Computer Vision Using Deep Learning

Computer Vision (CV) has become one of the hottest research fields, with applications in areas such as automated medical image analysis and self-driving cars. With modern computer vision built on the backbone of deep learning, the tasks associated with computer vision have become much more advanced, allowing users to analyze more extensive visual datasets and achieve better-quality results. The main applications of CV include visual recognition tasks such as image classification and object detection at its core. The course focuses on implementing various computer vision tasks based on real-world data input, beginning with traditional computer vision topics such as image filtering, convolution operations, frequency domain analysis, and SIFT features. The later part of the course transitions to deep learning architectures such as CNN and R-CNN and transfer learning using pre-trained image classification models such as VGG-16, ResNet50, and Inceptionv3. Other topics discussed include generative models such as Generative Adversarial Networks and Variational Autoencoders, and computer vision in the cloud. Students will learn the concepts in practice via demos and assignments in the Python programming language.