A place where legacy creates future.

Program

CVDL Master
Detailed Curriculum
Index

Course 1 - MOCV
Mastering OpenCV with Python
|
Course 2 - CVIP
Fundamentals of Computer Vision & Image Processing
|
Course 3 - DLPT
Deep Learning with PyTorch
|
Course 4 - DLTK
Deep Learning with TensorFlow & Keras
|
Course 5 - DLAP
Computer Vision and Deep Learning Applications
|
Course 6 - GENAI
Mastering Generative AI for Art

2 of 30 CV Master Program
3 of 30 CV Master Program
Course 1 - MOCV

Mastering OpenCV with Python

1. Getting Started with Images

1.1. Image Basics (Basics of Image Formation and Image Formats)
1.2. Reading, Display and Writing Images in OpenCV
1.3. Color space conversion and different color spaces
1.4. Basic image manipulation (resizing, cropping, annotating,
creating a Region of Interest)

2. Basic Image Operations

2.1. Mathematical operations on images (brightness and contrast)
2.2. Image thresholding, bitwise operations and masking
2.3. Image blending and the alpha channel
2.4. Creating Digital signatures using alpha blending

3. Histograms and Color Segmentation

3.1. Image histograms and enhancement using Histogram
equalization
3.2. Color segmentation on images
3.3. Deforestation analysis using Color Segmentation
3.4. Satellite Imagery analysis using GeoTIFF Images

4. Video Processing and Analysis

4.1. Reading and Writing videos using OpenCV
4.2. Motion Detection analysis using Background Subtraction

5. Contours and Shape Analysis

5.1. Finding and Drawing Contours
5.2. Intruder detection using Contour Analysis

6. Human Computer interaction(HCI) using PyAutoGUI

6.1. Keyboard and Mouse Controls using PyAutoGUI
6.2. Playing Online Games using PyAutoGUI

7. Building and Deploying Apps with Streamlit

7.1. Building a Face detection application using streamlit

4 of 30 CV Master Program
 7.2. Deploying streamlit apps on Streamlit cloud
7.3. App Deployment on Heroku

8. Image Filtering and Enhancement

8.1. Image Filtering using Convolution Operations
8.2. Image Blurring and sharpening using convolutions
8.3. Edge Detection using Sobel Filters and Canny algorithm
8.4. Artistic Renderings using Image Filters

9. Hough Transforms
9.1. Detecting Lines using Hough Lines
9.2. Lane detection using using Hough Transforms from videos

10. Image Restoration Techniques

10.1. Noise Reduction using Median and Bilateral Filters
10.2. Image Inpainting for Image Restoration
10.3. Building a streamlit application on image restoration using
Inpainting.

11. Image Registration Techniques

11.1. Affine Transforms and Homography
11.2. Image Alignment using Homography and Feature Matching
11.3. Building Virtual billboards and Creating Panoramas

12. Augmented Reality

12.1. Overview of ArUco markers
12.2. Application: AR using ArUco Markers

13. Deep Learning using OpenCV

13.1. Introduction to OpenCv’s DNN Module.
13.2. Image classification using OpenCV DNN Module
13.3. Web application for Image Classification

14. Face and Landmark Detection

14.1. Face Detection using DNN Module
14.2. Face Blurring
14.3. Facial Landmarks Detection

5 of 30 CV Master Program
 14.4. Building a Real-time Blink Detection application

15. Object Detection

15.1. Object Detection using MobileNet SSD, YOLOv4 and YOLOv5
15.2. Building a Social Distance Monitoring Application

16. Object Tracking

16.1. Introduction on Object Tracking Models in OpenCV
16.2. Comparison across multiple tracking models.

17. Human Pose Estimation

17.1. Human Pose Estimation using MediaPipe
17.2. Sports Analytics using MediaPipe

18. Human Segmentation

18.1. Creating selfie-style photos using Person Segmentation through
MediaPipe

19. Text Detection and OCR

19.1. Text Detection using EAST and Differentiable Binarization (DB)
19.2. OCR on Natural Images
19.3. Language Translation using OCR

