├── .classpath
├── .gitignore
├── .project
├── AndroidManifest.xml
├── README.md
├── assets
    └── tessdata
    │   └── eng.traineddata
├── proguard.cfg
├── project.properties
├── res
    ├── drawable-hdpi
    │   └── ic_launcher.png
    ├── drawable-ldpi
    │   └── ic_launcher.png
    ├── drawable-mdpi
    │   └── ic_launcher.png
    ├── layout
    │   └── main.xml
    └── values
    │   └── strings.xml
└── src
    └── com
        └── datumdroid
            └── android
                └── ocr
                    └── simple
                        └── SimpleAndroidOCRActivity.java


/.classpath:
--------------------------------------------------------------------------------
1 | <?xml version="1.0" encoding="UTF-8"?>
2 | <classpath>
3 | 	<classpathentry kind="src" path="src"/>
4 | 	<classpathentry kind="src" path="gen"/>
5 | 	<classpathentry exported="true" kind="con" path="com.android.ide.eclipse.adt.ANDROID_FRAMEWORK"/>
6 | 	<classpathentry exported="true" kind="con" path="com.android.ide.eclipse.adt.LIBRARIES"/>
7 | 	<classpathentry kind="output" path="bin/classes"/>
8 | </classpath>
9 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
 1 | # Compiled source #
 2 | ###################
 3 | *.com
 4 | *.class
 5 | *.dll
 6 | *.exe
 7 | *.o
 8 | *.so
 9 | 
10 | # Packages #
11 | ############
12 | # it's better to unpack these files and commit the raw source
13 | # git has its own built in compression methods
14 | *.7z
15 | *.dmg
16 | *.gz
17 | *.iso
18 | *.jar
19 | *.rar
20 | *.tar
21 | *.zip
22 | 
23 | # Logs and databases #
24 | ######################
25 | *.log
26 | *.sql
27 | *.sqlite
28 | 
29 | # OS generated files #
30 | ######################
31 | .DS_Store*
32 | ehthumbs.db
33 | Icon?
34 | Thumbs.db
35 | 
36 | # Custom #
37 | ##########
38 | bin/
39 | gen/
40 | .settings/


--------------------------------------------------------------------------------
/.project:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="UTF-8"?>
 2 | <projectDescription>
 3 | 	<name>Simple-Android-OCR</name>
 4 | 	<comment></comment>
 5 | 	<projects>
 6 | 	</projects>
 7 | 	<buildSpec>
 8 | 		<buildCommand>
 9 | 			<name>com.android.ide.eclipse.adt.ResourceManagerBuilder</name>
10 | 			<arguments>
11 | 			</arguments>
12 | 		</buildCommand>
13 | 		<buildCommand>
14 | 			<name>com.android.ide.eclipse.adt.PreCompilerBuilder</name>
15 | 			<arguments>
16 | 			</arguments>
17 | 		</buildCommand>
18 | 		<buildCommand>
19 | 			<name>org.eclipse.jdt.core.javabuilder</name>
20 | 			<arguments>
21 | 			</arguments>
22 | 		</buildCommand>
23 | 		<buildCommand>
24 | 			<name>com.android.ide.eclipse.adt.ApkBuilder</name>
25 | 			<arguments>
26 | 			</arguments>
27 | 		</buildCommand>
28 | 	</buildSpec>
29 | 	<natures>
30 | 		<nature>com.android.ide.eclipse.adt.AndroidNature</nature>
31 | 		<nature>org.eclipse.jdt.core.javanature</nature>
32 | 	</natures>
33 | </projectDescription>
34 | 


