Примечания к выпускам

Последние версии

Последние версии Android API

Идентификатор группы	Название артефакта	Версия	Последнее обновление
com.google.android.gms	play-services-mlkit-barcode-scanning	18.3.1	08/07/2024
com.google.android.gms	play-services-mlkit-document-scanner	16.0.0	29.09.2025
com.google.android.gms	play-services-mlkit-face-detection	17.1.0	16.08.2022
com.google.android.gms	play-services-mlkit-image-labeling	16.0.8	16.08.2022
com.google.android.gms	play-services-mlkit-image-labeling-custom	16.0.0-бета5	11/07/2023
com.google.android.gms	play-services-mlkit-language-id	17.0.0	16.08.2022
com.google.android.gms	play-services-mlkit-smart-reply	16.0.0-бета1	12/06/2022
com.google.android.gms	play-services-mlkit-subject-segmentation	16.0.0-бета1	11/07/2023
com.google.android.gms	play-services-mlkit-распознавание текста	19.0.1	08/07/2024
com.google.android.gms	play-services-mlkit-text-recognition-chinese	16.0.1	08/07/2024
com.google.android.gms	play-services-mlkit-text-recognition-devanagari	16.0.1	08/07/2024
com.google.android.gms	play-services-mlkit-text-recognition-japanese	16.0.1	08/07/2024
com.google.android.gms	play-services-mlkit-text-recognition-korean	16.0.1	08/07/2024
com.google.android.gms	play-services-code-scanner	16.1.0	08/01/2023
com.google.mlkit	сканирование штрих-кода	17.3.0	08/07/2024
com.google.mlkit	камера	16.0.0-бета3	25.01.2022
com.google.mlkit	распознавание цифровых чернил	19.0.0	29.08.2025
com.google.mlkit	извлечение сущностей	16.0.0-бета6	18.04.2025
com.google.mlkit	распознавание лиц	16.1.7	08/07/2024
com.google.mlkit	обнаружение лицевой сетки	16.0.0-бета3	08/07/2024
com.google.mlkit	genai-image-description	1.0.0-бета1	14.05.2025
com.google.mlkit	genai-prompt	1.0.0-альфа1	29.10.2025
com.google.mlkit	генай-корректура	1.0.0-бета1	14.05.2025
com.google.mlkit	переписывание генаев	1.0.0-бета1	14.05.2025
com.google.mlkit	генай-суммирование	1.0.0-бета1	14.05.2025
com.google.mlkit	маркировка изображений	17.0.9	08/07/2024
com.google.mlkit	маркировка изображений-на заказ	17.0.3	08/07/2024
com.google.mlkit	идентификатор языка	17.0.6	08/07/2024
com.google.mlkit	linkfirebase	17.0.0	25.01.2022
com.google.mlkit	обнаружение объектов	17.0.2	08/07/2024
com.google.mlkit	обнаружение объектов-настраиваемое	17.0.2	08/07/2024
com.google.mlkit	playstore-dynamic-feature-support	16.0.0-бета2	25.01.2022
com.google.mlkit	определение позы	18.0.0-бета5	08/07/2024
com.google.mlkit	точное определение позы	18.0.0-бета5	08/07/2024
com.google.mlkit	сегментация-селфи	16.0.0-бета6	08/07/2024
com.google.mlkit	умный ответ	17.0.4	08/07/2024
com.google.mlkit	распознавание текста	16.0.1	08/07/2024
com.google.mlkit	распознавание текста на китайском языке	16.0.1	08/07/2024
com.google.mlkit	распознавание текста-деванагари	16.0.1	08/07/2024
com.google.mlkit	распознавание текста на японском языке	16.0.1	08/07/2024
com.google.mlkit	распознавание текста на корейском языке	16.0.1	08/07/2024
com.google.mlkit	переводить	17.0.3	08/07/2024

