SlideShare a Scribd company logo
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Venkatesh Bagaria
Senior Product Manager, Amazon Rekognition
Micky Dionisio
CTO, Open Influence
BDA303
Amazon Rekognition
Deep learning-based Image and Video Analysis
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition
VideoImag
e
&
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition Image
Object and Scene
Detection
Facial
Analysis
Face
Recognition
Text in Image
Deep learning-based image analysis service
Unsafe Image
Detection
Celebrity
Recognition
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition Video
Deep learning-based video analysis service
Object and Activity
Detection
Person Tracking Face Detection &
Recognition
Real-time Live
Stream
Unsafe Video
Detection
Celebrity
Recognition
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Console Demo
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
DetectLabels
{
"Image": {
"Bytes": blob,
"S3Object": {
"Bucket": "string",
"Name": "string",
"Version": "string"
}
},
"MaxLabels": number,
"MinConfidence": number
}
Image API – Request and Response
{
"Labels": [
{
"Confidence": number,
"Name": "string”
}
],
"OrientationCorrection": "string"
}
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
GetLabelDetection
StartLabelDetection
{
“ClientRequestToken": "string",
"JobTag": "string",
"MinConfidence": number,
"NotificationChannel": {
"RoleArn": "string",
"SNSTopicArn": "string”
},
"Video": {
"S3Object": {
"Bucket": "string",
"Name": "string",
"Version": "string”
}
}
}
Video API - Request and Response
{
"JobStatus": string,
"StatusMessage": string,
"VideoMetadata": {
"Format": string,
"Codec": string,
"DurationMillis": number,
"FrameRate": float,
"FrameWidth": number,
"FrameHeight": number
},
"NextToken": string,
"Labels": [
{
"Timestamp": number,
"Label":
{
"Name": string,
"Confidence": float
}
}
],
...
JobId
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition
Regions
US West (Oregon)
(us-west-2) US East (N. Virginia)
(us-east-1)
EU (Ireland)
(eu-west-1)
GovCloud (US)
(us-gov-west-1)
Asia Pacific (Tokyo)
(ap-northeast-1)
Asia Pacific (Sydney)
(ap-southeast-2)
US East (Ohio)
(us-east-2)
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition Customers
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Influencer Marketing
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Micky Dionisio, CTO
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
What is Influencer Marketing?
Marketing focused on
identifying individuals
who have influence
over potential buyers
Oversaturation of
information has created a
trust deficit
4-10x higher
conversion when
companies turn to
brand advocates
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
What is OpenInfluence?
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Our Use Case: Pain Points with Hashtags
• 2015  Hashtags were extremely popular
• 2018  Influencers don’t use hashtags
• How do we differentiate our offering to gain an edge over the
competition?
Image Recognition
First party data consisting of
over 1B+ data points
+
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Before
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
After
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Before & After Comparison
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Operational Efficiency
• Became a company that ran on technology-enabled
services
• Went from sourcing influencers in days/weeks to within
seconds
• Decreased influencer approval process time by 40%
• Over 60% of searches on our platform include some aspect
of label criteria
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Dating and Social Platforms
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Analyze User Generated Content
No faces detected
Age Range: 0-2 years
One face detected
10 faces detected
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Analyze User Generated Content
Person 99.2%
Dog 95.7%
Person 99.2%
Snowboarding 98.1%
No Moderation labels
detected
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
2. Submit
Image
4. DetectFaces 7. DetectText
1. Upload
3. Store image Lambda Step Functions
5.DetectLabels 6.DetectModerationLabels
8. Store Metadata
& analysis
DynamoDB
ElasticSearch
Analyze User Generated Content
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Public Safety
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Person Tracking
© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
"Persons": [
{
"Timestamp": number,
"Person":
{
"Index": number,
"BoundingBox":
{
"Width": number,
"Top": number,
"Height": number,
"Left": number
},
"Face":
{
"BoundingBox": { ... },
"Landmarks": { ... },
"Pose": { ... },
"Quality": { ... },
"Confidence": number
}
},
...
GetPersonTracking
StartPersonTracking
Person Tracking
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Real-time face search against tens of millions of faces
Face Search
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Persons of Interest
300,000+ images of previous offenders indexed in 2 days
Match time reduced from multiple days to seconds
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Persons of Interest
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Immediate Response for Public Safety or Home Automation
Live Street Camera Amazon Kinesis Video Streams Amazon Rekognition Video Face collection
1. Camera-captured video
streams are processed by
Kinesis Video Streams
2. Rekognition Video analyses the
video and searches faces on screen
against a collection of millions of faces
L i v e r e c o g n i t i o n o f P e r s o n s o f I n t e r e s t
End User
3. End user is notified
in case of face matches
Amazon SNS AWS Lambda Amazon Kinesis
Streams
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Authentication
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Face-based verification
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Face-based verification
 Multi-factor authentication
 Identity Verification
 Use Cases:
 Access control
 New customer enrolment
 Remote password reset
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Face v3
Improved Accuracy for real-time face search and verification
Up to 25% more accurate in search against millions
of faces
Up to 80% more accurate in rejecting similar faces
Up to 35% more accurate in accepting variations
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Demo
Real-time Face Search
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Device Camera
1. Images stored in S3
AWS Lambda
Amazon DynamoDB
Amazon Rekognition
Amazon Cognito
Face
collection
Amazon S3
Amazon Rekognition
2. Use Lambda to
process images with
Rekognition
3. Index faces into a
face collection, get
FaceId
4. Create person name
and collection stats
metadata with FaceId5.
SearchFacesByImage
with the collection using
AWS SDK
6. Get back search
results with names and
stats
Face Search Demo
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Best Practices for Faces
• Faces at least ~5% of shorter image dimension,
minimum 24-32 pixels
• For live use cases, send image as bytes (5MB limit)
• Reduce image resolution for faster response
• Add multiple reference images per identity
• Face Model Versioning
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Developer Resources for Amazon
Rekognition
Homepage: https://aws.amazon.com/rekognition/
AWS Machine Learning Blog – Amazon Rekognition:
https://aws.amazon.com/blogs/ai/tag/amazon-rekognition/
Serverless Image Recognition processing backend:
https://github.com/awslabs/lambda-refarch-imagerecognition
Reviewing User Generated Content Demo Code:
https://github.com/aws-samples/amazon-rekognition-policing-user-content

