Artificial Intelligence

Computer Vision Essentials


Skill level


Course cost

About this course

Computer vision (CV) is a set of techniques that are used to help machines to “see” and comprehend what is contained in digital imagery such as photos and videos. It has varied applications such as in medical imaging, motion capture, surveillance, automating retail checkouts, and in optical character recognition. This course starts with the basic steps of digitizing images, sampling them and compressing them (quantization). It then covers various methods to work with images including classification, identification, detection, etc.

Skills covered

  • Working with Images
  • Convolution
  • Pooling
  • Transfer learning
  • Convolutional Neural Networks

Course Syllabus

Computer Vision Essentials

  • Working with Images_Introduction
  • Working with Images - Digitization, Sampling, and Quantization
  • Working with images - Filtering
  • Introduction to Convolutions
  • 2D convolutions for Images
  • Convolution - Forward
  • Convolution - Backward
  • Transposed Convolution and Fully Connected Layer as a Convolution
  • Pooling : Max Pooling and Other pooling options
  • CNN Architectures and LeNet Case Study
  • GPU vs CPU
  • Transfer Learning Principles and Practice
  • Visualization (run pacakge, occlusion experiment)


Dog Breed Classification with Transer Learning

In Face Detection,the computer recognizes the face within an image and locates its position.The dataset in this project comprises of 120 breeds of dogs. The goal of the project is to create a classifier capable of determining a dog's breed from a photo

Course Certificate

Get Computer Vision Essentials course completion certificate from Great learning which you can share in the Certifications section of your LinkedIn profile, on printed resumes, CVs, or other documents.

GL Academy Sample Certificate
popup asset

Welcome to Great Learning Academy