Machine Learning for Image Processing (MLIP) Course - Videos
This Course is taught during Jan-June 2022, at IIT Tirupati.
Click here to view the YouTube Playlist of the videos of this course.
Module-1: Overview
L01 - Course Description - Video
L02 - Is the Buzz Around Machine Learning Just a Hype? - Video
Module-2: Image Processing (Independent Module, 9 Lectures)
L03 - Introduction to ML, Image Acquisition, Sampling, Quantization - Video
L04 - Sampling, Quantization, Image processing vs Computer Vision - Video
L05 - Intensity Transform, Power-law, Piecewise Linear Transform - Video
L06 - Contrast Stretching and Histogram Equalization - Video
L07 - Histogram Equalization Continuation, Histogram Specification - Video
L08 - Variants of Histogram Equalization, Correlation, Convolution - Video
L09 - Convolution, Correlation, Gaussian Filter, Statistical Filters - Video
L10 - Dealing with Boundaries, Image Padding, Gradient Computation - Video
L11 - Kernels for Gradients, Edge Detection, Derivatives, Sharpening - Video
Module-3: Bayesian Classification (Independent Module, 14 Lectures)
L12 - Overview of Machine Learning, Classifier, Feature Vector - Video Notes
L13 - Bayes Theorem, A posteriori Probability, Likelihood - Video Notes
L14 - Decision Error, Average Risk, Generalizing to M Classes - Video Notes
L15 - Min. Average Risk, Likelihood Ratio-based Decision Rule - Video Notes
L16 - Decision Surfaces, Discriminant Functions, 1D Gaussian - Video Notes
L17 - Multivariate Gaussian Distribution, Isocurves, Examples - Video Notes
L18 - Normally Distributed Classes, 2D Discriminant Functions - Video Notes
L19 - Illustration of Discriminant Functions & Decision Planes - Video Notes
L20 - Decision Hyper Planes for Different Covariance Matrices - Video Notes
L21 - Decision planes, Minimum Distance Classifier, Examples - Video Notes
L22 - Recap, Maximum Likelihood (ML) Parameter Estimation Part-1 - Video Notes
L23 - Discussion of the Midterm Exam Paper - Video
L24 - ML Parameter Estimation Part-2 - Video Notes
L25 - Maximum a Posteriori Probability (MAP) Estimation - Video
Module-4: Neural Networks (Independent Module, 7 Lectures)
L26 - Linear Classifier Part-1 - Video
L27 - Linear Classifier Part-2 - Video
L28 - Nonlinear Classifier Part-1 - Video
L29 - Nonlinear Classifier Part-2 - Video
L30 - Backpropagation Part-1 - Video
L31 - Backpropagation Part-2 - Video
L32 - General Guidelines about Implementation of Neural Networks - Video
Module-5: Support Vector Machines - SVM (Independent Module, 4 Lectures)
L33 - Introduction to SVM - Video
L34 - SVM for Linear Separable Classification - Video
L35 - SVM for Linear Nonseparable and Nonlinear Classification - Video
L36 - SVM for Nonlinear Classification and Linear Regression - Video
L37 - Principal Component Analysis - Video
Assignments
1. Programming Assignment-1: PDF Images
2. Written Assignment-1: PDF
3. Programming Assignment-2: PDF Data
Exam Papers
1. Mid-term Exam Paper: PDF
2. Final Exam Paper: PDF
Click here to view the YouTube Playlist of the videos of this course.
Module-1: Overview
L01 - Course Description - Video
L02 - Is the Buzz Around Machine Learning Just a Hype? - Video
Module-2: Image Processing (Independent Module, 9 Lectures)
L03 - Introduction to ML, Image Acquisition, Sampling, Quantization - Video
L04 - Sampling, Quantization, Image processing vs Computer Vision - Video
L05 - Intensity Transform, Power-law, Piecewise Linear Transform - Video
L06 - Contrast Stretching and Histogram Equalization - Video
L07 - Histogram Equalization Continuation, Histogram Specification - Video
L08 - Variants of Histogram Equalization, Correlation, Convolution - Video
L09 - Convolution, Correlation, Gaussian Filter, Statistical Filters - Video
L10 - Dealing with Boundaries, Image Padding, Gradient Computation - Video
L11 - Kernels for Gradients, Edge Detection, Derivatives, Sharpening - Video
Module-3: Bayesian Classification (Independent Module, 14 Lectures)
L12 - Overview of Machine Learning, Classifier, Feature Vector - Video Notes
L13 - Bayes Theorem, A posteriori Probability, Likelihood - Video Notes
L14 - Decision Error, Average Risk, Generalizing to M Classes - Video Notes
L15 - Min. Average Risk, Likelihood Ratio-based Decision Rule - Video Notes
L16 - Decision Surfaces, Discriminant Functions, 1D Gaussian - Video Notes
L17 - Multivariate Gaussian Distribution, Isocurves, Examples - Video Notes
L18 - Normally Distributed Classes, 2D Discriminant Functions - Video Notes
L19 - Illustration of Discriminant Functions & Decision Planes - Video Notes
L20 - Decision Hyper Planes for Different Covariance Matrices - Video Notes
L21 - Decision planes, Minimum Distance Classifier, Examples - Video Notes
L22 - Recap, Maximum Likelihood (ML) Parameter Estimation Part-1 - Video Notes
L23 - Discussion of the Midterm Exam Paper - Video
L24 - ML Parameter Estimation Part-2 - Video Notes
L25 - Maximum a Posteriori Probability (MAP) Estimation - Video
Module-4: Neural Networks (Independent Module, 7 Lectures)
L26 - Linear Classifier Part-1 - Video
L27 - Linear Classifier Part-2 - Video
L28 - Nonlinear Classifier Part-1 - Video
L29 - Nonlinear Classifier Part-2 - Video
L30 - Backpropagation Part-1 - Video
L31 - Backpropagation Part-2 - Video
L32 - General Guidelines about Implementation of Neural Networks - Video
Module-5: Support Vector Machines - SVM (Independent Module, 4 Lectures)
L33 - Introduction to SVM - Video
L34 - SVM for Linear Separable Classification - Video
L35 - SVM for Linear Nonseparable and Nonlinear Classification - Video
L36 - SVM for Nonlinear Classification and Linear Regression - Video
L37 - Principal Component Analysis - Video
Assignments
1. Programming Assignment-1: PDF Images
2. Written Assignment-1: PDF
3. Programming Assignment-2: PDF Data
Exam Papers
1. Mid-term Exam Paper: PDF
2. Final Exam Paper: PDF