More Related Content

What's hot

Building Customer-Centric Contact Centers in Financial Services
Building Customer-Centric Contact Centers in Financial Services Building Customer-Centric Contact Centers in Financial Services
Building Customer-Centric Contact Centers in Financial Services
Amazon Web Services
 
Real-Time Web Analytics with Amazon Kinesis Data Analytics (ADT401) - AWS re:...
Real-Time Web Analytics with Amazon Kinesis Data Analytics (ADT401) - AWS re:...Real-Time Web Analytics with Amazon Kinesis Data Analytics (ADT401) - AWS re:...
Real-Time Web Analytics with Amazon Kinesis Data Analytics (ADT401) - AWS re:...
Amazon Web Services
 
Five New Security Automations Using AWS Security Services & Open Source (SEC4...
Five New Security Automations Using AWS Security Services & Open Source (SEC4...Five New Security Automations Using AWS Security Services & Open Source (SEC4...
Five New Security Automations Using AWS Security Services & Open Source (SEC4...
Amazon Web Services
 
SRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
SRV317 Creating and Publishing AR and VR Apps with Amazon SumerianSRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
SRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
Amazon Web Services
 
DEM04 Fearless: From Monolith to Serverless with Dynatrace
DEM04 Fearless: From Monolith to Serverless with DynatraceDEM04 Fearless: From Monolith to Serverless with Dynatrace
DEM04 Fearless: From Monolith to Serverless with Dynatrace
Amazon Web Services
 
SRV309 AWS Purpose-Built Database Strategy: The Right Tool for the Right Job
 SRV309 AWS Purpose-Built Database Strategy: The Right Tool for the Right Job SRV309 AWS Purpose-Built Database Strategy: The Right Tool for the Right Job
SRV309 AWS Purpose-Built Database Strategy: The Right Tool for the Right Job
Amazon Web Services
 
Don’t Wait Until Tomorrow: From Batch to Streaming (ANT360) - AWS re:Invent 2018
Don’t Wait Until Tomorrow: From Batch to Streaming (ANT360) - AWS re:Invent 2018Don’t Wait Until Tomorrow: From Batch to Streaming (ANT360) - AWS re:Invent 2018
Don’t Wait Until Tomorrow: From Batch to Streaming (ANT360) - AWS re:Invent 2018
Amazon Web Services
 
