SlideShare ist ein Scribd-Unternehmen logo
1 von 20
Remote
сontrol
With the Neural Networks-based solution
visual search
The goal & Problem
Choose proper product ID
from a product base by a
photo. Avoid a human
factor or lack of staff
experience.
For example, only a manager with extensive
experience can recognize broken remote
control with only half of the buttons present. A
recently hired employee cannot cope with
such a task — he needs to be trained for a
long time.
They all are very similar!
Visual search as a trend
Visual search is a growing trend: just take a
picture of what is interesting and the system
will find a product among millions of options.
You no longer need to describe the color, style
or other features of a product
Visual search is used by such global retail
companies as: ASOS, eBay, Neimann Marcus, Ted
Baker, Blippar, EasyJet, Levi’s, Disney, Walmart,
Salesforce, Syte, Houseology CarStory,
Snapchat’s, Farfetch, Marks, Pinterest, Amazon
Our Solution
We spent near a year to find the best solution, that uses
custom neural networks, GPU-based servers to achieve
speed and accuracy
Visual
With the CNN ensemble-based solution
Product
Recognition
We’ve created
Preparing data
We prepared thousands of images of all the remotes,
with different backgrounds, lighting, and positions.
We mark each remote control picture, so the neural
network can understand where there’s an object the
systems needs to identify. We’ve created special
virtual studio, which generates markup images
(material) for neural network training. And we've
combined a dataset from this studio with manually
collected images
Our neural network made
over 6 million of steps
Solution features
As a result, our solutions can recognize a
remote from a photo1
too bright or dark
in hands
of erased buttons or labels
with a complex background
taken from an angle
Solution features
2 A neural network is able to
recognize remotes that look
identical. Dozens of remotes.
Hundreds.
Even the most experienced
employee, on whose training you
would spend a lot of time and funds,
could not show such accuracy and
speed of recognition
Solution features
The assembly of neural networks for the task of
recognizing remotes allows you to accurately determine
the model, and it does not depend on the language of
the buttons and labels
[IN THE ROADMAP] Solution will allow a re-training
without the participation of a developer. You will quickly
and efficiently train the network with new products
3
4
Comparison with hash-based
Hash-based algorithms are
used in Google’s visual search
and can quickly distinguish a
“cat” from a “car”, but not
more
Like Google visual search
cat car
cat same cat?
Comparison with SIFT/SURF
Algorithms that allow to detect
points of interest on an image,
but are too sensitive to light,
damage of an original object,
etc.
SIFT/SURF
Colosseum
Colosseum ???
Colosseum
Comparison with custom CNN
(as in Google Lens, Google
AutoML Vision and in other
boxed solutions) - allows you
to perfectly distinguish one
class of the remote from
another, but makes mistakes if
remotes are visually similar
Google AutoML,
Google Lens
Different
Same?
Technologies used
TensorFlow
The machine learning framework. We used it create the neural network with
the model that is optimally suitable for further training
Google Cloud Vision, Soundex
To recognize labels, we used the Google Cloud Vision API, and to find the
best match among the possible results, we used full-text search, Levenshtein
distance calculation, and Soundex. Soundex is an algorithm for comparing
two strings by their sound, setting the same index for strings that have a
similar sound in English.
Solution business values
Visual search is a growing
trend in retail. Book your
place now!
Help wholesale partner.
Save their costs for staff
training and give them a
trendy tool for
end-customers
Be an innovative
company!
Unique solution for your
company
Easy integration
with API service
Algorithms are better than
used in analogues
Business value
Services for an end-customer:
- Integrate it to chatbots, websites, mobile apps of
your wholesales partners and allow your
end-customers to find a remote by photo
- Achieve an advantage: you will be on a priority list
because your goods are easier to find
- Measure a demand: collect what models appends
in search often than others
Future development
A system that allows upload photos
of a new product and retrain a neural network (current network
is trained on 90 products from several thousand of remotes)
Mobile application + server for the automated markup of training
material (now a lot of manual labor is used to prepare the
material for training, we can automate it)
1
Future development
A control panel with a dashboard that allows you to understand
how many times a particular remote has been searched.
Notifications about unrecognized items and re-training with them
2
Pricing model
The client gets an access to the API service and the control panel to view a statistics
Yearly
Per
scan
Delivery of the solution
as a ready-made boxed solution
with an annual subscription
Payment for each scan /
package scans
or
Contacts
Sergey Kravtsov
skravtsov@evergreens.com.ua
+38 096 335 00 47