Последние версии iOS API

Название артефакта	Версия	Последнее обновление
GoogleMLKit	9.0.0	27.06.2025
MLKitBarcodeScanning	8.0.0	27.06.2025
MLKitCommon	14.0.0	27.06.2025
MLKitDigitalInkRecognition	8.0.0	27.06.2025
MLKitEntityExtraction	1.0.0-бета15	27.06.2025
MLKitFaceDetection	8.0.0	27.06.2025
MLKitImageLabeling	8.0.0	27.06.2025
MLKitImageLabelingCommon	10.0.0	27.06.2025
MLKitImageLabelingCustom	8.0.0	27.06.2025
MLKitLanguageID	9.0.0	27.06.2025
MLKitLinkFirebase	8.0.0	27.06.2025
MLKitObjectDetection	8.0.0	27.06.2025
MLKitObjectDetectionCommon	10.0.0	27.06.2025
MLKitObjectDetectionCustom	8.0.0	27.06.2025
MLKitPoseDetection	1.0.0-бета16	27.06.2025
MLKitPoseDetectionAccurate	1.0.0-бета16	27.06.2025
MLKitPoseDetectionCommon	1.0.0-бета16	27.06.2025
MLKitSegmentationCommon	1.0.0-бета14	27.06.2025
MLKitSegmentationSelfie	1.0.0-бета14	27.06.2025
MLKitSmartReply	8.0.0	27.06.2025
MLKitTextRecognition (v2)	7.0.0	27.06.2025
MLKitTextRecognitionCommon	6.0.0	27.06.2025
MLKitTextRecognitionChinese	6.0.0	27.06.2025
MLKitTextRecognitionДеванагари	6.0.0	27.06.2025
MLKitTextRecognitionJapanese	6.0.0	27.06.2025
MLKitTextRecognitionKorean	6.0.0	27.06.2025
MLKitTranslate	8.0.0	27.06.2025
MLKitVision	10.0.0	27.06.2025
MLImage	1.0.0-бета8	27.06.2025

История релизов

29 октября 2025 г.

Новые функции

• На Android выпущен API GenAI Prompt для генерации текстового контента на основе пользовательского текстового или многомодального приглашения.

29 сентября 2025 г.

Новые функции

• На Android приложение Document Scanner переведено из стадии бета-версии в стадию общедоступной версии.

29 августа 2025 г.

На Android обновлен SDK распознавания цифровых рукописей для поддержки размеров страниц 16 КБ .

27 июня 2025 г.

В этом выпуске исправлены ошибки.

Исправления ошибок

• На iOS удалена ссылка на домен для предотвращения отклонения заявки на отправку приложения.

14 мая 2025 г.

Выпущены следующие API GenAI на Android:

• API описания изображений для предоставления кратких описаний изображений.
• API корректуры для улучшения короткого контента путем улучшения грамматики и исправления орфографических ошибок.
• Переписывание API для перефразирования контента в разных стилях, например формально, кратко или даже с использованием эмодзи.
• API реферирования для резюмирования статей и бесед в чате в виде маркированных списков из 1–3 пунктов.

18 апреля 2025 г.

На Android исправлена ​​проблема с загрузкой Entity Extraction API на арабском языке. Также обновлена ​​минимальная поддерживаемая версия Android API до 26 для лучшей поддержки страниц размером 16 КБ .

25 марта 2025 г.

В этот выпуск включены улучшения.

Улучшения

• На iOS минимальная поддерживаемая версия Xcode увеличена до 16.0.0.

30 сентября 2024 г.

В этот выпуск включены улучшения.

Улучшения

• На iOS минимальная поддерживаемая версия Xcode увеличена до 15.3.0.
• На iOS минимальная поддерживаемая версия iOS увеличена до 15.5.0.
• На iOS обновлен диапазон версий зависимости GoogleUtilities/UserDefaults в MLKitCommon с «>= 7.13.0, < 8.0» до «~> 8.0».
• На iOS обновлен диапазон версий зависимости GoogleDataTransport в MLKitCommon с «>= 9.4.1, < 10.0» до «~> 10.0».

