Vision Entity

Entity

Entity class for holding information returned from annotating an image.

class google.cloud.vision.entity.EntityAnnotation(bounds, description, locale, locations, mid, score)

Bases: object

Representation of an entity returned from the Vision API.

Parameters:

• bounds (dict) – Dictionary of bounary information of detected entity.
• description (str) – Description of entity detected in an image.
• locale (str) – The language code for the locale in which the entity textual description (next field) is expressed.
• locations (list of LocationInformation.) – List of LocationInformation instances.
• mid (str) – Opaque entity ID.
• score (float) – Overall score of the result. Range [0, 1].

bounds

Bounding polygon of detected image feature.

Return type:Bounds Returns:Instance of Bounds with populated vertices.

description

Description of feature detected in image.

Return type:str Returns:String description of feature detected in image.

classmethod from_api_repr(response)

Factory: construct entity from Vision API response.

Parameters:response (dict) – Dictionary response from Vision API with entity data. Return type:EntityAnnotation Returns:Instance of EntityAnnotation.

locale

The language code for text discovered in an image.

Return type:str Returns:String language code of text found in the image.

locations

Location coordinates landmarks detected.

Return type:LocationInformation Returns:LocationInformation populated with latitude and longitude of object detected in an image.

mid

MID of feature detected in image.

Return type:str Returns:String MID of feature detected in image.

score

Overall score of the result. Range [0, 1].

Return type:float Returns:Overall score of the result. Range [0, 1].