![]() ![]() For example, a 'bulldog' would have a parent of 'dog'.Īpproximate location of the detected object.Īn object describing a face identified in the image. ![]() The parent object is a more generic form of this object. The parent object, from a taxonomy perspective. NameĪ message explaining the error reported by the service.Ĭonfidence score of having observed the brand in the image, as a value ranging from 0 to 1.Īpproximate location of the detected brand.Ĭonfidence score of having observed the object in the image, as a value ranging from 0 to 1. NameĪ value indicating if the image is black and white.ĭetails about the API request error. Location of the identified face in the image.Īn object providing additional metadata describing color attributes. NameĬonfidence level for the celebrity recognition as a value ranging from 0 to 1. NameĪn array of celebrities if any identified.Īn object describing possible celebrity identification. NameĪn object describing additional category details. Y-coordinate of the top left point of the area, in pixels.Īn object describing identified category. X-coordinate of the top left point of the area, in pixels. Width measured from the top-left point of the area, in pixels. Height measured from the top-left point of the area, in pixels. Score from 0 to 1 that indicates how suggestive is the image.Ī bounding box for an area inside an image. Score from 0 to 1 that indicates how gory is the image.Ī value indicating if the image contains adult-oriented content. Score from 0 to 1 that indicates how much the content is considered adult-oriented within the image. ![]() a brief description of what the image depicts.Ī collection of content tags, along with a list of captions sorted by confidence level, and image metadata.Īn entity observation in the image, along with the confidence score.Īn object providing possible image types and matching confidence levels.Īn object describing whether the image contains adult-oriented content and/or is racy. "requestId": "0dbec5ad-a3d3-4f7e-96b4-dfd57efe967d",Īn object describing whether the image contains adult-oriented content and/or is racy.Ī bounding box for an area inside an image.Īn object describing identified category.Īn object describing additional category details.Īn object describing possible celebrity identification.Īn object providing additional metadata describing color attributes.Īn object describing a face identified in the image.Īn image caption, i.e. "text": "Satya Nadella sitting on a bench", LineDrawingTypeNon - LineDrawing = 0, LineDrawing = 1. Non - clipart = 0, ambiguous = 1, normal - clipart = 2, good - clipart = 3. Here is the definitions for enumeration types: The response include the extracted features in JSON format. The Brands argument is only available in English. Brands - detects various brands within an image, including the approximate location. The Objects argument is only available in English. Objects - detects various objects within an image, including the approximate location. Sexually suggestive content (aka racy content) is also detected. Adult - detects if the image is pornographic in nature (depicts nudity or a sex act), or is gory (depicts extreme violence or blood). Color - determines the accent color, dominant color, and whether an image is black&white. ImageType - detects if image is clipart or a line drawing. If present, generate coordinates, gender and age. Description - describes the image content with a complete English sentence. Tags - tags the image with a detailed list of words related to the image content. Valid visual feature types include: Categories - categorizes image content according to a taxonomy defined in documentation. Multiple values should be comma-separated. A string indicating what visual feature types to return. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |