SlideShare une entreprise Scribd logo
1  sur  31
Télécharger pour lire hors ligne
COMPUTER VISION
A BEGINNERS GUIDE TO
A BEGINNERS GUIDE TO COMPUTER VISION
INTRODUCTION: ANDREW RANGEL
▸ Background: Mobile Development
▸ Passion for new and exciting technologies
▸ Working with and learning CV for ~1 year
▸ Wanted to share my experience
A BEGINNERS GUIDE TO COMPUTER VISION
INTRODUCTION: COMPUTER VISION
▸ What is it
▸ What is it for
▸ Who uses it
▸ Examples
▸ How can you use it
▸ Misconceptions
A BEGINNERS GUIDE TO COMPUTER VISION
WHAT IS IT
▸ Computer Vision is the process of using a computer based
algorithm to identify patterns in the data of images
▸ Basic Steps:
▸ Process the image
▸ Use an algorithm to identify a pattern
▸ Present that pattern in a meaningful way
A BEGINNERS GUIDE TO COMPUTER VISION
WHAT IS IT
A BEGINNERS GUIDE TO COMPUTER VISION
WHAT IS IT
A BEGINNERS GUIDE TO COMPUTER VISION
WHAT IS IT
A BEGINNERS GUIDE TO COMPUTER VISION
WHAT IS IT
A BEGINNERS GUIDE TO COMPUTER VISION
WHAT IS IT
A BEGINNERS GUIDE TO COMPUTER VISION
WHAT IS IT
▸ Matrix math
▸ From basic to
complex
▸ “Seeing” the
matrix
A BEGINNERS GUIDE TO COMPUTER VISION
WHAT IS IT FOR
▸ More uses than you may imagine
▸ Sorting fruit
▸ Self driving vehicles
▸ Snapchat filters
▸ Identifying animals
▸ Identifying patterns humans cannot
COMPUTER VISION HAS
SURPRISING
APPLICATIONS
A BEGINNERS GUIDE TO COMPUTER VISION
WHO USES IT
▸ Companies from farming to Snapchat
▸ Computer Vision allows companies to process unique
input in a way that creates innovation and new industries
▸ Will be integrated more as Augmented Reality grows in
popularity
A BEGINNERS GUIDE TO COMPUTER VISION
BAD AI BOT: MY EXCURSION INTO COMPUTER VISION
▸ I wanted to show my family and friends what I meant by
“computer vision”
▸ When I showed them they were rarely impressed “meh”
▸ I noticed how terrible it is to use a “stock” model to try and
identify the world
▸ Got a much bigger result from friends and family when
showing them bad results
A BEGINNERS GUIDE TO COMPUTER VISION
BAD AI BOT: MY EXCURSION INTO COMPUTER VISION
A BEGINNERS GUIDE TO COMPUTER VISION
BAD AI BOT: MY EXCURSION INTO COMPUTER VISION
▸ Started with Inception3 model (open source)
▸ Apple example code
▸ Created UI wrapper and image picker interface
▸ Business logic when sending / receiving images from
model
A BEGINNERS GUIDE TO COMPUTER VISION
BAD AI BOT: MY EXCURSION INTO COMPUTER VISION
CAMERA OPENCV
INCEPTION
V3
RESULTS UI
A BEGINNERS GUIDE TO COMPUTER VISION
BAD AI BOT: MY EXCURSION INTO COMPUTER VISION
OPENCV INCEPTION V3 RESULTS
MODELIMAGEIMAGEIMAGE
ERRORADJUST
LABELS
A BEGINNERS GUIDE TO COMPUTER VISION
SEE FIRE: A MORE SERIOUS PROJECT
▸ Started with Netflix, naturally
▸ Wildfire epidemic on the west coast
▸ Prevention may be impossible but containment could save
lives / homes / money
▸ What if you distributed a mesh network connected army of
fire spotters?
A BEGINNERS GUIDE TO COMPUTER VISION
SEE FIRE: A MORE SERIOUS PROJECT
▸ This project seemed more suited for TensorFlow
▸ How to choose images
▸ Decide on how to train model
▸ Determine how you will test model
▸ Next steps
A BEGINNERS GUIDE TO COMPUTER VISION
SEE FIRE: A MORE SERIOUS PROJECT
▸ Sourcing images
▸ Google images (search tools for reuse)
▸ Programming is your friend: Python script
▸ Reviewing images
▸ Content is key
A BEGINNERS GUIDE TO COMPUTER VISION
HOW CAN YOU USE IT
▸ Easiest way to try computer vision is OpenCV on the
desktop
▸ Easiest way to use computer vision is a mobile application
▸ 3 easy steps
A BEGINNERS GUIDE TO COMPUTER VISION
HOW CAN YOU USE IT: STEP 1
▸ Think of a use for computer vision
▸ Don’t start with the technology
▸ Get creative!
▸ Have a clear vision for what you want to achieve
A BEGINNERS GUIDE TO COMPUTER VISION
HOW CAN YOU USE IT: STEP 2
▸ Evaluate training your own model vs. cloud based
▸ Train your model / start working with API
▸ Test using data the model has never seen
A BEGINNERS GUIDE TO COMPUTER VISION
HOW CAN YOU USE IT: STEP 2 (DETOUR)
▸ OpenCV
▸ TensorFlow
▸ Google Cloud Vision API
▸ Microsoft Azure Computer Vision
▸ Amazon Rekognition
A BEGINNERS GUIDE TO COMPUTER VISION
HOW CAN YOU USE IT: STEP 3
▸ Integrate your model into your program / app
▸ Test. Test. TEST!
▸ Deploy!
A BEGINNERS GUIDE TO COMPUTER VISION
HOW CAN YOU USE IT: STEP 3
▸ Integrate your model into your program / app
▸ Test. Test. TEST!
▸ Deploy!
▸ …draw the rest of the owl
A BEGINNERS GUIDE TO COMPUTER VISION
MISCONCEPTIONS
▸ Terminator
▸ Self driving cars
▸ Computer Vision vs. Artificial Intelligence
▸ Facial Recognition
▸ Human behind the computer
A BEGINNERS GUIDE TO MACHINE LEARNING
THANK YOU!