20. Super Resolution

20.1. Image Super Resolution techniques using OpenCV

21. Deploying Web Applications on Cloud Services

21.1. Building web applications using streamlit
21.2. Deploying web applications using AWS, GCP, and Azure

6 of 30 CV Master Program
Course 2 - CVIP

Fundamentals of Computer Vision & Image Processing

Module 1
Getting Started with OpenCV
|
Module 2
Video IO and GUI
|
Module 3
Binary Image Processing
|
Module 4
Image Enhancement and Filtering
|
Module 5
Advanced Image Processing and
Computational Photography
|
Module 6
Geometric Transforms and Image Features
|
Module 7
Image Segmentation and Recognition
|
Module 8
Video Analysis and Object Tracking
|
Module 9
Deep Learning with OpenCV

7 of 30 CV Master Program
 1 Getting Started with OpenCV
1.1 Introduction to Computer Vision
1.1.1 Image Processing VS Computer Vision
1.1.2 Problems in Computer Vision
1.2 Introduction to images
1.2.1 How are images formed?
1.2.2 Digital image
1.2.3 Image as a matrix
1.2.4 Manipulating pixels
1.2.5 Displaying and saving an image
1.2.6 Display utility functions
1.2.7 Color image
1.2.8 Image channels
1.2.9 Splitting and merging channels
1.2.10 Manipulating color pixels
1.2.11 Images with Alpha channel
1.3 Basic image operations
1.3.1 How to create new images?
1.3.2 Cropping an image section
1.3.3 Copying a region to another in an image
1.3.4 Resizing an image
1.3.5 Creating an image mask
1.4 Mathematical operations on images
1.4.1 Datatype conversion
1.4.2 Contrast enhancement
1.4.3 Brightness enhancement
1.5 Sunglass filter: A simple application
1.5.1 Load images
1.5.2 Use naive replacement
1.5.3 Use arithmetic operations
1.6 Bitwise operations
1.6.1 Different bitwise operations
1.7 Image annotations
1.7.1 Draw a line over an image
1.7.2 Draw a circle over an image
1.7.3 Draw a rectangle over an image
1.7.4 Draw an ellipse over an image
1.7.5 Draw text over an image

8 of 30 CV Master Program
 Assignment 1 Build a QR Code Detector

2 Video IO & GUI

2.1 Video IO using HighGUI
2.1.1 Video IO jargon
2.1.2 Read and display video
2.1.3 Properties of video capture
2.1.4 How to write a video
2.2 Callback Functions
2.2.1 What are Callback Functions?
2.3 Keyboard as input device
2.3.1 How to take input from keyboard

Assignment 2 Perform Image Annotation Using Mouse

Assignment 3 Enhance GUI features with Sliders

3 Binary Image Processing

3.1 Thresholding
3.1.1 What is Thresholding?
3.1.2 Thresholding in OpenCV
3.2 Erosion / Dilation
3.2.1 Overview on Erosion and Dilation
3.2.2 Erosion and Dilation in OpenCV
3.3 Opening and Closing
3.3.1 Overview on Opening and Closing
3.3.2 Opening and Closing on OpenCV
3.4 Connected Component Analysis
3.4.1 What is Connected Component Analysis?
3.4.2 Connected Component Analysis in OpenCV
3.5 Contour Analysis
3.5.1 What are Contours?
3.5.2 Contour Analysis in OpenCV
3.6 Blob detection
3.6.1 Blob detection in OpenCV

9 of 30 CV Master Program
 Assignment 4 Implement Different Morphological Operations