--------------------------------------------------------------------------------
/AndroidManifest.xml:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="utf-8"?>
 2 | <manifest xmlns:android="http://schemas.android.com/apk/res/android"
 3 |     package="com.datumdroid.android.ocr.simple"
 4 |     android:versionCode="1"
 5 |     android:versionName="1.0">
 6 | 
 7 |     <uses-sdk
 8 |         android:minSdkVersion="24"
 9 |         android:targetSdkVersion="28" />
10 | 
11 |     <application
12 |         android:icon="@drawable/ic_launcher"
13 |         android:label="@string/app_name"
14 |         android:debuggable="true">
15 |         <activity
16 |             android:configChanges="orientation|keyboardHidden"
17 |             android:label="@string/app_name"
18 |             android:name=".SimpleAndroidOCRActivity">
19 |             <intent-filter >
20 |                 <action android:name="android.intent.action.MAIN" />
21 | 
22 |                 <category android:name="android.intent.category.LAUNCHER" />
23 |             </intent-filter>
24 |         </activity>
25 |     </application>
26 | 
27 |     <uses-permission android:name="android.permission.CAMERA" />
28 |     <uses-permission android:name="android.permission.FLASHLIGHT" />
29 |     <uses-permission android:name="android.permission.WRITE_EXTERNAL_STORAGE" />
30 | 
31 |     <uses-feature
32 |         android:name="android.hardware.camera"
33 |         android:required="false" />
34 |     <uses-feature
35 |         android:name="android.hardware.camera.autofocus"
36 |         android:required="false" />
37 | 
38 | </manifest>
39 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | ![OCR on Android](http://gaut.am/wp-content/uploads/2011/11/capture_3-300x225.jpg)
2 | 
3 | For more information, check this tutorial: http://gaut.am/making-an-ocr-android-app-using-tesseract/
4 | 


--------------------------------------------------------------------------------
/assets/tessdata/eng.traineddata:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/GautamGupta/Simple-Android-OCR/53c77e74a0317a1b5246cc75b99271a52ad95e38/assets/tessdata/eng.traineddata


--------------------------------------------------------------------------------
/proguard.cfg:
--------------------------------------------------------------------------------
 1 | -optimizationpasses 5
 2 | -dontusemixedcaseclassnames
 3 | -dontskipnonpubliclibraryclasses
 4 | -dontpreverify
 5 | -verbose
 6 | -optimizations !code/simplification/arithmetic,!field/*,!class/merging/*
 7 | 
 8 | -keep public class * extends android.app.Activity
 9 | -keep public class * extends android.app.Application
10 | -keep public class * extends android.app.Service
11 | -keep public class * extends android.content.BroadcastReceiver
12 | -keep public class * extends android.content.ContentProvider
13 | -keep public class * extends android.app.backup.BackupAgentHelper
14 | -keep public class * extends android.preference.Preference
15 | -keep public class com.android.vending.licensing.ILicensingService
16 | 
17 | -keepclasseswithmembernames class * {
18 |     native <methods>;
19 | }
20 | 
21 | -keepclasseswithmembers class * {
22 |     public <init>(android.content.Context, android.util.AttributeSet);
23 | }
24 | 
25 | -keepclasseswithmembers class * {
26 |     public <init>(android.content.Context, android.util.AttributeSet, int);
27 | }
28 | 
29 | -keepclassmembers class * extends android.app.Activity {
30 |    public void *(android.view.View);
31 | }
32 | 
33 | -keepclassmembers enum * {
34 |     public static **[] values();
35 |     public static ** valueOf(java.lang.String);
36 | }
37 | 
38 | -keep class * implements android.os.Parcelable {
39 |   public static final android.os.Parcelable$Creator *;
40 | }
41 | 


--------------------------------------------------------------------------------
/project.properties:
--------------------------------------------------------------------------------
 1 | # This file is automatically generated by Android Tools.
 2 | # Do not modify this file -- YOUR CHANGES WILL BE ERASED!
 3 | #
 4 | # This file must be checked in Version Control Systems.
 5 | #
 6 | # To customize properties used by the Ant build system use,
 7 | # "ant.properties", and override values to adapt the script to your
 8 | # project structure.
 9 | 
10 | # Project target.
11 | target=android-10
12 | android.library.reference.1=../tess-two
13 | 