Weitere ähnliche Inhalte

Ähnlich wie Remote control object recognition - Evergreen

5 Algorithms Every Web Developer Can Use and Understand
5 Algorithms Every Web Developer Can Use and Understand5 Algorithms Every Web Developer Can Use and Understand
5 Algorithms Every Web Developer Can Use and UnderstandMatt Kiser
 
Future of Ecommerce: How to Improve the Online Shopping Experience Using Mach...
Future of Ecommerce: How to Improve the Online Shopping Experience Using Mach...Future of Ecommerce: How to Improve the Online Shopping Experience Using Mach...
Future of Ecommerce: How to Improve the Online Shopping Experience Using Mach...Skyl.ai
 
Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionKavika Roy
 
Case Study to build a tablet based app that is a shopping assistant.
Case Study to build a tablet based app that is a shopping assistant.Case Study to build a tablet based app that is a shopping assistant.
Case Study to build a tablet based app that is a shopping assistant.Vivek Parihar
 
How an AI-backed recommendation system can help increase revenue for your onl...
How an AI-backed recommendation system can help increase revenue for your onl...How an AI-backed recommendation system can help increase revenue for your onl...
How an AI-backed recommendation system can help increase revenue for your onl...Skyl.ai
 
RPA and AI impact on Banking - 4th Annual Back Office Operations Forum, Vienna
RPA and AI impact on Banking - 4th Annual Back Office Operations Forum, ViennaRPA and AI impact on Banking - 4th Annual Back Office Operations Forum, Vienna
RPA and AI impact on Banking - 4th Annual Back Office Operations Forum, ViennaUiPath
 
Track 2 Session 5_ 利用 SageMaker 深度學習容器化在廣告推播之應用
Track 2 Session 5_ 利用 SageMaker 深度學習容器化在廣告推播之應用Track 2 Session 5_ 利用 SageMaker 深度學習容器化在廣告推播之應用
Track 2 Session 5_ 利用 SageMaker 深度學習容器化在廣告推播之應用Amazon Web Services
 
[DSC Europe 23] Igor Ilic - Redefining User Experience with Large Language Mo...
[DSC Europe 23] Igor Ilic - Redefining User Experience with Large Language Mo...[DSC Europe 23] Igor Ilic - Redefining User Experience with Large Language Mo...
[DSC Europe 23] Igor Ilic - Redefining User Experience with Large Language Mo...DataScienceConferenc1
 
AI for Customer Service: How to Improve Contact Center Efficiency with Machin...
AI for Customer Service: How to Improve Contact Center Efficiency with Machin...AI for Customer Service: How to Improve Contact Center Efficiency with Machin...
AI for Customer Service: How to Improve Contact Center Efficiency with Machin...Skyl.ai
 
Artificial intelligence in android development
Artificial intelligence in android developmentArtificial intelligence in android development
Artificial intelligence in android developmentanikeshkumar11
 
Keeping your touch screen kiosk content creation business future
Keeping your touch screen kiosk content creation business futureKeeping your touch screen kiosk content creation business future
Keeping your touch screen kiosk content creation business futureIntuiface
 
Want to integrate your business phone system or contact center with your CRM?
Want to integrate your business phone system or contact center with your CRM?Want to integrate your business phone system or contact center with your CRM?
Want to integrate your business phone system or contact center with your CRM?Coreyskute Turner
 
