Tutorials

Single-feature tutorials

• Crop hints tutorial

  Return an optimized cropped image.

• Dense document text detection (OCR) tutorial

  Return text annotations from a dense text document.

• Face detection tutorial

  Perform image face detection.

• Web detection tutorial

  Search the Internet to return image-related information, including web entities, matching pages, and fully- and partially matching image URLs.

Multiple-feature / multiple-product tutorials

• Detect and translate image text with Cloud Storage, Vision, Translation, Cloud Run functions, and Pub/Sub

  Read Cloud Run functions documentation to learn how to use Cloud Storage, Cloud Vision, Cloud Translation, Cloud Run functions, and Pub/Sub to upload images, extract text from the images, translate the text, and save the translations.

• Translating and speaking text from a photo

  Read Cloud Translation documentation to learn how to detect text in a photo, personalize a translation of the detected text, and generate synthetic audio of the translated text.

• Codelab: Use the Vision API with C# (label, text/OCR, landmark, and face detection)

  Learn how to set up your environment, authenticate, install the C# client library, and send requests for the following features: label detection, text detection (OCR), landmark detection, and face detection (external link).

• Codelab: Use the Vision API with Python (label, text/OCR, landmark, and face detection)

  Learn how to set up your environment, authenticate, install the Python client library, and send requests for the following features: label detection, text detection (OCR), landmark detection, and face detection (external link).

Sample applications

• View sample applications.

  View several specific applications using the Vision API.