ImageUnderstandingIndexingImageRegion

Posted on by Darth Emmett

GoogleApi.ContentWarehouse.V1.Model.ImageUnderstandingIndexingImageRegion

Table of Contents ▼

Jump to a specific part of the page:

Description

Image region produced by a detector.

Attributes List

This module has the following attributes (case-insensitive ascending order):

View Attributes

Attributes

  1. box (type: GoogleApi.ContentWarehouse.V1.Model.PhotosVisionGroundtruthdbNormalizedBoundingBox, default: nil)
    - Bounding box normalized to [0,1] scale independent on the image size. For example if the original image has the size 1600x1200, the rectangle [200, 200, 800, 600] from the image would have a normalized bounding box [1/8, 1/6, 1/2, 1/2].
  2. score (type: number(), default: nil)
    - Box confidence score. This is used to store the confidence of the box proposal, not the score associated with any specific labels. The box proposal confidence score is a float number per region between [0, 1] indicating how likely a box contains an "object".
  3. version (type: String.t, default: nil)
    -

Type

@type t() :: %GoogleApi.ContentWarehouse.V1.Model.ImageUnderstandingIndexingImageRegion{
box: GoogleApi.ContentWarehouse.V1.Model.PhotosVisionGroundtruthdbNormalizedBoundingBox.t() | nil,
score: number() | nil,
version: String.t() | nil
}

Function

@spec decode(struct(), keyword()) :: struct()

Data sourced from HexDocs : GoogleApi.ContentWarehouse.V1.Model.ImageUnderstandingIndexingImageRegion