WOLFRAM

Wolfram Language & System Documentation Center

ImageBoundingBoxes[image]

gives an association of lists of bounding boxes for each identified category of objects in image.

ImageBoundingBoxes[image,category]

gives a list of bounding boxes for subimages identified as an instance of the specified category.

ImageBoundingBoxes[video,…]

gives a time series of detected bounding boxes in frames of video.

Details and Options
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Data  
Categories  
Options  
AcceptanceThreshold  
MaxFeatures  
MaxOverlapFraction  
TargetDevice  
Properties & Relations  
Interactive Examples  
See Also
Related Guides
History
Cite this Page

ImageBoundingBoxes

ImageBoundingBoxes[image]

gives an association of lists of bounding boxes for each identified category of objects in image.

ImageBoundingBoxes[image,category]

gives a list of bounding boxes for subimages identified as an instance of the specified category.

ImageBoundingBoxes[video,…]

gives a time series of detected bounding boxes in frames of video.

Details and Options

  • ImageBoundingBoxes attempts to find instances of an object category present in an image.
  • For each category, the result is given as a list of Rectangle objects.
  • Coordinates are assumed to be in the standard image coordinate system.
  • Possible forms for category include:
  • "concept"named concept, as used in "Concept" entities
    "word"English word, as used in WordData
    wordspecword sense specification, as used in WordData
    Entity[…]any appropriate entity
    category1|category2|…any of the categoryi
  • The following options can be given:
  • AcceptanceThreshold Automaticidentification acceptance threshold
    MaxFeatures Automaticmaximum number of subimages to return
    MaxOverlapFraction Automaticmaximum bounding box overlap
    TargetDevice "CPU"the target device on which to compute
  • ImageBoundingBoxes uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.
  • ImageBoundingBoxes may download resources that will be stored in your local object store at $LocalBase, and can be listed using LocalObjects[] and removed using ResourceRemove.

Examples

open all close all

Basic Examples  (1)

Find the bounding boxes around identified birds in an image:

Wolfram Language code: i = [image];
Wolfram Language code: ImageBoundingBoxes[i, Entity["Species", "Class:Aves"]]

Highlight the identified bounding boxes:

Wolfram Language code: HighlightImage[i, %]

Scope  (4)

Data  (2)

Detect all objects in an image:

Wolfram Language code: i = [image];
Wolfram Language code: ImageBoundingBoxes[i]

Highlight detected objects:

Wolfram Language code: HighlightImage[[image], %]

Detect instances of a specific object:

Wolfram Language code: ImageBoundingBoxes[[image], Entity["Concept", "Auto::p735c"]]

Highlight detected instances:

Wolfram Language code: HighlightImage[[image], %]

Detect objects in frames of video:

Wolfram Language code: ts = ImageBoundingBoxes[\!\(\*VideoBox["![Embedded Video Player](video://content-k8ee4)"]\), Entity["Concept", "Auto::p735c"]]

Highlight detected objects on the video frames:

Wolfram Language code: HighlightVideo[\!\(\*VideoBox["![Embedded Video Player](video://content-k8ee4)"]\), %]

Categories  (2)

Find all the detectable objects in an image:

Wolfram Language code: ImageBoundingBoxes[[image]]

Find all birds in the image:

Wolfram Language code: ImageBoundingBoxes[[image], Entity["Species", "Class:Aves"]]

Options  (4)

AcceptanceThreshold  (1)

Objects with low probability are not returned:

Wolfram Language code: i = [image];
Wolfram Language code: ImageBoundingBoxes[i, Entity["Concept", "Wineglass::w5dj5"]]

Allowing a lower probability may result in more objects being recognized:

Wolfram Language code: ImageBoundingBoxes[i, Entity["Concept", "Wineglass::w5dj5"], AcceptanceThreshold -> .1]
Wolfram Language code: HighlightImage[i, {Red, %, Blue, %%}]

MaxFeatures  (1)

By default, all the detected objects are returned:

Wolfram Language code: i = [image];
Wolfram Language code: ImageBoundingBoxes[i, Entity["Concept", "Wineglass::w5dj5"]]

Specify a maximum number of results:

Wolfram Language code: ImageBoundingBoxes[i, Entity["Concept", "Wineglass::w5dj5"], MaxFeatures -> 2]

MaxOverlapFraction  (1)

The detected bounding boxes may overlap each other:

Wolfram Language code: i = [image];
Wolfram Language code: ImageBoundingBoxes[i, Entity["Concept", "Wineglass::w5dj5"]]
Wolfram Language code: HighlightImage[i, %]

Find only non-intersecting objects:

Wolfram Language code: ImageBoundingBoxes[i, Entity["Concept", "Wineglass::w5dj5"], MaxOverlapFraction -> 0]
Wolfram Language code: HighlightImage[i, %]

TargetDevice  (1)

By default, the function is evaluated on CPU:

Wolfram Language code: i = [image];
Wolfram Language code: ImageBoundingBoxes[i, Entity["Concept", "Wineglass::w5dj5"]]//AbsoluteTiming

Use the TargetDevice option to specify a different device:

Wolfram Language code: ImageBoundingBoxes[i, Entity["Concept", "Wineglass::w5dj5"], TargetDevice -> "GPU"]//AbsoluteTiming

Properties & Relations  (1)

ImageBoundingBoxes is equivalent to ImageCases[image, All -> "BoundingBox"]:

Wolfram Language code: ImageBoundingBoxes[[image]]
Wolfram Language code: ImageCases[[image], All -> "BoundingBox"]

Interactive Examples  (1)

Dynamically locate an object in an image:

Wolfram Language code: Dynamic@HighlightImage[CurrentImage[], ImageBoundingBoxes[#, "person"]&]
Wolfram Research (2019), ImageBoundingBoxes, Wolfram Language function, https://reference.wolfram.com/language/ref/ImageBoundingBoxes.html (updated 2025).

Text

Wolfram Research (2019), ImageBoundingBoxes, Wolfram Language function, https://reference.wolfram.com/language/ref/ImageBoundingBoxes.html (updated 2025).

CMS

Wolfram Language. 2019. "ImageBoundingBoxes." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2025. https://reference.wolfram.com/language/ref/ImageBoundingBoxes.html.

APA

Wolfram Language. (2019). ImageBoundingBoxes. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/ImageBoundingBoxes.html

BibTeX

@misc{reference.wolfram_2026_imageboundingboxes, author="Wolfram Research", title="{ImageBoundingBoxes}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/ImageBoundingBoxes.html}", note=[Accessed: 13-June-2026]}

BibLaTeX

@online{reference.wolfram_2026_imageboundingboxes, organization={Wolfram Research}, title={ImageBoundingBoxes}, year={2025}, url={https://reference.wolfram.com/language/ref/ImageBoundingBoxes.html}, note=[Accessed: 13-June-2026]}