Assignment 5 Build a Coin Detection application using Contours

4 Image Enhancement & Filtering

4.1 Color spaces
4.1.1 RGB color space
4.1.2 HSV color space
4.1.3 Other color spaces
4.1.4 Application: Finding dominant color in an image
4.1.5 Application: Desaturation Filter
4.2 Color transforms
4.2.1 Histogram Equalization
4.2.2 Advanced Histogram Equalization (CLAHE)
4.2.3 Color adjustment using curves
4.3 Image filtering
4.3.1 Introduction to image filtering
4.3.2 What is Convolution?
4.3.3 Convolution in OpenCV
4.4 Image smoothing
4.4.1 Box Blur
4.4.2 Gaussian Blur
4.4.3 Median Blur
4.4.4 Median Blur in OpenCV
4.4.5 Bilateral filtering
4.4.6 Bilateral Blur in OpenCV
4.4.7 Comparison: Median VS Bilateral
4.5 Image gradients
4.5.1 Introduction to image gradients
4.5.2 First Order Derivative Filters
4.5.3 Why is smoothing important before gradient?
4.5.4 Second Order Derivative Filters
4.5.5 Application: Sharpening Filter
4.5.6 Canny Edge Detection
4.5.7 Canny Edge Detection in OpenCV

10 of 30 CV Master Program
 Assignment 6 Convert Your Images Into Different Color Spaces

Assignment 7 Implement Camera Autofocus using Image Analysis

5 Advanced Image Processing & Computational Photography

5.1 Hough transforms
5.1.1 What is a hough transform?
5.1.2 HoughLine: How to detect a line in an image?
5.1.3 HoughCircle: How to detect a circle in an image?
5.2 High Dynamic Range imaging
5.2.1 What is High Dynamic Range (HDR) imaging?
5.2.2 HDR in OpenCV
5.3 Seamless cloning
5.3.1 What is seamless cloning?
5.3.2 Seamless cloning in OpenCV
5.3.3 Application: Face Blending
5.4 Image inpainting
5.4.1 What is image inpainting?

● Create Your Own Instagram Filter

Project 1 ● Blemish Removal From Face
● Chroma Keying

6 Geometric Transforms & Image Features

6.1 Geometric transforms
6.1.1 Affine transform
6.1.2 Homography
6.1.3 Geometric transforms in OpenCV
6.2 Image features
6.2.1 Image feature: ORB
6.2.2 ORB feature in OpenCV
6.3 Feature matching
6.3.1 Different feature matching algorithms in OpenCV
6.3.2 RANSAC
6.4 Application: Image alignment

11 of 30 CV Master Program
 6.5 Application: Creating panoramas
6.6 Application: Finding known objects using OpenCV

Assignment 8 Create Panorama from Multiple Images

Assignment 9 Feature Matching-Based Image Alignment

Project 2 Implement a Document Scanner Application

7 Image Segmentation & Recognition

7.1 Image segmentation using GrabCut
7.1.1 GrabCut theory
7.1.2 GrabCut in OpenCV
7.2 Introduction to AI
7.2.1 Basic overview of AI
7.3 Image classification
7.3.1 Histogram of Oriented Gradients (HOG)
7.3.2 Support Vector Machines (SVM)
7.3.3 Eyeglass Classifier in OpenCV
7.4 Object detection
7.4.1 Pedestrian detection in OpenCV
7.4.2 Face detection using HAAR Cascade
7.4.3 Face detection in OpenCV

Create Your Own Selfie Application

Project 3 ● Skin Smoothing Filter
● Sunglass Filter

8 Video Analysis

8.1 Motion estimation using Optical Flow

8.1.1 What is Optical Flow?
8.1.2 Lucas-Kanade Optical Flow
8.2 Application: Video stabilization
8.3 Object tracking
8.3.1 Different object tracking algorithms
8.4 Different object trackers in OpenCV

12 of 30 CV Master Program
 8.4.1 Object tracking in OpenCV
8.4.2 Comparison of different trackers
8.5 Multiple object tracking
8.5.1 How to track multiple objects in OpenCV
8.6 Kalman filtering
8.6.1 Kalman Filter Tracker
8.7 MeanShift and CamShift
8.7.1 Tracking using MeanShift and CamShift

