Главная
Study mode:
on
1
- Introduction
2
- Box blur as an average
3
- Dealing with the edges
4
- Gaussian blur
5
- Visualizing gaussian blur
6
- Convolution
7
- Kernels and the gaussian kernel
8
- Looking at the convolution in Julia
9
- Julia: `ImageFiltering` package and Kernels
10
- Julia: `OffsetArray` with different indices
11
- Visualizing a kernel
12
- Computational complexity
13
- Julia: `prod` function for a product
14
- Example of a non-blurring kernel
15
- Sharpening edges in an image
16
- Edge detection with Sobel filters
17
- Relation to polynomial multiplication
18
- Convolution in polynomial multiplication
19
- Relation to Fourier transforms
20
- Fourier transform of an image
21
- Convolution via Fourier transform is faster
22
- Final thoughts
Description:
Explore the fundamentals of convolutions in image processing through this comprehensive 36-minute video lecture from MIT's 18.S191 Fall 2020 course. Delve into topics such as box blur, Gaussian blur, and edge detection using Sobel filters. Learn about kernels, computational complexity, and the relationship between convolutions and polynomial multiplication. Discover the connection to Fourier transforms and their application in image processing. Gain hands-on experience with Julia programming language, including the use of the ImageFiltering package and OffsetArrays. Follow along as the lecturer demonstrates various image processing techniques, from basic blurring to advanced edge sharpening, providing a solid foundation in computational thinking for image manipulation.

Convolutions in Image Processing - MIT 18.S191 Fall 2020 - Week 1

The Julia Programming Language
Add to list
0:00 / 0:00