Mit Sammlungen den Überblick behalten
Sie können Inhalte basierend auf Ihren Einstellungen speichern und kategorisieren.
Bildlabel
plat_iosplat_android
Mit den Bild-Labeling-APIs von Cloud Vision können Sie Entitäten in
ohne zusätzliche kontextbezogene Metadaten angeben zu müssen.
Durch die Bildbeschriftung erhalten Sie Einblick in den Inhalt von Bildern. Wenn Sie die
API erhalten Sie eine Liste der erkannten Entitäten: Personen, Dinge,
Orte, Aktivitäten usw. Jedes gefundene Label hat einen Wert,
gibt an, wie sicher das ML-Modell in Bezug auf seine Relevanz hat. Damit
Informationen enthalten, können Sie Aufgaben wie die automatische Metadatengenerierung durchführen.
und Inhaltsmoderation.
Die Image Labeling API von Firebase ML wird von Google Cloud unterstützt
branchenführenden Bilderkennungsfunktionen,
mit über 10.000 Labels in vielen Kategorien. (Siehe unten.)
Zusätzlich zur Textbeschreibung jedes Labels, die Firebase ML
gibt es auch die Google Knowledge Graph-Entitäts-ID des Labels zurück.
Diese ID ist ein String, der die durch
das Label enthält, und es handelt sich um dieselbe ID, die vom
Knowledge Graph Search API
Sie können diesen String verwenden, um eine Entität sprachübergreifend zu identifizieren.
unabhängig von der Formatierung der Textbeschreibung.
[[["Leicht verständlich","easyToUnderstand","thumb-up"],["Mein Problem wurde gelöst","solvedMyProblem","thumb-up"],["Sonstiges","otherUp","thumb-up"]],[["Benötigte Informationen nicht gefunden","missingTheInformationINeed","thumb-down"],["Zu umständlich/zu viele Schritte","tooComplicatedTooManySteps","thumb-down"],["Nicht mehr aktuell","outOfDate","thumb-down"],["Problem mit der Übersetzung","translationIssue","thumb-down"],["Problem mit Beispielen/Code","samplesCodeIssue","thumb-down"],["Sonstiges","otherDown","thumb-down"]],["Zuletzt aktualisiert: 2025-07-25 (UTC)."],[],[],null,["Image Labeling \nplat_ios plat_android \n\nWith Cloud Vision's image labeling APIs, you can recognize entities in\nan image without having to provide any additional contextual metadata.\n\nImage labeling gives you insight into the content of images. When you use the\nAPI, you get a list of the entities that were recognized: people, things,\nplaces, activities, and so on. Each label found comes with a score that\nindicates the confidence the ML model has in its relevance. With this\ninformation, you can perform tasks such as automatic metadata generation\nand content moderation.\n\n\u003cbr /\u003e\n\nReady to get started? Choose your platform:\n\n[iOS+](/docs/ml/ios/label-images)\n[Android](/docs/ml/android/label-images)\n\n\u003cbr /\u003e\n\n| **Want to label images with your own categories?** Train your own image labeling models with [AutoML Vision Edge](/docs/ml/automl-image-labeling).\n| **Looking for on-device image labeling?** Try the [standalone ML Kit library](https://developers.google.com/ml-kit/vision/image-labeling).\n\nKey capabilities\n\n|--------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| High-accuracy image labeling | Firebase ML's image labeling API is powered by Google Cloud's industry-leading image understanding capability, which can classify images with 10,000+ labels in many categories. (See below.) Try it yourself with the [Cloud Vision API demo](https://cloud.google.com/vision/docs/drag-and-drop). |\n| Knowledge Graph entity support | In addition the text description of each label that Firebase ML returns, it also returns the label's Google Knowledge Graph entity ID. This ID is a string that uniquely identifies the entity represented by the label, and is the same ID used by the [Knowledge Graph Search API](https://developers.google.com/knowledge-graph/). You can use this string to identify an entity across languages, and independently of the formatting of the text description. |\n| Limited no-cost use | No-cost for first 1000 uses of this feature per month: see [Pricing](/pricing) |\n\nExample labels\n\nThe image labeling API supports 10,000+ labels, including the following examples\nand many more:\n\n| Category | Example labels | Category | Example labels |\n|------------------------|------------------------------------------|----------------------|-----------------------------------------------|\n| Arts \\& entertainment | `Sculpture` `Musical Instrument` `Dance` | Astronomical objects | `Comet` `Galaxy` `Star` |\n| Business \\& industrial | `Restaurant` `Factory` `Airline` | Colors | `Red` `Green` `Blue` |\n| Design | `Floral` `Pattern` `Wood Stain` | Drink | `Coffee` `Tea` `Milk` |\n| Events | `Meeting` `Picnic` `Vacation` | Fictional characters | `Santa Claus` `Superhero` `Mythical creature` |\n| Food | `Casserole` `Fruit` `Potato chip` | Home \\& garden | `Laundry basket` `Dishwasher` `Fountain` |\n| Activities | `Wedding` `Dancing` `Motorsport` | Materials | `Ceramic` `Textile` `Fiber` |\n| Media | `Newsprint` `Document` `Sign` | Modes of transport | `Aircraft` `Motorcycle` `Subway` |\n| Occupations | `Actor` `Florist` `Police` | Organisms | `Plant` `Animal` `Fungus` |\n| Organizations | `Government` `Club` `College` | Places | `Airport` `Mountain` `Tent` |\n| Technology | `Robot` `Computer` `Solar panel` | Things | `Bicycle` `Pipe` `Doll` |\n\nExample results Photo: Clément Bucco-Lechat / Wikimedia Commons / CC BY-SA 3.0\n\n| Label | Knowledge Graph entity ID | Confidence |\n|-------------------------|---------------------------|------------|\n| sport venue | /m/0bmgjqz | 0.9860726 |\n| player | /m/02vzx9 | 0.9797604 |\n| stadium | /m/019cfy | 0.9635762 |\n| soccer specific stadium | /m/0404y4 | 0.95806926 |\n| football player | /m/0gl2ny2 | 0.9510419 |\n| sports | /m/06ntj | 0.9253524 |\n| soccer player | /m/0pcq81q | 0.9033665 |\n| arena | /m/018lrm | 0.8897188 |"]]