7 августа 2024 г.

Обновлены Android SDK для поддержки размеров страниц 16 КБ .

17 апреля 2024 г.

В этот выпуск включены улучшения.

Улучшения

• На iOS обновлен манифест конфиденциальности.
• На iOS обновлен диапазон версий зависимости GoogleToolboxForMac в MLKitCommon с "~>2.1" до ">= 4.2.1, < 5.0".
• На iOS обновлен диапазон версий зависимости GTMSessionFetcher/Core в MLKitCommon с «>= 1.1, < 4.0» до «>= 3.3.2, < 4.0».
• На iOS обновлен диапазон версий зависимости GoogleDataTransport в MLKitCommon с "~>9.0" до "">= 9.4.1, < 10.0".
• На iOS обновлен диапазон версий зависимости GoogleUtilities/UserDefaults в MLKitCommon с "~> 7.0" до ">= 7.13.0, < 8.0".
• На iOS обновлен диапазон версий зависимости FirebaseCore в MLKitLinkFirebase с «>= 10.0, <12.0» до «>= 10.23.0, <12.0».
• На iOS обновлен диапазон версий зависимости FirebaseInstallations в MLKitLinkFirebase с «>= 10.0, <12.0» до «>= 10.23.0, <12.0».

20 февраля 2024 г.

Этот выпуск включает новые функции и улучшения.

Новые функции

• На Android добавлен новый API сканера документов , который обеспечивает поток сканирования с использованием как пользовательского интерфейса, так и машинного обучения.

Улучшения

• На Android исправлена ​​уязвимость безопасности , вызванная старой версией зависимости play-services-basement.
• На iOS добавлена ​​поддержка Xcode 15.1.0.
• На iOS исправлена ​​уязвимость безопасности, обнаруженная в библиотеке libwebp.
• На iOS обновлены зависимости Cocoapods для совместимости с Firebase 10.
• На iOS исправлено распознавание текста для использования более новой версии FlatBuffers.
• На устройствах iOS добавлено описание использования требуемых API-интерфейсов в файлах манифеста конфиденциальности.
• На iOS минимальная поддерживаемая версия iOS увеличена с 11.0 до 12.0.

7 ноября 2023 г.

Этот выпуск включает новые функции и улучшения.

Новые функции

• На Android добавлен новый API сегментации объектов , который позволяет разработчикам отделять несколько объектов от фона на изображении.

Улучшения

• На Android исправлена ​​проблема загрузки в API перевода , пользовательской маркировки изображений и обнаружения пользовательских объектов .
• Минимальная поддерживаемая версия Android API обновлена ​​с 19 до 21.

1 августа 2023 г.

В этом выпуске реализованы новые функции.

Новые функции

• На Android добавлена ​​поддержка функции auto-zoom в API сканирования штрихкодов и сканера Google Code .

2 мая 2023 г.

В этом выпуске реализованы новые функции.

Новые функции

• На Android обновлена ​​отдельная версия API распознавания текста для латиницы 29 марта 2023 года. Улучшена производительность и добавлена ​​поддержка всех ориентаций.
• Расширенная версия распознавания текста для Android, поддерживающая китайскую, деванагари, японскую, корейскую письменности и латиницу. Этот API обеспечивает тот же функционал, что и встроенная версия, но с поддержкой сервисов Google Play, что позволило уменьшить размер приложения до всего около 260 КБ.
• На Android пакетная версия распознавания текста v2 переведена из стадии бета-версии в стадию общедоступной.

21 марта 2023 г.

В этом выпуске реализованы новые функции.

Новые функции

• На Android сканер кода Google переведен из стадии бета-тестирования в стадию общедоступного тестирования.
• На Android добавлена ​​поддержка возврата всех потенциальных штрихкодов при сканировании штрихкодов .
• На iOS распознавание текста v2 переведено из стадии бета-версии в стадию общедоступной версии.

