Syllabus

INTRODUCTION TO COMPUTER VISION AND BASIC CONCEPTS OF IMAGE FORMATION: Introduction and Goals of Computer Vision and Image Processing, Image Formation Concepts, Geometric Transformations, Geometric Camera Models, Camera Calibration, Image Formation in a Stereo Vision Setup, Image Reconstruction from a Series of Projections. [6 hours]

IMAGE PROCESSING CONCEPTS, IMAGE TRANSFORMS, IMAGE ENHANCEMENT: Image sampling and quantization, 2D Fourier Transform, DFT, FFT, Separable Image Transforms, Walsh – Hadamard, Discrete Cosine Transform, Haar, Slant – Karhunen – Loeve Transforms. Some basic gray level transformations, Histogram processing, smoothing and sharpening spatial filters, smoothing and sharpening frequency domain filters, Homomorphic filtering. [6 hours]

IMAGE SEGMENTATION: Boundary detection based methods, region-based methods, template matching, Hough transform, Mean shift, active contours, Use of motion in segmentation [4 hours]

IMAGE DESCRIPTION: Boundary descriptors, Shape numbers, Fourier descriptors, Statistical moments, Regional descriptors, Topological descriptors, Texture, Moment invariants, Use of principal components for description, Relational descriptors, SHAPE REPRESENTATION: Contour based representation, Region based representation, De-formable curves and surfaces, Snakes and active contours, Level set representations, Fourier, and wavelet descriptors, Medial representations. [8 hours]

FEATURE DETECTION AND MATCHING: Points and patches, Edges and contours, Contour tracking, Lines and vanishing points, SIFT, SURF IMAGE ALIGNMENT AND STITCHING Pairwise alignment, Image stitching, Global alignment, Compositing, MOTION ESTIMATION Motion models, Parametric motion, Optical flow, Motion tracking. [6 hours]

IMAGE UNDERSTANDING: Pattern recognition methods, Object recognition, Image Classification, Face detection and recognition, 3D shape models of faces. COMPUTER VISION APPLICATIONS: Surveillance, medical image analysis for detection of diseases, In-vehicle vision system: locating roadway, identifying road signs, locating pedestrians etc. [6 hours]

To describe and explain foundation of image formation, digital image processing and understand the geometric relationships between 2D images and the 3D world.

To design and implement algorithms that perform image processing and image analysis (e.g. noise removal and image enhancement & image segmentation).

To understand and implement various methods for image description and representation, alignment, and matching in images.

To understand and implement the technical approaches for object/scene detection, recognition and categorization from images.

To have an exposure to advanced concepts, including state of the art machine learning architectures, in all aspects of computer vision.

Be familiar with both the theoretical and practical aspects of image computing, foundation of image formation, measurement, and analysis.

Demonstrate on broad range of fundamental image processing and analysis techniques and concepts (linear and non-linear filtering, denoising, edge detection, segmentation etc.)

Understand the geometric relationships between 2D images and the 3D world.

Understand and implement the methods for robust image description, representation, image alignment and matching.

Have gained exposure to object/scene recognition, tracking, classification from images.

Identify, demonstrate and apply their knowledge by analyzing computer vision problems and employing (or proposing) effective solutions for various applications.

Rafael C Gonzalez, Richard E Woods, Digital Image Processing, Pearson Education 2014

Richard Szeliski, Computer Vision: Algorithms and Applications, Springer, 2010

J. R. Parker, Algorithms for Image Processing and Computer Vision, Wiley and Sons, 2nd edition 2010

T. Morris, Computer Vision and Image Processing, Palgrave McMillan

1. IEEE Transaction on Image Processing, IEEE International Conference on Image Processing
2. IEEE Transaction on Pattern Analysis and Machine Intelligence
3. IEEE conference on Computer Vision & Pattern Recognition
4. https://sites.usc.edu/iris-cvlab/