WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

ImageCases
✖
ImageCases

Updatedshow changeshide changes[Experimental]

✖
ImageCases[image]

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

✖
ImageCases[image,category]

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

✖
ImageCases[image,categoryprop]

gives the specified property prop for each identified subimage.

✖
ImageCases[image,{category1,category2,…}]

gives an association with lists of subimages identified as being instances of each of the categoryi.

✖
ImageCases[video,…]

gives a time series of detected objects in frames of video.

Details and Options

  • ImageCases is also known as object detection and attempts to find instances of an object category present in an image and returns a list of subimages per category.
  • 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 property prop can be any of the following:
  • "BoundingBox"the bounding box given as a Rectangle
    "Confidence"confidence of the identification
    "Dimensions"width and height of the subimage
    "Image"the identified subimage (default)
    "Position"center of the identified bounding box
    {prop1,prop2,…}a list of properties
  • Masked subimage properties:
  • "Mask"binary mask indicating the object
    "MaskBoundingBox"the bounding box of the masked image
    "MaskCentroid"centroid of the mask
    "MaskedImage"subimage masked by the component shape
    "MaskMedoid"medoid of the mask
    "MaskPosition"center of the mask bounding box
  • The following options can be given:
  • AcceptanceThreshold Automaticidentification acceptance threshold
    MaxFeatures Automaticmaximum number of subimages to return
    MaxOverlapFraction Automaticmaximum bounding box overlap
    PerformanceGoal"Balanced"aspects of performance to try to optimize
    TargetDevice "CPU"the target device on which to compute
  • ImageCases uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.
  • ImageCases 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 allclose all

Basic Examples  (3)Summary of the most common use cases

Find identified subimages of an image:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-c8mi0q
Out[1]=1

Find subimages identified as a dog:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-z78axq
Out[1]=1

Get the detected and segmented objects of an image:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-pnneyv
Out[1]=1

Scope  (11)Survey of the scope of standard use cases

Data  (2)

Detect objects in an image:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-v82x5d
Out[1]=1

Detect objects in frames of video:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-opf1sv
Out[1]=1

Objects at a given time:

In[2]:=2
✖
https://wolfram.com/xid/0enzd2uuq-lcx641
Out[2]=2

Categories  (2)

Find all the detectable objects in an image:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-viajfy
Out[1]=1

Find all birds in the image:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-l9m5j4
Out[1]=1

Properties  (7)

Find the birds' bounding boxes:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-uzx6q8
Out[1]=1

Return multiple properties:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-zlmoeb
Out[1]=1

Query properties of the concept:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-ns5hpx
Out[1]=1

Group together the detection for multiple categories:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-2vy3ub
Out[1]=1

Return the specified properties for all the detectable categories:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-ncbbau
Out[1]=1

Get the detected and segmented objects of an image:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-mj18b2
Out[1]=1

Mask of each detected subimage:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-rbc9jc
Out[1]=1

Options  (4)Common values & functionality for each option

AcceptanceThreshold  (1)

Objects with low probability are not returned:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-dsunaa
In[2]:=2
✖
https://wolfram.com/xid/0enzd2uuq-0mxv3l
Out[2]=2

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

In[3]:=3
✖
https://wolfram.com/xid/0enzd2uuq-j2w9ni
Out[3]=3

MaxFeatures  (1)

By default, all the detected objects are returned:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-bvh3ms
In[2]:=2
✖
https://wolfram.com/xid/0enzd2uuq-e3jqww
Out[2]=2

Specify a maximum number of results:

In[3]:=3
✖
https://wolfram.com/xid/0enzd2uuq-qouuhv
Out[3]=3

MaxOverlapFraction  (1)

The detected bounding boxes may overlap each other:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-rnkvfy
In[2]:=2
✖
https://wolfram.com/xid/0enzd2uuq-x2r6r9
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/0enzd2uuq-m5but2
Out[3]=3

Find only non-intersecting objects:

In[4]:=4
✖
https://wolfram.com/xid/0enzd2uuq-x9wjm5
Out[5]=5

TargetDevice  (1)

By default, the function is evaluated on CPU:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-w5dfg6
In[4]:=4
✖
https://wolfram.com/xid/0enzd2uuq-z2ecct
Out[4]=4

Use the TargetDevice option to specify a different device:

In[5]:=5
✖
https://wolfram.com/xid/0enzd2uuq-vf245g
Out[5]=5

Applications  (1)Sample problems that can be solved with this function

Build an image captioning function using the counts of detected objects:

In[1]:=1
✖
https://wolfram.com/xid/0enzd2uuq-uc5ohk
Out[1]=1

Transform the object counts in a string:

In[2]:=2
✖
https://wolfram.com/xid/0enzd2uuq-l2cjpl
Out[2]=2

Package all the code in a function to automatically generate captions:

In[7]:=7
✖
https://wolfram.com/xid/0enzd2uuq-qwekvv
In[8]:=8
✖
https://wolfram.com/xid/0enzd2uuq-njk94v
Out[8]=8

Try the function on a different image:

In[9]:=9
✖
https://wolfram.com/xid/0enzd2uuq-ueq8x8
Out[9]=9

Caption an image with no identified objects:

In[10]:=10
✖
https://wolfram.com/xid/0enzd2uuq-yzinv0
Out[10]=10
Wolfram Research (2019), ImageCases, Wolfram Language function, https://reference.wolfram.com/language/ref/ImageCases.html (updated 2025).
✖
Wolfram Research (2019), ImageCases, Wolfram Language function, https://reference.wolfram.com/language/ref/ImageCases.html (updated 2025).

Text

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

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

CMS

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

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

APA

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

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

BibTeX

@misc{reference.wolfram_2025_imagecases, author="Wolfram Research", title="{ImageCases}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/ImageCases.html}", note=[Accessed: 16-April-2025 ]}

✖
@misc{reference.wolfram_2025_imagecases, author="Wolfram Research", title="{ImageCases}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/ImageCases.html}", note=[Accessed: 16-April-2025 ]}

BibLaTeX

@online{reference.wolfram_2025_imagecases, organization={Wolfram Research}, title={ImageCases}, year={2025}, url={https://reference.wolfram.com/language/ref/ImageCases.html}, note=[Accessed: 16-April-2025 ]}

✖
@online{reference.wolfram_2025_imagecases, organization={Wolfram Research}, title={ImageCases}, year={2025}, url={https://reference.wolfram.com/language/ref/ImageCases.html}, note=[Accessed: 16-April-2025 ]}