Contenu connexe

Tendances

Kid Pix And Blue Screening Presentation
Kid Pix And Blue Screening PresentationKid Pix And Blue Screening Presentation
Kid Pix And Blue Screening Presentationjhawtin
 
Magazine pre production
Magazine pre productionMagazine pre production
Magazine pre productionJamesSykes17
 
Week 5. Part4 - Hands On Activity
Week 5. Part4 - Hands On ActivityWeek 5. Part4 - Hands On Activity
Week 5. Part4 - Hands On Activityeducw200
 
Facilitating Remote Sessions in MURAL
Facilitating Remote Sessions in MURALFacilitating Remote Sessions in MURAL
Facilitating Remote Sessions in MURALMURAL
 
¿Que necesita para ser una buena desarrolladora?
¿Que necesita para ser una buena desarrolladora?¿Que necesita para ser una buena desarrolladora?
¿Que necesita para ser una buena desarrolladora?Software Guru
 
From Photographer to Developer
From Photographer to DeveloperFrom Photographer to Developer
From Photographer to DeveloperAshley McNamara
 
Making Moodle multi device friendly with bootstrap - Bas brands
Making Moodle multi device friendly with bootstrap - Bas brandsMaking Moodle multi device friendly with bootstrap - Bas brands
Making Moodle multi device friendly with bootstrap - Bas brandsIreland & UK Moodlemoot 2012
 
What I learned about innovation (Pragmatic Ideas)
What I learned about innovation (Pragmatic Ideas)What I learned about innovation (Pragmatic Ideas)
What I learned about innovation (Pragmatic Ideas)Lucian Ghinda
 
Innovation is a habit
Innovation is a habitInnovation is a habit
Innovation is a habitEd Kraay
 
Key takeaways from stanford university
Key takeaways from stanford universityKey takeaways from stanford university
Key takeaways from stanford universityAnuj Magazine
 
Revision techniques for students 2018 v3
Revision techniques for students 2018 v3Revision techniques for students 2018 v3
Revision techniques for students 2018 v3David Drake
 
Why we fail at ml ai why we fail at ml_ai
Why we fail at ml ai why we fail at ml_aiWhy we fail at ml ai why we fail at ml_ai
Why we fail at ml ai why we fail at ml_aiBrian Ray
 
All Method, No Madness: Guiding Agile Teams Through Research
All Method, No Madness: Guiding Agile Teams Through ResearchAll Method, No Madness: Guiding Agile Teams Through Research
All Method, No Madness: Guiding Agile Teams Through ResearchAggregage
 