Улучшения

• На iOS минимальная поддерживаемая версия Xcode увеличена до 14.2.0.
• На iOS минимальная поддерживаемая версия iOS увеличена с 10.0 до 11.0.
• В iOS удалена поддержка биткода.
• На iOS обновлены диапазоны версий зависимостей GTMSessionFetcher/Core в MLKitCommon, MLKitLinkFirebase, MLKitNaturalLanguage и MLKitVision для поддержки Firebase 10.

31 января 2023 г.

В этом выпуске реализованы новые функции.

Новые функции

• For Digital Ink Recognition on Android , added gesture classifier models for some standard text editing gestures.

6 декабря 2022 г.

This release includes new features and bug fixes.

Новые функции

• Added unbundled version of Smart reply API on Android. The unbundled version reduces app download size by 5.5MB compared to the bundled version.

Исправления ошибок

• On Android, fixed a Barcode scanning issue that didn't support Bitmap config other than ARGB_8888.

20 сентября 2022 г.

This release includes new features and improvements.

Новые функции

• Added bundled version of Face mesh detection API on Android. The public beta of the API works best for faces within ~2 meters (~7 feet) from camera and provides 468 3D points and triangle info for detected faces with low latency(14ms on Pixel 3 devices). When in BOUNDING_BOX_ONLY mode, the latency can be further reduced by ~20%.

Улучшения

• On Android, improved latency of Pose detection API by enabling fp16 model inference on supported CPUs.
• On Android, improved Text recognition v2 by providing symbol and rotation information in recognition result.

20 сентября 2022 г.

This release includes new features and improvements.

Новые функции

• Added bundled version of Face Mesh Detection API on Android. The public beta of the API works best for faces within ~2 meters, or ~6.5 feet from camera and provides 468 3D points and triangle info for detected faces with low latency(14ms on Pixel 3 devices). When in BOUNDING_BOX_ONLY mode the latency can be further reduced by ~20%.

Улучшения

• On Android, improved latency of Pose Detection API by enabling fp16 model inference on supported CPUs.
• On Android, improved Text recognition v2 by providing symbol and rotation information in recognition result.

23 августа 2022 г.

Улучшения

• On Android, upgraded the unbundled version of the Barcode Scanning API. Improved recall, long tail latency, low-quality image tolerance and bounding box stability. Brought its performance on pair with that of the bundled version. Google Play Services handles this upgrade automatically, so no change is needed in your app.

16 августа 2022 г.

This release includes improvements.

Улучшения

• On Android and iOS, upgraded models for Translate for better accuracy.
• On Android, graduated the unbundled version of Language Identification out of Beta.
• On Android, exposed confidence score for Text Recognition and Text recognition v2 .
• On Android, implemented OptionalModuleApi interface for each ML Kit Detector supporting unbundled version, so that you can use Google Play services ModuleInstallClient API to control the install and check availability when using the unbundled versions.
• On iOS, upgraded the version range of FirebaseCore and FirebaseInstallations dependencies in MLKitLinkFirebase from 8.x to 9.x, to make ML Kit compatible with Firebase 9.x.

28 июня 2022 г.

This release includes improvements.

Улучшения

• Improved Smart Reply model to generate more accurate replies and significantly reduced 5 MB model size.
• On Android, added option to allow users to input barcode manually from the scanner view in Google Code Scanner API .

10 мая 2022 г.

This release includes new features.

Новые функции

• Added new Google Code Scanner API on Android. The public beta of the Google code scanner provides a complete solution for scanning codes without requiring your app to request camera permission, while preserving user privacy. This is accomplished by delegating the task of scanning the code to Google Play services and returning only the scan results to your app.

26 апреля 2022 г.

This release includes improvements.

Улучшения

• Improved Smart Reply model to better detect sensitive topics.
• On Android, upgraded all language models in the bundled version of the Text recognition v2 API. Improved performance and added all-orientation support for Latin.
• On iOS, raised the minimum supported version of Xcode to 13.2.1.

22 февраля 2022 г.

This release includes new features and improvements.