Bargento 2014 : conférence Smile « ElasticSearch booste la recherche Magento »
Bargento 2014 : conférence Smile « ElasticSearch booste la recherche Magento »Bargento 2014 : conférence Smile « ElasticSearch booste la recherche Magento »
Bargento 2014 : conférence Smile « ElasticSearch booste la recherche Magento »Smile I.T is open
 
Hyf azure ml_1
Hyf azure ml_1Hyf azure ml_1
Hyf azure ml_1KatoK1
 
First to Market, World's First App Fully Powered by Google's New AI Technolog...
First to Market, World's First App Fully Powered by Google's New AI Technolog...First to Market, World's First App Fully Powered by Google's New AI Technolog...
First to Market, World's First App Fully Powered by Google's New AI Technolog...DulalChandraMondal
 
Google Analytics Konferenz 2018_Machine Learning / AI mit Google_Lukman Ramse...
Google Analytics Konferenz 2018_Machine Learning / AI mit Google_Lukman Ramse...Google Analytics Konferenz 2018_Machine Learning / AI mit Google_Lukman Ramse...
Google Analytics Konferenz 2018_Machine Learning / AI mit Google_Lukman Ramse...e-dialog GmbH
 
Magnolia 6 release walkthrough
Magnolia 6 release walkthroughMagnolia 6 release walkthrough
Magnolia 6 release walkthroughMagnolia
 
Deep learning and its problem types
Deep learning and its problem typesDeep learning and its problem types
Deep learning and its problem typesQualitasTechnology
 

Ähnlich wie Remote control object recognition - Evergreen (20)

unit_5.pdf
unit_5.pdfunit_5.pdf
unit_5.pdf
 
5 Algorithms Every Web Developer Can Use and Understand
5 Algorithms Every Web Developer Can Use and Understand5 Algorithms Every Web Developer Can Use and Understand
5 Algorithms Every Web Developer Can Use and Understand
 
Future of Ecommerce: How to Improve the Online Shopping Experience Using Mach...
Future of Ecommerce: How to Improve the Online Shopping Experience Using Mach...Future of Ecommerce: How to Improve the Online Shopping Experience Using Mach...
Future of Ecommerce: How to Improve the Online Shopping Experience Using Mach...
 
Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer Vision
 
Case Study to build a tablet based app that is a shopping assistant.
Case Study to build a tablet based app that is a shopping assistant.Case Study to build a tablet based app that is a shopping assistant.
Case Study to build a tablet based app that is a shopping assistant.
 
How an AI-backed recommendation system can help increase revenue for your onl...
How an AI-backed recommendation system can help increase revenue for your onl...How an AI-backed recommendation system can help increase revenue for your onl...
How an AI-backed recommendation system can help increase revenue for your onl...
 
RPA and AI impact on Banking - 4th Annual Back Office Operations Forum, Vienna
RPA and AI impact on Banking - 4th Annual Back Office Operations Forum, ViennaRPA and AI impact on Banking - 4th Annual Back Office Operations Forum, Vienna
RPA and AI impact on Banking - 4th Annual Back Office Operations Forum, Vienna
 
Track 2 Session 5_ 利用 SageMaker 深度學習容器化在廣告推播之應用
Track 2 Session 5_ 利用 SageMaker 深度學習容器化在廣告推播之應用Track 2 Session 5_ 利用 SageMaker 深度學習容器化在廣告推播之應用
Track 2 Session 5_ 利用 SageMaker 深度學習容器化在廣告推播之應用
 
[DSC Europe 23] Igor Ilic - Redefining User Experience with Large Language Mo...
[DSC Europe 23] Igor Ilic - Redefining User Experience with Large Language Mo...[DSC Europe 23] Igor Ilic - Redefining User Experience with Large Language Mo...
[DSC Europe 23] Igor Ilic - Redefining User Experience with Large Language Mo...
 