Project 4 Implement fusion of Detection + Tracking

9 Deep Learning with OpenCV

9.1 Image classification
9.1.1 Image classification using Caffe and TensorFlow
9.2 Object detection
9.2.1 Single Shot Multibox Detector (SSD)
9.2.2 You Only Look Once Detector (YOLO)
9.3 Face detection
9.3.1 SSD-Based Face Detector
9.4 Human pose estimation
9.4.1 OpenPose

13 of 30 CV Master Program
Course 3 - DLPT

Deep Learning with PyTorch

Module 1
Getting Started with PyTorch
|
Module 2
Neural Networks
|
Module 3
Convolutional Neural Networks
|
Module 4
Deep Neural Networks
|
Module 5
Best Practices in Deep Learning
|
Module 6
Object Detection
|
Module 7
Single Stage Object Detectors
|
Module 8
Segmentation
|
Module 9
Pose Estimation
|
Module 10
Bonus Module: Generative Adversarial Networks (GANs)

14 of 30 CV Master Program
 1 Getting Started with PyTorch
1.1 Introduction to Artificial Intelligence
1.1.1 History of AI
1.1.2 Applications of AI
1.1.3 AI in Computer Vision
1.1.4 AI terminology
1.1.5 Why is Deep Learning so popular?
1.2 NumPy refresher
1.3 Introduction to PyTorch
1.3.1 Why use PyTorch?
1.3.2 Overview of PyTorch
1.3.3 PyTorch basics
1.4 What is inside an ML algorithm?
1.4.1 Machine Learning pipeline
1.4.2 Solving ML problems
1.4.3 Gradient Descent
1.4.4 Gradient Descent for Optimization

Assignment 1 Implement ReLu, Softmax & Neuron Using PyTorch

Assignment 2 Implement Gradient Descent For Two Variables

2 Neural Networks
2.1 Feature Vectors 1-D to N-D
2.1.1 Feature Vectors & Normalization
2.2 Basics of Neural Networks
2.2.1 What is a Neural Network?
2.2.2 Loss Functions for Regression
2.2.3 Loss Functions for Classifications
2.2.4 Types of Activation Functions
2.2.5 How does the network learn?
2.2.6 Demystifying Neural Networks
2.3 Binary Classification using Perceptrons
2.4 PyTorch NN module
2.4.1 Introduction to PyTorch NN Module
2.4.2 MLP using Functional API
2.4.3 MLP using Sequential API
2.5 Image Classification using Multilayer Perceptron
2.5.1 MLP Classifier for Handwritten Digits (MNIST)

15 of 30 CV Master Program
 Assignment 3 Implement MSE & MAE Loss Functions

3 Convolutional Neural Networks

3.1 Convolution operation
3.1.1 What is a Convolution operation?
3.1.2 CNN building blocks
3.1.3 Layers in CNN
3.2 How to implement LeNet using PyTorch?
3.2.1 How to implement LeNet?
3.2.2 Implementing LeNet using PyTorch
3.2.3 LeNet with Batch Normalization
3.2.4 Effects of Batch Normalization
3.3 Evaluation of Classification Performance
3.3.1 Performance metrics for Classification
3.3.2 How to implement Classification metrics?
3.4 Introduction to Torchvision
3.4.1 Torchvision overview
3.4.2 Datasets
3.4.3 What are the different Transforms used to train a network?
3.4.4 Different models in Torchvision
3.5 Important CNN architectures
3.5.1 Different CNN architectures
3.5.2 Pre-trained models in Torchvision
3.5.3 Pre-trained Classification models in Torchvision

Implement CNN For Image Classification On CIFAR10

Assignment 4
Dataset

4 Deep Neural Networks

4.1 Optimization
4.1.1 What are Optimizers?
4.1.2 Learning Rate Decay methods
4.1.3 LR Scheduler
4.2 Training Deep Neural Networks
4.2.1 Step 1: Data understanding
4.2.2 Step 2: Data preparation
4.2.3 Step 3: Check training pipeline
4.2.4 Step 4: Train the model
4.2.5 Step 5: Improve the model

16 of 30 CV Master Program
 4.2.6 Check training pipeline
4.3 How to add robustness to a model?
4.3.1 Bias-variance tradeoff
4.3.2 How to prevent Overfitting?
4.3.3 Training with Regularization
4.4 Data loader with ImageFolder
4.4.1 How to load custom datasets in PyTorch?

