M.5 Label Images

Image Labeling

With ML Kit's image labeling APIs, you can recognize entities in an image without having to provide any additional contextual metadata, using either an on-device API or a cloud-based API.

Image labeling gives you insight into the content of images. When you use the API, you get a list of the entities that were recognized: people, things, places, activities, and so on. Each label found comes with a score that indicates the confidence the ML model has in its relevance. With this information, you can perform tasks such as automatic metadata generation and content moderation.

NOTICE: This is a beta release of ML Kit for Firebase. This API might be changed in backward-incompatible ways and is not subject to any SLA or deprecation policy.

Create a VisionImage first:

import com.myflashlab.air.extensions.firebase.mlkit.*;

// initialize ML Kit AFTER FirebaseCore is successfully started
Mlkit.init();

/*
    You can create VisionImage instance from BitmapData, File or ByteArray

    Mlkit.createVisionImageFromBitmapData
    Mlkit.createVisionImageFromFile
    Mlkit.createVisionImageFromBytes
*/

var image:File = File.applicationDirectory.resolvePath("img.jpg");

// This is beta version and for some reason, creating vision 
// images from file is not working! instead you may use 
// BitmapData for now!

var loader:Loader = new Loader();
loader.load(new URLRequest(image.url));
loader.contentLoaderInfo.addEventListener(Event.COMPLETE, function loaderComplete(e:Event):void
{
	var bm:Bitmap = e.target.content as Bitmap;

	// create a VisionImage
	var visionImg:VisionImage = Mlkit.createVisionImageFromBitmapData(bm.bitmapData);
				
	trace("visionImg.id = " + visionImg.id);
});

Extract information from the image

// (Optional) initialize an instance of ImageLabelerOptions
//var options:ImageLabelerOptions = new ImageLabelerOptions();
//options.confidenceThreshold = 
//...

var detector:ImageLabeler = Mlkit.initImageLabeler(Mlkit.ON_DEVICE, options);
detector.process(visionImg,function ($images:Vector.<VisionImageLabel>, $error:Error):void
{
	if($error) trace($error.message);
				
	if($images)
	{
		trace("--------- VisionImageLabel ------");
		for(var i:int=0; i < $images.length; i++)
		{
			var img:VisionImageLabel = $images[i];
			trace("\t" + img.toString());
		}
		trace("---------------------------------");
	}
				
	detector.close();
});