Digital Publishing: What to take away
Digital Publishing: What to take awayDigital Publishing: What to take away
Digital Publishing: What to take awayJohannes Henseler
 
7 ways to a winning Investor pitch
7 ways to a winning Investor pitch7 ways to a winning Investor pitch
7 ways to a winning Investor pitchATUL RAJA
 
Change is a Constant: Technology, Service, and Constant Change
Change is a Constant: Technology, Service, and Constant ChangeChange is a Constant: Technology, Service, and Constant Change
Change is a Constant: Technology, Service, and Constant ChangeEmily Clasper
 
5. pre production(3)
5. pre production(3)5. pre production(3)
5. pre production(3)TheaJennings1
 
Technology Training for Non-Techies
Technology Training for Non-TechiesTechnology Training for Non-Techies
Technology Training for Non-TechiesEmily Clasper
 
Collaborating in MURAL
Collaborating in MURALCollaborating in MURAL
Collaborating in MURALMURAL
 
Obstacles of Digital Transformation Evolution
Obstacles of Digital Transformation EvolutionObstacles of Digital Transformation Evolution
Obstacles of Digital Transformation EvolutionEqual Experts
 

Tendances (20)

Kid Pix And Blue Screening Presentation
Kid Pix And Blue Screening PresentationKid Pix And Blue Screening Presentation
Kid Pix And Blue Screening Presentation
 
Magazine pre production
Magazine pre productionMagazine pre production
Magazine pre production
 
Week 5. Part4 - Hands On Activity
Week 5. Part4 - Hands On ActivityWeek 5. Part4 - Hands On Activity
Week 5. Part4 - Hands On Activity
 
Facilitating Remote Sessions in MURAL
Facilitating Remote Sessions in MURALFacilitating Remote Sessions in MURAL
Facilitating Remote Sessions in MURAL
 
¿Que necesita para ser una buena desarrolladora?
¿Que necesita para ser una buena desarrolladora?¿Que necesita para ser una buena desarrolladora?
¿Que necesita para ser una buena desarrolladora?
 
From Photographer to Developer
From Photographer to DeveloperFrom Photographer to Developer
From Photographer to Developer
 
Making Moodle multi device friendly with bootstrap - Bas brands
Making Moodle multi device friendly with bootstrap - Bas brandsMaking Moodle multi device friendly with bootstrap - Bas brands
Making Moodle multi device friendly with bootstrap - Bas brands
 
What I learned about innovation (Pragmatic Ideas)
What I learned about innovation (Pragmatic Ideas)What I learned about innovation (Pragmatic Ideas)
What I learned about innovation (Pragmatic Ideas)
 
Innovation is a habit
Innovation is a habitInnovation is a habit
Innovation is a habit
 
Key takeaways from stanford university
Key takeaways from stanford universityKey takeaways from stanford university
Key takeaways from stanford university
 
Revision techniques for students 2018 v3
Revision techniques for students 2018 v3Revision techniques for students 2018 v3
Revision techniques for students 2018 v3
 
Why we fail at ml ai why we fail at ml_ai
Why we fail at ml ai why we fail at ml_aiWhy we fail at ml ai why we fail at ml_ai
Why we fail at ml ai why we fail at ml_ai
 
All Method, No Madness: Guiding Agile Teams Through Research
All Method, No Madness: Guiding Agile Teams Through ResearchAll Method, No Madness: Guiding Agile Teams Through Research
All Method, No Madness: Guiding Agile Teams Through Research
 
Digital Publishing: What to take away
Digital Publishing: What to take awayDigital Publishing: What to take away
Digital Publishing: What to take away
 
7 ways to a winning Investor pitch
7 ways to a winning Investor pitch7 ways to a winning Investor pitch
7 ways to a winning Investor pitch
 
Change is a Constant: Technology, Service, and Constant Change
Change is a Constant: Technology, Service, and Constant ChangeChange is a Constant: Technology, Service, and Constant Change
Change is a Constant: Technology, Service, and Constant Change
 
5. pre production(3)
5. pre production(3)5. pre production(3)
5. pre production(3)
 
Technology Training for Non-Techies
Technology Training for Non-TechiesTechnology Training for Non-Techies
Technology Training for Non-Techies
 
Collaborating in MURAL
Collaborating in MURALCollaborating in MURAL
Collaborating in MURAL
 
