Computer Vision

Introduction

Computer Vision is a rapidly growing field of Artificial Intelligence that enables machines to interpret, analyze, and understand visual data such as images and videos. It plays a vital role in applications like facial recognition, medical imaging, autonomous vehicles, surveillance systems, and industrial automation. This course provides a practical and structured introduction to Computer Vision, combining deep learning concepts with real-world implementation techniques.

The program begins with the basics of neural networks and progresses to convolutional neural networks (CNNs), focusing on the internal layers of convolutional architectures and how they extract visual features. Learners will explore core computer vision tasks including image classification, object detection, and image segmentation, and will build custom neural networks for image classification from scratch.

Participants will also gain exposure to pre-trained models and the transfer learning concept, enabling faster and more efficient model development. The course introduces the OpenCV library for hands-on work with images and videos, covering essential image processing and video analysis techniques. Advanced topics include an introduction to the YOLO (You Only Look Once) model for real-time object detection and tracking, along with configuring YOLO for custom datasets and applications.

By the end of this course, learners will have a strong foundation in Computer Vision, practical experience with industry-standard tools, and the ability to build and deploy intelligent vision-based solutions.