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
Firebase ML Kit for iOS Developer
Search
Kajornsak Peerapathananont
October 07, 2018
Technology
0
71
Firebase ML Kit for iOS Developer
Firebase Dev Day 2018 @Bangkok, Thailand
Kajornsak Peerapathananont
October 07, 2018
Tweet
Share
More Decks by Kajornsak Peerapathananont
See All by Kajornsak Peerapathananont
Understanding your Android build
kajornsakp
0
37
iOSDevTH #21
kajornsakp
0
43
What's new in Flutter (Google I/O Extended Bangkok 22)
kajornsakp
0
61
Mobile Design System at scale
kajornsakp
0
81
What's new in Flutter 2020
kajornsakp
0
60
Mobile Machine Learning for All Skill Levels
kajornsakp
0
30
What's new in Flutter 1.9
kajornsakp
0
51
Kotlin meets Web
kajornsakp
0
22
From design to develop with Material Components
kajornsakp
0
140
Other Decks in Technology
See All in Technology
はじめての転職講座/The Guide of First Career Change
kwappa
5
4.4k
「AIと一緒にやる」が当たり前になるまでの奮闘記
kakehashi
PRO
3
170
ファッションコーディネートアプリ「WEAR」における、Vertex AI Vector Searchを利用したレコメンド機能の開発・運用で得られたノウハウの紹介
zozotech
PRO
0
610
アカデミーキャンプ 2025 SuuuuuuMMeR「燃えろ!!ロボコン」 / Academy Camp 2025 SuuuuuuMMeR "Burn the Spirit, Robocon!!" DAY 1
ks91
PRO
0
150
ロールが細分化された組織でSREと協働するインフラエンジニアは何をするか? / SRE Lounge #18
kossykinto
0
230
九州の人に知ってもらいたいGISスポット / gis spot in kyushu 2025
sakaik
0
190
メルカリIBIS:AIが拓く次世代インシデント対応
0gm
2
430
いま、あらためて考えてみるアカウント管理 with IaC / Account management with IaC
kohbis
1
260
AIが住民向けコンシェルジュに?Amazon Connectと生成AIで実現する自治体AIエージェント!
yuyeah
0
170
Jamf Connect ZTNAとMDMで実現! 金融ベンチャーにおける「デバイストラスト」実例と軌跡 / Kyash Device Trust
rela1470
1
210
家族の思い出を形にする 〜 1秒動画の生成を支えるインフラアーキテクチャ
ojima_h
3
1.3k
Amazon Qで2Dゲームを作成してみた
siromi
0
160
Featured
See All Featured
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
23
1.4k
Optimising Largest Contentful Paint
csswizardry
37
3.4k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
15
1.6k
The Cost Of JavaScript in 2023
addyosmani
53
8.8k
Gamification - CAS2011
davidbonilla
81
5.4k
YesSQL, Process and Tooling at Scale
rocio
173
14k
The Cult of Friendly URLs
andyhume
79
6.5k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
161
15k
Done Done
chrislema
185
16k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
34
3.1k
A Modern Web Designer's Workflow
chriscoyier
695
190k
Transcript
ML Kit for iOS developers Kajornsak Peerapathananont Agoda
Machine Learning
#FirebaseDevDay
Google Lens
Smart Reply
On-device Machine Learning
#FirebaseDevDay Doable, but hard.
#FirebaseDevDay
#FirebaseDevDay Get Image Image Classification Transform Interpret Get Result
#FirebaseDevDay Transform unsigned char *sourceBaseAddr = (unsigned char *)(CVPixelBufferGetBaseAddress(pixelBuffer)); int
image_height; unsigned char *sourceStartAddr; if (fullHeight <= image_width) { image_height = fullHeight; sourceStartAddr = sourceBaseAddr; } else { image_height = image_width; const int marginY = ((fullHeight - image_width) / 2); sourceStartAddr = (sourceBaseAddr + (marginY * sourceRowBytes)); } const int image_channels = 4; assert(image_channels >= wanted_input_channels); tensorflow::Tensor image_tensor( tensorflow::DT_FLOAT, tensorflow::TensorShape( {1, wanted_input_height, wanted_input_width, wanted_input_channels})); auto image_tensor_mapped = image_tensor.tensor<float, 4>(); tensorflow::uint8 *in = sourceStartAddr; float *out = image_tensor_mapped.data(); for (int y = 0; y < wanted_input_height; ++y) { float *out_row = out + (y * wanted_input_width * wanted_input_channels); for (int x = 0; x < wanted_input_width; ++x) { const int in_x = (y * image_width) / wanted_input_width; const int in_y = (x * image_height) / wanted_input_height; tensorflow::uint8 *in_pixel = in + (in_y * image_width * image_channels) + (in_x * image_channels); float *out_pixel = out_row + (x * wanted_input_channels); for (int c = 0; c < wanted_input_channels; ++c) { out_pixel[c] = (in_pixel[c] - input_mean) / input_std; } } }
#FirebaseDevDay Interpret if (tf_session.get()) { std::vector<tensorflow::Tensor> outputs; tensorflow::Status run_status =