Serverless:It All Started in Vegas (DVC306) - AWS re:Invent 2018
Serverless:It All Started in Vegas (DVC306) - AWS re:Invent 2018Serverless:It All Started in Vegas (DVC306) - AWS re:Invent 2018
Serverless:It All Started in Vegas (DVC306) - AWS re:Invent 2018
Amazon Web Services
 
SRV204 Creating Your Virtual Data Center: VPC Fundamentals and Connectivity ...
 SRV204 Creating Your Virtual Data Center: VPC Fundamentals and Connectivity ... SRV204 Creating Your Virtual Data Center: VPC Fundamentals and Connectivity ...
SRV204 Creating Your Virtual Data Center: VPC Fundamentals and Connectivity ...
Amazon Web Services
 
Building Highly Scalable Retail Order Management Systems with Serverless
Building Highly Scalable Retail Order Management Systems with ServerlessBuilding Highly Scalable Retail Order Management Systems with Serverless
Building Highly Scalable Retail Order Management Systems with Serverless
Amazon Web Services
 
High Velocity DevOps: Four Ways to Leverage CloudFront in Faster DevOps Workf...
High Velocity DevOps: Four Ways to Leverage CloudFront in Faster DevOps Workf...High Velocity DevOps: Four Ways to Leverage CloudFront in Faster DevOps Workf...
High Velocity DevOps: Four Ways to Leverage CloudFront in Faster DevOps Workf...
Amazon Web Services
 
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Amazon Web Services
 
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Amazon Web Services
 
Building Real-time Serverless Backends with GraphQL
Building Real-time Serverless Backends with GraphQLBuilding Real-time Serverless Backends with GraphQL
Building Real-time Serverless Backends with GraphQL
Amazon Web Services
 
SRV315 Building Enterprise-Grade Serverless Apps
 SRV315 Building Enterprise-Grade Serverless Apps SRV315 Building Enterprise-Grade Serverless Apps
SRV315 Building Enterprise-Grade Serverless Apps
Amazon Web Services
 
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
Amazon Web Services
 
BDA301 Working with Machine Learning in Amazon SageMaker: Algorithms, Models,...
BDA301 Working with Machine Learning in Amazon SageMaker: Algorithms, Models,...BDA301 Working with Machine Learning in Amazon SageMaker: Algorithms, Models,...
BDA301 Working with Machine Learning in Amazon SageMaker: Algorithms, Models,...
Amazon Web Services
 
A New Approach to Continuous Monitoring in the Cloud: Migrate to AWS with NET...
A New Approach to Continuous Monitoring in the Cloud: Migrate to AWS with NET...A New Approach to Continuous Monitoring in the Cloud: Migrate to AWS with NET...
A New Approach to Continuous Monitoring in the Cloud: Migrate to AWS with NET...
Amazon Web Services
 
Build Intelligent Apps with Amazon ML
Build Intelligent Apps with Amazon ML Build Intelligent Apps with Amazon ML
Build Intelligent Apps with Amazon ML
Amazon Web Services
 
Enable Your Marketing Teams to Engage Users with Relevant & Personalized Cont...
Enable Your Marketing Teams to Engage Users with Relevant & Personalized Cont...Enable Your Marketing Teams to Engage Users with Relevant & Personalized Cont...
Enable Your Marketing Teams to Engage Users with Relevant & Personalized Cont...
Amazon Web Services
 

What's hot (20)

Building Customer-Centric Contact Centers in Financial Services
Building Customer-Centric Contact Centers in Financial Services Building Customer-Centric Contact Centers in Financial Services
Building Customer-Centric Contact Centers in Financial Services
 
Real-Time Web Analytics with Amazon Kinesis Data Analytics (ADT401) - AWS re:...
Real-Time Web Analytics with Amazon Kinesis Data Analytics (ADT401) - AWS re:...Real-Time Web Analytics with Amazon Kinesis Data Analytics (ADT401) - AWS re:...
Real-Time Web Analytics with Amazon Kinesis Data Analytics (ADT401) - AWS re:...
 
Five New Security Automations Using AWS Security Services & Open Source (SEC4...
Five New Security Automations Using AWS Security Services & Open Source (SEC4...Five New Security Automations Using AWS Security Services & Open Source (SEC4...
Five New Security Automations Using AWS Security Services & Open Source (SEC4...
 
SRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
SRV317 Creating and Publishing AR and VR Apps with Amazon SumerianSRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
SRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
 
DEM04 Fearless: From Monolith to Serverless with Dynatrace
DEM04 Fearless: From Monolith to Serverless with DynatraceDEM04 Fearless: From Monolith to Serverless with Dynatrace
DEM04 Fearless: From Monolith to Serverless with Dynatrace
 
SRV309 AWS Purpose-Built Database Strategy: The Right Tool for the Right Job
 SRV309 AWS Purpose-Built Database Strategy: The Right Tool for the Right Job SRV309 AWS Purpose-Built Database Strategy: The Right Tool for the Right Job
SRV309 AWS Purpose-Built Database Strategy: The Right Tool for the Right Job
 
Don’t Wait Until Tomorrow: From Batch to Streaming (ANT360) - AWS re:Invent 2018
Don’t Wait Until Tomorrow: From Batch to Streaming (ANT360) - AWS re:Invent 2018Don’t Wait Until Tomorrow: From Batch to Streaming (ANT360) - AWS re:Invent 2018
Don’t Wait Until Tomorrow: From Batch to Streaming (ANT360) - AWS re:Invent 2018
 
Serverless:It All Started in Vegas (DVC306) - AWS re:Invent 2018
Serverless:It All Started in Vegas (DVC306) - AWS re:Invent 2018Serverless:It All Started in Vegas (DVC306) - AWS re:Invent 2018
Serverless:It All Started in Vegas (DVC306) - AWS re:Invent 2018
 
SRV204 Creating Your Virtual Data Center: VPC Fundamentals and Connectivity ...
 SRV204 Creating Your Virtual Data Center: VPC Fundamentals and Connectivity ... SRV204 Creating Your Virtual Data Center: VPC Fundamentals and Connectivity ...
SRV204 Creating Your Virtual Data Center: VPC Fundamentals and Connectivity ...
 
Building Highly Scalable Retail Order Management Systems with Serverless
Building Highly Scalable Retail Order Management Systems with ServerlessBuilding Highly Scalable Retail Order Management Systems with Serverless
Building Highly Scalable Retail Order Management Systems with Serverless
 
High Velocity DevOps: Four Ways to Leverage CloudFront in Faster DevOps Workf...
High Velocity DevOps: Four Ways to Leverage CloudFront in Faster DevOps Workf...High Velocity DevOps: Four Ways to Leverage CloudFront in Faster DevOps Workf...
High Velocity DevOps: Four Ways to Leverage CloudFront in Faster DevOps Workf...
 
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
 
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
 
Building Real-time Serverless Backends with GraphQL
Building Real-time Serverless Backends with GraphQLBuilding Real-time Serverless Backends with GraphQL
Building Real-time Serverless Backends with GraphQL
 
SRV315 Building Enterprise-Grade Serverless Apps
 SRV315 Building Enterprise-Grade Serverless Apps SRV315 Building Enterprise-Grade Serverless Apps
SRV315 Building Enterprise-Grade Serverless Apps
 
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
 
BDA301 Working with Machine Learning in Amazon SageMaker: Algorithms, Models,...
BDA301 Working with Machine Learning in Amazon SageMaker: Algorithms, Models,...BDA301 Working with Machine Learning in Amazon SageMaker: Algorithms, Models,...
BDA301 Working with Machine Learning in Amazon SageMaker: Algorithms, Models,...
 
A New Approach to Continuous Monitoring in the Cloud: Migrate to AWS with NET...
A New Approach to Continuous Monitoring in the Cloud: Migrate to AWS with NET...A New Approach to Continuous Monitoring in the Cloud: Migrate to AWS with NET...
A New Approach to Continuous Monitoring in the Cloud: Migrate to AWS with NET...
 
Build Intelligent Apps with Amazon ML
Build Intelligent Apps with Amazon ML Build Intelligent Apps with Amazon ML
Build Intelligent Apps with Amazon ML
 
Enable Your Marketing Teams to Engage Users with Relevant & Personalized Cont...
Enable Your Marketing Teams to Engage Users with Relevant & Personalized Cont...Enable Your Marketing Teams to Engage Users with Relevant & Personalized Cont...
Enable Your Marketing Teams to Engage Users with Relevant & Personalized Cont...
 

