Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
ML Kit Introduction (for Android)
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Elvis Lin
July 18, 2018
Programming
0
300
ML Kit Introduction (for Android)
Introduce the basic concept of ML Kit and how to use it in Android development
Elvis Lin
July 18, 2018
Tweet
Share
More Decks by Elvis Lin
See All by Elvis Lin
Protect Users' Privacy in iOS 14
elvismetaphor
0
54
Dubugging Tips and Tricks for iOS development
elvismetaphor
0
54
Strategies of Facebook LightSpeed project
elvismetaphor
0
90
Background Execution And WorkManager
elvismetaphor
2
490
作為一個跨平台的 Mobile App 開發者,從入門到放棄!?
elvismetaphor
2
530
Dependency Injection for testability of iOS app
elvismetaphor
1
1.4k
Briefly Introduction of Kotlin coroutines
elvismetaphor
1
310
MotionLayout Brief Introduction
elvismetaphor
1
340
Chapter 10. Pattern Matching with Regular Expressions
elvismetaphor
0
50
Other Decks in Programming
See All in Programming
AIと一緒にレガシーに向き合ってみた
nyafunta9858
0
160
それ、本当に安全? ファイルアップロードで見落としがちなセキュリティリスクと対策
penpeen
7
2.4k
責任感のあるCloudWatchアラームを設計しよう
akihisaikeda
3
160
20260127_試行錯誤の結晶を1冊に。著者が解説 先輩データサイエンティストからの指南書 / author's_commentary_ds_instructions_guide
nash_efp
0
890
dchart: charts from deck markup
ajstarks
3
990
AI Agent Tool のためのバックエンドアーキテクチャを考える #encraft
izumin5210
6
1.8k
SourceGeneratorのススメ
htkym
0
190
Architectural Extensions
denyspoltorak
0
270
humanlayerのブログから学ぶ、良いCLAUDE.mdの書き方
tsukamoto1783
0
180
【卒業研究】会話ログ分析によるユーザーごとの関心に応じた話題提案手法
momok47
0
190
QAフローを最適化し、品質水準を満たしながらリリースまでの期間を最短化する #RSGT2026
shibayu36
2
4.3k
FOSDEM 2026: STUNMESH-go: Building P2P WireGuard Mesh Without Self-Hosted Infrastructure
tjjh89017
0
140
Featured
See All Featured
The AI Search Optimization Roadmap by Aleyda Solis
aleyda
1
5.2k
YesSQL, Process and Tooling at Scale
rocio
174
15k
The Spectacular Lies of Maps
axbom
PRO
1
510
Designing Experiences People Love
moore
144
24k
Lightning talk: Run Django tests with GitHub Actions
sabderemane
0
110
Leadership Guide Workshop - DevTernity 2021
reverentgeek
1
200
Navigating Algorithm Shifts & AI Overviews - #SMXNext
aleyda
0
1.1k
A brief & incomplete history of UX Design for the World Wide Web: 1989–2019
jct
1
290
Leo the Paperboy
mayatellez
4
1.4k
Money Talks: Using Revenue to Get Sh*t Done
nikkihalliwell
0
150
Why Your Marketing Sucks and What You Can Do About It - Sophie Logan
marketingsoph
0
71
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
320
Transcript
ML Kit 使⽤用簡介 Elvis Lin @Android Taipei 2018-07-18
關於我 • Elvis Lin • Android 與 iOS 永遠的初學者 •
Twitter: @elvismetaphor • Blog: https://blog.elvismetaphor.me
不是業配 https://youtu.be/Z-dqGRSsaBs
⼤大綱 • 什什麼是(我理理解的)機器學習 • 移動裝置上實作機器學習應⽤用的限制 • TensorFlow Lite 與 ML
Kit • 範例例
機器學習的應⽤用
機器學習 • 從資料中歸納出有⽤用的規則 • 訓練模型 • 使⽤用模型 • Mobile Application
Engineer 參參與開發主要是在「使⽤用模型」 這個範圍
Data Result (Trained) Model
移動裝置上 實作機器學習應⽤用的限制 • 記憶體有限與儲存空間有限 • 計算能⼒力力不如⼤大型伺服器 • 電池容量量有限
移動裝置上 實作機器學習應⽤用的改良⽅方向 • 記憶體有限與儲存空間有限 —> 減少模型(Model)的體積 • 計算能⼒力力不如⼤大型伺服器 —> 降低演算法的複雜度
• 電池容量量有限 —> 降低演算法的複雜度
Google 推出的解決⽅方案 • TensorFlow Lite • ML Kit
https://www.tensorflow.org/mobile/tflite/
Neural Networks API Metal
ML Kit • Cloud Vision API / Mobile Vision API
• Tensorflow Lite • 整合 Firebase,託管「客製化的模型」
ML Kit Base APIs • Image labeling • Text recognition
(OCR) • Face detection • Barcode scanning • Landmark detection • others……
使⽤用 ML Kit
建立⼀一個 Firebase 專案
建立⼀一個 Android app 下載設定檔 設定好 Package Name 下載 google-service.json
