Built-in Object Recognition

Semantic object detection allows you to find instances of a specific object appearing in an image. Version 12 comes with a complete family of object detection functions.

Return all the identified subimages using ImageCases.

Extract the object bounding boxes with ImageBoundingBoxes and use them to highlight the original image.

Track the position of specific objects using ImagePosition.

Check whether the image contains an object category with ImageContainsQ.

Use ImageContents to get an automatic summary of the content of an image.

Highlight the detected objects on the original image.