Assignment 5 Implement the Adam Optimizer

Project 1 Implement An Image Classifier From Scratch

5 Best Practices in Deep Learning

5.1 Troubleshooting training with TensorBoard
5.1.1 TensorBoard overview
5.1.2 TensorBoard dashboard
5.1.3 Logging using TensorBoard
5.1.4 Sharing TensorBoard logs
5.2 Leverage pre-trained models
5.2.1 CNN architectures (Recap)
5.2.2 Fine-tuning and Transfer Learning
5.2.3 Fine-turning using ResNet
5.3 How to structure your project for scale?
5.3.1 Introduction to py_modules package
5.3.2 Motivation of Trainer Pipeline
5.3.3 Hands-on Trainer Pipeline
5.4 Introduction to PyTorch Lightning
5.4.1 PyTorch Lightning overview
5.4.2 Inference on Production (ONNX)
5.4.3 Transfer Learning with Lightning

Project 2 Kaggle Competition On Image Classification

6 Object Detection
6.1 Overview of Object Detection
6.1.1 Introduction to Object Detection
6.2 Evaluation metrics

17 of 30 CV Master Program
 6.2.1 Evaluation metrics for Object Detection
6.2.2 Compute evaluation metrics
6.3 Traditional algorithms in Object Detection
6.3.1 Different traditional algorithms
6.3.2 Implement Non-Maximum Suppression
6.4 Two-Stage Object Detectors
6.4.1 Introduction to Two-Stage Object Detectors
6.4.2 Faster RCNN using Torchvision
6.4.3 Understanding faster RCNN
6.4.4 Fine-tuning of faster RCNN
6.4.5 Fine-tuning training of faster RCNN

7 Single Stage Object Detectors

7.1 You Only Look Once (YOLO)
7.1.1 Introduction to YOLO
7.2 Single Stage Multibox Detector (SSD)
7.2.1 Introduction to SSD
7.2.2 SSD with PyTorch Hub
7.3 RetinaNet
7.3.1 Introduction to RetinaNet
7.3.2 RetinaNet with Detectron2
7.4 How to create a custom Single State Multibox Detector (SSD)?
7.4.1 Detector NN architecture
7.4.2 Generating Anchor Boxes
7.4.3 Matching predictions with ground truth
7.4.4 Loss Function
7.4.5 Experiment

Assignment 6 Implementing Focal Loss for Object Detection

Project 3 Automatic Number Plate Detection

8 Segmentation
8.1 Semantic Segmentation architecture
8.1.1 Types of Semantic Segmentation architectures
8.1.2 Dilated Convolution
8.1.3 Transposed Convolution
8.1.4 Fully Convolutional Network (FCN)
8.1.5 U-Net

18 of 30 CV Master Program
 8.1.6 SegNet
8.1.7 DeepLab
8.2 Evaluation metrics for Semantic Segmentation
8.2.1 Dice Coefficient metrics
8.3 LinkNet architecture
8.3.1 Introduction to LinkNet architecture
8.4 Soft-Dice Loss
8.4.1 Introduction to Soft-Dice Loss
8.5 FCN and DeepLab using Torchvision
8.5.1 FCN and DeepLabV3 using Torchvision
8.6 U-Net for MRI Abnormality Segmentation
8.7 Train your model from scratch
8.8 Instance Segmentation
8.8.1 Instance Segmentation using Mask RCNN