Новые функции

• On Android, added GPU acceleration support to Pose Detection.

Улучшения

• On Android, upgraded models in the bundled version of the Face Detection API. Improved recall, latency for accurate mode and reduced the apk size impact from 11.6 MB to 6.9 MB.
• On iOS, support ECI code for CP437 text encoding in Barcode Scanning API.

January 25, 2022

This release includes internal improvements and bug fixes on Android.

Улучшения

• Strict nullability annotations ( @NonNull and @Nullable ) are being used where previously @RecentlyNonNull and @RecentlyNullable were used. With this change, what once caused a nullness warning will now cause an error when building Kotlin code or using Java null checking frameworks.
• On Android, support ECI code for CP437 text encoding in Barcode Scanning API. .

Исправления ошибок

• Fixed a Barcode Scanning issue that code 128B and code 128C raw value has an additional character.

14 декабря 2021 г.

This release includes internal improvements and bug fixes.

Исправления ошибок

• Fixed an issue in Text recognition v2 preventing text recognition results from returning recognized languages correctly.
• On Android, fixed an issue in Language Identification where the app may crash when upgrading to AGP 7.0.0 or later.
• On Android, fixed an issue in Pose Detection where the local reference table could overflow.
• On Android, fixed an issue in Digital Ink Recognition and Entity Extraction where a runtime exception could be thrown when the app targets API level 31 and runs on Android S.
• On iOS, return nil for rawValue when the barcode is not encoded in UTF-8 format to match API reference.

28 сентября 2021 г.

This release includes new features, improvements and bug fixes.

Новые функции

• On Android, added unbundled version of Custom Image Labeling API , backed by Google Play Services, to reduce the impact on apk size from 5.5 MB to 600 KB.
• On iOS, added recognizedLanguages property to TextElement for Text recognition v2 .

Улучшения

• On Android, enabled NNAPI(TPU) acceleration for Object Detection & Tracking with Base models and Pose Detection on Pixel 2021 devices.
• On iOS, raised the minimum supported version of Xcode to 12.5.1.
• On iOS, upgraded model for Language Identification with improved quality.

Исправления ошибок

• On Android, fixed an issue in Language Identification where the SDK could return an unexpected unknown tag.
• On iOS, fixed a bitcode recompilation issue when generating the .ipa file.

August 11, 2021

This release includes new features and improvements.

Новые функции

• Added Text recognition v2 , which adds support for Chinese, Devanagari, Japanese and Korean scripts in addition to Latin and greatly increases range of supported languages . This API is offered as a bundled library and includes improved ML-based block/paragraph detection and updated models to boost recognition accuracy.
• On Android, added unbundled version of Language Identification , backed by Google Play Services, to reduce the impact on apk size by about 500KB.

Улучшения

• Upgraded the bundled version of the Barcode Scanning API. Improved recall, long tail latency, low-quality image tolerance and bounding box stability.
• Upgraded the Pose Detection API for better accuracy. Also, added the experimental Z coordinates for facial landmarks.
• On Android, updated models for Language Identification , to improve accuracy.

Критические изменения

• On Android, there are two breaking changes for Text Recognition :
  • The deprecated TextRecognition.getClient() method is removed. Please use TextRecognition.getClient(TextRecognizerOptions.DEFAULT_OPTIONS) instead.
  • TextRecognizerOptions is moved from com.google.mlkit.vision.text to com.google.mlkit.vision.text.latin .
• On Android, for Barcode Scanning and Language Identification , the major version bumps are only due to breaking changes on non-public APIs. No code change is required when upgrading their dependency versions in your app.
• On Android, ML Kit no longer supports API levels 16, 17 and 18, due to extremely low use. API level 19 (KitKat) is now the minimum level supported.

Примечание

• On iOS, to keep your project on the v1 version of Text Recognition make sure to pin to version 2.2.0 or lower in your podfile. For example, adding pod 'GoogleMLKit/TextRecognition','2.2.0' to the pod file will pin your app to the latest v1 version of this feature.