Similar to BDA303 Amazon Rekognition: Deep Learning-Based Image and Video Analysis

Amazon Rekognition: Deep Learning-Based Image and Video Analysis - BDA303 - C...
Amazon Rekognition: Deep Learning-Based Image and Video Analysis - BDA303 - C...Amazon Rekognition: Deep Learning-Based Image and Video Analysis - BDA303 - C...
Amazon Rekognition: Deep Learning-Based Image and Video Analysis - BDA303 - C...
Amazon Web Services
 
Build, Deploy, and Serve Machine Learning Models on Streaming Data (ANT345-R1...
Build, Deploy, and Serve Machine Learning Models on Streaming Data (ANT345-R1...Build, Deploy, and Serve Machine Learning Models on Streaming Data (ANT345-R1...
Build, Deploy, and Serve Machine Learning Models on Streaming Data (ANT345-R1...
Amazon Web Services
 
Build a Searchable Media Library & Moderate Content at Scale Using Machine Le...
Build a Searchable Media Library & Moderate Content at Scale Using Machine Le...Build a Searchable Media Library & Moderate Content at Scale Using Machine Le...
Build a Searchable Media Library & Moderate Content at Scale Using Machine Le...
Amazon Web Services
 
Deep Dive on Amazon Rekognition, ft. Pinterest (AIM307-R1) - AWS re:Invent 2018
Deep Dive on Amazon Rekognition, ft. Pinterest (AIM307-R1) - AWS re:Invent 2018Deep Dive on Amazon Rekognition, ft. Pinterest (AIM307-R1) - AWS re:Invent 2018
Deep Dive on Amazon Rekognition, ft. Pinterest (AIM307-R1) - AWS re:Invent 2018
Amazon Web Services
 
Use Amazon Rekognition to Power Video Creative Asset Production (ADT202) - AW...
Use Amazon Rekognition to Power Video Creative Asset Production (ADT202) - AW...Use Amazon Rekognition to Power Video Creative Asset Production (ADT202) - AW...
Use Amazon Rekognition to Power Video Creative Asset Production (ADT202) - AW...
Amazon Web Services
 
Retail Marketing with Machine Learning & Amazon Rekognition (RET205) - AWS re...
Retail Marketing with Machine Learning & Amazon Rekognition (RET205) - AWS re...Retail Marketing with Machine Learning & Amazon Rekognition (RET205) - AWS re...
Retail Marketing with Machine Learning & Amazon Rekognition (RET205) - AWS re...
Amazon Web Services
 
Unlock the Full Potential of Your Media Assets, ft. Fox Entertainment Group (...
Unlock the Full Potential of Your Media Assets, ft. Fox Entertainment Group (...Unlock the Full Potential of Your Media Assets, ft. Fox Entertainment Group (...
Unlock the Full Potential of Your Media Assets, ft. Fox Entertainment Group (...
Amazon Web Services
 
Amazon Rekognition
Amazon RekognitionAmazon Rekognition
Amazon Rekognition
Amazon Web Services Japan
 
Build Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon RekognitionBuild Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon Rekognition
Amazon Web Services
 
Build Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon RekognitionBuild Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon Rekognition
Amazon Web Services
 
Amazon Rekognition: Deep Learning-Based Image and Video Analysis
Amazon Rekognition: Deep Learning-Based Image and Video AnalysisAmazon Rekognition: Deep Learning-Based Image and Video Analysis
Amazon Rekognition: Deep Learning-Based Image and Video Analysis
Amazon Web Services
 
Build a "Who's Who" App for Your Media Content (AIM409) - AWS re:Invent 2018
Build a "Who's Who" App for Your Media Content (AIM409) - AWS re:Invent 2018Build a "Who's Who" App for Your Media Content (AIM409) - AWS re:Invent 2018
Build a "Who's Who" App for Your Media Content (AIM409) - AWS re:Invent 2018
Amazon Web Services
 
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
Amazon Web Services
 
Build Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon RekognitionBuild Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon Rekognition
Amazon Web Services
 
Build Computer Vision Applications with Amazon Rekognition: Machine Learning ...
Build Computer Vision Applications with Amazon Rekognition: Machine Learning ...Build Computer Vision Applications with Amazon Rekognition: Machine Learning ...
Build Computer Vision Applications with Amazon Rekognition: Machine Learning ...
Amazon Web Services
 
AI - State of the Union
AI - State of the UnionAI - State of the Union
AI - State of the Union
Amazon Web Services
 
