MODULE-I: Image formation and image models: cameras, geometric camera models, geometric camera calibration, radiometry measuring light, sources, and shading, color [4 Hours]
MODULE-II: Early Vision - Single Image: linear filters, edge detection, texture [6 Hours]
MODULE-III: Early Vision - Multiple Images: the geometry of multiple views, stereopsis [4 Hours]
MODULE-IV: Mid-Level Vision: Segmentation by clustering, segmentation by fitting a model [8 Hours]
MODULE-V: High-Level Vision: Learning to classify- classification, error and loss, Major classification strategy, Practical methods for building classifiers, Classifying Images- Building good image features, Classifying images of single objects [10 Hours]
MODULE-VI: Applications like object recognition, character recognition, face recognition, gait recognition [5 Hours]

To understand how an image is formed

To understand image filtering techniques

To get familiarized with image segmentation techniques

To understand how a classifier works

After completion of this course, a student will be able:
1) To understand the fundamental concepts of image acquisition and image processing systems
2) To comprehend, analyze and design/ develop the spatial-domain and frequency-domain filters for various applications
3) To comprehend, analyze and design/ develop various image segmentation algorithms
4) To comprehend, analyze and design/ develop various feature extraction techniques
5) To comprehend, analyze and design/ develop various classifiers employed for recognition

David A. Forsyth and Jean Ponce, Computer Vision: A Modern Approach, Pearson Education , 2012

R C Gonzalez and R E Woods, Digital Image Processing, Pearson , 2014

Richard Hartley and Andrew Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press , 2004

Richard Szeliski, Computer Vision: Algorithms and Applications, Springer , 2011