Gain an overview of the field of computer vision and how ANNs are integrated into modern vision systems. Understand use cases and challenges.

Learn how to prepare and enhance images using filtering, normalization, noise reduction, and contrast adjustments for optimal model input.

Explore classic and deep learning-based feature extraction techniques like edge detection, histograms, and CNN-based descriptors.

Implement techniques such as bounding boxes and sliding windows to detect and localize objects within an image.

Build classification models using convolutional neural networks (CNNs) to label and categorize images based on content.

Differentiate objects within an image using pixel-wise classification methods, including semantic and instance segmentation.

Track the movement of objects across video frames and analyse motion patterns using RNNs and deep learning.

Dive into cutting-edge applications like facial recognition, gesture detection, augmented reality, and vision in robotics.