ML Kit는 강력하고 사용하기 쉬운 패키지로 Android 및 iOS 앱에 Google의 머신러닝 전문 지식을 적용하는 모바일 SDK입니다. 머신러닝 분야에 경험이 있든 없든 코드 몇 줄만 작성하면 필요한 기능을 구현할 수 있습니다. 따라서 신경망이나 모델 최적화에 대한 심층적인 지식 없이도 시작할 수 있습니다. 숙련된 ML 개발자인 경우, 모바일 앱에서 커스텀 TensorFlow Lite 모델을 사용하는 데 유용한 ML Kit의 API를 사용할 수 있습니다.
주요 기능
일반적인 사용 사례에 즉시 사용
ML Kit에는 텍스트 인식, 얼굴 인식, 랜드마크 인식, 바코드 스캔, 이미지 라벨 지정, 텍스트 언어 식별 등 일반적인 모바일 사용 사례에 즉시 사용 가능한 API 집합이 제공됩니다. ML Kit 라이브러리에 데이터를 전달하기만 하면 필요한 정보를 확인할 수 있습니다.
온디바이스 또는 클라우드 API
ML Kit는 기기에서 실행되거나 클라우드에서 실행되는 API를 제공합니다. 온디바이스 API는 데이터를 빠르게 처리할 수 있으며 네트워크 연결 없이도 작동합니다. 반면 클라우드 기반 API는 Google Cloud의 강력한 머신러닝 기술을 활용하므로 보다 높은 정확성을 확보할 수 있습니다.
커스텀 모델 배포
ML Kit의 API로 사용 사례를 해결할 수 없는 경우 언제든지 고유한 기존 TensorFlow Lite 모델을 가져올 수 있습니다. 모델을 Firebase에 업로드만 하면 앱에 대한 호스팅 및 서비스가 자동으로 처리됩니다. ML Kit는 커스텀 모델에 대한 API 레이어로 작동하여 간단하게 실행하고 사용할 수 있습니다.
[null,null,["최종 업데이트: 2025-08-04(UTC)"],[],[],null,["ML Kit for Firebase \nplat_ios plat_android \nUse machine learning in your apps to solve real-world problems.\n\nML Kit is a mobile SDK that brings Google's machine learning expertise to\nAndroid and iOS apps in a powerful yet easy-to-use package. Whether you're new\nor experienced in machine learning, you can implement the functionality\nyou need in just a few lines of code. There's no need to have deep knowledge of\nneural networks or model optimization to get started. On the other hand, if you\nare an experienced ML developer, ML Kit provides convenient APIs that help\nyou use your custom TensorFlow Lite models in your mobile apps.\n| This is a beta release of ML Kit for Firebase. This API might be changed in backward-incompatible ways and is not subject to any SLA or deprecation policy.\n\nKey capabilities\n\n|---------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| Production-ready for common use cases | ML Kit comes with a set of ready-to-use APIs for common mobile use cases: recognizing text, detecting faces, identifying landmarks, scanning barcodes, labeling images, and identifying the language of text. Simply pass in data to the ML Kit library and it gives you the information you need. |\n| On-device or in the cloud | ML Kit's selection of APIs run on-device or in the cloud. Our on-device APIs can process your data quickly and work even when there's no network connection. Our cloud-based APIs, on the other hand, leverage the power of Google Cloud's machine learning technology to give you an even higher level of accuracy. |\n| Deploy custom models | If ML Kit's APIs don't cover your use cases, you can always bring your own existing TensorFlow Lite models. Just upload your model to Firebase, and we'll take care of hosting and serving it to your app. ML Kit acts as an API layer to your custom model, making it simpler to run and use. |\n\nHow does it work?\n\nML Kit makes it easy to apply ML techniques in your apps by bringing Google's\nML technologies, such as the\n[Google Cloud Vision API](https://cloud.google.com/vision/),\n[TensorFlow Lite](https://www.tensorflow.org/mobile/tflite/), and the\n[Android Neural Networks API](https://developer.android.com/ndk/guides/neuralnetworks/)\ntogether in a single SDK. Whether you need the power of cloud-based processing,\nthe real-time capabilities of mobile-optimized on-device models, or the\nflexibility of custom TensorFlow Lite models, ML Kit makes it possible with\njust a few lines of code.\n\nWhat features are available on device or in the cloud?\n\n| Feature | On-device | Cloud |\n|---------------------------------------------------------------|-----------|-------|\n| [Text recognition](/docs/ml-kit/recognize-text) | | |\n| [Face detection](/docs/ml-kit/detect-faces) | | |\n| [Barcode scanning](/docs/ml-kit/read-barcodes) | | |\n| [Image labeling](/docs/ml-kit/label-images) | | |\n| [Object detection \\& tracking](/docs/ml-kit/object-detection) | | |\n| [Landmark recognition](/docs/ml-kit/recognize-landmarks) | | |\n| [Language identification](/docs/ml-kit/identify-languages) | | |\n| [Translation](/docs/ml-kit/translation) | | |\n| [Smart Reply](/docs/ml-kit/generate-smart-replies) | | |\n| [AutoML model inference](/docs/ml-kit/automl-image-labeling) | | |\n| [Custom model inference](/docs/ml-kit/use-custom-models) | | |\n\n| Use of ML Kit to access Cloud ML functionality is subject to the [Google Cloud Platform License\n| Agreement](https://cloud.google.com/terms/) and [Service\n| Specific Terms](https://cloud.google.com/terms/service-terms), and billed accordingly. For billing information, see the Firebase [Pricing](/pricing) page.\n\nImplementation path\n\n|---|---------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| | Integrate the SDK | Quickly include the SDK using Gradle or CocoaPods. |\n| | Prepare input data | For example, if you're using a vision feature, capture an image from the camera and generate the necessary metadata such as image rotation, or prompt the user to select a photo from their gallery. |\n| | Apply the ML model to your data | By applying the ML model to your data, you generate insights such as the emotional state of detected faces or the objects and concepts that were recognized in the image, depending on the feature you used. Use these insights to power features in your app like photo embellishment, automatic metadata generation, or whatever else you can imagine. |\n\nNext steps\n\n- Explore the ready-to-use APIs: [text recognition](/docs/ml-kit/recognize-text), [face detection](/docs/ml-kit/detect-faces), [barcode scanning](/docs/ml-kit/read-barcodes), [image labeling](/docs/ml-kit/label-images), [object detection \\& tracking](/docs/ml-kit/object-detection), [landmark recognition](/docs/ml-kit/recognize-landmarks), [Smart Reply](/docs/ml-kit/generate-smart-replies), [translation](/docs/ml-kit/translation), and [language identification](/docs/ml-kit/identify-languages).\n- Train your own image labeling model with [AutoML Vision Edge](/docs/ml-kit/automl-image-labeling).\n- Learn about using mobile-optimized [custom models](/docs/ml-kit/use-custom-models) in your app."]]
