This 8-week intensive course provides foundational and applied knowledge in computer vision, equipping students to build intelligent image-processing systems using Python and modern cloud platforms. Students will explore the core principles of image representation, feature extraction, convolutional neural networks (CNNs), object detection, and deep learning-based applications.
A strong emphasis is placed on hands-on experience, enabling students to develop and deploy computer vision models in realistic scenarios such as facial recognition, object tracking, and emotion analysis. Through structured activities and guided projects, students will not only build functional models but also learn to evaluate performance, apply transfer learning, and deploy scalable solutions using platforms like Azure Machine Learning, IBM Watson Studio, and open-source frameworks such as TensorFlow and Streamlit.
The broader goal is to connect the underlying mathematics and algorithms of computer vision with real-world applications, preparing students to solve complex problems in areas such as healthcare, security, manufacturing, and digital services. The course is an essential component for anyone pursuing careers in machine learning, AI application development, or cloud-based intelligent systems.