SlideShare une entreprise Scribd logo
1  sur  25
"The eye doesn't see any shapes, it sees
only what is differentiated through light
and dark or through colors."
-Johann Wolfgang Von Goethe
(1749–1832), German poet.
An Overview of
Human and
Computer Vision
BarCamp Omaha 2010
Corey A. Spitzer
Hi.
The Eye
http://en.wikipedia.org/wiki/File:Diagram_of_eye_evolution.svg
The Retina
http://www.colorado.edu/intphys/Class/IPHY3730/07vision.html
The Retina
http://openwetware.org/wiki/Image:Ch11f12.gif
Beyond the Retina
http://en.wikipedia.org/wiki/File:ERP_-_optic_cabling.jpg (Attribution: Ratznium at en.wikipedia )
Beyond the Retina
http://langabi.name/blog/2005/09/26/optical-illusions-and-visual-phenomena
Beyond the Retina
http://langabi.name/blog/2005/09/26/optical-illusions-and-visual-phenomena
Computer Vision
http://en.wikipedia.org/wiki/File:Studijskifotoaparat.JPG
Low-level Image Processing
http://en.wikipedia.org/wiki/File:Aliasing_a.png
http://en.wikipedia.org/wiki/Histogram_equalization
Image Segmentation
http://en.wikipedia.org/wiki/File:EdgeDetectionMathematica.png
Edge Detection
Image Segmentation
http://people.cs.uchicago.edu/~pff/segment/
Region-based Segmentation
Object and Facial Recognition
High-level Image Processing
brosnan et. al.*
Movement / Object Tracking
http://www.youtube.com/watch?v=OjLlZJTahUw&t=1m12s
Depth Perception using Structured Light
http://www.youtube.com/watch?v=rYD6L1X1GUI
http://www.youtube.com/watch?v=854ZTvs8UoU&t=6m42s
Stereopsis
Stereopsis
Ogale and Aloimonos**
Stereopsis
Stereopsis
Stereopsis
~ 37.13 cm
Stereopsis
~ 23.52 cm
Sources and Further Information
Brain and Behavior course website
University of Colorado at Boulder
http://www.colorado.edu/intphys/Class/IPHY3730/07vision.html
* Improving quality inspection of food products by computer vision––a review
Tadhg Brosnan, Da-Wen Sun
** Shape and the stereo correspondence problem
Abhijit S. Ogale and Yiannis Aloimonos
Sources and Further Information

Contenu connexe

Dernier

Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 

Dernier (20)

Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu SubbuApidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
 

En vedette

How Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental HealthHow Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental Health
ThinkNow
 
Social Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie InsightsSocial Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie Insights
Kurio // The Social Media Age(ncy)
 

En vedette (20)

2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by Hubspot2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by Hubspot
 
Everything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPTEverything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPT
 
Product Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage EngineeringsProduct Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage Engineerings
 
How Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental HealthHow Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental Health
 
AI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdfAI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdf
 
Skeleton Culture Code
Skeleton Culture CodeSkeleton Culture Code
Skeleton Culture Code
 
PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024
 
Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)
 
How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024
 
Social Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie InsightsSocial Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie Insights
 
Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024
 
5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summary5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summary
 
ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd
 
Getting into the tech field. what next
Getting into the tech field. what next Getting into the tech field. what next
Getting into the tech field. what next
 
Google's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search IntentGoogle's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search Intent
 
How to have difficult conversations
How to have difficult conversations How to have difficult conversations
How to have difficult conversations
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data Science
 
Time Management & Productivity - Best Practices
Time Management & Productivity -  Best PracticesTime Management & Productivity -  Best Practices
Time Management & Productivity - Best Practices
 
The six step guide to practical project management
The six step guide to practical project managementThe six step guide to practical project management
The six step guide to practical project management
 
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
 

Overview of Human and Computer Vision

Notes de l'éditeur

  1. fovea - pit that has provides the greatest focus rods and cones turn light into electrochemical signals that are sent to the brain
  2. cones are dedicated to bright light and colors 3 kinds of cones rods are active in processing dim light hard to see color in dim light
  3. left and right fields get processed together and in parallel Doesn't show path to the superior colliculus -- SC serves to generate quick and usually unconscious movements of the eye (saccades); -- often purely reflexive -- focuses attention onto regions of interest such as areas where a texture or color is different from its surroundings or where movement has been detected by higher areas of the brain LGN -- each LGN has 6 layers of processing, 3 for each eye; -- exact function is not known, but information is sent to and from V1 Visual Cortex -- 5 major layers processing: orientation, position, size; _; form and shape; color; motion -- two paths: "where" and "what" processed in parallel No one completely knows how vision works in a mathematical / algorithmic sense
  4. Processing involves more than just working with the image coming from the retina Retinal images don't tell us the difference between a hole in the ground and a shadow. The brain adds hints to the image for correct interpretation based on probability, past experience, and knowledge. Brain tweaks the image; may add additional shading or changing perceived colors to synthetically add features like depth cues What the brain allows you to see isn't always the image that's actually coming in. Not raw data
  5. Huge area of study full of huge sub-areas of study Things are more objective and discrete with pixels versus fuzzy biological signals
  6. Huge area. Deals with preprocessing an image to aid higher-level analysis High/low pass filtering (e.g. sharpening, blurring) aliasing / antialiasing Histogram equalization - redistributes the gray-level intensities amongst the pixels, shifting all pixels with a given intensity together (i.e. all pixels that had the same intensity before have the same intensity now, it's just a different value), thus increasing the global contrast cumulative distribution function - at point X, how many pixels have intensity at or below X
  7. after image is prepared to be analyzed at a high level.. Need to be able to tell difference between the foreground and background, areas / objects of interest in the image, etc. subproblem of a lot of different high-level problems such as -- object recognition/detection -- image classification discontinuities - adjacent pixel regions where local contrast exceeds some threshold local contrasts - define edges - define boundaries of shapes - define objects Canny edge detector problems: -- can create edges that don't actually exist -- can ignore edges that do exist -- no inherent way to tell if an edge is part of an object or is an object boundary; e.g. textures
  8. looking for homogeneity wrt certain features (e.g. color, texture, etc); think of the paint bucket tool in photoshop; spread out in all directions looking for contiguous pixels that are similar can be used in conjunction with edge detection
  9. High level image processing feature detection
  10. Images from a system that classifies pizzas as good or bad based on the pattern and distribution of toppings
  11. Disparity - thumb exercise Brain offers hints and cues for distance -- parallax - moving head, closer objects move across field of view faster; moon follows you wherever you go -- shadows -- knowledge of what things look like Correspondence problem -- some pixels don't correspond at all due to occlusions; can see more AROUND the left side with left eye, right side with right eye -- some areas are going to appear as different widths in the different images (e.g. slanted)
  12. Smoothed image to eliminate noise Segmented based mostly on color and contrast. -- colors weren't the same due to different cameras, different lighting from different angles, noise, etc.
  13. Triangulation using distance between each camera, focal points, and relative positions of the corresponding segments