Detecting other features

The Vision API is capable of detecting a wide variety of features in your images.

Optical character recognition and labels are covered in more detail on their respective pages.

Crop hints

Crop hints requests return the coordinates of a bounding box that surrounds the dominant object or face in an image. These coordinates can be used to crop the image to feature that dominant object.

The crop hints feature type is CROP_HINTS.

Refer to the following documentation for more information:

Faces

Face Detection detects multiple faces within an image and provides coordinates of key facial features. It also returns emotional state predictions (such as joy, anger, and surprise) and whether headwear is being worn.

The face detection feature type is FACE_DETECTION.

Refer to the following documentation for more information:

Image properties

An image properties request returns the dominant colors in the image as RGB values and percent of the total pixel count.

The image properties feature type is IMAGE_PROPERTIES.

Refer to the following documentation for more information:

Landmarks

Landmark requests detect well-known natural and human-made landmarks, and return identifying information such as an entity ID (that may be available in the Google Knowledge Graph), the landmark's name and location, and the bounding box that surrounds the landmark in the image.

The landmarks feature type is LANDMARK_DETECTION.

Refer to the following documentation for more information:

Logos

Logo detection requests detect popular product and corporate logos within an image. The response includes the logo name, an entity ID (that may be referenceable in the Google Knowledge Graph), and the bounding box that surrounds the logo position in the image.

The logo detection feature type is LOGO_DETECTION.

Refer to the following documentation for more information:

Safe Search requests examine an image for potentially unsafe or undesirable content. Likelihood of such imagery is returned in 4 categories:

  • adult indicates content generally suited for 18 years plus, such as nudity, sexual activity, and pornography (including cartoons or anime).

  • spoof indicates content that has been modified from the original to make it funny or offensive.

  • medical indicates content such as surgeries or MRIs.

  • violent indicates violent content, including but not limited to the presence of blood, war images, weapons, injuries, or car crashes.

Likelihood levels are bucketed into 4 categories, ranging from VERY_UNLIKELY to VERY_LIKELY.

The Safe Search feature type is SAFE_SEARCH_DETECTION.

Refer to the following documentation for more information:

Web entities

Web entities requests return information about the contents of the image as they relate to the Google Knowledge Graph, as well as the image's relation to other pages and images on the web.

The response includes entity IDs that are detected (which may be referenceable in the Google Knowledge Graph), web pages that contain this exact image, URLs of exact matches and partial matches on the image, and URLs of visually similar images.

The web entities feature type is WEB_DETECTION.

Refer to the following documentation for more information:

Monitor your resources on the go

Get the Google Cloud Console app to help you manage your projects.

Send feedback about...

Google Cloud Vision API Documentation