flutter_tesseract_ocr 0.3.0

Tesseract 4 adds a new neural net (LSTM) based OCR engine which is focused on line recognition. It has unicode (UTF-8) support, and can recognize more than 100 languages.

example/lib/main.dart

import 'package:flutter/material.dart';
import 'package:path_provider/path_provider.dart';
import 'package:tesseract_ocr/flutter_tesseract_ocr.dart';
import 'package:flutter/services.dart' show ByteData, rootBundle;
import 'dart:io';

void main() {
  runApp(MyApp());
}

class MyApp extends StatelessWidget {
  // This widget is the root of your application.
  @override
  Widget build(BuildContext context) {
    return MaterialApp(
      title: 'Tesseract Demo',
      theme: ThemeData(
        // This is the theme of your application.
        //
        // Try running your application with "flutter run". You'll see the
        // application has a blue toolbar. Then, without quitting the app, try
        // changing the primarySwatch below to Colors.green and then invoke
        // "hot reload" (press "r" in the console where you ran "flutter run",
        // or simply save your changes to "hot reload" in a Flutter IDE).
        // Notice that the counter didn't reset back to zero; the application
        // is not restarted.
        primarySwatch: Colors.blue,
      ),
      home: MyHomePage(title: 'Tesseract Demo'),
    );
  }
}

class MyHomePage extends StatefulWidget {
  MyHomePage({Key? key, required this.title}) : super(key: key);

  // This widget is the home page of your application. It is stateful, meaning
  // that it has a State object (defined below) that contains fields that affect
  // how it looks.

  // This class is the configuration for the state. It holds the values (in this
  // case the title) provided by the parent (in this case the App widget) and
  // used by the build method of the State. Fields in a Widget subclass are
  // always marked "final".

  final String title;

  @override
  _MyHomePageState createState() => _MyHomePageState();
}

class _MyHomePageState extends State<MyHomePage> {
  String _ocrText = '';
  String _ocrHocr = '';

  Future<void> writeToFile(ByteData data, String path) {
    final buffer = data.buffer;
    return new File(path).writeAsBytes(
        buffer.asUint8List(data.offsetInBytes, data.lengthInBytes));
  }

  void _ocr() async {
    final filename = 'test1.png';
    var bytes = await rootBundle.load("assets/test1.png");
    String dir = (await getApplicationDocumentsDirectory()).path;
    writeToFile(bytes, '$dir/$filename');

    // ---- dynamic add traineddata ---- ▼
    // https://github.com/tesseract-ocr/tessdata/raw/master/dan_frak.traineddata
    // download
    // String newTessDataFile = "deu.traineddata";
    // Directory d = Directory(await TesseractOcr.getTessdataPath());
    // d.list().forEach((event) {
    //   print(event);
    // });
    // File('${d.path}/${newTessDataFile}').writeAsBytes([Uint8List bytes]);
    // ---- dynamic add traineddata ---- ▲

    _ocrText = await TesseractOcr.extractText('$dir/$filename',
        language: 'kor+eng',
        args: {
          "psm": "4",
          "preserve_interword_spaces": "1",
        });
    print(_ocrText);

    setState(() {});
  }

  @override
  Widget build(BuildContext context) {
    // This method is rerun every time setState is called, for instance as done
    // by the _incrementCounter method above.
    //
    // The Flutter framework has been optimized to make rerunning build methods
    // fast, so that you can just rebuild anything that needs updating rather
    // than having to individually change instances of widgets.
    return Scaffold(
      appBar: AppBar(
        // Here we take the value from the MyHomePage object that was created by
        // the App.build method, and use it to set our appbar title.
        title: Text(widget.title),
      ),
      body: Center(
        // Center is a layout widget. It takes a single child and positions it
        // in the middle of the parent.
        child: Column(
          // Column is also a layout widget. It takes a list of children and
          // arranges them vertically. By default, it sizes itself to fit its
          // children horizontally, and tries to be as tall as its parent.
          //
          // Invoke "debug painting" (press "p" in the console, choose the
          // "Toggle Debug Paint" action from the Flutter Inspector in Android
          // Studio, or the "Toggle Debug Paint" command in Visual Studio Code)
          // to see the wireframe for each widget.
          //
          // Column has various properties to control how it sizes itself and
          // how it positions its children. Here we use mainAxisAlignment to
          // center the children vertically; the main axis here is the vertical
          // axis because Columns are vertical (the cross axis would be
          // horizontal).
          mainAxisAlignment: MainAxisAlignment.start,
          children: <Widget>[
            Text(
              'OCR result:',
            ),
            Text(
              '$_ocrText',
              style: Theme.of(context).textTheme.headline4,
            ),
            Text(
              '$_ocrHocr',
              style: Theme.of(context).textTheme.bodyText1,
            ),
          ],
        ),
      ),
      floatingActionButton: FloatingActionButton(
        onPressed: _ocr,
        tooltip: 'OCR',
        child: Icon(Icons.add),
      ), // This trailing comma makes auto-formatting nicer for build methods.
    );
  }
}