AI for Customer Service: How to Improve Contact Center Efficiency with Machin...
AI for Customer Service: How to Improve Contact Center Efficiency with Machin...AI for Customer Service: How to Improve Contact Center Efficiency with Machin...
AI for Customer Service: How to Improve Contact Center Efficiency with Machin...
 
Artificial intelligence in android development
Artificial intelligence in android developmentArtificial intelligence in android development
Artificial intelligence in android development
 
Keeping your touch screen kiosk content creation business future
Keeping your touch screen kiosk content creation business futureKeeping your touch screen kiosk content creation business future
Keeping your touch screen kiosk content creation business future
 
Want to integrate your business phone system or contact center with your CRM?
Want to integrate your business phone system or contact center with your CRM?Want to integrate your business phone system or contact center with your CRM?
Want to integrate your business phone system or contact center with your CRM?
 
Bargento 2014 : conférence Smile « ElasticSearch booste la recherche Magento »
Bargento 2014 : conférence Smile « ElasticSearch booste la recherche Magento »Bargento 2014 : conférence Smile « ElasticSearch booste la recherche Magento »
Bargento 2014 : conférence Smile « ElasticSearch booste la recherche Magento »
 
Hyf azure ml_1
Hyf azure ml_1Hyf azure ml_1
Hyf azure ml_1
 
Introduction to ML.NET
Introduction to ML.NETIntroduction to ML.NET
Introduction to ML.NET
 
First to Market, World's First App Fully Powered by Google's New AI Technolog...
First to Market, World's First App Fully Powered by Google's New AI Technolog...First to Market, World's First App Fully Powered by Google's New AI Technolog...
First to Market, World's First App Fully Powered by Google's New AI Technolog...
 
Google Analytics Konferenz 2018_Machine Learning / AI mit Google_Lukman Ramse...
Google Analytics Konferenz 2018_Machine Learning / AI mit Google_Lukman Ramse...Google Analytics Konferenz 2018_Machine Learning / AI mit Google_Lukman Ramse...
Google Analytics Konferenz 2018_Machine Learning / AI mit Google_Lukman Ramse...
 
Magnolia 6 release walkthrough
Magnolia 6 release walkthroughMagnolia 6 release walkthrough
Magnolia 6 release walkthrough
 
Deep learning and its problem types
Deep learning and its problem typesDeep learning and its problem types
Deep learning and its problem types
 

Kürzlich hochgeladen

9892124323 | Book Call Girls in Juhu and escort services 24x7
9892124323 | Book Call Girls in Juhu and escort services 24x79892124323 | Book Call Girls in Juhu and escort services 24x7
9892124323 | Book Call Girls in Juhu and escort services 24x7Pooja Nehwal
 
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost LoverPowerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost LoverPsychicRuben LoveSpells
 
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual serviceCALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual serviceanilsa9823
 
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,Pooja Nehwal
 
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCRFULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCRnishacall1
 
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun serviceCALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun serviceanilsa9823
 
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort ServiceDelhi Call girls
 

Kürzlich hochgeladen (7)

9892124323 | Book Call Girls in Juhu and escort services 24x7
9892124323 | Book Call Girls in Juhu and escort services 24x79892124323 | Book Call Girls in Juhu and escort services 24x7
9892124323 | Book Call Girls in Juhu and escort services 24x7
 
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost LoverPowerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
 
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual serviceCALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
 
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
 
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCRFULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
 
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun serviceCALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
 
