Visitar URL original
ImageIdentify: Classify an image into a category of objects, scenes, etc.—Wolfram Documentation

WOLFRAM

Wolfram Language & System Documentation Center

ImageIdentify[image]

yields the result of attempting to identify what image is a picture of.

ImageIdentify[image,category]

restricts the identification of image to objects within the specified category.

ImageIdentify[image,category,n]

gives a list of up to n possible identifications.

ImageIdentify[image,category,n,"prop"]

gives the specified property for each identification.

ImageIdentify[video,…]

returns a time series of identifications for video frames.

Details and Options
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Options  
AcceptanceThreshold  
PerformanceGoal  
SpecificityGoal  
Properties & Relations  
Possible Issues  
Neat Examples  
See Also
Related Guides
Related Links
History
Cite this Page

ImageIdentify

ImageIdentify[image]

yields the result of attempting to identify what image is a picture of.

ImageIdentify[image,category]

restricts the identification of image to objects within the specified category.

ImageIdentify[image,category,n]

gives a list of up to n possible identifications.

ImageIdentify[image,category,n,"prop"]

gives the specified property for each identification.

ImageIdentify[video,…]

returns a time series of identifications for video frames.

Details and Options

  • ImageIdentify[{image1,image2,…},…] can be used to identify objects in multiple images.
  • In ImageIdentify[image,category], possible forms for category include:
  • "type"entity type, as used in Interpreter
    "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
  • By default, ImageIdentify returns objects of the form Entity["Concept",…].
  • The property "prop" can be one of the following:
  • "Concept"a concept entity object
    "Entity"when possible, a concrete entity object
    "Probability"an association of concepts and probabilities
    "cprop"a property supported by "Concept" entities
    {prop1,…}a list of property specifications
  • The following options can be given:
  • AcceptanceThreshold Automaticidentification acceptance threshold
    PerformanceGoal Automaticwhat to optimize in the identification
    SpecificityGoal Automaticwhat specificity of object type to seek
    TargetDevice"CPU"the target device on which to compute
  • Possible settings for PerformanceGoal include "Speed" and "Quality".
  • Possible settings for SpecificityGoal include:
  • "Low"favor general categories of objects
    "High"favor specific kinds of objects
    sspecificity between 0 (lowest) and 1 (highest)
  • When no content is found at an acceptable threshold, Missing["Unidentified"] is returned.
  • ImageIdentify uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.
  • ImageIdentify 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  (2)

Identify the object present in the image:

Wolfram Language code: ImageIdentify[[image]]

Identify what type of dog is present in the image:

Wolfram Language code: ImageIdentify[[image], Entity["Species", "Infraspecies:CanisLupusFamiliaris"]]

Scope  (4)

Return a result in a specific category:

Wolfram Language code: ImageIdentify[[image], Entity["Concept", "Fruit::855t9"]]

Return a list of results:

Wolfram Language code: ImageIdentify[[image], All, 6]

Return a list of results and their associated probability:

Wolfram Language code: ImageIdentify[[image], Entity["Concept", "Fruit::855t9"], 10, "Probability"]

Return multiple properties:

Wolfram Language code: ImageIdentify[[image], Entity["Concept", "Fruit::855t9"], 10, {"Entity", "Probability", "Definition"}]//Dataset

Options  (4)

AcceptanceThreshold  (1)

The AcceptanceThreshold is selected automatically:

Wolfram Language code: ImageIdentify[[image]]

Specify a custom threshold:

Wolfram Language code: ImageIdentify[[image], AcceptanceThreshold -> .99]

If no identification is above the threshold, a Missing object is returned:

Wolfram Language code: ImageIdentify[[image], AcceptanceThreshold -> 1]

PerformanceGoal  (1)

Use PerformanceGoal"Speed" to get a result as fast as possible:

Wolfram Language code: ImageIdentify[[image], PerformanceGoal -> "Speed"]//AbsoluteTiming

Use a slower, more accurate recognition:

Wolfram Language code: ImageIdentify[[image], PerformanceGoal -> "Quality"]//AbsoluteTiming

SpecificityGoal  (2)

Privilege a result with a low specificity:

Wolfram Language code: ImageIdentify[[image], SpecificityGoal -> "Low"]

Privilege a result with a high specificity:

Wolfram Language code: ImageIdentify[[image], SpecificityGoal -> "High"]

Use a custom value:

Wolfram Language code: ImageIdentify[[image], SpecificityGoal -> 0]

Get a table of identifications for different values of specificity:

Wolfram Language code: DeleteDuplicatesBy[Table[{s, ImageIdentify[[image], SpecificityGoal -> s]}, {s, 0, 1, .1}], Last]

Properties & Relations  (2)

The neural net used by ImageIdentify can be accessed using NetModel:

Wolfram Language code: net = NetModel["Wolfram ImageIdentify Net V2"]
Wolfram Language code: net[[image], "TopProbabilities"]

In order to detect and recognize objects in an image, use ImageCases:

Wolfram Language code: ImageCases[[image]]

Possible Issues  (1)

If a recognition category is specified, probabilities are renormalized in that category:

Wolfram Language code: ImageIdentify[[image], "tree", 3, "Probability"]

Remove the category constraint to recognize the object correctly:

Wolfram Language code: ImageIdentify[[image], All, 3, "Probability"]

Neat Examples  (1)

Get 10 different identifications, along with their probabilities:

Wolfram Language code: data = ImageIdentify[[image], All, 10, "Probability"]

Visualize the result of object identification using a WordCloud:

Wolfram Language code: WordCloud[data]
Wolfram Research (2015), ImageIdentify, Wolfram Language function, https://reference.wolfram.com/language/ref/ImageIdentify.html (updated 2025).

Text

Wolfram Research (2015), ImageIdentify, Wolfram Language function, https://reference.wolfram.com/language/ref/ImageIdentify.html (updated 2025).

CMS

Wolfram Language. 2015. "ImageIdentify." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2025. https://reference.wolfram.com/language/ref/ImageIdentify.html.

APA

Wolfram Language. (2015). ImageIdentify. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/ImageIdentify.html

BibTeX

@misc{reference.wolfram_2026_imageidentify, author="Wolfram Research", title="{ImageIdentify}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/ImageIdentify.html}", note=[Accessed: 14-November-2026]}

BibLaTeX

@online{reference.wolfram_2026_imageidentify, organization={Wolfram Research}, title={ImageIdentify}, year={2025}, url={https://reference.wolfram.com/language/ref/ImageIdentify.html}, note=[Accessed: 14-November-2026]}