Computer Vision

Course details

Computer Vision is a multifaceted discipline that enables machines to interpret and make decisions based on visual data. This course offers a deep dive into the techniques and algorithms that simulate the human ability to interpret and act upon visual information. With an emphasis on practical applications, students will explore topics from basic image processing to advanced deep learning methods.

Start Date
TBD
Duration
14-15 weeks
Prerequisites
Foundations of AI & ML, and Basic Linear Algebra.
Learning Objectives
  • Understand the foundational concepts of image processing.
  • Analyze and process images and videos to extract meaningful information.
  • Implement computer vision algorithms.
  • Employ deep learning techniques for advanced visual recognition tasks.
  • Explore the real-world applications and ethical implications of computer vision.
Key Features
  • Real-world image and video datasets for hands-on labs.
  • Use of popular computer vision libraries such as OpenCV and TensorFlow.
  • Exposure to the latest advancements in computer vision research.
Learning path
  • Unit 1: Introduction to Computer Vision (2)
  • Unit 2: Basics of Image Processing (4)
  • Unit 3: Advanced Image Processing & Analysis (5)
  • Unit 4: Machine Learning for Vision (4)
  • Unit 5: Advanced Deep Learning Techniques (4)
  • Unit 6: 3D Vision and Recognition (3)
  • Unit 7: Applications & Special Topics (4)
  • Unit 8: Wrap-up and Exploration (2)

Topics covered

  • Overview of Computer Vision
  • Image Representation, Color Spaces

  • Image Enhancement Techniques
  • Morphological Operations
  • Image Segmentation
  • Feature Extraction

  • Optical Flow & Motion Analysis
  • Image Registration & Stitching
  • Image Restoration
  • Texture Analysis
  • Shape Analysis and Object Detection

  • K-NN, SVM for Image Classification
  • Decision Trees and Random Forests in Vision
  • Introduction to CNNs
  • Transfer Learning

  • YOLO & SSD for Object Detection
  • Semantic and Instance Segmentation: U-Net, Mask R-CNN
  • Generative Adversarial Networks (GANs)
  • Capsule Networks

  • Depth Cameras & 3D Reconstruction
  • Point Cloud Data Processing
  • 3D Object Recognition

  • Face Detection & Recognition
  • Action Recognition in Videos
  • Augmented Reality & Virtual Reality
  • Ethical Implications and Biases in Computer Vision

  • Cutting-edge Research in Computer Vision
  • Course Recap and Discussion

Grading:

  • Class Participation: 10%
  • Weekly Assignments: 30%
  • Group Projects: 20%
  • Mid-Term Examination: 20%
  • Final Examination: 20%

Reading Material: A blend of standard textbooks, latest research papers, and notable articles in the domain of Computer Vision.

Assignments: Real-world challenges, image and video processing tasks, and model-building projects.

Faculty: Renowned expert in the domain of Computer Vision.

Teaching Instructors: TBD

Contact Us

E-mail

arun.reddy@globuslearn.com

For Information & Queries
Loading
Something went wrong
Your query has been sent. We will contact you soon!