Master computer vision and image processing essentials. Learn to extract important features from image data, and apply deep learning techniques to classification tasks.
Linear image processing, Model fitting, Frequency domain analysis, Camera Models and Views, Camera models, Stereo geometry, Camera calibration, Multiple views, Image Features, Feature detection, Feature descriptors, Model fitting, Lighting, Photometry, Lightness, Shape from shading
Overview of image motion, Optical flow, Introduction to tracking, Parametric models, Non-parametric models, Tracking considerations, Classification and, recognitionClassification: Generative models, Discriminative model, Action recognitionUseful Methods: Color spaces and segmentation, Binary morphology, 3D perception
CNNs for Recognition, Verification, Detection, Segmentation:CNNs for Recognition and Verification (Siamese Networks, Triplet Loss, Contrastive Loss, Ranking Loss); CNNs for Detection:Background of Object Detection, R-CNN, Fast R-CNN, Faster R-NN, YOLO, SSD, RetinaNet; CNNs for Segmentation: FCN, SegNet, U-Net, Mask-RCNN, CNN + RNN Models for Video Understanding: Spatio-temporal Models, Action/Activity Recognition
Introduction to Attention Models in Vision; Vision and Language: Image Captioning, Visual QA, Visual Dialog; Spatial Transformers; Transformer Networks
Review of (Popular) Deep Generative Models: GANs, VAEs; Other Generative Models: PixelRNNs, NADE, Normalizing Flows, etc, Variants and Applications of Generative Models in Vision:
PHI India makes a variety of student smart cards that can be presented to an authenticating reader and linked via IoT to an access control system. Types of cards include ones for physical access to facilities, photo I.D. (with hologram or UV printing), time and attendance, logical access (to monitor use of electronic data like coursework, e-learning resources, printers and Internet), loyalty and membership, payment (for vending machines, printing, photocopying) and health/medical data (blood type, emergency contacts).