deep learning in image processing
play

Deep Learning in Image Processing Topics: Image Filtering 101 - PowerPoint PPT Presentation

Nov 22, 2022 •648 likes •1.46k views

Deep Learning in Image Processing Topics: Image Filtering 101 CNNs 101 Image Processing Pipelines Frank Dellaert CS 4476 Computer Vision Many slides from Stanfords CS231N by Fei-Fei Li, Justin Johnson, Serena Yeung, as well as

  1. Deep Learning in Image Processing Topics: – Image Filtering 101 – CNNs 101 – Image Processing Pipelines Frank Dellaert CS 4476 Computer Vision Many slides from Stanford’s CS231N by Fei-Fei Li, Justin Johnson, Serena Yeung, as well as some slides on filtering from Devi Parikh and Kristen Grauman, who may in turn have borrowed some from others

  4. Contrast • g(x) = a f(x), a=1.1

  5. Brightness • g(x) = f(x) + b, b=16

  7. Image filtering • Compute a function of the local neighborhood at each pixel in the image – Function specified by a “filter” or mask saying how to combine values from neighbors. • Uses of filtering: – Enhance an image (denoise, resize, etc) – Extract information (texture, edges, etc) – Detect patterns (template matching) 7 Slide credit: Kristen Grauman, Adapted from Derek Hoiem

  8. Image filtering • Compute a function of the local neighborhood at each pixel in the image – Function specified by a “filter” or mask saying how to combine values from neighbors. • Uses of filtering: – Enhance an image (denoise, resize, etc) – Extract information (texture, edges, etc) – Detect patterns (template matching) 8 Slide credit: Kristen Grauman, Adapted from Derek Hoiem

  9. Motivation: noise reduction • Even multiple images of the same static scene will not be identical. 9 Slide credit: Adapted from Kristen Grauman

  10. Common types of noise – Salt and pepper noise : random occurrences of black and white pixels – Impulse noise: random occurrences of white pixels – Gaussian noise : variations in intensity drawn from a Gaussian normal distribution 10 Slide credit: Steve Seitz

  11. Gaussian noise >> noise = randn(size(im)).*sigma; >> output = im + noise; Slide credit: Kristen Grauman What is impact of the sigma? 11 Figure from Martial Hebert

  12. Motivation: noise reduction • Even multiple images of the same static scene will not be identical. • How could we reduce the noise, i.e., give an estimate of the true intensities? • What if there’s only one image? 12 Slide credit: Kristen Grauman

  13. First attempt at a solution • Let’s replace each pixel with an average of all the values in its neighborhood • Assumptions: – Expect pixels to be like their neighbors – Expect noise processes to be independent from pixel to pixel 13 Slide credit: Kristen Grauman

  14. First attempt at a solution • Let’s replace each pixel with an average of all the values in its neighborhood • Moving average in 1D: 14 Slide credit: S. Marschner

  15. Weighted Moving Average • Can add weights to our moving average • Weights [1, 1, 1, 1, 1] / 5 15 Slide credit: S. Marschner

  16. Weighted Moving Average • Non-uniform weights [1, 4, 6, 4, 1] / 16 16 Slide credit: S. Marschner

  17. Image filtering • Image filtering: compute function of local neighborhood at each position • Really important! – Enhance images • Denoise, resize, increase contrast, etc. – Extract information from images • Texture, edges, distinctive points, etc. – Detect patterns • Template matching – Deep Convolutional Networks

  18. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 0 0 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 18 Slide credit: Steve Seitz

  19. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 0 0 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 19 Slide credit: Steve Seitz

  20. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 0 0 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 20 Slide credit: Steve Seitz

  21. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 0 0 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 21 Slide credit: Steve Seitz

  22. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 0 0 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 22 Slide credit: Steve Seitz

  23. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 20 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 0 0 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 23 Slide credit: Steve Seitz

  24. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 20 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 0 0 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 24 Slide credit: Steve Seitz

  25. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 20 30 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 0 0 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 25 Slide credit: Steve Seitz

  26. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 10 20 30 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 0 0 0 0 0 90 90 90 90 90 0 0 0 0 0 90 90 90 90 90 0 0 0 0 0 90 0 90 90 90 0 0 0 0 0 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 26 Slide credit: Steve Seitz

  27. Moving Average In 2D 0 0 0 0 0 0 0 0 0 0 0 10 20 30 30 0 0 0 0 0 0 0 0 0 0 0 0 0 90 90 90 90 90 0 0 0 0 0 90 90 90 90 90 0 0 0 0 0 90 90 90 90 90 0 0 0 0 0 90 0 90 90 90 0 0 0 0 0 90 90 90 90 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 27 Slide credit: Steve Seitz

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

BBM413 Fundamentals of Image Processing Introduction to Deep Learning Erkut Erdem

BBM413 Fundamentals of Image Processing Introduction to Deep Learning Erkut Erdem

BBM413 Fundamentals of Image Processing Introduction to Deep Learning Erkut Erdem Hacettepe University Computer Vision Lab (HUCVL) What is deep learning? Y. LeCun, Y. Bengio, G. Hinton, "Deep Learning" , Nature,

