ImagePosition [image]
gives an association of image positions for each identified category of objects in image.
ImagePosition [image,obj]
gives a list of image positions for subimages identified as instances of the specified category.
ImagePosition [video,…]
gives a time series of detected object positions in frames of video.
ImagePosition
ImagePosition [image]
gives an association of image positions for each identified category of objects in image.
ImagePosition [image,obj]
gives a list of image positions for subimages identified as instances of the specified category.
ImagePosition [video,…]
gives a time series of detected object positions in frames of video.
Details and Options
- ImagePosition attempts to find instances of an object category present in an image and returns a list of {x,y} positions.
- Coordinates {x,y} 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 WordDatawordspec word sense specification, as used in WordDatacategory1|category2|… any of the categoryi
- The following options can be given:
-
- ImagePosition uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.
- ImagePosition 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 allBasic Examples (1)
Find the image positions of birds in an image:
Scope (4)
Data (2)
Detect all objects in an image:
Highlight detected objects:
Detect instances of a specific object:
Highlight detected instances:
Detect objects in frames of video:
Highlight detected objects on the video frames:
Categories (2)
Find all the detectable objects in an image:
Find all birds in the image:
Options (4)
AcceptanceThreshold (1)
Objects with low probability are not returned:
Allowing a lower probability may result in more objects being recognized:
MaxFeatures (1)
By default, all the detected objects are returned:
Specify a maximum number of results:
MaxOverlapFraction (1)
The detected bounding boxes may overlap each other:
Find only non-intersecting objects:
TargetDevice (1)
By default, the function is evaluated on CPU:
Use the TargetDevice option to specify a different device:
Properties & Relations (1)
ImagePosition is equivalent to ImageCases [image, All -> "Position"]:
Related Guides
Text
Wolfram Research (2019), ImagePosition, Wolfram Language function, https://reference.wolfram.com/language/ref/ImagePosition.html (updated 2025).
CMS
Wolfram Language. 2019. "ImagePosition." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2025. https://reference.wolfram.com/language/ref/ImagePosition.html.
APA
Wolfram Language. (2019). ImagePosition. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/ImagePosition.html
BibTeX
@misc{reference.wolfram_2025_imageposition, author="Wolfram Research", title="{ImagePosition}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/ImagePosition.html}", note=[Accessed: 17-November-2025]}
BibLaTeX
@online{reference.wolfram_2025_imageposition, organization={Wolfram Research}, title={ImagePosition}, year={2025}, url={https://reference.wolfram.com/language/ref/ImagePosition.html}, note=[Accessed: 17-November-2025]}