Assignment 7 LinkNet Architecture With VGG16

Project 4 Kaggle Competition On Semantic Segmentation

9 Pose Estimation
9.1 DensePose
9.1.1 Introduction to DensePose
9.1.2 DensePose inference
9.1.3 DensePose training
9.2 Create your own gym trainer
9.2.1 Automated Squat Counter

Project 5 Create An App Of Your Choice

10 Generative Adversarial Networks (GANS)

10.1 GANs
10.1.1 Introduction to GANs
10.1.2 Vanilla GAN using Fashion MNIST
10.1.3 DCGAN using Flickr Faces
10.1.4 CGAN using Fashion MNIST

19 of 30 CV Master Program
Course 4 - DLTK

Deep Learning with TensorFlow & Keras

Module 1
Getting Started with Tensorflow and Keras
|
Module 2
Neural Networks
|
Module 3
Convolutional Neural Networks
|
Module 4
Best Practices In Deep Learning
|
Module 5
Object Detection
|
Module 6
Image Segmentation
|
Module 7
Pose Estimation
|
Module 8
Bonus: Generative Adversarial Networks (GANS)

20 of 30 CV Master Program
 1 Getting Started with TensorFlow and Keras
1.1 Introduction to Artificial Intelligence
1.2 AI in Computer Vision
1.3 AI terminology
1.4 NumPy refresher
1.5 Introduction to TensorFlow & Keras
1.6 What is inside an ML algorithm?
1.7 Gradient-based Optimization techniques in ML

Implement Leaky ReLu, Softmax & Convolution Using

Assignment 1
TensorFlow

Assignment 2 Implement Gradient Descent For Two Variables

2 Neural Networks
2.1 Feature Vectors & Normalization
2.2 Basics of Neural Networks
2.3 Understanding Backpropagation in a Neural Network
2.4 Loss Functions for Recgression and Classification Tasks.
2.5 Mathematical foundation for Regression & Classification
2.6 Implementing a single neuron to model Linear Regression
2.7 Binary Classification using Perceptrons
2.8 Image Classification using Multilayer Perceptron
2.9 Model Complexit, Generalizaation and handling Overfitting
2.10 Understand and implement the building blocks like the different Activation
Functions, Loss Functions, Hidden Layers

Implement A Multi-Layer Perceptron For Apparel

Assignment 3
Classification

3 Convolutional Neural Networks

3.1 The Convolution operation
3.2 CNN building blocks and Layers
3.3 Evaluation metrics for Classification Performance
3.4 Important CNN architectures like VGGNet and ResNet
3.5 Leverage pre-trained models using Transfer Learning and Fine-tuning
3.6 Building custom models from scratch using your own data
3.7 Handling Overfitting through Data augmentations

21 of 30 CV Master Program
 Assignment 4 Conversion from Sequential API to Functional API.

Implement a CNN For Image Classification On CIFAR10/100

Assignment 5
Dataset

Project 1 Implement An Image Classifier From Scratch

4 Best Practices in Deep Learning

4.1 Advanced Optimizers in Keras
4.2 Training Deep Neural Networks
4.3 Handling Data in TensorFlow using TF Data, Sequence Class, and TF Records
4.4 Learning Rate Schedulers
4.5 Model Interpretability using GradCAM

Assignment 6 Implement AdamW Optimizer

Project 2 Kaggle Competition For Sports Item Classification

5 Semantic Segmentation
5.1 Problem formulation, custom layers and Loss Functions associated with
Segmentation, like Dilated & Transposed Convolution, Dice Loss, Pixel
Accuracy, etc.
5.2 Semantic Segmentation Datasets and Architectures
5.3 Evaluation metrics for Semantic Segmentation
5.4 Custom DataLoader for Segementation Datasets
5.5 Fully Convolutional Networks (FCNs) and UNet training for Binary
Segmentation on Road Data
5.6 UNet and DeepLab v3+ Training on Multi-class segmentation on CamVid
Data.
5.7 Improving DeepLab v3+ on Segmentation of Underwater Imagery (SUIM)

