Edit

class ImageAnalysis::ContentCaption

Represents a generated phrase that describes the content of the whole image or a region in the image.

Members

Content

Syntax: public std::string Content;

A generated phrase that describes the content of the whole image or a region in the image.

Confidence

Syntax: public double Confidence;

A score, in the range of 0 to 1, representing the confidence that this description is accurate.

Confidence scores span the range of 0.0 to 1.0 (inclusive), with higher values indicating higher probability.

BoundingBox

Syntax: public Rectangle BoundingBox;

A rectangular boundary to which the caption applies.

Coordinates are are in pixels, with (0,0) being the top-left of the source image. For the ImageAnalysisFeature::Caption result, this will be the whole image. For the ImageAnalysisFeature::DenseCaption result, this will either be the whole image or a region within the image.