Description
Computer vision is an interdisciplinary scientific field that deals with how computers can gain high-level understanding from digital images or videos. From the perspective of engineering, it seeks to understand and automate tasks that the human visual system can do.
Syllabus
Beginners
- Unit-1: Introduction
- Components of Vision
- Imaging Systems
- Signal processing for computer vision
- Pattern recognition for computer vision
- Performance evaluation of algorithms
- Unit-2: Imaging Optics
- Introduction
- Basic Concepts of Geometric Optics
- Reflection and Refraction
- Multimedia Refraction
- Paraxial Optics
- Lenses
- Definitions: Optical Axis, Cardinal Planes, Focal Length
- Spherical Lenses
- Aspherical Lenses
- Toroidal Lenses
- Paraxial Lenses
- Thick lenses
- Systems of Lenses
- Matrix Optics
- Optical Properties of Glasses Dispersion
- Technical Characterization of Dispersion
- Aberrations
- Spherical Aberrations
- Coma
- Astigmatism
- Field Curvature
- Distortions
- Chromatic Aberrations
- Reducing Aberrations
- Optical Image Formation
- Geometry of Image Formation
- Depth-of-Field and Focus
- Telecentric Optics
- Wave and Fourier Optics
- Linear Optical Systems
- Optical Transfer Function
Intermediate
- Unit-3: Solid-State Image Sensing
- Introduction
- Fundamentals of Solid-State Photosensing
- Semiconductor photo sensors
- Propagation of Photons in the Image Sensor
- Generation of Photo charge Pairs
- Photocurrent Processing
- Photo charge integration in photodiodes CCDs
- Programmable Offset Subtraction
- Programmable Gain Pixels
- Avalanche Photocurrent Multiplication
- Nonlinear Photocurrent to Signal Voltage Conversion
- Transportation of Photo signals
- Charge-Coupled-Device Photocharge Transportation
- Photodiode Photocharge Signal Transmission
- Voltage Signal Transmission
- Electronic Signal Detection
- Signal-to-Noise (SNR) and Dynamic Range
- The basic MOSFET Source Follower
- Noise Sources in MOSFETs
- Electronic Signal Detection
- Architectures of Image Sensors
- Frame-Transfer Charge-Coupled-Devices
- Interline-Transfer Charge-Coupled-Devices
- Field-Interline-Transfer Charged-Coupled-Devices
- Conventional Photodiode (MOS) Arrays
- Active Pixel Sensor Technology
- Colour Vision and Colour Imaging
- Human Colour Vision
- Primary Colours
- Colour Chips and Colour Cameras
- Practical Limitations of Semiconductor Photosensors
- Pixel No uniformity and Dead Pixels
- Sensor Nonlinearity
- Unit-4(Part-1):Representation of Multidimensional Signals
- Introduction
- Types of Signals
- Continuous Signals
- Some Types of Signals g Depending on D Parameters
- Unified Description
- Multichannel Signals
Professional
- Unit-5: Fuzzy Image Processing
- Introduction
- Basics of Fuzzy Set Theory
- Fuzzy Logic
- Defuzzification
- Fuzzy Logic versus Probability Theory
- Images as an Array of Fuzzy Singletons.
- Fuzzy Image Understanding
- A New Image Definition: Images as Fuzzy Sets
- Image Fuzzification: From Images to Memberships
- Feature Fuzzification
- Fuzzy Topology: Noncrisp Definitions of Topological Relationships
- Fuzzy Image Processing Systems
- Operations in Membership Plane
- Fuzzification (coding of image information)
- The Three Stages of Fuzzy Image Processing for a Modification-based Approach.
- Defuzzification (decoding of the results)
- Theoretical Components of Fuzzy Image Processing
- Fuzzy geometry
- Fuzzy Elongatedness
- Measures of fuzziness and image information
- Rule-based systems
- Fuzzy/possibilistic clustering
- Crisp Clustering
- Fuzzy morphology
- Fuzzy measure theory
- Fuzzy Grammars
- Selected application examples
- Minimization of image fuzziness
- Fuzzy histogram hyperbolization
- Fuzzy rule-based approach
- Rule-based edge detection
- Image segmentation
- Fuzzy Thresholding
- Fuzzy clustering algorithms and rule-based
- Unit-6:(Part-1)Neural Net Computing for Image Processing
- Introduction
- Features of Artificial Neural Networks
- Components of Neural Models
- Multilayer Perceptron (MLP)
- Backpropagation-type Neural Networks
- Convolution Neural Networks (CNN)
- Self-organizing Neural Networks
- Kohonen Maps
- Self-organized Map
- Learning Vector Quantization
- Unit-6:(Part-2)Neural Net Computing for Image Processing
- Radial-basis neural networks (RBNN)
- Radial-basis Function (RBF)
- Transformation Radial-basis Networks (TRBNN)
- Hopfield Neural Networks
- Modified Hopfield Network
- Application Examples of Neural Networks
- Region-based Classification
- Pixel-based Classification and Image Segmentation