Obstacles of Digital Transformation Evolution
Obstacles of Digital Transformation EvolutionObstacles of Digital Transformation Evolution
Obstacles of Digital Transformation Evolution
 

Similaire à Computer vision Des Moines (Prairie Code)

Diving into event-sourcing and event-driven architectures
Diving into event-sourcing and event-driven architecturesDiving into event-sourcing and event-driven architectures
Diving into event-sourcing and event-driven architecturesUnai Esteibar
 
WORKSHOP: Making the World Easier with Interaction Design
WORKSHOP: Making the World Easier with Interaction DesignWORKSHOP: Making the World Easier with Interaction Design
WORKSHOP: Making the World Easier with Interaction DesignCheryl Platz
 
From Prototyping to Optimization; UX/UI a continuous process
From Prototyping to Optimization; UX/UI a continuous processFrom Prototyping to Optimization; UX/UI a continuous process
From Prototyping to Optimization; UX/UI a continuous processArabNet ME
 
Programming for non-Programmers
Programming for non-ProgrammersProgramming for non-Programmers
Programming for non-ProgrammersEvgeny Tsarkov
 
Worse Is Better, for Better or for Worse
Worse Is Better, for Better or for WorseWorse Is Better, for Better or for Worse
Worse Is Better, for Better or for WorseKevlin Henney
 
Worse Is Better, for Better or for Worse
Worse Is Better, for Better or for WorseWorse Is Better, for Better or for Worse
Worse Is Better, for Better or for WorseKevlin Henney
 
Computers Are Opening Their Eyes - And They're Already Better at Seeing Than ...
Computers Are Opening Their Eyes - And They're Already Better at Seeing Than ...Computers Are Opening Their Eyes - And They're Already Better at Seeing Than ...
Computers Are Opening Their Eyes - And They're Already Better at Seeing Than ...Christopher Mohritz
 
Evaluation question 2 A2 Media
Evaluation question 2 A2 MediaEvaluation question 2 A2 Media
Evaluation question 2 A2 MediaAshleat153
 
How To Write a Symphony of Automation With Appium by Dan Cuellar sauce con18
How To Write a Symphony of Automation With Appium by Dan Cuellar sauce con18How To Write a Symphony of Automation With Appium by Dan Cuellar sauce con18
How To Write a Symphony of Automation With Appium by Dan Cuellar sauce con18Sauce Labs
 
How To Write A Symphony of Automation With Appium
How To Write A Symphony of Automation With AppiumHow To Write A Symphony of Automation With Appium
How To Write A Symphony of Automation With AppiumSauce Labs
 
Google Lens ShopTalk
Google Lens ShopTalkGoogle Lens ShopTalk
Google Lens ShopTalkSMED Tests
 
A2 Media Evaluation Question 2
A2 Media Evaluation Question 2A2 Media Evaluation Question 2
A2 Media Evaluation Question 2Ashleat153
 
A2 Media Evaluation
A2 Media Evaluation A2 Media Evaluation
A2 Media Evaluation Ashleat153
 
A2 Media Evaluation Q.2
A2 Media Evaluation Q.2A2 Media Evaluation Q.2
A2 Media Evaluation Q.2Ashleat153
 
Automated Testing in Angular Slides
Automated Testing in Angular SlidesAutomated Testing in Angular Slides
Automated Testing in Angular SlidesJim Lynch
 

Similaire à Computer vision Des Moines (Prairie Code) (20)

Diving into event-sourcing and event-driven architectures
Diving into event-sourcing and event-driven architecturesDiving into event-sourcing and event-driven architectures
Diving into event-sourcing and event-driven architectures
 
WORKSHOP: Making the World Easier with Interaction Design
WORKSHOP: Making the World Easier with Interaction DesignWORKSHOP: Making the World Easier with Interaction Design
WORKSHOP: Making the World Easier with Interaction Design
 
From Prototyping to Optimization; UX/UI a continuous process
From Prototyping to Optimization; UX/UI a continuous processFrom Prototyping to Optimization; UX/UI a continuous process
From Prototyping to Optimization; UX/UI a continuous process
 
Programming for non-Programmers
Programming for non-ProgrammersProgramming for non-Programmers
Programming for non-Programmers
 
Introduction to user-centric design process
Introduction to user-centric design processIntroduction to user-centric design process
Introduction to user-centric design process
 
Worse Is Better, for Better or for Worse
Worse Is Better, for Better or for WorseWorse Is Better, for Better or for Worse
Worse Is Better, for Better or for Worse
 
Planning .pptx
Planning .pptxPlanning .pptx
Planning .pptx
 
Worse Is Better, for Better or for Worse
Worse Is Better, for Better or for WorseWorse Is Better, for Better or for Worse
Worse Is Better, for Better or for Worse
 
Computers Are Opening Their Eyes - And They're Already Better at Seeing Than ...
Computers Are Opening Their Eyes - And They're Already Better at Seeing Than ...Computers Are Opening Their Eyes - And They're Already Better at Seeing Than ...
Computers Are Opening Their Eyes - And They're Already Better at Seeing Than ...
 