1.12k views • 84 slides
Image Processing Todays Class Image Representations: Matrices Image Representations: RGB,

Image Processing Todays Class Image Representations: Matrices Image Representations: RGB,

CS6501: Deep Learning for Visual Recognition Image Processing Todays Class Image Representations: Matrices Image Representations: RGB, HSV, etc Image Processing: Brightness Image Filtering: Mean Filter, Median Filter Image Filtering:

959 views • 77 slides
Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI Mission Helping people solve challenging problems using AI and deep learning. Developers, data scientists and engineers Self-driving cars,

1.44k views • 72 slides
TOWARDS CREATING A KNOWLEDGE GAP FOR DEEP LEARNING BASED MEDICAL IMAGE ANALYSIS Dr. S.

TOWARDS CREATING A KNOWLEDGE GAP FOR DEEP LEARNING BASED MEDICAL IMAGE ANALYSIS Dr. S.

TOWARDS CREATING A KNOWLEDGE GAP FOR DEEP LEARNING BASED MEDICAL IMAGE ANALYSIS Dr. S. Kevin Zhou, Chinese Academy of Sciences Deep learning Input Algorithm: Output image variable Deep network X Y Y = f(X; W) Learning: arg min W S

685 views • 36 slides
A comparative study of deep learning based Dadashi-Tazehozi rd2669 methods for MRI image

A comparative study of deep learning based Dadashi-Tazehozi rd2669 methods for MRI image

A comparative study of deep learning based methods for MRI image processing Robert A comparative study of deep learning based Dadashi-Tazehozi rd2669 methods for MRI image processing Introduction Articles Motivation Medical Robert

624 views • 27 slides
Learning State of the Art 1 19.11.2019 What is Deep Learning? https://youtu.be/Kfe5hKNwrCU

Learning State of the Art 1 19.11.2019 What is Deep Learning? https://youtu.be/Kfe5hKNwrCU

Applications and Deep Learning State of the Art 1 19.11.2019 What is Deep Learning? https://youtu.be/Kfe5hKNwrCU Long pipeline of processing operations Designed by showing examples Example: TUT Age Estimation Image Recognition

556 views • 52 slides
Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin Clark Deep Learning for NLP 5 years ago No Seq2Seq No Attention No large-scale QA/reading comprehension datasets No TensorFlow or

1.41k views • 92 slides
Interpretable & Transparent Deep Learning Fraunhofer HHI, Machine Learning Group Wojciech

Interpretable & Transparent Deep Learning Fraunhofer HHI, Machine Learning Group Wojciech

Fraunhofer Image Processing Heinrich Hertz Institute Interpretable & Transparent Deep Learning Fraunhofer HHI, Machine Learning Group Wojciech Samek Northern Lights Deep Learning Workshop (NLDL19) Troms, Norway 8th January 2019

1.15k views • 51 slides
Deep Learning Europython 2016 - Bilbao G. French University of East Anglia Image montages from

Deep Learning Europython 2016 - Bilbao G. French University of East Anglia Image montages from

Deep Learning Europython 2016 - Bilbao G. French University of East Anglia Image montages from http://www.image-net.org Focus: Mainly image processing This talk is more about the principles and the maths than code Got to fit this into 1

2.37k views • 191 slides
Deep Learning on Massively Parallel Processing Databases Frank McQuillan Feb 2019 2 A Brief

Deep Learning on Massively Parallel Processing Databases Frank McQuillan Feb 2019 2 A Brief

Deep Learning on Massively Parallel Processing Databases Frank McQuillan Feb 2019 2 A Brief Introduction to Deep Learning Artificial Intelligence Landscape Deep Learning 4 Example Deep Learning Algorithms Multilayer Recurrent

651 views • 44 slides
Hybrid Deep Learning Topology for Image Classification Petru Radu petru.radu@ness.com 27 th

Hybrid Deep Learning Topology for Image Classification Petru Radu petru.radu@ness.com 27 th

15.07.2019 Hybrid Deep Learning Topology for Image Classification Petru Radu petru.radu@ness.com 27 th Summer School on Image Processing, Timisoara 2019 SSIP 2019 Introduction Classical Neural Networks employed in image classification have a

513 views • 33 slides
Towards Interpretable Deep Learning for Natural Language Processing Roy Schwartz University of

Towards Interpretable Deep Learning for Natural Language Processing Roy Schwartz University of

Towards Interpretable Deep Learning for Natural Language Processing Roy Schwartz University of Washington & Allen Institute for Artificial Intelligence December 2018 1 / 37 ( Deep-Learning -Based) AI Today 2 / 37 3 / 37 Deep Learning

1.63k views • 140 slides
Image Captioning Image Captioning Image Captioning A survey of recent deep-learning approaches

Image Captioning Image Captioning Image Captioning A survey of recent deep-learning approaches

