Filtering in Computer Vision - Lecture 2

Explore key concepts in computer vision through this comprehensive lecture on filtering. Delve into various image types, including binary, gray level, and color images with RGB channels. Examine image histograms and different noise types such as Gaussian, uniform distribution, and salt and pepper. Learn about analytical and discrete derivatives, including finite differences and derivatives in 2D. Investigate correlation, convolution, and linear filtering techniques, with a focus on Gaussian filters and their properties. Compare Gaussian and averaging filters for noise reduction, and understand the principle of linearity in filtering. Gain practical knowledge of MATLAB functions for implementing these concepts in image processing applications.

CAP 5415 Computer Vision
Contents
Images: General
Binary Images
Gray Level Image
Gray Scale Image
Color Image Red, Green, Blue Channels
Image Histogram
Histogram Code
Image Noise
Gaussian Noise
Uniform Distribution
Salt and pepper Noise
Definitions
Examples: Analytic Derivatives
Discrete Derivative Finite Difference
Derivatives in 2 Dimensions
Derivatives of Images
Correlation and Convolution
Averages
Gaussian Filter
Properties of Gaussian
Linear Filtering
Filtering Examples
Filtering Gaussian
Gaussian vs. Averaging
Noise Filtering
Linearity
MATLAB Functions