Evaluation question 2 A2 Media
Evaluation question 2 A2 MediaEvaluation question 2 A2 Media
Evaluation question 2 A2 Media
 
How To Write a Symphony of Automation With Appium by Dan Cuellar sauce con18
How To Write a Symphony of Automation With Appium by Dan Cuellar sauce con18How To Write a Symphony of Automation With Appium by Dan Cuellar sauce con18
How To Write a Symphony of Automation With Appium by Dan Cuellar sauce con18
 
How To Write A Symphony of Automation With Appium
How To Write A Symphony of Automation With AppiumHow To Write A Symphony of Automation With Appium
How To Write A Symphony of Automation With Appium
 
Portfolio
PortfolioPortfolio
Portfolio
 
Google Lens ShopTalk
Google Lens ShopTalkGoogle Lens ShopTalk
Google Lens ShopTalk
 
A2 Media Evaluation Question 2
A2 Media Evaluation Question 2A2 Media Evaluation Question 2
A2 Media Evaluation Question 2
 
A2 Media Evaluation
A2 Media Evaluation A2 Media Evaluation
A2 Media Evaluation
 
A2 Media Evaluation Q.2
A2 Media Evaluation Q.2A2 Media Evaluation Q.2
A2 Media Evaluation Q.2
 
Q6
Q6Q6
Q6
 
Q6
Q6Q6
Q6
 
Automated Testing in Angular Slides
Automated Testing in Angular SlidesAutomated Testing in Angular Slides
Automated Testing in Angular Slides
 

Dernier

Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Principled Technologies
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
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?Igalia
 
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 DiscoveryTrustArc
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024The Digital Insurer
 
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 SavingEdi Saputra
 
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
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
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, Adobeapidays
 

Dernier (20)

Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
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?
 
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
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024
 
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
 
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...
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
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 - 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
 

Computer vision Des Moines (Prairie Code)

