Pre-requisites:
An Introductory Course on Pattern Recognition that includes Neural Networks
An Introductory Course on Image Processing
Good to have knowledge of CNN, GAN, RNN, Autoencoders, The Transformer Network [pre-recorded lectures will be shared]
Course Syllabus:
Images
-Color Image Photography
-Image Features
-Image Filtering
-Semantic Image Segmentation
-Object Detection
-Saliency and Salient Object Detection
-Action Recognition
Videos
-Color Videography and Deinterlacing
-Optical Flow, Motion Estimation
-Spatio-temporal Filtering
-Shot Detection and Video Segmentation
-Video Saliency and Salient Object Detection
-Video Action Recognition
-Audio Recording
-Audio Features
-Audio Filters
Audio-Visual Applications
-AV Saliency
-AV Action Recognition
-AV Surveillance
Graph
-Graph Signals and Representation
-Graph Processing
-Graph Neural Network
-Graph based Vision
References:
- Research Papers @ IEEE TIP, IEEE TMM, CVPR, ICCV, ACM MM etc.
- Computer Vision: Algorithms and Applications by Richard Szeliski
- Fundamentals of Digital Image Processing by Anil K. Jain
- Digital Video Processing by A. Murat Tekalp
- Digital Image Processing by Rafael C. GonzaLez and Richard E. Woods
- Image Processing for Cinema by Marcelo BertalmĂo
- The Essential Guide to Video Processing by Alan C. Bovik
- Deep Learning on Graphs by Yao Ma and Jiliang Tang
- Audio and Speech Processing with MATLAB by Paul R. Hill
- Applied Speech and Audio Processing by Ian McLoughlin
- Speech and Audio Signal Processing: Processing and Perception of
Speech and Music by Ben Gold and Nelson Morgan
- Fundamentals of Multimedia by Ze-Nian Li and Mark S. Drew
Lecture Resources:
- Through Google Classroom [invitation based, exclusive to those who officially register]
Office Hours:
- Send e-mail to dsen[at]ece.iitkgp.ac.in seeking appointment [Only those who have officially registered]