Computer Vision

This course provides an introduction to computer vision including fundamentals of image formation, camera imaging geometry, feature detection and matching, multi view geometry including stereo, motion estimation and tracking, and classification. We’ll develop basic methods for applications that include finding known models in images, depth recovery from stereo, camera calibration, image stabilization, automated alignment (e.g. panoramas), tracking, and action recognition.(Online classes available)

What you’ll learn

Become an advanced, confident, and modern Computer Vision expert from scratch
How to think and work like a developer: problem-solving, researching, workflows
Digital image processing: gray level transformations, geometric transformations, convolution, image enhancement and smoothing, morphological filters, etc.

Course Content:

Module1: Introduction to Computer Vision

Basic Concept
Image Filtering Techniques

Module2: Human Visual System

Module3: Feature Detection and Matching Techniques

Edge Detection
Corner Detection
Discriminative Interest Point Detectors
Interview Questions and Preparation

Module4:Camera Models and 3D Computer Vision

Camera Calibration
Stereo Vision
Generating 3D images from 2D views (exciting, isn’t it?)
Interview Questions and Preparation

Module5: Machine Learning Fundamentals

Supervised Learning
Feature selection and learning
Classification Techniques
Generative and Discriminative Models (GANs)
Semi-supervised Learning
Unsupervised Learning
Self-Supervised Learning
Interview Questions and Preparation

Module6: Deep Learning

Introduction to Convolutional Neural Network
CNN Artchitecture: DenseNET, Res NET, Fully Convolutional Network
Interview Questions and Preparation

Module7: Object Detection

RCNN, Fast-RCNN, Faster RCNN, Mask RCNN
YOLO, SSD for Object Detection
Feature Pyramid Networks
EfficientDet
Interview Questions and Preparation

Module8:Image Segmentation

UNET
Fast FCN
Gated SCNN
DeepLab
Interview Questions and Preparation

Module9:Object Tracking

Single and Multiple Object Tracking using deep learning

Module10: Medical Image Diagnosis

Tissue, bone and muscle segmentation in X-ray, CT and MRI
Automatic cancer detection in liver, pancreas, brain, kidney, lung and other organ
Radiologists in the loop systems

Module11Action Recognition