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 iOS)
Search
Elvis Lin
July 19, 2018
Programming
170
0
Share
ML Kit Introduction (for iOS)
Introduce the basic concept of ML Kit and how to use it in iOS development
Elvis Lin
July 19, 2018
More Decks by Elvis Lin
See All by Elvis Lin
Protect Users' Privacy in iOS 14
elvismetaphor
0
60
Dubugging Tips and Tricks for iOS development
elvismetaphor
0
65
Strategies of Facebook LightSpeed project
elvismetaphor
0
110
Background Execution And WorkManager
elvismetaphor
2
500
作為一個跨平台的 Mobile App 開發者,從入門到放棄!?
elvismetaphor
2
540
Dependency Injection for testability of iOS app
elvismetaphor
1
1.5k
Briefly Introduction of Kotlin coroutines
elvismetaphor
1
320
MotionLayout Brief Introduction
elvismetaphor
1
350
Chapter 10. Pattern Matching with Regular Expressions
elvismetaphor
0
65
Other Decks in Programming
See All in Programming
なぜあなたのコードには「コシ」がないのか?〜AI時代に問う、最後まで美味しい設計と戦略〜 #phpconkagawa / phpconkagawa2026
shogogg
0
210
ソースコード→AST→オペコード、の旅を覗いてみる
o0h
PRO
1
140
Skillは並べた。動かなかった。契約で繋いだ。— 65個のSkillから、自走する開発サイクルへ
junholee
0
670
Kubernetesを使わない環境にもCloud Nativeなデプロイを実現する / Enabling Cloud Native deployments without the complexity of Kubernetes
linyows
3
430
色即是空、空即是色、データサイエンス
kamoneggi
1
140
2026年のソフトウェア開発を考える(2026/05版) / Software Engineering Scrum Fest Niigata 2026 Edition
twada
PRO
24
14k
サプライチェーン攻撃対策「層を重ねて落ちない壁」を10日間で組み上げた話 #TechLeadConf2026
kashewnuts
1
310
Modding RubyKaigi for Myself
yui_knk
0
370
継続的な負荷検証を目指して
pyama86
3
1.3k
AWSはOSSをどのように 考えているのか?
akihisaikeda
0
130
ReactとSvelteのその先、Ripple-TS / Beyond React and Svelte: Ripple-TS
ssssota
2
470
Agentic UI beyond Chats Architecture Patterns & Open Standards @ngMunich 05/2026
manfredsteyer
PRO
0
120
Featured
See All Featured
VelocityConf: Rendering Performance Case Studies
addyosmani
333
25k
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
inesmontani
PRO
3
2.2k
How to Build an AI Search Optimization Roadmap - Criteria and Steps to Take #SEOIRL
aleyda
1
2k
A Modern Web Designer's Workflow
chriscoyier
698
190k
職位にかかわらず全員がリーダーシップを発揮するチーム作り / Building a team where everyone can demonstrate leadership regardless of position
madoxten
62
54k
The Art of Programming - Codeland 2020
erikaheidi
57
14k
Building the Perfect Custom Keyboard
takai
2
770
The B2B funnel & how to create a winning content strategy
katarinadahlin
PRO
1
360
Ten Tips & Tricks for a 🌱 transition
stuffmc
0
110
Reality Check: Gamification 10 Years Later
codingconduct
0
2.1k
Skip the Path - Find Your Career Trail
mkilby
1
120
Typedesign – Prime Four
hannesfritz
42
3k
Transcript
ML Kit 使⽤用簡介 (iOS) Elvis Lin @Cocoahead Taipei 2018-07-19
關於我 • Elvis Lin • iOS 與 Android 永遠的初學者 •
Twitter: @elvismetaphor • Blog: https://blog.elvismetaphor.me
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
Tensorflow Lite https://youtu.be/ByJnpbDd-zc
https://www.tensorflow.org/mobile/tflite/
轉換 Tensorflow 檔案的⼯工具 • Tensorflow converter • 轉成 Tensorflow Lite
格式 • Tensorflow-CoreML converter • 轉成 CoreML 格式 • https://github.com/tf-coreml/tf-coreml
ML Kit https://youtu.be/Z-dqGRSsaBs
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……
託管客製化的模型 ⽬目前只⽀支援 Tensorflow Lite 格式
使⽤用 ML Kit
建立⼀一個 Firebase 專案
建立⼀一個 iOS app 然後下載設定檔 設定好 Bundle ID 下載 GoogleService-info.plist
新增 plist 檔案到專案 • 將 GoogleService-Info.plist 放到 <root>/<application_folder>/ 下
安裝 Firebase 函式庫 • 修改 Podfile,新增以下的內容 • cd <root> pod
install • 打改 <project_name>.xcworkspace pod 'Firebase/Core' pod 'Firebase/MLVision' pod 'Firebase/MLVisionTextModel' pod 'Firebase/MLVisionFaceModel' pod 'Firebase/MLVisionBarcodeModel' pod 'Firebase/MLVision' pod 'Firebase/MLVisionLabelModel'
掃描 Barcode (Local) let barcodeDetector: VisionBarcodeDetector = Vision.vision().barcodeDetector(options: options)
let visionImage = VisionImage(image: pickedImage) barcodeDetector.detect(in: visionImage) { (barcodes, error) in guard error == nil, let barcodes = barcodes, !barcodes.isEmpty else { self.dismiss(animated: true, completion: nil) self.resultView.text = "No Barcode Detected" return } for barcode in barcodes { // handle the detected barcode } }
第1步:初始化 Detector let barcodeDetector: VisionBarcodeDetector = Vision.vision().barcodeDetector(options: options) let
visionImage = VisionImage(image: pickedImage)
第2步:取得結果 barcodeDetector.detect(in: visionImage) { (barcodes, error) in guard error ==
nil, let barcodes = barcodes, !barcodes.isEmpty else { self.dismiss(animated: true, completion: nil) self.resultView.text = "No Barcode Detected" return } for barcode in barcodes { // handle the detected barcode } }
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) lazy var textDetector: VisionTextDetector = Vision.vision().textDetector() func
runTextRecognition(with image: UIImage) { let visionImage = VisionImage(image: image) textDetector.detect(in: visionImage) { (features, error) in if let error = error { print("Received error: \(error)") } self.processResult(from: features, error: error) } }
辨識⽂文字 (Cloud) Lazy var cloudTextDetector: VisionCloudTextDetector = Vision.vision().cloudTextDetector() func
runCloudTextRecognition(with image: UIImage) { let visionImage = VisionImage(image: image) cloudTextDetector.detect(in: visionImage) { (features, error) in if let error = error { print("Received error: \(error)") } self.processCloudResult(from: features, error: error) } }
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-ios/ • https://github.com/firebase/quickstart-ios/tree/master/ mlvision • https://www.appcoda.com.tw/ml-kit/
None