Scribd
Upload
51 views1 page

Machine Learning for Image Processing Course

The document provides details about a machine learning for image processing course. The 3 credit course is offered to postgraduate students and is a modification of an existing course. It will be offered starting July 2022 by the Department of Electrical Engineering. The course objectives are to understand concepts, theory, and algorithms for real-world image recognition and classification. The content covers topics like feature extraction, machine learning algorithms, deep learning methods and applications. Required textbooks are listed.

Uploaded by

Sai Vishal Thukkaraju
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
51 views1 page

Machine Learning for Image Processing Course

The document provides details about a machine learning for image processing course. The 3 credit course is offered to postgraduate students and is a modification of an existing course. It will be offered starting July 2022 by the Department of Electrical Engineering. The course objectives are to understand concepts, theory, and algorithms for real-world image recognition and classification. The content covers topics like feature extraction, machine learning algorithms, deep learning methods and applications. Required textbooks are listed.

Uploaded by

Sai Vishal Thukkaraju
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

1.

Title of the course Machine Learning for Image Processing


2. Course number EE508L
3. Structure of credits 3-0-0-3
4. Offered to PG
5. New course/modification to Modification To EE5024/4
6. To be offered by Department of Electrical Engineering
7. To take effect from July 2022
8. Prerequisite CoT
9. Course Objective(s): Student will understand the concepts, theory and computational algorithms
needed for several real world recognition or classification from Image data, leading to automated
scene understanding or summarization and decision making. Provides necessary skills for
understanding of similar tasks on text, speech, video and other forms of data. Can developing
several exciting learning tasks, in several domains ranging from medical, engineering to state of the
art industrial and societal needs
10. Course Content: Introduction to Image and Video data, Representation, Classification or
Recognition from data, Machine Learning; Feature extraction: From Images (SIFT, Wavelet, HoG)
and Videos (BoVW); Machine Learning: Linear Perceptron, Support vector Machines and Neural
Networks (NNs). Self Organizing Maps; Deep learning methods: Training in Deep Feed forward
NNs; Convolutional NNs, Training CNNs. Standard architectures; Features of Deep Networks:
Transfer learning, Multi-task learning, Transformation invariant learning etc.; Applications of Deep
Nets: Image segmentation, Object recognition, Transformation invariant recognition. Visual Tracking
with Deep trained nets; Introduction to other Deep learning Methods: GANs (Generative adversarial
networks). Bayesian Belief Networks for Semi-supervised learning. Recurrent NN.
11. Textbook(s):
1. Goodfellow I and BengioY, Deep Learning, MIT Press (2016).
2. Duda R O and Hart P E, Pattern Classification, WILEY (2001).

12. Reference(s):
1. Gonzalez R C and Woods R E, Digital Image Processing, Pearson Education (2001).

Powered by TCPDF ([Link])

You might also like