[REPEAT] Better Analytics Through Natural Language Processing (AIM405-R) - AW...
[REPEAT] Better Analytics Through Natural Language Processing (AIM405-R) - AW...[REPEAT] Better Analytics Through Natural Language Processing (AIM405-R) - AW...
[REPEAT] Better Analytics Through Natural Language Processing (AIM405-R) - AW...
Amazon Web Services
 
Using AI for real-life data enrichment - Tel Aviv Summit 2018
Using AI for real-life data enrichment - Tel Aviv Summit 2018Using AI for real-life data enrichment - Tel Aviv Summit 2018
Using AI for real-life data enrichment - Tel Aviv Summit 2018
Amazon Web Services
 
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
Amazon Web Services
 
Using Data to Delight and Retain Customers with ML
Using Data to Delight and Retain Customers with MLUsing Data to Delight and Retain Customers with ML
Using Data to Delight and Retain Customers with ML
Amazon Web Services
 

Similar to BDA303 Amazon Rekognition: Deep Learning-Based Image and Video Analysis (20)

Amazon Rekognition: Deep Learning-Based Image and Video Analysis - BDA303 - C...
Amazon Rekognition: Deep Learning-Based Image and Video Analysis - BDA303 - C...Amazon Rekognition: Deep Learning-Based Image and Video Analysis - BDA303 - C...
Amazon Rekognition: Deep Learning-Based Image and Video Analysis - BDA303 - C...
 
Build, Deploy, and Serve Machine Learning Models on Streaming Data (ANT345-R1...
Build, Deploy, and Serve Machine Learning Models on Streaming Data (ANT345-R1...Build, Deploy, and Serve Machine Learning Models on Streaming Data (ANT345-R1...
Build, Deploy, and Serve Machine Learning Models on Streaming Data (ANT345-R1...
 
Build a Searchable Media Library & Moderate Content at Scale Using Machine Le...
Build a Searchable Media Library & Moderate Content at Scale Using Machine Le...Build a Searchable Media Library & Moderate Content at Scale Using Machine Le...
Build a Searchable Media Library & Moderate Content at Scale Using Machine Le...
 
Deep Dive on Amazon Rekognition, ft. Pinterest (AIM307-R1) - AWS re:Invent 2018
Deep Dive on Amazon Rekognition, ft. Pinterest (AIM307-R1) - AWS re:Invent 2018Deep Dive on Amazon Rekognition, ft. Pinterest (AIM307-R1) - AWS re:Invent 2018
Deep Dive on Amazon Rekognition, ft. Pinterest (AIM307-R1) - AWS re:Invent 2018
 
Use Amazon Rekognition to Power Video Creative Asset Production (ADT202) - AW...
Use Amazon Rekognition to Power Video Creative Asset Production (ADT202) - AW...Use Amazon Rekognition to Power Video Creative Asset Production (ADT202) - AW...
Use Amazon Rekognition to Power Video Creative Asset Production (ADT202) - AW...
 
Retail Marketing with Machine Learning & Amazon Rekognition (RET205) - AWS re...
Retail Marketing with Machine Learning & Amazon Rekognition (RET205) - AWS re...Retail Marketing with Machine Learning & Amazon Rekognition (RET205) - AWS re...
Retail Marketing with Machine Learning & Amazon Rekognition (RET205) - AWS re...
 
Unlock the Full Potential of Your Media Assets, ft. Fox Entertainment Group (...
Unlock the Full Potential of Your Media Assets, ft. Fox Entertainment Group (...Unlock the Full Potential of Your Media Assets, ft. Fox Entertainment Group (...
Unlock the Full Potential of Your Media Assets, ft. Fox Entertainment Group (...
 
Amazon Rekognition
Amazon RekognitionAmazon Rekognition
Amazon Rekognition
 
Build Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon RekognitionBuild Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon Rekognition
 
Build Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon RekognitionBuild Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon Rekognition
 
Amazon Rekognition: Deep Learning-Based Image and Video Analysis
Amazon Rekognition: Deep Learning-Based Image and Video AnalysisAmazon Rekognition: Deep Learning-Based Image and Video Analysis
Amazon Rekognition: Deep Learning-Based Image and Video Analysis
 
Build a "Who's Who" App for Your Media Content (AIM409) - AWS re:Invent 2018
Build a "Who's Who" App for Your Media Content (AIM409) - AWS re:Invent 2018Build a "Who's Who" App for Your Media Content (AIM409) - AWS re:Invent 2018
Build a "Who's Who" App for Your Media Content (AIM409) - AWS re:Invent 2018
 
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
Deep Dive on Amazon Rekognition, ft. Tinder & News UK (AIM307-R) - AWS re:Inv...
 