tf_session->Run( {{input_layer_name, image_tensor}}, {output_layer_name}, {}, &outputs); if (!run_status.ok()) { LOG(ERROR) << "Running model failed:" << run_status; } else { tensorflow::Tensor *output = &outputs[0]; auto predictions = output->flat<float>(); NSMutableDictionary *newValues = [NSMutableDictionary dictionary]; for (int index = 0; index < predictions.size(); index += 1) { const float predictionValue = predictions(index); if (predictionValue > 0.05f) { std::string label = labels[index % predictions.size()]; NSString *labelObject = [NSString stringWithUTF8String:label.c_str()]; NSNumber *valueObject = [NSNumber numberWithFloat:predictionValue]; [newValues setObject:valueObject forKey:labelObject]; } } dispatch_async(dispatch_get_main_queue(), ^(void) { [self setPredictionValues:newValues]; }); } }
None
#FirebaseDevDay
#FirebaseDevDay Real-world Common Use Cases
#FirebaseDevDay FIRVisionImage | VisionImage NS_SWIFT_NAME(VisionImage) @interface FIRVisionImage : NSObject @property(nonatomic,
nullable) FIRVisionImageMetadata *metadata; - (instancetype)initWithImage:(UIImage *)image NS_DESIGNATED_INITIALIZER; - (instancetype)initWithBuffer:(CMSampleBufferRef)sampleBuffer NS_DESIGNATED_INITIALIZER; - (instancetype)init NS_UNAVAILABLE; @end
Text Recognition - On-device - On-cloud
#FirebaseDevDay https://firebase.google.com/docs/ml-kit/recognize-text
#FirebaseDevDay FIRVisionText | VisionText NS_SWIFT_NAME(VisionText) @interface FIRVisionText : NSObject @property(nonatomic,
readonly) NSString *text; @property(nonatomic, readonly) NSArray<FIRVisionTextBlock *> *blocks; - (instancetype)init NS_UNAVAILABLE; @end
#FirebaseDevDay On-device Usage let textRecognizer = vision.onDeviceTextRecognizer() textRecognizer.process(visionImage) { (text,
error) in guard let text = text else { return } // do something with your text }
#FirebaseDevDay On-cloud Usage let textRecognizer = vision.cloudTextRecognize() textRecognizer.process(visionImage) { (text,
error) in guard let text = text else { return } // do something with your text }
Image Labeling - On-device (400+ labels) - On-cloud (10,000+ labels)
#FirebaseDevDay https://firebase.google.com/docs/ml-kit/label-images
#FirebaseDevDay FIRVisionLabel | VisionLabel NS_SWIFT_NAME(VisionLabel) @interface FIRVisionLabel : NSObject @property(nonatomic,
readonly) CGRect frame; @property(nonatomic, readonly) float confidence; @property(nonatomic, copy, readonly) NSString *entityID; @property(nonatomic, copy, readonly) NSString *label; @end
#FirebaseDevDay On-device Usage let labelDetector = vision.labelDetector() labelDetector.detect(in: visionImage) {
(labels, error) in guard let error == nill, let labels = labels, !labels.isEmpty else { return } // do something with your labels }
#FirebaseDevDay On-cloud Usage let labelDetector = vision.cloudLabelDetector() labelDetector.detect(in: visionImage) {
(labels, error) in guard let error == nill, let labels = labels, !labels.isEmpty else { return } // do something with your labels }
Face detection - On-device
#FirebaseDevDay
#FirebaseDevDay FIRVisionFace | VisionFace NS_SWIFT_NAME(VisionFace) @interface FIRVisionFace : NSObject @property(nonatomic,
readonly) CGRect frame; @property(nonatomic, readonly) BOOL hasTrackingID; @property(nonatomic, readonly) NSInteger trackingID; @property(nonatomic, readonly) BOOL hasHeadEulerAngleY; @property(nonatomic, readonly) CGFloat headEulerAngleY; @property(nonatomic, readonly) BOOL hasHeadEulerAngleZ; @property(nonatomic, readonly) CGFloat headEulerAngleZ; @property(nonatomic, readonly) BOOL hasSmilingProbability; @property(nonatomic, readonly) CGFloat smilingProbability; @property(nonatomic, readonly) BOOL hasLeftEyeOpenProbability; @property(nonatomic, readonly) CGFloat leftEyeOpenProbability; @property(nonatomic, readonly) BOOL hasRightEyeOpenProbability; @property(nonatomic, readonly) CGFloat rightEyeOpenProbability; - (instancetype)init NS_UNAVAILABLE; - (nullable FIRVisionFaceLandmark *)landmarkOfType:(FIRFaceLandmarkType)type; #ifdef ENABLE_FACE_CONTOUR - (nullable FIRVisionFaceContour *)contourOfType:(FIRFaceContourType)type; #endif // ENABLE_FACE_CONTOUR @end
#FirebaseDevDay On-device Usage let faceDetector = vision.faceDetector() faceDetector.detect(in: visionImage) {
(faces, error) in guard let error == nill, let faces = faces, !faces.isEmpty else { return } // do something with your faces }
#FirebaseDevDay Face Contour?