Assignment 7 Implementation of PSPNet

Kaggle Competition On Semantic Segmentation Of

Project 3
FloodNet Dataset

22 of 30 CV Master Program
 6 Object Detection
6.1 Evolution from traditional Object Detection algorithms to state-of-the-art
Deep Learning-based methods
6.2 Exploring Object detection Datasets.
6.3 Revisiting Image Classification, and comparing it with Object Detection.
6.4 Two-Stage & Single Stage Object Detectors
6.5 Problem formulation, custom layers and Loss Functions used in Object
Detection like Anchors, NMS, IoU, etc.
6.6 Learn about Object Detection models like RCNN, SSD, RetinaNet, YOLO,
EfficientDet
6.7 Evaluation metrics for Object Detection: Precision, Recall, Average
Precison(AP) and mean average Precison (mAP)
6.8 Using the TensorFlow Object Detection (TFOD) API
6.9 Fine-tuning of Object Detection Models available on TFOD API on a subset of
Pascal VOC data.
6.10 Building a Custom SSD Model with FPN and training it on PenFudanPed
Dataset

Encoding And Decoding Of Ground Truths For Anchor Box

Assignment 8
Implementation

Build A Custom Object Detection Model For Detecting

Project 4
Safety Kits In Construction Sites

7 Pose Estimation using MediaPipe

7.1 Real-time Posture analysis using MediaPipe Pose
7.2 Drowsy Driver Detection using MediaPipe

8 Generative Adversarial Networks (GANS)

8.1 Introduction to GANs
8.2 Vanilla GAN using Fashion MNIST
8.3 DCGAN using Flickr Faces
8.4 CGAN using Fashion MNIST

23 of 30 CV Master Program
Course 5 - DLAP

Computer Vision and Deep Learning Applications

Module 1
Facial Landmark Detection
|
Module 2
Applications of Facial Landmarks
|
Module 3
Snapchat Filters
|
Module 4
Face Recognition
|
Module 5
Introduction to Deep Learning with CNNs
|
Module 6
State-of-the-art Object Detection
|
Module 7
Text Detection And OCR
|
Module 8
Deploy Applications On Cloud

24 of 30 CV Master Program
 1 Facial Landmark Detection
1.1 Different face processing applications
1.2 Facial Landmark Detection using Dlib
1.2.1 Introduction to Dlib
1.2.2 Facial Landmark Detection using Dlib
1.3 Application: Face Alignment
1.4 Improving Facial Landmark Detector
1.4.1 Improving speed
1.4.2 Improving stability
1.4.3 Landmark stabilization in OpenCV
1.4.4 Optical Flow
1.4.5 Lucas-Kanade Optical Flow
1.5 Facial Landmark Detection Theory
1.5.1 Machine Learning basics
1.5.2 Research paper review
1.6 Train a custom Facial Landmark Detector
1.6.1 How to train a custom Landmark Detector?

2 Applications of Facial Landmarks

2.1 Alpha Blending
2.1.1 Alpha Blending in OpenCV
2.2 Image Warping
2.2.1 Affine Transform
2.2.2 Geometric Transform
2.2.3 Triangle Warping
2.3 Delaunay Triangulation
2.3.1 Theory of Delaunay Triangulation
2.4 Face Averaging
2.4.1 Face Averaging using OpenCV
2.5 Face Morphing
2.5.1 Face Morphing using OpenCV
2.6 Application: Bug Eyes
2.6.1 Create a Big Eye app
2.7 Head Pose Estimation
2.7.1 Head Pose Estimation in OpenCV

Assignment 1 Build an Automatic Smile Detection Application

25 of 30 CV Master Program
 3 Snapchat Filters
3.1 Face Swap
3.1.1 How can Face Swapping be achieved?
3.1.2 Seamless Cloning
3.1.3 Seamless Cloning in OpenCV
3.1.4 Face Swapping in a video
3.2 Application: Beard Filter
3.3 Application: Aging Filter
3.4 Non-linear Deformations
3.4.1 Moving Least Squares
3.4.2 Application: Happify and Fatify filters on face

