google_mlkit_digital_ink_recognition 0.2.1

A Flutter plugin to use Google's ML Kit Digital Ink Recognition to recognize handwritten text on a digital surface in hundreds of languages, as well as classify sketches.

Google's ML Kit Digital Ink Recognition for Flutter

A Flutter plugin to use Google's ML Kit Digital Ink Recognition to recognize handwritten text on a digital surface in hundreds of languages, as well as classify sketches.

Getting Started

Before you get started read about the requirements and known issues of this plugin here.

Usage

Digital Ink Recognition

Create an instance of DigitalInkRecognizer

String languageCode; // BCP-47 Code from https://developers.google.com/ml-kit/vision/digital-ink-recognition/base-models?hl=en#text
final digitalInkRecognizer = DigitalInkRecognizer(languageCode: languageCode);

Process ink

Stroke stroke1 = Stroke(); // it contains all of the StrokePoint
stroke1.point = [StrokePoint(x: x1, y: y1, t: t1), StrokePoint(x: x2, y: y2, t: t2), ...]

Ink ink = Ink(); // it contains all of the Stroke
ink.strokes = [stroke1, stroke2, ...];

final List<RecognitionCandidate> candidates = await digitalInkRecognizer.recognize(ink);

for (final candidate in candidates) {
  final text = candidate.text;
  final score = candidate.score;
}

Make sure you download the language model before processing any Ink.

Release resources with close()

digitalInkRecognizer.close();

Managing remote models

Create an instance of model manager

final modelManager = DigitalInkRecognizerModelManager();

Check if model is downloaded

final bool response = await modelManager.isModelDownloaded(model);

Download model

final bool response = await modelManager.downloadModel(model);

Delete model

final bool response = await modelManager.deleteModel(model);

Example app

Find the example app here.

Contributing

Contributions are welcome. In case of any problems look at existing issues, if you cannot find anything related to your problem then open an issue. Create an issue before opening a pull request for non trivial fixes. In case of trivial fixes open a pull request directly.