multivariate normal densities, Chi squared test.

Unit V: Statistical Patten Recognition

Bayesian Decision Theory, Classifiers, Normal density and discriminant functions, Parameter estimation methods: Maximum-Likelihood estimation, Bayesian Parameter estimation, Dimension reduction methods – Principal Component Analysis (PCA), Fisher Linear discriminant analysis, Expectation-maximization (EM), Hidden Markov Models (HMM),Gaussian mixture models.


  1. Digital Image Processing – Ganzalez and Wood, Addison Wesley, 1993.
  2. Fundamental of Image Processing – Anil K.Jain, Prentice Hall of India.
  3. Pattern Classification – R.O. Duda, P.E. Hart and D.G. Stork, Second Edition John Wiley, 2006


  1. Digital Picture Processing – Rosenfeld and Kak, vol.I & vol.II, Academic,1982
  2. Computer Vision – Ballard and Brown, Prentice Hall, 1982
  3. An Introduction to Digital Image Processing – Wayne Niblack, Prentice Hall, 1986
  4. Pattern Recognition and Machine Learning – C. M. Bishop, Springer, 2009.
  5. Pattern Recognition – S. Theodoridis and K. Koutroumbas, 4th Edition, Academic Press,2009