Filtering in Computer Vision - Lecture 2

Explore filtering techniques in computer vision through this comprehensive lecture. Delve into various image types, including binary, grayscale, and color images, and understand their characteristics. Learn about image histograms and different types of noise, particularly Gaussian noise. Examine discrete derivatives, finite differences, and two-dimensional derivatives in image processing. Investigate correlation, convolution, and various filtering methods, with a focus on Gaussian filters and their properties. Compare blurring techniques and noise filtering approaches. Gain practical knowledge of MATLAB functions for image processing. Discover edge detection techniques, including the concept of edges, detecting discontinuities, and applying derivatives to images. Understand the relationship between derivatives and noise, and explore image smoothing methods. Study various edge detectors and their applications in computer vision.

General
Binary Images
Gray Level Image
Gray Scale Image
Color Image Red, Green, Blue Channels
Image Histogram
Image Noise
Gaussian Noise
Definitions
Discrete Derivative Finite Difference
Derivatives in 2 Dimensions
Derivatives of Images
Correlation
Convolution
Averages
Gaussian Filter
Properties of Gaussian
Linear Filtering
Filtering Examples
Blurring Examples
Filtering Gaussian
Gaussian vs. Smoothing
Noise Filtering
MATLAB Functions
An Application
Edge Detection in Images
What is an Edge?
Detecting Discontinuities
Derivative in Two-Dimensions
Image Derivatives
Derivatives and Noise
Image Smoothing
Gaussian Smoothing (Examples)
Edge Detectors