<root>/build.gradle dependencies { classpath 'com.android.tools.build:gradle:3.1.3' classpath 'com.google.gms:google-services:4.0.2' }
<root>/app/build.gradle dependencies { // ... implementation 'com.google.firebase:firebase-ml-vision:16.0.0' }
掃描 barcode (local) FirebaseVisionImage image = FirebaseVisionImage.fromBitmap(image); FirebaseVisionBarcodeDetectorOptions options =
new FirebaseVisionBarcodeDetectorOptions.Builder() .setBarcodeFormats( FirebaseVisionBarcode.FORMAT_QR_CODE, FirebaseVisionBarcode.FORMAT_AZTEC ) .build(); FirebaseVisionBarcodeDetector detector = FirebaseVision.getInstance() .getVisionBarcodeDetector(options); detector.detectInImage(image) .addOnSuccessListener( new OnSuccessListener<List<FirebaseVisionBarcode>>() { @Override public void onSuccess(List<FirebaseVisionBarcode> barcodes) {} }) .addOnFailureListener(new OnFailureListener() { @Override public void onFailure(@NonNull Exception e) {} });
初始化 Detector FirebaseVisionImage image = FirebaseVisionImage.fromBitmap(image); FirebaseVisionBarcodeDetectorOptions options = new
FirebaseVisionBarcodeDetectorOptions.Builder() .setBarcodeFormats( FirebaseVisionBarcode.FORMAT_QR_CODE, FirebaseVisionBarcode.FORMAT_AZTEC ) .build(); FirebaseVisionBarcodeDetector detector = FirebaseVision .getInstance() .getVisionBarcodeDetector(options);
取得結果 detector.detectInImage(image) .addOnSuccessListener( new OnSuccessListener<List<FirebaseVisionBarcode>>() { @Override public void onSuccess(List<FirebaseVisionBarcode>
barcodes) {} }) .addOnFailureListener(new OnFailureListener() { @Override public void onFailure(@NonNull Exception e) {} });
⽀支援的 barcode 格式 • Code 128 (FORMAT_CODE_128) • Code 39
(FORMAT_CODE_39) • Code 93 (FORMAT_CODE_93) • Codabar (FORMAT_CODABAR) • EAN-13 (FORMAT_EAN_13) • EAN-8 (FORMAT_EAN_8) • ITF (FORMAT_ITF) • UPC-A (FORMAT_UPC_A) • UPC-E (FORMAT_UPC_E) •QR Code (FORMAT_QR_CODE) • PDF417 (FORMAT_PDF417) • Aztec (FORMAT_AZTEC) • Data Matrix (FORMAT_DATA_MATRIX)
辨識⽂文字 (local) FirebaseVisionImage image = FirebaseVisionImage.fromBitmap(selectedImage); FirebaseVisionTextDetector detector = FirebaseVision.getInstance().getVisionTextDetector();
detector.detectInImage(image) .addOnSuccessListener(new OnSuccessListener<FirebaseVisionText>() { @Override public void onSuccess(FirebaseVisionText text) {} }) .addOnFailureListener(new OnFailureListener() { @Override public void onFailure(@NonNull Exception e) {} });
辨識⽂文字 (cloud) FirebaseVisionCloudDetectorOptions options = new FirebaseVisionCloudDetectorOptions.Builder() .setModelType(FirebaseVisionCloudDetectorOptions.LATEST_MODEL) .setMaxResults(15) .build();
FirebaseVisionImage image = FirebaseVisionImage.fromBitmap(selectedImage); FirebaseVisionCloudDocumentTextDetector detector = FirebaseVision.getInstance() .getVisionCloudDocumentTextDetector(options); detector.detectInImage(image) .addOnSuccessListener(new OnSuccessListener<FirebaseVisionCloudText>() { @Override public void onSuccess(FirebaseVisionCloudText text) {} }) .addOnFailureListener(new OnFailureListener() { @Override public void onFailure(@NonNull Exception e) {} });
補充資料 • ML Kit 簡介 (for Android) https://blog.elvismetaphor.me/ml-kit-fundamentals-for- android-6444e2db0fdb •
ML Kit 簡介 (for iOS) https://blog.elvismetaphor.me/ml-kit-fundamentals-for- ios-cb705044e69b
參參考資料 • https://youtu.be/Z-dqGRSsaBs • https://codelabs.developers.google.com/codelabs/mlkit- android/ • https://github.com/firebase/quickstart-android/tree/ master/mlkit
None