Landmark recognition - On-cloud
#FirebaseDevDay
#FirebaseDevDay FIRVisionCloudLandmark | VisionCloudLandmark NS_SWIFT_NAME(VisionCloudLandmark) @interface FIRVisionCloudLandmark : NSObject @property(nonatomic,
copy, readonly, nullable) NSString *entityId; @property(nonatomic, copy, readonly, nullable) NSString *landmark; @property(nonatomic, readonly, nullable) NSNumber *confidence; @property(nonatomic, readonly) CGRect frame; @property(nonatomic, readonly, nullable) NSArray<FIRVisionLatitudeLongitude *> *locations; - (instancetype)init NS_UNAVAILABLE; @end
#FirebaseDevDay On-cloud Usage let landmarkDetector = vision.cloudLandmarkDetector() landmarkDetector.detect(in: visionImage) {
(landmarks, error) in guard let error == nill, let landmarks = landmarks, !landmarks.isEmpty else { return } // do something with your landmarks }
Barcode scanning - On-device
#FirebaseDevDay https://firebase.google.com/docs/ml-kit/label-images
#FirebaseDevDay FIRVisionBarcode | VisionBarcode NS_SWIFT_NAME(VisionBarcode) @interface FIRVisionBarcode : NSObject @property(nonatomic,
readonly) CGRect frame; @property(nonatomic, readonly, nullable) NSString *rawValue; @property(nonatomic, readonly, nullable) NSString *displayValue; @property(nonatomic, readonly) FIRVisionBarcodeFormat format; @property(nonatomic, readonly, nullable) NSArray<NSValue *> *cornerPoints; @property(nonatomic, readonly) FIRVisionBarcodeValueType valueType; @property(nonatomic, readonly, nullable) FIRVisionBarcodeEmail *email; @property(nonatomic, readonly, nullable) FIRVisionBarcodePhone *phone; @property(nonatomic, readonly, nullable) FIRVisionBarcodeSMS *sms; @property(nonatomic, readonly, nullable) FIRVisionBarcodeURLBookmark *URL; @property(nonatomic, readonly, nullable) FIRVisionBarcodeWiFi *wifi; @property(nonatomic, readonly, nullable) FIRVisionBarcodeGeoPoint *geoPoint; @property(nonatomic, readonly, nullable) FIRVisionBarcodeContactInfo *contactInfo; @property(nonatomic, readonly, nullable) FIRVisionBarcodeCalendarEvent *calendarEvent; @property(nonatomic, readonly, nullable) FIRVisionBarcodeDriverLicense *driverLicense; - (instancetype)init NS_UNAVAILABLE; @end
#FirebaseDevDay FIRVisionBarcodeCalendarEvent | VisionBarcodeCalendarEvent NS_SWIFT_NAME(VisionBarcodeCalendarEvent) @interface FIRVisionBarcodeCalendarEvent : NSObject @property(nonatomic,
readonly, nullable) NSString *eventDescription; @property(nonatomic, readonly, nullable) NSString *location; @property(nonatomic, readonly, nullable) NSString *organizer; @property(nonatomic, readonly, nullable) NSString *status; @property(nonatomic, readonly, nullable) NSString *summary; @property(nonatomic, readonly, nullable) NSDate *start; @property(nonatomic, readonly, nullable) NSDate *end; - (instancetype)init NS_UNAVAILABLE; @end
#FirebaseDevDay On-device Usage let barcodeDetector = vision.barcodeDetector() barcodeDetector.detect(in: visionImage) {
(barcodes, error) in guard let error == nill, let barcodes = barcodes, !barcodes.isEmpty else { return } // do something with your barcodes }
Custom model - Tensorflow Lite
#FirebaseDevDay let conditions = ModelDownloadConditions(isWiFiRequired: true, canDownloadInBackground: true) let cloudModelSource
= CloudModelSource( modelName: "my_cloud_model", enableModelUpdates: true, initialConditions: conditions, updateConditions: conditions ) let registrationSuccessful = ModelManager.modelManager().register(cloudModelSource)
Demo
Thank You! #FirebaseDevDay Helpful resources fb.com/FirebaseThailand fb.com/groups/FirebaseDevTH medium.com/FirebaseThailand Kajornsak Peerapathananont