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
 

Remote control object recognition - Evergreen

  • 1. Remote сontrol With the Neural Networks-based solution visual search
  • 2. The goal & Problem Choose proper product ID from a product base by a photo. Avoid a human factor or lack of staff experience. For example, only a manager with extensive experience can recognize broken remote control with only half of the buttons present. A recently hired employee cannot cope with such a task — he needs to be trained for a long time. They all are very similar!
  • 3. Visual search as a trend Visual search is a growing trend: just take a picture of what is interesting and the system will find a product among millions of options. You no longer need to describe the color, style or other features of a product Visual search is used by such global retail companies as: ASOS, eBay, Neimann Marcus, Ted Baker, Blippar, EasyJet, Levi’s, Disney, Walmart, Salesforce, Syte, Houseology CarStory, Snapchat’s, Farfetch, Marks, Pinterest, Amazon
  • 4.
  • 5. Our Solution We spent near a year to find the best solution, that uses custom neural networks, GPU-based servers to achieve speed and accuracy
  • 6. Visual With the CNN ensemble-based solution Product Recognition We’ve created
  • 7. Preparing data We prepared thousands of images of all the remotes, with different backgrounds, lighting, and positions. We mark each remote control picture, so the neural network can understand where there’s an object the systems needs to identify. We’ve created special virtual studio, which generates markup images (material) for neural network training. And we've combined a dataset from this studio with manually collected images Our neural network made over 6 million of steps
  • 8. Solution features As a result, our solutions can recognize a remote from a photo1 too bright or dark in hands of erased buttons or labels with a complex background taken from an angle
  • 9. Solution features 2 A neural network is able to recognize remotes that look identical. Dozens of remotes. Hundreds. Even the most experienced employee, on whose training you would spend a lot of time and funds, could not show such accuracy and speed of recognition
  • 10. Solution features The assembly of neural networks for the task of recognizing remotes allows you to accurately determine the model, and it does not depend on the language of the buttons and labels [IN THE ROADMAP] Solution will allow a re-training without the participation of a developer. You will quickly and efficiently train the network with new products 3 4
  • 11. Comparison with hash-based Hash-based algorithms are used in Google’s visual search and can quickly distinguish a “cat” from a “car”, but not more Like Google visual search cat car cat same cat?
  • 12. Comparison with SIFT/SURF Algorithms that allow to detect points of interest on an image, but are too sensitive to light, damage of an original object, etc. SIFT/SURF Colosseum Colosseum ??? Colosseum
  • 13. Comparison with custom CNN (as in Google Lens, Google AutoML Vision and in other boxed solutions) - allows you to perfectly distinguish one class of the remote from another, but makes mistakes if remotes are visually similar Google AutoML, Google Lens Different Same?
  • 14. Technologies used TensorFlow The machine learning framework. We used it create the neural network with the model that is optimally suitable for further training Google Cloud Vision, Soundex To recognize labels, we used the Google Cloud Vision API, and to find the best match among the possible results, we used full-text search, Levenshtein distance calculation, and Soundex. Soundex is an algorithm for comparing two strings by their sound, setting the same index for strings that have a similar sound in English.
  • 15. Solution business values Visual search is a growing trend in retail. Book your place now! Help wholesale partner. Save their costs for staff training and give them a trendy tool for end-customers Be an innovative company! Unique solution for your company Easy integration with API service Algorithms are better than used in analogues
  • 16. Business value Services for an end-customer: - Integrate it to chatbots, websites, mobile apps of your wholesales partners and allow your end-customers to find a remote by photo - Achieve an advantage: you will be on a priority list because your goods are easier to find - Measure a demand: collect what models appends in search often than others
  • 17. Future development A system that allows upload photos of a new product and retrain a neural network (current network is trained on 90 products from several thousand of remotes) Mobile application + server for the automated markup of training material (now a lot of manual labor is used to prepare the material for training, we can automate it) 1
  • 18. Future development A control panel with a dashboard that allows you to understand how many times a particular remote has been searched. Notifications about unrecognized items and re-training with them 2
  • 19. Pricing model The client gets an access to the API service and the control panel to view a statistics Yearly Per scan Delivery of the solution as a ready-made boxed solution with an annual subscription Payment for each scan / package scans or