Hi Guest, 30 September 2020 Wednesday IST

About CUSAT | About Department | Alumni | Sitemap | Disclaimer  

     
 
  Home > Academic/Programmes > Programme Structure > CSE (2017)
       
       
 
CSE3203: MACHINE LEARNING FOR MULTIMEDIA ANALYSIS
Core/Elective: Elective Semester: 2 Credits: 4
Course Description

This course is about the machine learning techniques and algorithms used for acquiring, processing and extracting useful information from Audio, images and Video.

Course Objectives

To study machine learning concepts of Audio, Image and Video Processing.
To understand the mathematical foundations for machine learning approaches for manipulation of Audio, Image and Video Processing.

Course Content

1.Audio Acquisition, Representation and Storage- Introduction- Sound Physics, Production and Perception- Audio Acquisition- Sampling and Aliasing-The Sampling Theorem- Linear Quantization-Nonuniform Scalar Quantization- Audio Encoding and Storage Formats- Time-Domain Audio Processing

2.Image and Video Acquisition, Representation and Storage- Introduction- Human Eye Physiology-Structure of the Human Eye- Image Acquisition Devices-Digital Camera -Color Representation-Human Color Perception- Color Models-Image Formats-Image File Format Standards-JPEG Standard-Video Principles-MPEG Standard

3. Machine Learning- Taxonomy of Machine Learning- Learning from Examples- Supervised Learning-Reinforcement Learning-Unsupervised Learning-Bayesian Theory of Decision- Bayes Decision Rule- Bayes Classifier- Loss Function- Zero-One Loss Function- Discriminant Functions- Gaussian Density- Discriminant Functions for Gaussian Likelihood- Receiver Operating Curves

4. Clustering Methods- Expectation and Maximization Algorithm- Basic Notions and Terminology- K-Means- Self-Organizing Maps- Optimization by EM Algorithm- Fuzzy Clustering Algorithms- Hierarchical Clustering- Artificial Neural Networks and Neural Computation- Markovian Models for Sequential Data.

5. Applications- Speech and Handwriting Recognition- The General Approach- HMM Training- Recognition and Performance Measures- Automatic Face Recognition- Face Detection and Localization- Lighting Normalization- Feature Extraction- Classification-Video Segmentation and Keyframe Extraction- Shot Boundary Detection- Keyframe Extraction.

REFERNCES

1. Francesco Camastra, Alessandro Vinciarelli, Machine Learning for Audio, Image and Video Analysis: Theory and Applications, Springer; 2 edition (July 21, 2015)
2. Machine Learning: A Probabilistic Perspective, Kevin P Murphy, MIT Press (2012)
3. Pattern Recognition and Machine Learning, Christopher M Bishop, Springer, (2006)
4. The Elements of Statistical Learning: Data mining, Inference, and Prediction, Trevor Hastie et. al., 2nd Edn, Springer, (2009)


Copyright © 2009-20 Department of Computer Science,CUSAT
Design,Hosted and Maintained by Department of Computer Science
Cochin University of Science & Technology
Cochin-682022, Kerala, India
E-mail: csdir@cusat.ac.in
Phone: +91-484-2577126
Fax: +91-484-2576368