Artificial Intelligence - Tell You What I See

Tell You What I See - Marvin Heng
This topic will be showcasing how to make use of multiple Microsoft Cognitive Services to create better real-life use cases that could be useful for your businesses or daily application.

Read more AI topics at www.techconnect.io

1. Tell You What I See

2. https://www.techconnect.io
@hmheng
“To him,
turning innovative ideas into
reality is great excitement and
achievement.”
Microsoft MVP | Tech + AI Enthusiast
Marvin Heng

3. What & Why AI?

5. •Flexible rational
agent
•Maximize its
chance of
success
•Mimics cognitive
functions

6. Singapore
“Singapore is partnering with
software giant Microsoft to develop
next-generation digital government
services via chatbots that will enable
conversation —be it voice or text.”
-Dr Vivian Balakrishnan,
Minister-In-Charge of the Smart Nation Initiative

7. What’s Microsoft
Cognitive Service

8. Microsoft Cognitive Service
Vision

9. Description { "tags": [ "plant", "flower", "daisy", "vase", "small",
"sitting", "yellow", "white", "green", "table", "water" ],
"captions": [ { "text": "a close up of a flower",
"confidence": 0.9661043 } ] }
Tags [ { "name": "plant", "confidence": 0.9983455 }, {
"name": "flower", "confidence": 0.9967173 }, {
"name": "daisy", "confidence": 0.938212633 } ]
Categories [ { "name": "plant_flower", "score": 0.99609375 } ]
Return tagging, domain-specific models, and descriptions.
Identify content and label it with confidence
Analyze An Image

10. Result{"boundingBox": [ 271, 185, 320, 176, 323, 194, 273, 203 ],
"text": "KEEP",
"words": [ {
"boundingBox": [ 269, 185, 317, 176, 321, 194, 272, 202 ],
"text": "KEEP"
}]
},
{"boundingBox": [ 269, 208, 330, 198, 333, 217, 272, 226],
"text": "CALM",
"words": [ {
"boundingBox": [ 272, 208, 322, 201, 325, 218, 274, 226 ],
"text": "CALM"
}]
…
Detect text in an image and extract the recognized words into
a machine-readable character stream.
Read Text in Images (OCR)

11. ResultVerification result: The two faces belong to the same person.
Confidence is 0.7349.
Check the likelihood that two faces belong to the same person. The API will return a
confidence score about how likely it is that the two faces belong to one person.
Face verification

12. The Face API returns the confidence across a set of emotions for each face in the
image such as anger, contempt, disgust, fear, happiness, and surprise.
Emotion recognition
ANGER 0.00002
CONTEMPT 0.00025
DISGUST 0.00005
FEAR 0.00115
HAPPINESS0.00006
NEUTRAL 0.00494
SADNESS 0.00001
SURPRISE 0.99352

13. Microsoft Cognitive Service
Speech

14. Overcome speech recognition barriers such as speaking style,
vocabulary, and background noise.
Custom speech service: Speech Transcription
with Custom Model

15. Build apps and services that speak to users naturally. more than 75 voices in over
45 languages or locales, including options for male and female voices, and adjust
parameters like speed, pitch, volume, pronunciation, and additional pauses.
Bring natural voice to your apps

16. Microsoft Cognitive Service
Language

17. A machine learning-based service to build natural language understanding into
apps, bots, and IoTdevices. Quickly create enterprise-ready, custom models that
continuously improve.
Language Understanding
TURN THE RIGHT LIGHT ON
{ "query": "turn the right light on",
"topScoringIntent": {
"intent": "TurnOn",
"score": 0.900771737
},
"entities": [ {
"entity": "right",
"type": "Light",
"startIndex": 9,
"endIndex": 13,
"resolution": null,
"score": 0.8766971
} ]
}

18. Easily conduct real-time text translation with a simple REST API call
Translator Text
Translate text in your mobile, desktop, and web applications to and
from 60+ supported languages through the open REST interface of
Translator API.

19. Microsoft Cognitive Service
Vision Speech Language Knowledge Search
Computer Vision
Face
Video Indexer
Content Moderator
Custom Vision
Speech to Text
Speaker Recognition
Text to Speech
Speech Translation
Text Analytics
Bing Spell Check
Language Understanding
Translator Text
Content Moderator
QnAMaker Bing Web Search
Bing Custom Search
Bing Video Search
Bing Image Search
Bing Visual Search
Bing Entity Search
Bing News Search
Bing Autosuggest

20. Why Microsoft
Cognitive Service?

21. Why Microsoft Cognitive Service?
Roll your own with REST APIs
No on-premises infrastructure. Hosted on Microsoft Azure cloud.
Easy
Flexible
Tested
Easy integration with all platforms.
Built by experts in their field from Microsoft Research, Bing, and Azure
Machine Learning
Quality documentation, sample code and community support

22. Bringing it all
together
The Seeing App
Computer Vision,
Image Speech
Recognition,
NLP and
ML from Microsoft
Cognitive Services

23. Demo

24. Hands On Lab

25. THE
JOURNEY
CONTINUES TO
DEVELOP…

26. https://www.techconnect.io
@hmheng
Microsoft MVP | Tech + AI Enthusiast
Marvin Heng
THANK YOU!
www.techconnect.io
Twitter@hmheng

27. Tell You What I See