29 июня 2021 г.

This release includes new features and improvements.

Новые функции

• Added support for com.google.android.odml.image.MlImage on Android and MLImage on iOS, a common image container (Beta) for on-device machine learning frameworks.

Улучшения

• Upgraded the entity extraction models with improved quality for both Android and iOS.
• On Android, improved Pose Detection performance for certain CPU specs.
• On Android, fixed okhttp3 incompatible issue for Entity Extraction and Digital Ink Recognition APIs.
• On iOS, raised the minimum supported version of Xcode to 12.4.
• On iOS, upgraded the version range of GoogleDataTransport dependency in MLKitCommon from 8.x to 9.x and the version range of FirebaseCore dependency in MLKitLinkFirebase from 7.x to 8.x, to make ML Kit compatible with Firebase 8.x. Migrated MLKitLinkFirebase from FirebaseInstanceID to FirebaseInstallations .
• Breaking change: On iOS, removed label support for the deprecated remote AutoML-trained custom models without labels embedded in the model metadata. Please update such remote models hosted on Firebase Console with ones containing labels in its metadata.

2 июня 2021 г.

This patch release fixed a bug in the com.google.mlkit:face-detection library.

25 мая 2021 г.

This release includes new feature and improvements.

Улучшения

• On Android, introduced a playstore dynamic feature support library for features depending on ML Kit and the ML Kit dependencies to be put in a dynamic feature module when app is built with play store app bundle .

• On Android, deprecated TextRecognition#getClient() API in Text Recognition SDK.

4 мая 2021 г.

This patch release fixes a crash regression in the Custom Image Labeling API.

Исправления ошибок

• On Android, fixed a crash issue in Custom Image Labeling API when the model is downloaded from Firebase.

27 апреля 2021 г.

This release includes new feature and improvements.

Улучшения

• On Android, introduced a camera helper library for MLKit vision features to be used with Camera output directly in streaming mode. It uses CameraX internally.

• On Android, enabled NNAPI acceleration for Object Detection & Tracking with Base models on more devices which provides faster model inference and saves energy.

Исправления ошибок

• On Android, fixed an issue in FaceDetection API when the InputImage is constructed by bitmap with a non-zero rotationDegrees.

30 марта 2021 г.

This release includes improvements and bug fixes.

Улучшения

• Added new models for Devanagari script languages for Digital Ink Recognition APIs.
• On Android, updated version of external dependencies for Face Detection APIs and Image Labeling APIs.

Исправления ошибок

• On Android, added Network permission to Translate API so app doesn't need to declare it.

2 марта 2021 г.

This release includes new features and improvements.

Новые функции

• Added Selfie Segmentation API, a CPU-based solution for developers to easily separate the background from users within a scene and focus on what matters.

Улучшения

• Raised the minimum supported version of Xcode to 12.2 in iOS.

Feburary 5, 2021

This patch release fixes a regression bug in the Face Detection APIs.

Improvements and bug fixes

• There was a regression bug introduced in Face Detection versions 16.1.3 (thin) and 16.0.4 (bundled) which resulted in poor face detection. This patch release fixes the bug.

26 января 2021 г.

This release includes new features, improvements and bug fixes.

Новые функции

• New Z Coordinate support in the Pose Detection API.

Improvements and bug fixes

• The Pose Detection API recognizes more poses, such as when a user is directly facing the camera while doing squats and pushups.
• The Pose Detection API base and accurate models are significantly smaller. This change does not impact the quality of the models.
• The Android Vision APIs have been updated. The size of the unbundled variants in the pull-in SDKs backed by Google Play Services is reduced by approximately 16% (~160KB).

8 декабря 2020 г.

This release includes new features, improvements and bug fixes.

Новые функции

• ML Kit is no longer in Beta. All of ML Kit's APIs (excluding Pose Detection and Entity Extraction) have graduated to General Availability status.

