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
Make faces big by Vision and CoreGraphics
Search
naru-jpn
March 02, 2018
Technology
0
490
Make faces big by Vision and CoreGraphics
“Can you make faces big?”
naru-jpn
March 02, 2018
Tweet
Share
More Decks by naru-jpn
See All by naru-jpn
配信アプリのためのリアルタイムプッシュ通知ぼかしの夢
narujpn
3
940
PiPを応用した配信コメントバー機能の開発秘話と技術の詳解 / pip_streaming_comment_bar
narujpn
3
4.3k
Updating an App to Use Swift Concurrency 解説
narujpn
2
350
PiP で実現するミラティブの配信コメントバー / pip-streaming-comment-bar
narujpn
0
1.2k
App Extension のスタックトレース情報からクラッシュを解析/集計する / Analyzing app extension's stack trace
narujpn
3
1.6k
ミラティブとWebRTC - WebRTC framework の中身を覗いてみよう / WebRTC framework AudioUnit Processing
narujpn
1
2.2k
CoreML3のオンデバイストレーニングでつくる母音推定
narujpn
0
450
AltConfと周辺の歩き方
narujpn
0
2k
エンジニア経験を活かしたスクラムマスターとして 開発チームとプロダクトを成長させる
narujpn
1
420
Other Decks in Technology
See All in Technology
許しとアジャイル
jnuank
1
130
生成AIを活用したZennの取り組み事例
ryosukeigarashi
0
210
社内報はAIにやらせよう / Let AI handle the company newsletter
saka2jp
6
910
ユニットテストに対する考え方の変遷 / Everyone should watch his live coding
mdstoy
0
130
生成AIで「お客様の声」を ストーリーに変える 新潮流「Generative ETL」
ishikawa_satoru
1
330
about #74462 go/token#FileSet
tomtwinkle
1
420
How to achieve interoperable digital identity across Asian countries
fujie
0
120
KMP の Swift export
kokihirokawa
0
340
Optuna DashboardにおけるPLaMo2連携機能の紹介 / PFN LLM セミナー
pfn
PRO
2
900
Adminaで実現するISMS/SOC2運用の効率化 〜 アカウント管理編 〜
shonansurvivors
2
320
Goに育てられ開発者向けセキュリティ事業を立ち上げた僕が今向き合う、AI × セキュリティの最前線 / Go Conference 2025
flatt_security
0
350
SOC2取得の全体像
shonansurvivors
1
410
Featured
See All Featured
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
9
580
Unsuck your backbone
ammeep
671
58k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.5k
Context Engineering - Making Every Token Count
addyosmani
5
200
Learning to Love Humans: Emotional Interface Design
aarron
274
40k
Done Done
chrislema
185
16k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
9
850
The Art of Programming - Codeland 2020
erikaheidi
56
14k
Producing Creativity
orderedlist
PRO
347
40k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
32
2.2k
jQuery: Nuts, Bolts and Bling
dougneiner
64
7.9k
Scaling GitHub
holman
463
140k
Transcript
Make faces big by Vision and CoreGraphics VisionͱCoreGraphicsͰإΛσΧ͘͢Δ Naruki Chigira,
Timers inc. @naruchigi Try! Swift 2018
“Can you make faces big?”
“In about a week.”
None
Core Image want actual
Core ML too much learning cost (also for me) …
Vision
Vision ɾFace Detection and Recognition ɾBarcode Detection ɾText Detection ɾHorizon
Detection ɾObject Detection and Tracking
VNFaceLandmarkRegion2D Class 2D geometry information for a specific facial feature.
VNFaceObservation Class Face or facial-feature information detected by an image analysis request.
Face Couture [CGPoint]
// 1. Create VNDetectFaceLandmarksRequest let request = VNDetectFaceLandmarksRequest() { (request,
error) in guard let results = request.results else { return } let faceObservations = results.flatMap({ $0 as? VNFaceObservation }) // 3. Handle results // … } // 2. Create VNImageRequestHandler and perform let handler = VNImageRequestHandler(cgImage: cgImage, options: [:]) try! handler.perform([request]) How to get VNFaceLandmarkRegion2D
Face Couture
None
None
None
None
None
Core Graphics
CGPoint Structure A structure that contains a point in a
two-dimensional coordinate system.
CGAffineTransform Structure An affine transformation matrix for use in drawing
2D graphics.
CGPoint Structure Instance Method func applying(_ t: CGAffineTransform) -> CGPoint
O
O 1. translate
O 1. translate 2. rotate
O 1. translate 2. rotate 3. reverse + joint
O 1. translate 2. rotate 3. reverse + joint 4.
rotate-1
O 1. translate 2. rotate 3. reverse + joint 4.
rotate-1 5. translate-1
O A A-1 } } 1. translate 2. rotate 3.
reverse + joint 4. rotate-1 5. translate-1
Modify [CGPoint] in Swift // 1. Create CGAffineTransform A let
A = CGAffineTransform(rotationAngle: -theta).translatedBy(x: x, y: y) // 2. Apply A let transformed = points.map { $0.applying(A) } // 3. Reverse & Joint let oval = transformed + transformed.map { CGPoint(x: -$0.x, y: -$0.y) } // 4. Apply A-1 let result = oval.map { $0.applying(A.inverted()) }
Result
None
None
Summary Get facial features from Vision (iOS 11.0~) Process data
using CoreGraphics (iOS 2.0~) +
Thank you!