Image Captioning Image Captioning Image Captioning A survey of recent deep-learning approaches Kiran Vodrahalli February 23, 2015 The task We want to automatically describe images with words Why? 1) It's cool 2) Useful for

934 views • 40 slides
CS 4803 / 7643: Deep Learning Topics: Image Classification Supervised Learning view

CS 4803 / 7643: Deep Learning Topics: Image Classification Supervised Learning view

CS 4803 / 7643: Deep Learning Topics: Image Classification Supervised Learning view K-NN Linear Classifier Zsolt Kira Georgia Tech Last Time High-level intro to what deep learning is Fast brief of logistics

1.24k views • 100 slides
ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY MEDIA & ENTERTAINMENT SECURITY & DEFENSE AUTONOMOUS MACHINES Image

307 views • 26 slides
BBM 413 Today Fundamentals of What is image processing? Image Processing What does it

BBM 413 Today Fundamentals of What is image processing? Image Processing What does it

BBM 413 Today Fundamentals of What is image processing? Image Processing What does it mean, to see? Vision as a computational problem Sample image processing problems Erkut Erdem Dept. of Computer Engineering Hacettepe

399 views • 13 slides
Gaussian filters Remove high-frequency components from the image ( low- pass filter )

Gaussian filters Remove high-frequency components from the image ( low- pass filter )

Gaussian filters Remove high-frequency components from the image ( low- pass filter ) Convolution with self is another Gaussian So can smooth with small- kernel, repeat, and get same result as larger- CMPSCI 370HH: Intro to

880 views • 5 slides
Pixels Measure Brightness over an Area Digital Images Sample the 2D space on a regular grid

Pixels Measure Brightness over an Area Digital Images Sample the 2D space on a regular grid

9/21/16 A Digital Image is a Matrix of Pixels Image Filtering 0.92 0.93 0.94 0.97 0.62 0.37 0.85 0.97 0.93 0.92 0.99 0.95 0.89 0.82 0.89 0.56 0.31 0.75 0.92 0.81 0.95 0.91 0.89 0.72 0.51 0.55 0.51 0.42 0.57 0.41 0.49

699 views • 38 slides
Image Filtering and Image Frequencies Various slides from previous courses by: D.A. Forsyth

Image Filtering and Image Frequencies Various slides from previous courses by: D.A. Forsyth

CS4501: Introduction to Computer Vision Image Filtering and Image Frequencies Various slides from previous courses by: D.A. Forsyth (Berkeley / UIUC), I. Kokkinos (Ecole Centrale / UCL). S. Lazebnik (UNC / UIUC), S. Seitz (MSR / Facebook), J.

890 views • 74 slides
Cameras and Images Sanja Fidler Intro to Image Understanding 1 / 57 Pinhole Camera [Source: A.

Cameras and Images Sanja Fidler Intro to Image Understanding 1 / 57 Pinhole Camera [Source: A.

Cameras and Images Sanja Fidler Intro to Image Understanding 1 / 57 Pinhole Camera [Source: A. Torralba] Make your own camera http://www.foundphotography.com/PhotoThoughts/ archives/2005/04/pinhole_camera_2.html Sanja Fidler Intro to Image

1.1k views • 106 slides
Synchronizers, Arbiters, GALS and Metastability David Kinniment University of Newcastle, UK

Synchronizers, Arbiters, GALS and Metastability David Kinniment University of Newcastle, UK

Synchronizers, Arbiters, GALS and Metastability David Kinniment University of Newcastle, UK Based on contributions from: Alex Bystrov, Keith Heron, Nikolaos Minas, Gordon Russell, Alex Yakovlev, and Jun Zhou 1 TUBS 1 July 2009 Outline

718 views • 58 slides
Filtering vs Convolution 16-385 Computer Vision Filters we have learned so far Gaussian

Filtering vs Convolution 16-385 Computer Vision Filters we have learned so far Gaussian

Filtering vs Convolution 16-385 Computer Vision Filters we have learned so far Gaussian filter The Box filter 1 2 1 1 1 1 1 1 2 4 2 1 1 1 9 16 1 2 1 1 1 1 Sobel filter Laplace filter 1 0 -1 0 1 0 2 0 -2

578 views • 8 slides
CS4495/6495 Introduction to Computer Vision 6B-L3 Hierarchical LK Revisiting the small motion

CS4495/6495 Introduction to Computer Vision 6B-L3 Hierarchical LK Revisiting the small motion

CS4495/6495 Introduction to Computer Vision 6B-L3 Hierarchical LK Revisiting the small motion assumption Is this motion small enough? Probably not much larger than one pixel How might we solve this problem? Garden image

1.52k views • 34 slides
Reconnaissance dobjets et vision artificielle Josef Sivic http://www.di.ens.fr/~josef

Reconnaissance dobjets et vision artificielle Josef Sivic http://www.di.ens.fr/~josef

Reconnaissance dobjets et vision artificielle 2009 Reconnaissance dobjets et vision artificielle Josef Sivic http://www.di.ens.fr/~josef Equipe-projet WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire dInformatique, Ecole Normale

527 views • 36 slides

More recommend