• Added the Entity Extraction API (Beta). This API allows you to detect and locate entities (eg addresses, date/time etc.) from raw text. It supports 11 entity types and 15 languages, using the same technology that powers smart text selection in Android Q+.

  Entity Extraction works fully offline (aside from a one-time download of selected language model, which is ~700KB), and supports both Android and IOS.

Improvements and bug fixes

• Breaking change: The AutoML image labeling API is removed. Instead, custom image classification models trained using AutoML Vision Edge are now supported by the Custom Image Labeling and Custom Object Detection & Tracking APIs directly.
• The Custom Image Labeling and Custom Object Detection & Tracking now support remote models that are hosted in Firebase .
  • Added RemoteModelSource , FirebaseModelSource , and CustomRemoteModel classes to support custom models hosted remotely on Firebase server. Also added the support for creating a LocalModel instance from a manifest path of a local custom model trained by AutoML Vision Edge.
  • For the custom image labeling API, added the remote custom model support to the CustomImageLabelerOptions class.
  • For the custom object detection API, added the remote custom model support to the CustomObjectDetectorOptions class.
• On Android, significantly reduced the SDK size for Vision APIs. For APIs with unbundled variants (backed by Google Play Services) the pull-in SDK's size reduces by ~900KB (~65% of original size). For all other Vision APIs, the pull-in SDK's size reduces by ~600KB. The exception is Digital Ink Recognition, for which the SDK size remains the same.
• On Android, enabled NNAPI acceleration for Object Detection & Tracking with Base models in STREAM_MODE on selected devices and OSes (Pixel 3, 3XL, 4, 4XL with Android Q or R at the moment), which provides faster model inference and saves energy.
• On Android, fixed an issue in Barcode Scanning API where it did not work on some devices running with camera-camera2:1.0.0-beta08 version or later.

2 ноября 2020 г.

This release includes improvements and bug fixes.

iOS: GoogleMLKit/LinkFirebase 0.64.1

Improvements and bug fixes

• Upgraded the version range of FirebaseCore dependency in MLKitLinkFirebase from 6.x to 7.x, FirebaseInstanceID dependency from 4.x to 7.x.

29 октября 2020 г.

This release includes improvements and bug fixes.

iOS: GoogleMLKit/Common 0.64.2

Improvements and bug fixes

• Upgraded the version range of GoogleUtilities/UserDefaults dependency in MLKitCommon from 6.x to 7.x.

October 26, 2020

This release includes improvements and bug fixes.

iOS: GoogleMLKit/Common 0.64.1

Improvements and bug fixes

• Upgraded the version range of GoogleDataTransport dependency in MLKitCommon from 7.x to 8.x.

29 сентября 2020 г.

This release includes new features, improvements and bug fixes.

iOS API Version: 0.64.0

Новые функции

• On Android, added a “thin” variant of Image Labeling API , backed by Google Play Services. Reduces size impact to your app by ~3 MB compared to the bundled variant.

Improvements and bug fixes

• Breaking change : Split Pose Detection into two libraries for size optimization. One library only bundles the fast models, while the other only bundles the accurate models. This helps save the application size, if you only use one set of the models. Same change happened to iOS: The PoseDetection pod now contains only the fast models. To use the accurate models, use the PoseDetectionAccurate pod instead.
• On iOS, fixed a memory leak which occurred during pose detector deallocation.

25 августа 2020 г.

This release includes new features, improvements and bug fixes.

iOS API Version: 0.63.0

Новые функции

• Added the Pose Detection API, a CPU-based, lightweight and versatile solution for developers to track a user's physical actions in real time within their apps. Pose Detection offers a 33 point skeletal match (with hands and feet tracking) of a users body in real time and has been tuned to work well for complex athletic use cases.

  Pose detection also works fully offline, comes with two operating modes (fast and accurate), and supports both Android and iOS.

