0

我已经关注了这些链接: http: //gaut.am/making-an-ocr-android-app-using-tesseract/#comment-184181

http://gaut.am/making-an-ocr-android-app-using-tesseract/

在 android studio 上制作 OCR 应用程序。当我在 src->main->assets 文件夹中包含 eng.traineddata 时,该应用程序运行良好但是,当我使用 ara.traineddata 为阿拉伯语制作 OCR 应用程序时,该应用程序卡住了

我使用调试点检查问题可能出在哪里,似乎问题出 baseApi.init(DATA_PATH, lang); 在 MainActivity.java

这是我的 MainActivity.java

package com.innam.tryingtomaketesseractwork;

import android.app.Activity;
import android.content.Intent;
import android.content.res.AssetManager;
import android.graphics.Bitmap;
import android.graphics.BitmapFactory;
import android.graphics.Matrix;
import android.media.ExifInterface;
import android.net.Uri;
import android.os.Bundle;
import android.os.Environment;
import android.provider.MediaStore;
import android.util.Log;
import android.view.View;
import android.widget.Button;
import android.widget.EditText;

import com.googlecode.tesseract.android.TessBaseAPI;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;


public class MainActivity extends Activity {

public static final String PACKAGE_NAME =     "com.datumdroid.android.ocr.simple";
public static final String DATA_PATH = Environment
        .getExternalStorageDirectory().toString() + "/SimpleAndroidOCR/";

// You should have the trained data file in assets folder
// You can get them at:
// http://code.google.com/p/tesseract-ocr/downloads/list
public static final String lang = "ara";

private static final String TAG = "SimpleAndroidOCR.java";

protected Button _button;
// protected ImageView _image;
protected EditText _field;
protected String _path;
protected boolean _taken;

protected static final String PHOTO_TAKEN = "photo_taken";

@Override
protected void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);
    setContentView(R.layout.activity_main);
    String[] paths = new String[] { DATA_PATH, DATA_PATH + "tessdata/" };

    for (String path : paths) {
        File dir = new File(path);
        if (!dir.exists()) {
            if (!dir.mkdirs()) {
                Log.v(TAG, "ERROR: Creation of directory " + path + " on sdcard failed");
                return;
            } else {
                Log.v(TAG, "Created directory " + path + " on sdcard");
            }
        }

    }

    // lang.traineddata file with the app (in assets folder)
    // You can get them at:
    // http://code.google.com/p/tesseract-ocr/downloads/list
    // This area needs work and optimization
    if (!(new File(DATA_PATH + "tessdata/" + lang + ".traineddata")).exists()) {
        try {

            AssetManager assetManager = getAssets();
            InputStream in = assetManager.open("tessdata/" + lang + ".traineddata");
            //GZIPInputStream gin = new GZIPInputStream(in);
            OutputStream out = new FileOutputStream(DATA_PATH
                    + "tessdata/" + lang + ".traineddata");

            // Transfer bytes from in to out
            byte[] buf = new byte[1024];
            int len;
            //while ((lenf = gin.read(buff)) > 0) {
            while ((len = in.read(buf)) > 0) {
                out.write(buf, 0, len);
            }
            in.close();
            //gin.close();
            out.close();

            Log.v(TAG, "Copied " + lang + " traineddata");
        } catch (IOException e) {
            Log.e(TAG, "Was unable to copy " + lang + " traineddata " + e.toString());
        }
    }



    // _image = (ImageView) findViewById(R.id.image);
    _field = (EditText) findViewById(R.id.field);
    _button = (Button) findViewById(R.id.button);
    _button.setOnClickListener(new ButtonClickHandler());

    _path = DATA_PATH + "/ocr.jpg";
}

public class ButtonClickHandler implements View.OnClickListener {
    public void onClick(View view) {
        Log.v(TAG, "Starting Camera app");
        startCameraActivity();
    }
}

// Simple android photo capture:
// http://labs.makemachine.net/2010/03/simple-android-photo-capture/

protected void startCameraActivity() {
    File file = new File(_path);
    Uri outputFileUri = Uri.fromFile(file);

    final Intent intent = new Intent(MediaStore.ACTION_IMAGE_CAPTURE);
    intent.putExtra(MediaStore.EXTRA_OUTPUT, outputFileUri);

    startActivityForResult(intent, 0);
}

@Override
protected void onActivityResult(int requestCode, int resultCode, Intent data) {

    Log.i(TAG, "resultCode: " + resultCode);

    if (resultCode == -1) {
        onPhotoTaken();
    } else {
        Log.v(TAG, "User cancelled");
    }
}

@Override
protected void onSaveInstanceState(Bundle outState) {
    outState.putBoolean(MainActivity.PHOTO_TAKEN, _taken);
}

