Search packages, repositories and app categories

GitHub repositorybrianmtully/flutter_google_ml_vision

flutter_google_ml_vision

Flutter Plugin for Google ML Kit Vision

flutter_google_ml_vision project cover
Stars
46
Forks
49
Last push (UTC)
Aug 21, 2023
Project status
Active

Original README

English project snapshot. Visit GitHub for the latest content.

Google ML Kit Vision Plugin

(https://pub.dev/packages/google_ml_vision)

A Flutter plugin to use the capabilities of on-device Google ML Kit Vision APIs

Usage

To use this plugin, add google_ml_vision as a dependency in your pubspec.yaml file.

Using an ML Vision Detector

1. Create a GoogleVisionImage.

Create a GoogleVisionImage object from your image. To create a GoogleVisionImage from an image File object:

final File imageFile = getImageFile();
final GoogleVisionImage visionImage = GoogleVisionImage.fromFile(imageFile);
2. Create an instance of a detector.
final BarcodeDetector barcodeDetector = GoogleVision.instance.barcodeDetector();
final FaceDetector faceDetector = GoogleVision.instance.faceDetector();
final ImageLabeler labeler = GoogleVision.instance.imageLabeler();
final TextRecognizer textRecognizer = GoogleVision.instance.textRecognizer();

You can also configure all detectors, except TextRecognizer, with desired options.

final ImageLabeler labeler = GoogleVision.instance.imageLabeler(
  ImageLabelerOptions(confidenceThreshold: 0.75),
);
3. Call detectInImage() or processImage() with visionImage.
final List<Barcode> barcodes = await barcodeDetector.detectInImage(visionImage);
final List<Face> faces = await faceDetector.processImage(visionImage);
final List<ImageLabel> labels = await labeler.processImage(visionImage);
final VisionText visionText = await textRecognizer.processImage(visionImage);
4. Extract data.

a. Extract barcodes.

for (Barcode barcode in barcodes) {
  final Rectangle<int> boundingBox = barcode.boundingBox;
  final List<Point<int>> cornerPoints = barcode.cornerPoints;

  final String rawValue = barcode.rawValue;

  final BarcodeValueType valueType = barcode.valueType;

  // See API reference for complete list of supported types
  switch (valueType) {
    case BarcodeValueType.wifi:
      final String ssid = barcode.wifi.ssid;
      final String password = barcode.wifi.password;
      final BarcodeWiFiEncryptionType type = barcode.wifi.encryptionType;
      break;
    case BarcodeValueType.url:
      final String title = barcode.url.title;
      final String url = barcode.url.url;
      break;
  }
}

b. Extract faces.

for (Face face in faces) {
  final Rectangle<int> boundingBox = face.boundingBox;

  final double rotY = face.headEulerAngleY; // Head is rotated to the right rotY degrees
  final double rotZ = face.headEulerAngleZ; // Head is tilted sideways rotZ degrees

  // If landmark detection was enabled with FaceDetectorOptions (mouth, ears,
  // eyes, cheeks, and nose available):
  final FaceLandmark leftEar = face.getLandmark(FaceLandmarkType.leftEar);
  if (leftEar != null) {
    final Point<double> leftEarPos = leftEar.position;
  }

  // If classification was enabled with FaceDetectorOptions:
  if (face.smilingProbability != null) {
    final double smileProb = face.smilingProbability;
  }

  // If face tracking was enabled with FaceDetectorOptions:
  if (face.trackingId != null) {
    final int id = face.trackingId;
  }
}

c. Extract labels.

for (ImageLabel label in labels) {
  final String text = label.text;
  final String entityId = label.entityId;
  final double confidence = label.confidence;
}

d. Extract text.

String text = visionText.text;
for (TextBlock block in visionText.blocks) {
  final Rect boundingBox = block.boundingBox;
  final List<Offset> cornerPoints = block.cornerPoints;
  final String text = block.text;
  final List<RecognizedLanguage> languages = block.recognizedLanguages;

  for (TextLine line in block.lines) {
    // Same getters as TextBlock
    for (TextElement element in line.elements) {
      // Same getters as TextBlock
    }
  }
}
5. Release resources with close().
barcodeDetector.close();
faceDetector.close();
labeler.close();
textRecognizer.close();

Getting Started

See the example directory for a complete sample app using Google Machine Learning.

Brian M Tully GitHub avatar
GitHub author

Brian M Tully ↗

Lotgistics LLCNew York, New York
LanguagesDartObjective-CJavaRuby

Packages published by this repository

Dependencies used

Dependency list 5 items

  • flutter{"sdk":"flutter"}
  • flutter_driverDevelopment{"sdk":"flutter"}
  • flutter_testDevelopment{"sdk":"flutter"}
  • pedanticDevelopment^1.8.0
  • testDevelopmentany

How do I choose a repository?

Start with your use case, compare repository activity, and check the original project before adopting it.

  1. Search by repository name, owner or description, then narrow the results by topic.
  2. Compare stars, forks and recent pushes. Stars show community interest, not a guarantee of quality.
  3. Read the README, license and issues on GitHub before using a project.

Sources and maintenance

“A repository is the most basic element of GitHub.”

GitHub Docs — About repositories ↗