Build Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon RekognitionBuild Computer Vision Applications with Amazon Rekognition
Build Computer Vision Applications with Amazon Rekognition
 
Build Computer Vision Applications with Amazon Rekognition: Machine Learning ...
Build Computer Vision Applications with Amazon Rekognition: Machine Learning ...Build Computer Vision Applications with Amazon Rekognition: Machine Learning ...
Build Computer Vision Applications with Amazon Rekognition: Machine Learning ...
 
AI - State of the Union
AI - State of the UnionAI - State of the Union
AI - State of the Union
 
[REPEAT] Better Analytics Through Natural Language Processing (AIM405-R) - AW...
[REPEAT] Better Analytics Through Natural Language Processing (AIM405-R) - AW...[REPEAT] Better Analytics Through Natural Language Processing (AIM405-R) - AW...
[REPEAT] Better Analytics Through Natural Language Processing (AIM405-R) - AW...
 
Using AI for real-life data enrichment - Tel Aviv Summit 2018
Using AI for real-life data enrichment - Tel Aviv Summit 2018Using AI for real-life data enrichment - Tel Aviv Summit 2018
Using AI for real-life data enrichment - Tel Aviv Summit 2018
 
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
 
Using Data to Delight and Retain Customers with ML
Using Data to Delight and Retain Customers with MLUsing Data to Delight and Retain Customers with ML
Using Data to Delight and Retain Customers with ML
 

More from Amazon Web Services

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Amazon Web Services
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Amazon Web Services
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
Amazon Web Services
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
Amazon Web Services
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
Amazon Web Services
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
Amazon Web Services
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Amazon Web Services
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
Amazon Web Services
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Amazon Web Services
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
Amazon Web Services
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
Amazon Web Services
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Amazon Web Services
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
Amazon Web Services
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Amazon Web Services
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
Amazon Web Services
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
Amazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
Amazon Web Services
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
Amazon Web Services
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
Amazon Web Services
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
Amazon Web Services
 

More from Amazon Web Services (20)