@Override
protected void onRestoreInstanceState(Bundle savedInstanceState) {
    Log.i(TAG, "onRestoreInstanceState()");
    if (savedInstanceState.getBoolean(MainActivity.PHOTO_TAKEN)) {
        onPhotoTaken();
    }
}

protected void onPhotoTaken() {
    _taken = true;

    BitmapFactory.Options options = new BitmapFactory.Options();
    options.inSampleSize = 4;

    Bitmap bitmap = BitmapFactory.decodeFile(_path, options);

    try {
        ExifInterface exif = new ExifInterface(_path);
        int exifOrientation = exif.getAttributeInt(
                ExifInterface.TAG_ORIENTATION,
                ExifInterface.ORIENTATION_NORMAL);

        Log.v(TAG, "Orient: " + exifOrientation);

        int rotate = 0;

        switch (exifOrientation) {
            case ExifInterface.ORIENTATION_ROTATE_90:
                rotate = 90;
                break;
            case ExifInterface.ORIENTATION_ROTATE_180:
                rotate = 180;
                break;
            case ExifInterface.ORIENTATION_ROTATE_270:
                rotate = 270;
                break;
        }

        Log.v(TAG, "Rotation: " + rotate);

        if (rotate != 0) {

            // Getting width & height of the given image.
            int w = bitmap.getWidth();
            int h = bitmap.getHeight();

            // Setting pre rotate
            Matrix mtx = new Matrix();
            mtx.preRotate(rotate);

            // Rotating Bitmap
            bitmap = Bitmap.createBitmap(bitmap, 0, 0, w, h, mtx, false);
        }

        // Convert to ARGB_8888, required by tess
        bitmap = bitmap.copy(Bitmap.Config.ARGB_8888, true);

    } catch (IOException e) {
        Log.e(TAG, "Couldn't correct orientation: " + e.toString());
    }

    // _image.setImageBitmap( bitmap );

    Log.v(TAG, "Before baseApi");

    TessBaseAPI baseApi = new TessBaseAPI();

    baseApi.setDebug(true);


    baseApi.init(DATA_PATH, lang);
    baseApi.setImage(bitmap);

    String recognizedText = baseApi.getUTF8Text();

    baseApi.end();

    // You now have the text in recognizedText var, you can do anything with it.
    // We will display a stripped out trimmed alpha-numeric version of it (if lang is eng)
    // so that garbage doesn't make it to the display.

    Log.v(TAG, "OCRED TEXT: " + recognizedText);

    if ( lang.equalsIgnoreCase("eng") ) {
        recognizedText = recognizedText.replaceAll("[^a-zA-Z0-9]+", " ");
    }

    recognizedText = recognizedText.trim();

    if ( recognizedText.length() != 0 ) {
        _field.setText(_field.getText().toString().length() == 0 ? recognizedText : _field.getText() + " " + recognizedText);
        _field.setSelection(_field.getText().toString().length());
    }

    // Cycle done.
}

// www.Gaut.am was here
// Thanks for reading!
}

日志猫:

08-04 12:58:38.900 24836-24836/com.innam.tryingtomaketesseractwork D/libEGL: loaded /system/lib/egl/libEGL_mali.so
08-04 12:58:38.905 24836-24836/com.innam.tryingtomaketesseractwork D/libEGL: loaded /system/lib/egl/libGLESv1_CM_mali.so
08-04 12:58:38.905 24836-24836/com.innam.tryingtomaketesseractwork D/libEGL: loaded /system/lib/egl/libGLESv2_mali.so

                                                                             [ 08-04 12:58:38.910 24836:24836 D/         ]
                                                                             Device driver API match
                                                                             Device driver API version: 10
                                                                             User space API version: 10 


                                                                             [ 08-04 12:58:38.910 24836:24836 D/         ]
                                                                             mali: REVISION=Linux-r2p4-02rel0 BUILD_DATE=Tue Oct 16 15:37:13 KST 2012 
08-04 12:58:38.960 24836-24836/com.innam.tryingtomaketesseractwork D/OpenGLRenderer: Enabling debug mode 0
08-04 12:58:38.965 24836-24836/com.innam.tryingtomaketesseractwork E/SensorManager: thread start
08-04 12:58:38.965 24836-24836/com.innam.tryingtomaketesseractwork D/SensorManager: registerListener :: handle = 1  name= LIS3DH Acceleration Sensor delay= 200000  

任何帮助将不胜感激

4

1 回答 1

1

您还需要所有ara.cube.*文件。

https://github.com/tesseract-ocr/tessdata

于 2016-08-05T00:55:04.993 回答