How-to guides

- [### Before you begin
  Perform all steps to enable and use the
  Vision API on the Google Cloud console.](https://docs.cloud.google.com/vision/docs/before-you-begin)
- [### Detect text in images (OCR)
  Run optical character recognition on an image to locate
  and extract UTF-8 text in an image.](https://docs.cloud.google.com/vision/docs/ocr)
- [### Detect handwriting in images (OCR)
  Run optical character recognition on an image to locate
  and extract handwritten text in an image.](https://docs.cloud.google.com/vision/docs/handwriting)
- [### Detect text in files (OCR - PDF/TIFF)
  Run dense text document optical character recognition
  to locate
  and extract text in a file.](https://docs.cloud.google.com/vision/docs/pdf)
- [### Detect crop hints
  Learn how to run crop hints on an image.](https://docs.cloud.google.com/vision/docs/detecting-crop-hints)
- [### Detect faces
  Learn how to perform image face detection.](https://docs.cloud.google.com/vision/docs/detecting-faces)
- [### Detect image properties
  Run image property detection to extract information
  such as dominant image colors.](https://docs.cloud.google.com/vision/docs/detecting-properties)
- [### Detect labels
  Learn how to get general labels about image content.](https://docs.cloud.google.com/vision/docs/labels)
- [### Detect landmarks
  Learn how to perform landmark detection on an image.](https://docs.cloud.google.com/vision/docs/detecting-landmarks)
- [### Detect logos
  Learn how to perform logo detection on an image.](https://docs.cloud.google.com/vision/docs/detecting-logos)
- [### Detect multiple objects
  Learn how to locate multiple objects in an image.](https://docs.cloud.google.com/vision/docs/object-localizer)
- [### Detect explicit content (SafeSearch)
  Learn how to perform explicit content (SafeSearch) detection
  on an image.
  Targeted categories include: `adult`, `spoof`, `medical`, `violence`, and `racy`.](https://docs.cloud.google.com/vision/docs/detecting-safe-search)
- [### Detect Web entities and pages
  Learn how to detect web entities and pages related to an image. Responses
  include information such as full matching images, partial matching images,
  similar images, and best guess label(s).](https://docs.cloud.google.com/vision/docs/detecting-web)
- [### Batch image annotation offline
  Get image annotations for all feature types on a batch of images. The
  results of this long-running (asynchronous) operation are stored in a
  Cloud Storage
  bucket when the operation completes.](https://docs.cloud.google.com/vision/docs/batch)
- [### Small batch file annotation online
  Get file annotations online (synchronously) for a small batch
  (up to 5 pages) of PDF/TIFF/GIF files.](https://docs.cloud.google.com/vision/docs/file-small-batch)
- [### Batch file annotation offline
  Get file annotations for all feature types on a multi-paged PDF/TIFF file.
  The results of this long-running (asynchronous) operation are stored in a
  Cloud Storage bucket when the operation completes.](https://docs.cloud.google.com/vision/docs/file-batch)
- [### Using Cloud Vision with Spring framework
  Instructions on using the Spring framework and
  Spring Cloud Google Cloud to interact with Vision API.](https://docs.cloud.google.com/vision/docs/adding-spring)
- [### Base64 Encode
  Instructions on base64-encoding for sending a local image.](https://docs.cloud.google.com/vision/docs/base64)