captionImage

Caption images using Moondream vision-language model (VLM)

Since R2026a

collapse all in page

    Syntax

    captions = captionImage(mdModel,I)
    captionsDS = captionImage(mdModel,imds)
    [___] = captionImage(___,CaptionVerbosity=verbosity)

    Description

    Add-On Required: This feature requires the Computer Vision Toolbox Model for Moondream Vision Language Model add-on.

    captions = captionImage(mdModel,I) generates a caption for image input I using the Moondream™ vision-language model mdModel.

    captionsDS = captionImage(mdModel,imds) generates captions for images in the input image datastore imds using the Moondream vision-language model mdModel.

    [___] = captionImage(___,CaptionVerbosity=verbosity) specifies the length of the generated captions, in addition to the arguments from previous syntaxes.

    example

    Examples

    collapse all

    This example uses:

    Open Live Script

    Load the Moondream vision-language model.

    mdModel = moondream;

    Load an image to caption into the workspace, and display the image.

    I = imread("peppers.png");
imshow(I)

    Figure contains an axes object. The hidden axes object contains an object of type image.

    Caption the image using the captionImage object function.

    captions = captionImage(mdModel,I);

    Display the generated image caption.

    display(captions)
    captions = 
" A purple tablecloth holds a vibrant array of red, green, yellow, and white peppers, onions, and garlic, arranged in a visually appealing composition."

    This example uses:

    Open Live Script

    Load the Moondream vision-language model.

    mdModel = moondream;

    Load an image to caption into the workspace, and display the image.

    I = imread("visionteam.jpg");
imshow(I)

    Generate a detailed caption for the image by specifying the CaptionVerbosity argument of the captionImage object function.

    captions = captionImage(mdModel,I,CaptionVerbosity="detail");

    Display the generated image caption.

    display(captions)
    captions = 
" The image shows six individuals standing in a row in what appears to be an office setting. The individuals are dressed in a variety of casual attire, including jeans, sweaters, and sweaters. The room has a neutral color scheme with beige walls and a dark gray or black carpet. The individuals are standing in front of a large painting or artwork depicting a serene landscape. The painting is framed in a dark brown or black frame. The individuals are standing in a relatively straight line, with their arms crossed, creating a sense of unity and camaraderie."

    Input Arguments

    collapse all

    Moondream vision-language model, specified as a moondream object.

    Input RGB image data, specified as one of these options:

    • H-by-W-by-3 numeric array representing a single truecolor image.

    • H-by-W-by-3-by-B numeric array representing a batch of B truecolor images. B is the number of images in the batch.

    Datastore of images, specified as any type of datastore that returns image data. If calling the datastore with the read function returns a cell array, then the image data must be in the first cell.

    Caption length, specified as one of these options:

    • "brief" — Returns a caption containing approximately 25 words or less.

    • "detail" — Returns a caption containing up to 60 words.

    Output Arguments

    collapse all

    Image captions, returned as one of these options, depending on the format of the input image I.

    • I is a single RGB image — String scalar.

    • I is a batch of RGB images — 1-by-B string array, in which each element is the caption for the corresponding image from the batch. B is the number of images in the batch.

    Datastore image captions, returned as an N-element string array. N is the number of images in the image datastore imds.

    Tips

    • The quality of Moondream outputs can vary across different data domains. Validate its predictions using a data set from a domain similar to your intended application.

    Version History

    Introduced in R2026a

    See Also

    Topics