It’s an ML full world! MLKit for Android Devs

on YouTube ↗34m

" summary

Demo of Firebase ML Kit shows ready-made vision APIs (text, face, barcode, label, landmark) plus TensorFlow Lite support for custom models; on-device text runs under ~300 ms while cloud OCR takes ~1 s and handles Hebrew, labeling is ~1.5 s on-device vs >3 s in cloud, and cloud accuracy is higher. Built a simple grocery-label reader for an elderly user that converts detected text to UI or speech and it works; note cloud calls become billable after ~1,000/month.

AI-written summary · about

" chapters (7)

1. 0:00Start
2. 13:48Vision library
3. 19:24Setup Detector
4. 22:59Cloud
5. 24:44FirebaseVision Image
6. 31:14Execute the model
7. 31:32Process output

" related talks

• 04mTop 5 reasons to add ML Kit to your Android or iOS appSachin Kotwani · Firebase Summit 2018
• 24mML Kit: Machine learning for mobile developersSachin Kotwani, Isabella Chen · Firebase Summit 2018
• 30mMachine Learning in Android Apps with ML KitFelipe Pedroso · AndroidFest Campinas 2018
• 47mExploring Firebase MLKit on AndroidHiren Dave · GDG DevFest Ahmedabad 2018
• 14mDo you want an easy way to add Machine Learning into your app?Sandra Dupré · Android Makers 2019
• 29mFirebase MLKit — AI in Android Town!!Sweety Bertilla Francis Xavier · Android Summit 2019
• 36mMachine Learning for Mobile DevelopersLaura Morinigo · Mobilization 8
• 21mLive Coding: Adding Machine Learning to Android Things in 10 MinsHoi Lam · droidcon Berlin 2018