Vision technique that, for every instance of an object, gives back a label, a confidence score and bounding-box coordinates, making it possible to find and count several objects or classes in an image.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Object detection in context, with comparison tables and the common traps.
Terms in this definition
- Route table label
Name for a set of route tables in Virtual WAN hubs, used when choosing where routes propagate; Default, for instance, covers the defaultRouteTable of every hub.
- Confidence score
Value between 0 and 1 attached to every prediction or extracted field to express the model's certainty; unlike accuracy, it isn't measured across a test set.
- COUNT
A DAX function returning how many non-blank numbers, dates or text values a column contains. Boolean columns need COUNTA instead, and for counting the rows of a table COUNTROWS is the better choice.
Related terms
- Bounding box
The x, y, width and height pixel coordinates marking where a detected object sits in an image; object detection outputs them, whereas image classification doesn't.
- Image type detection
A feature only in Image Analysis 3.2 that flags line drawings and scores clip art from 0 to 3. Descriptions and object detection do not determine image type.