Semester –VI

Course Title: Computer Vision and Deep Learning

Teaching Scheme Evaluation Scheme

Semester VI
Theory Practical
Term EVEN Th Tu Pr Credits TAE CAE ESE INT EXT

Course
C
Category
3 -- 2 4 10 15 50 25 --
Course UAIL303
Code UAIP303

Teaching
75 25
Mode
5 Total
Duration of
3 Hrs. 100
ESE

1. To introduce traditional Computer Vision

Course Objec- 2. Introduce Deep Learning Models and their applications to Computer Vision

tives
3. To apply Deep learning Techniques to various computer vision applications.

CO1:Understand and master basic knowledge, theories and methods in image

processing and computer vision.

CO2:Discuss feed forward networks and their training issues

Course Out- CO3:Select appropriate Deep Learning Networks for potential applications

comes CO4: Ability to recognize and implement various ways of selecting suitable model

parameters for different deep learning techniques.

CO5: Ability to integrate deep learning libraries and mathematical and statistical
tools for computer vision applications

Mapping of Course Outcomes with Program Outcomes and Program Specific Outcomes:

Course Out- Program Outcomes and Program Specific Outcomes

comes
PO PO PO PO PO PO PO PO PO PO PO PO PSO PSO 2
1 2 3 4 5 6 7 8 9 10 11 12 1

CO1 -- 3 3 3 2 -- -- -- -- -- -- -- 1 --

CO2 -- 3 3 2 -- -- -- -- -- -- -- -- 2 2
CO3 -- 3 3 -- -- -- -- -- -- -- -- -- -- 2
CO4 -- 3 3 -- -- -- -- -- -- -- -- -- -- --
CO5 2 3 3 -- -- -- -- -- -- -- -- -- -- --
 Curriculum for B. Tech. in Artificial Intelligence

Course Contents:

Hou rs
Unit Contents

History, Image Formation, Image Representation, Linear Filtering, Image in Frequency Domain, Image Sampling, Image Processing
I & Feature Extraction, 8
Correlation, Convolution

Visual Features & Representations- Edge, Blobs, Corner Detection; Scale Space and Scale Selection; SIFT, SURF; HoG, LBP, etc. Vis-
ual Matching - Bag- of-words, VLAD; RANSAC, Hough transform; Pyramid Matching; Optical Flow
II History of Deep Learning, Feedforward Networks & Backpropagation Learning Gradient Descent (GD), Gradient Descent Variants 8

Convolutional Neural Networks - Introduction to CNNs; Evolution of CNN Architectures: AlexNet, ZFNet, VGG, InceptionNets,
ResNets, DenseNets, Visualization and Understanding CNNs:Visualization of Kernels; Backprop- to-image/Deconvolution Methods;
Deep Dream, Hallucination, Neural Style
III 6
Transfer; CAM,Grad-CAM, Grad-CAM++; Recent Methods (IG, Segment-IG, SmoothGrad)

CNNs for Recognition, Verification, Detection, Segmentation:

CNNs for Recognition and Verification (Siamese Networks, Triplet Loss, Contrastive Loss, Ranking Loss); CNNs for Detection: Back-

IV ground of Object Detection, R-CNN, Fast R-CNN, Faster R-CNN, YOLO, SSD, RetinaNet; CNNs for Segmentation: FCN, SegNet, U-Net, 7
Mask-RCNN

Recurrent Neural Networks (RNNs): Review of RNNs; CNN + RNN Models for Video Understanding: Spatio-temporal Models, Ac-
tion/Activity Recognition,Attention Models -Introduction to Attention Models in Vision; Vision and Language: Image Captioning, Vis-
ual QA, Visual Dialog; Spatial Transformers; Transformer Networks, Deep Generative Models, Variants and Applications of Generative
V 9
Models in Vision:

―Computer Vision Metrics: Survey, Taxonomy, and Analysis‖ by Andy Krig Scott
1.

Deep Learning in Computer Vision,Principles and

Text 2.
Applications,MahmoudHassaballah, Ali Ismail Awad
Books
Modern Deep Learning and Advanced Computer Vision, A Perspective Approach, Dr.P.S.Jagadeesh Kumar, Prof. Thomas Bin-
3. ford, Dr.J. Ruby, J.
Lepika
Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville
1.
https://www.deeplearningbook.org/

E-Books Computer Vision: A Modern Approach (Second Edition) by David Forsyth and Jean Ponce
2. http://luthuli.cs.uiuc.edu/~daf/CV2E-site/cv2eindex.html

Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani, and

1
References Jerome Friedman
2. Computer Vision: Algorithms and Applications by Richard Szeliski

on line TL
1. https://nptel.ac.in/courses/106/106/106106224/
Material

P ag e |2
 Curriculum for B. Tech. in Artificial Intelligence

Sr. No. Name of Experiments / Mini Projects/ Case Studies

1 Introduction to OpenCV

2 Implement Image Classification using Deep Learning

3 Create and train a Convolutional Neural Network(CNN) on Animals/CIFAR-10

Dataset.
4 Perform Feature Extraction on a Pre-trained CNN.
5 Implement Object Detection Using Deep Learning
6 Implement ResNet on CIFAR-10 Dataset
7 Implement LeNet on MNIST Dataset.
8 Implement Pose Detection using Deep Learning and Posenet
9 Classify Images with Pre-trained Imagenet CNN.
Open Ended Experiments / New Experiments
1 Train a CNN to make a smile detection application
2 Implementing and Training a SRCNN
Details of on line Laboratory Resource Material Instruction / Operating Manuals

1. Practical Deep Learning

URL: https://github.com/PracticalDL/Practical-Deep-Learning-Book

P ag e |3