Improvements and bug fixes

• Added support to create a LocalModel with a URI on Android.
• New Latin script recognizers for Filipino ( fil / tl ), Uzbek ( uz-Latn ), and Berber ( ber-Latn ) in Digital Ink Recognition .
• Improved models for Cyrillic script languages in Digital Ink Recognition .
• Changed the Hebrew language code from iw to he in Language Identification on Android since iw is deprecated in BCP-47.

28 июля 2020 г.

This release includes new features, improvements, and bug fixes.

iOS API Version: 0.62.0

Новые функции

• Added a new Digital Ink Recognition API that recognizes text and shapes handwritten on a digital surface (eg touch screens). Supports 300+ languages, as well as emoji and autodraw. It is the same technology that powers handwriting recognition layouts in Gboard, the Google Translate apps and the Quick, Draw! game.

  Digital Ink Recognition works fully offline (aside from a one-time download of language packs), and supports both Android and iOS.

• On Android, added support for specifying your own custom Executor for running expensive tasks like model loading and inference to Image Labeling and Object Detection and Tracking. With this release, all ML Kit APIs now support custom executors.

  By default, ML Kit uses a highly optimized, internally managed thread pool to run background tasks. This API can help with specialized use cases where developers want to keep full control over the threads in their app instead.

Improvements and bug fixes

• On Android, for the Barcode Scanning API, fixed rotation handling of the input image.

15 июля 2020 г.

This release includes improvements and bug fixes.

iOS: GoogleMLKit/Common 0.61.1

Improvements and bug fixes

• Upgraded the version range of GoogleDataTransport dependency in MLKitCommon from 3.2 or higher to 7.0 or higher.
• Removed the GoogleDataTransportCCTSupport dependency from MLKitCommon.

1 июля 2020 г.

This release includes new features, improvements and bug fixes.

iOS API Version: 0.61.0

Новые функции

• The Image Labeling and Object Detection and Tracking APIs now support float-based custom models.

• On Android, added support for specifying your own custom Executor for running expensive tasks like model loading and inference to all APIs except Image Labeling and Object Detection and Tracking.

  By default, ML Kit uses a highly optimized, internally managed thread pool to run background tasks. This API can help with specialized use cases where developers want to keep full control over the threads in their app instead.

Improvements and bug fixes

• Breaking change: On iOS, for the Barcode Scanning API, fixed a typo in BarcodePersonName and renamed its pronounciation property to pronunciation .
• Fixed an issue on iOS in the Translate and Smart Reply APIs where the app would crash if the device locale does not specify a region (eg "en" instead of "en-US").

3 июня 2020 г.

Android: 16.0.0 / iOS: 0.60.0

This is the first release of ML Kit as a standalone SDK, independent from Firebase. This SDK offers all the on-device APIs that were previously offered through the ML Kit for Firebase SDK. For more information on this change and instructions on migrating your existing apps, please follow our migration guide .

This release includes new features, improvements and bug fixes.

Новые функции

• New Custom Image Labeling and Custom Object Detection and Tracking APIs, making it easy to use custom image classification models (pre-trained, or newly trained from a range of sources) in your apps and build real-time interactive experiences for users.

Improvements and bug fixes

• On Android, included support for Face Contours in “thin” variant of Face Detection API , backed by Google Play Services. Reduces size impact to your app by ~20.3 MB compared to bundled variant.
• On Android, improved CameraX and Camera2 performance for Barcode Scanning and Face Detection APIs by moving image processing code from Java to native code.
• Android Jetpack Lifecycle support has been added to all APIs. Developers can use addObserver to automatically manage the initiation and teardown of ML Kit APIs as the app goes through screen rotation or closure by the user / system. This makes CameraX integration easier.
• Text Recognition API: the most prevalent recognized language is now provided
• Face Detection API: the Euler X angle of a face is now provided.
• Barcode Scanning API [bundled]: added support for broken PDF417 start/stop pattern detection, improving recall by 10%.
• Object Detection and Tracking API: updated localizer model, improving average precision and reducing footprint by ~700KB.

Legacy releases

Changes prior to June 3, 2020 can be found in the Firebase release notes .