Course description

This course offers a fundamental exploration into the field of Computer Vision, the science of enabling machines to see, interpret, and understand the visual world. We will begin by understanding how images are represented and manipulated, then move to classic techniques for extracting meaningful features. The curriculum progresses to core tasks like object detection and recognition, and culminates with an in-depth look at how deep learning, particularly Convolutional Neural Networks (CNNs), has revolutionized the field. Students will gain a solid foundation in both the theory and application of modern computer vision.

What will i learn?

• Describe the core challenges and key applications of computer vision.
• Apply fundamental image processing techniques, including filtering, thresholding, and color space manipulation.
• Explain the principles behind traditional feature extraction methods like SIFT and HOG.
• Differentiate between image classification, object detection, and segmentation, and understand their respective goals and evaluation metrics.
• Detail the architecture and function of a Convolutional Neural Network (CNN) and its primary components.
• Recognize and describe advanced computer vision tasks such as semantic segmentation, generative modeling, and video analysis.

Frequently asked question