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 

BDA303 Amazon Rekognition: Deep Learning-Based Image and Video Analysis

  • 1. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Venkatesh Bagaria Senior Product Manager, Amazon Rekognition Micky Dionisio CTO, Open Influence BDA303 Amazon Rekognition Deep learning-based Image and Video Analysis
  • 2. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition VideoImag e &
  • 3. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Image Object and Scene Detection Facial Analysis Face Recognition Text in Image Deep learning-based image analysis service Unsafe Image Detection Celebrity Recognition
  • 4. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Video Deep learning-based video analysis service Object and Activity Detection Person Tracking Face Detection & Recognition Real-time Live Stream Unsafe Video Detection Celebrity Recognition
  • 5. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Console Demo
  • 6. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. DetectLabels { "Image": { "Bytes": blob, "S3Object": { "Bucket": "string", "Name": "string", "Version": "string" } }, "MaxLabels": number, "MinConfidence": number } Image API – Request and Response { "Labels": [ { "Confidence": number, "Name": "string” } ], "OrientationCorrection": "string" }
  • 7. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. GetLabelDetection StartLabelDetection { “ClientRequestToken": "string", "JobTag": "string", "MinConfidence": number, "NotificationChannel": { "RoleArn": "string", "SNSTopicArn": "string” }, "Video": { "S3Object": { "Bucket": "string", "Name": "string", "Version": "string” } } } Video API - Request and Response { "JobStatus": string, "StatusMessage": string, "VideoMetadata": { "Format": string, "Codec": string, "DurationMillis": number, "FrameRate": float, "FrameWidth": number, "FrameHeight": number }, "NextToken": string, "Labels": [ { "Timestamp": number, "Label": { "Name": string, "Confidence": float } } ], ... JobId
  • 8. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Regions US West (Oregon) (us-west-2) US East (N. Virginia) (us-east-1) EU (Ireland) (eu-west-1) GovCloud (US) (us-gov-west-1) Asia Pacific (Tokyo) (ap-northeast-1) Asia Pacific (Sydney) (ap-southeast-2) US East (Ohio) (us-east-2)
  • 9. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Customers
  • 10. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Influencer Marketing
  • 11. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Micky Dionisio, CTO
  • 12. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. What is Influencer Marketing? Marketing focused on identifying individuals who have influence over potential buyers Oversaturation of information has created a trust deficit 4-10x higher conversion when companies turn to brand advocates
  • 13. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. What is OpenInfluence?
  • 14. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Our Use Case: Pain Points with Hashtags • 2015  Hashtags were extremely popular • 2018  Influencers don’t use hashtags • How do we differentiate our offering to gain an edge over the competition? Image Recognition First party data consisting of over 1B+ data points +
  • 15. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Before
  • 16. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. After
  • 17. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Before & After Comparison
  • 18. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Operational Efficiency • Became a company that ran on technology-enabled services • Went from sourcing influencers in days/weeks to within seconds • Decreased influencer approval process time by 40% • Over 60% of searches on our platform include some aspect of label criteria
  • 19. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 20. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Dating and Social Platforms
  • 21. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Analyze User Generated Content No faces detected Age Range: 0-2 years One face detected 10 faces detected
  • 22. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Analyze User Generated Content Person 99.2% Dog 95.7% Person 99.2% Snowboarding 98.1% No Moderation labels detected
  • 23. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. 2. Submit Image 4. DetectFaces 7. DetectText 1. Upload 3. Store image Lambda Step Functions 5.DetectLabels 6.DetectModerationLabels 8. Store Metadata & analysis DynamoDB ElasticSearch Analyze User Generated Content
  • 24. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Public Safety
  • 25. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Person Tracking
  • 26. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 27. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. "Persons": [ { "Timestamp": number, "Person": { "Index": number, "BoundingBox": { "Width": number, "Top": number, "Height": number, "Left": number }, "Face": { "BoundingBox": { ... }, "Landmarks": { ... }, "Pose": { ... }, "Quality": { ... }, "Confidence": number } }, ... GetPersonTracking StartPersonTracking Person Tracking
  • 28. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Real-time face search against tens of millions of faces Face Search
  • 29. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Persons of Interest 300,000+ images of previous offenders indexed in 2 days Match time reduced from multiple days to seconds
  • 30. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Persons of Interest
  • 31. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Immediate Response for Public Safety or Home Automation Live Street Camera Amazon Kinesis Video Streams Amazon Rekognition Video Face collection 1. Camera-captured video streams are processed by Kinesis Video Streams 2. Rekognition Video analyses the video and searches faces on screen against a collection of millions of faces L i v e r e c o g n i t i o n o f P e r s o n s o f I n t e r e s t End User 3. End user is notified in case of face matches Amazon SNS AWS Lambda Amazon Kinesis Streams
  • 32. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Authentication
  • 33. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Face-based verification
  • 34. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Face-based verification  Multi-factor authentication  Identity Verification  Use Cases:  Access control  New customer enrolment  Remote password reset
  • 35. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Face v3 Improved Accuracy for real-time face search and verification Up to 25% more accurate in search against millions of faces Up to 80% more accurate in rejecting similar faces Up to 35% more accurate in accepting variations
  • 36. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Demo Real-time Face Search
  • 37. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Device Camera 1. Images stored in S3 AWS Lambda Amazon DynamoDB Amazon Rekognition Amazon Cognito Face collection Amazon S3 Amazon Rekognition 2. Use Lambda to process images with Rekognition 3. Index faces into a face collection, get FaceId 4. Create person name and collection stats metadata with FaceId5. SearchFacesByImage with the collection using AWS SDK 6. Get back search results with names and stats Face Search Demo
  • 38. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Best Practices for Faces • Faces at least ~5% of shorter image dimension, minimum 24-32 pixels • For live use cases, send image as bytes (5MB limit) • Reduce image resolution for faster response • Add multiple reference images per identity • Face Model Versioning
  • 39. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Developer Resources for Amazon Rekognition Homepage: https://aws.amazon.com/rekognition/ AWS Machine Learning Blog – Amazon Rekognition: https://aws.amazon.com/blogs/ai/tag/amazon-rekognition/ Serverless Image Recognition processing backend: https://github.com/awslabs/lambda-refarch-imagerecognition Reviewing User Generated Content Demo Code: https://github.com/aws-samples/amazon-rekognition-policing-user-content