ML Kit の概要と Base API / first step of ML Kit

by Yuki Anzai

Slide 1

Slide 1 text

ML Kit ͷ֓ཁͱ Base API Yuki Anzai @yanzm Google Developers Expert for Android ML for Mobile Developers

Slide 2

Slide 2 text

ML Kit ͱ͸ • Firebase ͷػೳͷҰͭ • ػցֶशΛར༻͢ΔػೳΛΞϓϦʹ؆୯ʹ૊ΈࠐΉͨΊͷϞόΠϧ SDK • ݱࡏ͸ β • iOS ͱ Android Ͱ࢖͑Δ • https:// fi rebase.google.com/docs/ml-kit/

Slide 3

Slide 3 text

on-device or in the cloud On-device Cloud Text recognition : ςΩετೝࣝ O O Face detection : إݕग़ O - Barcode scanning : όʔίʔυεΩϟϯ O - Image labeling : ը૾ͷϥϕϧ෇͚ O O Landmark recognition : ϥϯυϚʔΫೝࣝ - O Custom model inference : ΧελϜϞσϧਪ࿦ O -

Slide 4

Slide 4 text

on-device vs Cloud • on-device API • ϩʔΧϧͰಈ࡞ɺ଎͍ • Firebase ͕ػցֶशͷϞσϧΛ͋Β͔͡Ίμ΢ϯϩʔυͯ͘͠ΕΔ • Cloud API • αʔόʔͰॲཧɺߴػೳ • ωοτϫʔΫ઀ଓ͕ඞཁ

Slide 5

Slide 5 text

Pricing https:// fi rebase.google.com/pricing/ your account's fi rst 1000 Cloud Vision API calls/month are free

Slide 6

Slide 6 text

• Features • ը૾͔ΒςΩετΛೝࣝ • on-device API • ແྉ • શͯͷϥςϯจࣈΛೝࣝ • Cloud API • ຖ݄࠷ॳͷ 1000 API call ͸ແྉʢ1000+ ͔Β͸ैྔ՝ۚʣ • 50 Λ͑͜ΔݴޠΛೝࣝʢ೔ຊޠؚΉʣ Text recognition (OCR) : ςΩετೝࣝ

Slide 7

Slide 7 text

No content

Slide 8

Slide 8 text

No content

Slide 9

Slide 9 text

• Features • on-device API ͷΈ • إͷྖҬɺϥϯυϚʔΫʢ໨ɾ๹ɾඓɾࣖɾޱʣͷҐஔೝࣝ • إͷද৘ʢ໨ͷ։ด౓߹͍ɺসإͷ౓߹͍ʣͷೝࣝ • ಈըͷϑϨʔϜؒͰಉ͡إΛτϥοΫՄೳ • 100Ҏ্ͷ఺͔Βߏ੒͞ΕΔ2࣍ݩͷྠֲ৘ใʢإͷ֎ֲɾ໨ɾඑɾඓɾޱʣ Face detection : إݕग़

Slide 10

Slide 10 text

Face contour https:// fi rebase.google.com/docs/ml-kit/detect-faces

Slide 11

Slide 11 text

• Features • on-device API ͷΈ • ΄ͱΜͲͷඪ४ϑΥʔϚοτΛαϙʔτ • 1࣍ݩϑΥʔϚοτ : Codabar, Code 39, Code 93, Code 128, EAN-8, EAN-13, ITF, UPC-A, UPC-E • 2࣍ݩϑΥʔϚοτ : Aztec, Data Matrix, PDF417, QR Code • ࣗಈϑΥʔϚοτݕग़ • structured data ͷऔΓग़͠ • όʔίʔυͷ޲͖ʹΑΒͣݕग़Մೳ Barcode scanning : όʔίʔυεΩϟϯ

Slide 12

Slide 12 text

format : 256 valueType : 9 rawValue : WIFI:S:SB1Guest;P:12345;T:WEP;; displayValue : SB1Guest 12345 boundingBox : Rect(300, 457 - 669, 824) encryptionType : 3 ssid : SB1Guest password : 12345

Slide 13

Slide 13 text

• Features • ը૾ͷ಺༰Λղੳ͠ɺೝࣝͨ͠΋ͷͷϥϕϧΛ͚ͭΔ : ਓɺ෺ɺ৔ॴɺ׆ಈͳͲ • on-device API • ແྉ • 400+ labels Λαϙʔτ • Cloud API • ຖ݄࠷ॳͷ 1000 API call ͸ແྉʢ1000+ ͔Β͸ैྔ՝ۚʣ • 10,000+ labels Λαϙʔτ Image labeling : ը૾ͷϥϕϧ෇͚

Slide 14

Slide 14 text

label : Building con fi dence : 0.77894384 entityId : /m/0cgh4 label : Palace con fi dence : 0.75397676 entityId : /m/05zp8 label : landmark con fi dence : 0.9432406 entityId : /m/05_5t0l label : town con fi dence : 0.9333225 entityId : /m/0dx1j

Slide 15

Slide 15 text

label : Food con fi dence : 0.9649049 entityId : /m/02wbm label : Cuisine con fi dence : 0.91778296 entityId : /m/01ykh label : food con fi dence : 0.9399401 entityId : /m/02wbm label : cuisine con fi dence : 0.9263104 entityId : /m/01ykh

Slide 16

Slide 16 text

val options = FirebaseVisionLabelDetectorOptions .Builder() .setConfidenceThreshold(0.9f) .build()

Slide 17

Slide 17 text

• Features • ը૾͔Β༗໊ͳϥϯυϚʔΫΛೝࣝ • ϥϯυϚʔΫ໊ • ஍ཧ࠲ඪ • Knowledge Graph entity ID • ը૾಺ͰͷϥϯυϚʔΫͷྖҬ • ຖ݄࠷ॳͷ 1000 API call ͸ແྉʢ1000+ ͔Β͸ैྔ՝ۚʣ Landmark detection : ϥϯυϚʔΫೝࣝ

Slide 18

Slide 18 text

landmark : Amsterdam Centraal Railway Station con fi dence : 0.86155003 entityId : /m/0bbw52 locations : 52.378068, 4.899774 boundingBox : Rect(33, 504 - 956, 928) landmark : Amsterdam con fi dence : 0.5167069 entityId : /m/0k3p locations : 52.373811, 4.890951 boundingBox : Rect(187, 644 - 757, 843)

Slide 19

Slide 19 text

ΧελϜϞσϧਪ࿦ • Firebase Ͱ TensorFlow Lite ͷϞσϧΛϗεςΟϯά • Firebase SDK ͕Ϟσϧͷμ΢ϯϩʔυΛϋϯυϦϯά • Ϟσϧͷߋ৽΋Մೳ • apk ʹόϯυϧͨ͠ϞσϧΛ Firebase SDK ܦ༝Ͱར༻͢Δ͜ͱ΋Մೳ • on-device API ͱͯ͠ར༻