Adding Image and Voice Intelligence to Your Apps
summary
Microsoft Cognitive Services APIs get added to apps via simple REST calls or language SDKs and return JSON with concrete outputs: face boxes and ages, emotion scores 0–1 for each face, OCR as arrays of text areas/lines/words, and thumbnails that crop while keeping the subject. Demos use Vision, Face, Emotion, Speech and OCR; speech-to-text shows iterative edits as words resolve; free tier gives 30,000 transactions per month; code samples in Python, JavaScript and C# live on GitHub and the proxy pattern protects subscription keys.
AI-written summary · about
chapters (15)
- 0:00Image and voice intelligence intro
- 2:30ML challenges and Azure solutions
- 5:16Getting started with Cognitive Services
- 8:11Computer Vision API responses
- 10:20Developing with Cognitive Services APIs
- 16:28Python examples for Cognitive Services
- 18:02Windows app with Vision APIs
- 21:09Emotion analysis in images
- 23:56Face detection in JavaScript
- 29:59Optical character recognition demo
- 33:15Speech to text demo
- 35:03AI thumbnail generation
- 36:30Combining AI services
- 38:13Resources and learning
- 40:00Q&A
related talks
01h 05mMicrosoft Cognitive Services: Making AI Easy
01h 05mAI for the Masses - Microsoft Cognitive Services
54mMake Your Apps More Human with Cognitive Services
01h 03mEasier AI allows everyone to build smart apps
01h 00mA lap around Microsoft Cognitive Services Vision API
50mCognitive Services Extravaganza!
46mBuilding computer vision applications Q&A
01h 00mBoost your App with Machine Learning APIs