WOLFRAM

Wolfram Language & System Documentation Center

"FacialAge" (Built-in Classifier)

Estimate a person's age from a face in the image.

Classes

Details

  • The classifier is applied to the largest face found in the image.
  • The classifier is based on the MobileNet Model Trained on UTKFace Large-Scale Face Dataset.
  • The classifier may download resources that will be stored in your local object store at $LocalBase, and that can be listed using LocalObjects[] and removed using ResourceRemove.

Examples

open all close all

Basic Examples  (2)

Determine the age of a person:

Wolfram Language code: Classify["FacialAge", [image]]

Obtain the probabilities for the 3 most likely ages:

Wolfram Language code: Classify["FacialAge"][[image], "TopProbabilities" -> 3]

Obtain a ClassifierFunction for this classifier:

Wolfram Language code: c = Classify["FacialAge"]

Use the classifier function to find the age from an image:

Wolfram Language code: c[[image]]

Find the age of many examples at once:

Wolfram Language code: c[{[image], [image]}]

Scope  (2)

Find faces in an image:

Wolfram Language code: img = [image];
Wolfram Language code: faces = ImageTrim[img, #]& /@ FindFaces[img]

Use the classifier on each face:

Wolfram Language code: Classify["FacialAge", faces]

Load the ClassifierFunction corresponding to the built-in classifier:

Wolfram Language code: c = Classify["FacialAge"]

Obtain the possible classes:

Wolfram Language code: Information[c, "Classes"]

Options  (2)

ClassPriors  (1)

Use a custom ClassPriors to restrict the possible outputs:

Wolfram Language code: Classify["FacialAge", [image], ClassPriors -> <|45 -> 0.5, 46 -> 0.5|>]

IndeterminateThreshold  (1)

Use a custom IndeterminateThreshold:

Wolfram Language code: Classify["FacialAge", [image], IndeterminateThreshold -> 0.6]