Project 1 Build a Virtual Makeup Application

4 Face Recognition
4.1 Introduction to Face Recognition
4.2 Eigen Faces
4.3 Fisher Faces
4.4 Local Binary Patterns Histograms
4.5 Face Recognition API in OpenCV
4.6 Deep Learning-based Face Recognition [To be updated with latest models]

Project 2 DoppelGanger: Find Celebrity Look-Alike

5 Introduction to Deep Learning

5.1 Basics of Neural Networks
5.1.1 What is a Neural Network?
5.1.2 How do Neural Networks learn?
5.2 Introduction to Keras [To be updated to The PyTorch framework]
5.2.1 Deep Learning frameworks
5.2.2 The Keras Framework
5.2.3 Linear Regression using Keras
5.3 Convolutional Neural Network
5.3.1 What is a Convolutional Neural Network (CNN)?
5.3.2 Example: Image Classification using CNN
5.3.3 Data Augmentation (Python)
5.4 Transfer Learning and Fine-tuning and Logging
26 of 30 CV Master Program
 5.4.1 Weights and Biases Logging
5.4.2 Transfer Learning
5.4.3 Fine-Tuning

Assignment 2 Improve CNN Performance during Training

6 Object Detection
6.1 Object Detection overview
6.1.1 What is Object Detection?
6.1.2 Traditional Object Detection pipeline
6.2 YOLOv3 using DarkNet [To be updated to YOLOv8 using Ultralytics]
6.2.1 Inference using YOLOv3
6.2.2 Fine-Tuning using YOLOv3
6.3 YOLO-NAS [Will be added as part of the course update]
6.3.1 Inference using YOLO-NAS
6.3.2 Fine-Tuning using YOLO-NAS
6.4 RT-DETR [Will be added as part of the course update]
6.4.1 Inference using RT-DETR
6.4.2 Fine-Tuning using RT-DETR

Project 3 Train A Face Mask Detector using YOLO

7 Text Detection & OCR

7.1 Overview of OCR
7.1.1 What is OCR?
7.1.2 The OCR pipeline
7.1.3 Challenges
7.1.4 Datasets and competitions
7.2 Graphic Text Recognition using Tesseract
7.2.1 What is Tesseract?
7.2.2 Introduction to OCR using Tesseract
7.2.3 Tesseract OCR failure cases
7.2.4 Improving Tesseract OCR failures
7.3 Text Detection
7.3.1 Text Recognition using EAST
7.3.2 Text Recognition using CRAFT (Python)
7.4 Modified pipeline for scene Text Recognition using Tesseract (Python)

27 of 30 CV Master Program
 7.5 Inference using Transformer OCR (TrOCR)
7.6 Fine-Tuning Transformer OCR (TrOCR)
7.7 Case Study - ALPR (YOLO NAS + TrOCR)

Assignment 3 Build an app to perform OCR On Invoices

8 Deploy Applications on Cloud

8.1 Create a web application using Flask
8.1.1 What is Flask?
8.1.2 A minimal Flask application
8.1.3 Using HTML templates
8.1.4 A complete Flask application
8.2 Deploy a web application on Heroku [Paas]
8.2.1 What is Heroku?
8.2.2 How to create an account on Heroku?
8.2.3 Prepare application for deployment
8.2.4 How to deploy using Heroku CLI?
8.2.5 How to deploy using Heroku website?
8.3 Deploy a web application on Google GCP [Iaas]
8.3.1 What is Google Cloud Platform (GCP)?
8.3.2 Create account on Google Cloud Platform
8.3.3 Create and configure a VM instance
8.3.4 Setup VM and deploy app
8.3.5 Change firewall settings and check deployment

Assignment 4 Deploy Your Web App On Heroku

Explore Other Courses

28 of 30 CV Master Program