Real Time Face Analysis

Copyright © 2018 MicroStrategy Incorporated. All Rights Reserved.

Real Time Face Analysis and Image Recognition with MicroStrategyEduardo Fernández Díaz, MicroStrategy


Copyright and Safe Harbor Notice

This presentation may include statements that constitute “forward-looking statements” for purposes of the safe harbor provisions under the Private Securities Litigation Reform Act of 1995, including descriptions of technology and product features that are under development and estimates of future business prospects. Forward-looking statements inherently involve risks and uncertainties that could cause actual results of MicroStrategy Incorporated and its subsidiaries (collectively, the “Company”) to differ materially from the forward-looking statements.

Factors that could contribute to such differences include: the Company’s ability to meet product development goals while aligning costs with anticipated revenues; the Company’s ability to develop, market and deliver on a timely and cost-effective basis new or enhanced offerings that respond to technological change or new customer requirements; the extent and timing of market acceptance of the Company’s new offerings; continued acceptance of the Company’s other products in the marketplace; the timing of significant orders; competitive factors; general economic conditions; and other risks detailed in the Company’s Form 10-K for the year ended December 31, 2016 and other periodic reports filed with the Securities and Exchange Commission. By making these forward-looking statements, the Company undertakes noobligation to update these statements for revisions or changes after the date of this presentation.


Agenda

3

•Demo Architecture

•Facial Recognition and Facial Analysis

•AWS Rekognition

•REST API

•Real-Time controller

•Real-time plugin

•Live demonstration


Real Time Face Analysis and Image Recognition with MicroStrategyHow to use MicroStrategy REST API to get awesome solutions.

4


Demo Architecture

5

AWS Rekognition®

Intelligent Cube

Intelligence Server

MicroStrategyWeb/Mobile

Real-time visualization

JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis

- Hair color- Gender- Age Range- Open Eyes- Glasses- Smile- Beard- …

Json Data

Real-TimeController


Demo Architecture

6

AWS Rekognition®

Intelligent Cube

Intelligence Server



JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis


Json Data

Real TimeController


Demo Architecture

7

AWS Rekognition®

Intelligent Cube

Intelligence Server



JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis


Json Data

Real TimeController

AWS Rekognition ®

Copyright © 2018 MicroStrategy Incorporated. All Rights Reserved.8

Facial Recognition Facial Analysis

Facial Recognition vs Facial Analysis

•Locate faces within images and analyze faceatributes:

• the face is smiling

• the eyes are open•Beard or Mustache

•Age estimation and Gender•Human vision system can do these and many other things with faces very easily.

•Can we do the same with modern artificial intelligence algorithms?

•Technology capable of identifying or verifying a person from a digital image or a video frame.

• It works by comparing selected facial features from given image with faces within a database.

•Typically used as access control in security systems.

• Artificial intelligence and machine learning.


AWS Rekognition®

Amazon Service

9

Amazon Rekognition ®

• Makes it easy to add image analysis to your applications.

• Allows also the search and the detection of faces.• Rekognition’s API enables you to quickly add sophisticated deep learning-based visual search and image classification to your applications.

• The service uses artificial intelligence to "learn" which faces or objects are important.


AWS Rekognition®

Amazon Service

10

Key features• OBJECT AND SCENE DETECTION

• FACIAL RECOGNITION

• FACIAL ANALYSIS

• FACE COMPARISON

• UNSAFE IMAGE DETECTION

• CELEBRITY RECOGNITION


AWS Rekognition®

Amazon Service

11

Facial Analysis• Age Range• Gender• Open eyes• Eyeglasses• Open mouth• Smile• Beard and/or Mustache• Emotions:

• Happy• Angry• Sad


Demo Architecture

12

AWS Rekognition®

Intelligent Cube

Intelligence Server



JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis


Json Data

Real TimeController


Demo Architecture

13

AWS Rekognition®

Intelligent Cube

Intelligence Server



JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis


Json Data

Real TimeController

REST API


MicroStrategy REST API

14

The heart of the platform

JSON Data API 10.4•Stand alone server (deprecated)

•Reduced number of API Families:•Sessions•Cube•Datasets•Reports

•Only available until 10.10


MicroStrategy REST APIThe heart of the platform

15

REST API from 10.9•Part of MicroStrategy REST server

•HTTP requests:•POST•GET•PUSH•DELETE

•Light-weight JSON data XML API Layer

WebObjects Layer

REST Framework Layer

MicroStrategy Web – Java EE Server

MicroStrategy Intelligence Server

REST Client


MicroStrategy REST APIThe heart of the platform

16

REST API families•Expanded REST API families

•Extended functionality and more flexibility


Demo Architecture

17

AWS Rekognition®

Intelligent Cube

Intelligence Server



JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis


Json Data

Real TimeController


Demo Architecture

18

AWS Rekognition®

Intelligent Cube

Intelligence Server



JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis


Json Data

Real-TimeController

Real-Time Controller


Real-Time ControllerBuilt with NodeJs

20

Real-Time Controller• Built using NodeJS.

• Use of Socket.io library.

• New data is immediately informed.

• Publisher – Subscriber strategy.

• Enables listener server.

• Receives AWS results and stores it inside the cube.


Polling vs. Publisher-SubscriberDifferent Strategies

21

Polling (Client pull)• Is a mechanism to fetch fresh data.

•Client asks server for updates at certainregular intervals.

• Active behavior.

Publisher – Subscriber (Server push)•Data comes to you.

•Server is proactively pushing updates to the client.

•Limit the number of connections.

•Passive behavior.


Demo Architecture

22

AWS Rekognition®

Intelligent Cube

Intelligence Server



JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis


Json Data

Real TimeController


Demo Architecture

23

AWS Rekognition®

Intelligent Cube

Intelligence Server



JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis


Json Data

Real TimeController

Visualization Plugin


Real-Time Visualization PluginBuilt with MicroStrategy SDK

24

Real-Time Plugin•Built using MicroStrategy SDK

•Fully integrated with the platform

•Available for Dossier and Report Services

•Use of several javascript libraries:

• Jquery

•D3.js

•Amcharts.js


Real-Time Visualization PluginBuilt with MicroStrategy SDK

25

Real-time Plugin•Parameters using a standard data grid

•Use of REST API server to obtain the data.

•Different types of contents and charts

•Especial behaviors


Full Demo Architecture

26

AWS Rekognition®

Intelligent Cube

Intelligence Server



JSON APIServer

Data Input

Push / Get

Data

Data

Get

Facial Analysis


Json Data

Real-TimeController


Product DemonstrationLive demo.

27


Live demo

28

Real-time full dashboard


Live demo

29

List of pictures


Live demo

30

Facial Analysis KPIs


Live demo

31

Interactive charts


Live demo

32

Happiness level


Q&AEduardo Fernández [email protected]

Real Time Face Analysis

Documents

Transcript of Real Time Face Analysis