  • 2. A BEGINNERS GUIDE TO COMPUTER VISION INTRODUCTION: ANDREW RANGEL ▸ Background: Mobile Development ▸ Passion for new and exciting technologies ▸ Working with and learning CV for ~1 year ▸ Wanted to share my experience
  • 3. A BEGINNERS GUIDE TO COMPUTER VISION INTRODUCTION: COMPUTER VISION ▸ What is it ▸ What is it for ▸ Who uses it ▸ Examples ▸ How can you use it ▸ Misconceptions
  • 4. A BEGINNERS GUIDE TO COMPUTER VISION WHAT IS IT ▸ Computer Vision is the process of using a computer based algorithm to identify patterns in the data of images ▸ Basic Steps: ▸ Process the image ▸ Use an algorithm to identify a pattern ▸ Present that pattern in a meaningful way
  • 5. A BEGINNERS GUIDE TO COMPUTER VISION WHAT IS IT
  • 6. A BEGINNERS GUIDE TO COMPUTER VISION WHAT IS IT
  • 7. A BEGINNERS GUIDE TO COMPUTER VISION WHAT IS IT
  • 8. A BEGINNERS GUIDE TO COMPUTER VISION WHAT IS IT
  • 9. A BEGINNERS GUIDE TO COMPUTER VISION WHAT IS IT
  • 10. A BEGINNERS GUIDE TO COMPUTER VISION WHAT IS IT ▸ Matrix math ▸ From basic to complex ▸ “Seeing” the matrix
  • 11. A BEGINNERS GUIDE TO COMPUTER VISION WHAT IS IT FOR ▸ More uses than you may imagine ▸ Sorting fruit ▸ Self driving vehicles ▸ Snapchat filters ▸ Identifying animals ▸ Identifying patterns humans cannot
  • 13.
  • 14.
  • 15. A BEGINNERS GUIDE TO COMPUTER VISION WHO USES IT ▸ Companies from farming to Snapchat ▸ Computer Vision allows companies to process unique input in a way that creates innovation and new industries ▸ Will be integrated more as Augmented Reality grows in popularity
  • 16. A BEGINNERS GUIDE TO COMPUTER VISION BAD AI BOT: MY EXCURSION INTO COMPUTER VISION ▸ I wanted to show my family and friends what I meant by “computer vision” ▸ When I showed them they were rarely impressed “meh” ▸ I noticed how terrible it is to use a “stock” model to try and identify the world ▸ Got a much bigger result from friends and family when showing them bad results
  • 17. A BEGINNERS GUIDE TO COMPUTER VISION BAD AI BOT: MY EXCURSION INTO COMPUTER VISION
  • 18. A BEGINNERS GUIDE TO COMPUTER VISION BAD AI BOT: MY EXCURSION INTO COMPUTER VISION ▸ Started with Inception3 model (open source) ▸ Apple example code ▸ Created UI wrapper and image picker interface ▸ Business logic when sending / receiving images from model
  • 19. A BEGINNERS GUIDE TO COMPUTER VISION BAD AI BOT: MY EXCURSION INTO COMPUTER VISION CAMERA OPENCV INCEPTION V3 RESULTS UI
  • 20. A BEGINNERS GUIDE TO COMPUTER VISION BAD AI BOT: MY EXCURSION INTO COMPUTER VISION OPENCV INCEPTION V3 RESULTS MODELIMAGEIMAGEIMAGE ERRORADJUST LABELS
  • 21. A BEGINNERS GUIDE TO COMPUTER VISION SEE FIRE: A MORE SERIOUS PROJECT ▸ Started with Netflix, naturally ▸ Wildfire epidemic on the west coast ▸ Prevention may be impossible but containment could save lives / homes / money ▸ What if you distributed a mesh network connected army of fire spotters?
  • 22. A BEGINNERS GUIDE TO COMPUTER VISION SEE FIRE: A MORE SERIOUS PROJECT ▸ This project seemed more suited for TensorFlow ▸ How to choose images ▸ Decide on how to train model ▸ Determine how you will test model ▸ Next steps
  • 23. A BEGINNERS GUIDE TO COMPUTER VISION SEE FIRE: A MORE SERIOUS PROJECT ▸ Sourcing images ▸ Google images (search tools for reuse) ▸ Programming is your friend: Python script ▸ Reviewing images ▸ Content is key
  • 24. A BEGINNERS GUIDE TO COMPUTER VISION HOW CAN YOU USE IT ▸ Easiest way to try computer vision is OpenCV on the desktop ▸ Easiest way to use computer vision is a mobile application ▸ 3 easy steps
  • 25. A BEGINNERS GUIDE TO COMPUTER VISION HOW CAN YOU USE IT: STEP 1 ▸ Think of a use for computer vision ▸ Don’t start with the technology ▸ Get creative! ▸ Have a clear vision for what you want to achieve
  • 26. A BEGINNERS GUIDE TO COMPUTER VISION HOW CAN YOU USE IT: STEP 2 ▸ Evaluate training your own model vs. cloud based ▸ Train your model / start working with API ▸ Test using data the model has never seen
  • 27. A BEGINNERS GUIDE TO COMPUTER VISION HOW CAN YOU USE IT: STEP 2 (DETOUR) ▸ OpenCV ▸ TensorFlow ▸ Google Cloud Vision API ▸ Microsoft Azure Computer Vision ▸ Amazon Rekognition
  • 28. A BEGINNERS GUIDE TO COMPUTER VISION HOW CAN YOU USE IT: STEP 3 ▸ Integrate your model into your program / app ▸ Test. Test. TEST! ▸ Deploy!
  • 29. A BEGINNERS GUIDE TO COMPUTER VISION HOW CAN YOU USE IT: STEP 3 ▸ Integrate your model into your program / app ▸ Test. Test. TEST! ▸ Deploy! ▸ …draw the rest of the owl
  • 30. A BEGINNERS GUIDE TO COMPUTER VISION MISCONCEPTIONS ▸ Terminator ▸ Self driving cars ▸ Computer Vision vs. Artificial Intelligence ▸ Facial Recognition ▸ Human behind the computer
  • 31. A BEGINNERS GUIDE TO MACHINE LEARNING THANK YOU!