Prerequisite course: Basics of Machine Learning, Deep Learning

Course Content

Module I: Introduction

Introduction to images, 2D geometric transformations, Geometric transformation estimation, Visual Features and Representations: Edge, Blobs, Corner Detection; Scale Space and Scale Selection; SIFT, SURF; HoG, LBP, etc. Visual Matching: Bag-of-words, VLAD; RANSAC, Hough transform; Pyramid Matching; Optical Flow (Lecture - 10, Tutorial - 3)

Module II: Convolution Neural Network for Visual Recognition

Introduction, Image classification, Loss function and optimization, Neural networks, CNN architectures: AlexNet, ZFNet, VGG, InceptionNets, ResNets, DenseNets, Training (Lecture - 8, Tutorial - 3)

Module III: Recurrent Neural Networks

Review of RNNs; CNN + RNN Models: Spatio-temporal Models, Action/Activity Recognition (Lecture - 6, Tutorial - 2)

Module IV: Detection, segmentation, visualizing and understanding

CNNs for Detection: Background of Object Detection, R-CNN, Fast R-CNN, Faster R-CNN, YOLO, SSD, RetinaNet; CNNs for Segmentation: FCN, SegNet, U-Net, Mask-RCNN, Visualizing CNN features DeepDream, Style Transfer (Lecture - 10, Tutorial - 3)

Module V: Special Topic

Attention Models, Generative Models: GAN, VaE, Efficient hardware for deep learning, hyperspectral imaging (Lecture - 6, Tutorial - 2)

Learning Objectives

This is an advanced course on Computer Vision. This will enable the students to learn concepts of image processing, computer vision and utilize these techniques to implement vision algorithms efficiently for use in research or industry.

Learning Outcomes:

At the end of the course, the students will be able to:

  • Implement fundamental image processing techniques required for computer vision
  • Understand Image formation process
  • Develop computer vision applications

Textbooks

  1. Richard Szeliski, Computer Vision: Algorithms and Applications, 2010.
  2. Simon Prince, Computer Vision: Models, Learning, and Inference, 2012.
  3. Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, 2016

References

Past Offerings

(Note: Past offerings could be under a different course number.)
  • Offered in Aug-Nov, 2023 by Satyajit Das
  • Offered in Aug-Dec, 2022 by Satyajit Das
  • Offered in Jul-Dec, 2021 by Satyajit

Course Metadata

Item Details
Course Title Computer Vision
Course Code DS5602
Course Credits 3-1-0-4
Course Category PME
Proposing Faculty Satyajit Das
Approved on Senate 16 of IIT Palakkad
Course prerequisites Basics of Machine Learning, Deep Learning
Course status New
Course revision information Same as CS5602
Course pre-revision code CS5620