Computer Vision in AI

Why should you take Computer Vision in AI course?

• Learning Outcomes
• Gain a strong foundation in image processing and visual data interpretation
• Learn to use industry-standard tools like OpenCV, TensorFlow, and Keras for building Computer Vision models
• Understand and implement Convolutional Neural Networks (CNNs) for tasks like image classification and object detection
• Master real-world techniques like face detection, gesture recognition, and image segmentation
• Work with real-time data from images and videos to build intelligent AI-powered systems
• Develop hands-on experience through practical projects in domains like Healthcare, Security, Autonomous Vehicles, and more
• Boost your profile for roles in AI, ML, Data Science, and Computer Vision Engineering

Who should take Computer Vision in AI course?

• Aspiring AI and Machine Learning Professionals - Those looking to specialise in visual intelligence and expand their AI skill set
• Data Scientists and Analysts - Professionals who want to enhance their capabilities in image and video data analysis.
• Software Developers and Engineers - Developers aiming to integrate AI-powered visual systems into applications
• Students and Researchers - Those involved in academic or research projects in Artificial Intelligence, Robotics, or Image Processing
• Tech Enthusiasts and Innovators - Anyone passionate about working on cutting-edge technologies like facial recognition, AR/VR, or autonomous vehicles
• Professionals from domains like Healthcare, Retail, Security, and Automotive - Who want to leverage Computer Vision solutions in their field

Curriculum

• Computer Vision
• Working with Images
• Introduction to Convolutions
• 2D Convolutions for Images
• Convolution Forward and Backward
• Transposed Convolution and Fully Connected Layer as a Convolution
• Pooling: Max Pooling and other Poolings
• CNN Architectures
• AlexNet, LeNet, ZFNet, VGGNet, GoogleNet, ResNet
• GPU vs CPU
• Transfer Learning
• Semantic Segmentation using U-Net
• Inception and Mobile Net Models
• Object Detection with Region Proposals, YOLO and SSD
• Bounding Box Regressoion
• Siamese Network for Metric Learning

Tools you will learn in Computer Vision in AI course?

Skills You Will Gain:

• Image Processing Fundamentals: Filtering, Edge Detection, Colour Space Conversion
• Building and Training Convolutional Neural Networks (CNNs)
• Image Classification and Object Detection Techniques
• Real-time Face and Gesture Recognition
• Image Segmentation and Contour Detection
• Data Augmentation And Preprocessing for Computer Vision
• Implementing Transfer Learning with Pre-trained Models
• Applying Computer Vision in domains like Healthcare, Security, and Automation

Tools and Frameworks You Will Use:

• OpenCV - For image and video processing
• TensorFlow and Keras - For building and training deep learning models
• NumPy - For numerical operations and image matrix handling
• Matplotlib and Seaborn - For visualising image data and model results
• YOLO (You Only Look Once), SSD (Single Shot Detector), Faster R-CNN - For object detection
• Google Colab/Jupyter Notebooks - For hands-on development and testing