Program Objectives:

• Understand and apply foundational computer vision concepts and techniques.
• Perform image preprocessing, classification, and segmentation.
• Implement object detection algorithms like YOLO and Faster R-CNN.
• Develop and train convolutional neural networks (CNNs) for image analysis.
• Utilize transfer learning for efficient model development.
• Implement facial recognition systems, including face detection and alignment.
• Gain proficiency in advanced computer vision tasks using deep learning frameworks.
• Apply computer vision techniques to real-world applications and projects.
• Enhance coding skills in Python and use libraries such as OpenCV, TensorFlow, and Keras.

What you will learn?

Introduction to Computer Vision:

• Overview of Computer Vision and its Applications.
• Key Concepts and Terminologies in Computer Vision.
• Image Processing Basics.

Image Classification:

• Introduction to Image Classification.
• Convolutional Neural Networks (CNNs).
• Training CNNs for Image Classification.
• Transfer Learning for Image Classification.

Object Detection:

• Basics of Object Detection.
• YOLO (You Only Look Once) Algorithm.
• Faster R-CNN (Region-Based Convolutional Neural Networks).
• Implementing Object Detection Models.

Image Segmentation:

• Introduction to Image Segmentation.
• Semantic Segmentation.
• Instance Segmentation.
• Using U-Net for Image Segmentation.

Facial Recognition:

• Understanding Facial Recognition.
• Face Detection and Alignment.
• Face Embeddings and Recognition.
• Implementing Facial Recognition Systems.

Advanced Computer Vision with Deep Learning:

• Deep Learning Architectures for Computer Vision.
• Implementing Advanced Models with TensorFlow and Keras.
• Real-World Applications of Computer Vision.