--------------------------------------------------------------------------------
/res/drawable-hdpi/ic_launcher.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/GautamGupta/Simple-Android-OCR/53c77e74a0317a1b5246cc75b99271a52ad95e38/res/drawable-hdpi/ic_launcher.png


--------------------------------------------------------------------------------
/res/drawable-ldpi/ic_launcher.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/GautamGupta/Simple-Android-OCR/53c77e74a0317a1b5246cc75b99271a52ad95e38/res/drawable-ldpi/ic_launcher.png


--------------------------------------------------------------------------------
/res/drawable-mdpi/ic_launcher.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/GautamGupta/Simple-Android-OCR/53c77e74a0317a1b5246cc75b99271a52ad95e38/res/drawable-mdpi/ic_launcher.png


--------------------------------------------------------------------------------
/res/layout/main.xml:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="utf-8"?>
 2 | <LinearLayout xmlns:android="http://schemas.android.com/apk/res/android"
 3 |     android:layout_width="fill_parent"
 4 |     android:layout_height="fill_parent"
 5 |     android:orientation="vertical" >
 6 | 
 7 |     <Button
 8 |         android:id="@+id/button"
 9 |         android:layout_width="match_parent"
10 |         android:layout_height="wrap_content"
11 |         android:text="@string/button_text" />
12 | 
13 |     <EditText
14 |         android:id="@+id/field"
15 |         android:layout_width="match_parent"
16 |         android:layout_height="wrap_content"
17 |         android:hint="@string/text_hint" />
18 | 
19 | </LinearLayout>


--------------------------------------------------------------------------------
/res/values/strings.xml:
--------------------------------------------------------------------------------
1 | <?xml version="1.0" encoding="utf-8"?>
2 | <resources>
3 | 
4 |     <string name="hello">Hello World, DatumDroidOCRActivity!</string>
5 |     <string name="app_name">Simple Android OCR</string>
6 |     <string name="button_text">OCR!</string>
7 |     <string name="text_hint">OCRed Text will appear here</string>
8 | 
9 | </resources>


--------------------------------------------------------------------------------
/src/com/datumdroid/android/ocr/simple/SimpleAndroidOCRActivity.java:
--------------------------------------------------------------------------------
  1 | package com.datumdroid.android.ocr.simple;
  2 | 
  3 | import java.io.File;
  4 | import java.io.FileInputStream;
  5 | import java.io.FileOutputStream;
  6 | import java.io.IOException;
  7 | import java.io.InputStream;
  8 | import java.io.OutputStream;
  9 | import java.util.zip.GZIPInputStream;
 10 | 
 11 | import android.app.Activity;
 12 | import android.content.Intent;
 13 | import android.content.res.AssetManager;
 14 | import android.graphics.Bitmap;
 15 | import android.graphics.BitmapFactory;
 16 | import android.graphics.Matrix;
 17 | import android.media.ExifInterface;
 18 | import android.net.Uri;
 19 | import android.os.Bundle;
 20 | import android.os.Environment;
 21 | import android.provider.MediaStore;
 22 | import android.util.Log;
 23 | import android.view.View;
 24 | import android.widget.Button;
 25 | import android.widget.EditText;
 26 | 
 27 | import com.googlecode.tesseract.android.TessBaseAPI;
 28 | 
 29 | public class SimpleAndroidOCRActivity extends Activity {
 30 | 	public static final String PACKAGE_NAME = "com.datumdroid.android.ocr.simple";
 31 | 	public static final String DATA_PATH = Environment
 32 | 			.getExternalStorageDirectory().toString() + "/SimpleAndroidOCR/";
 33 | 	
 34 | 	// You should have the trained data file in assets folder
 35 | 	// You can get them at:
 36 | 	// https://github.com/tesseract-ocr/tessdata
 37 | 	public static final String lang = "eng";
 38 | 
 39 | 	private static final String TAG = "SimpleAndroidOCR.java";
 40 | 
 41 | 	protected Button _button;
 42 | 	// protected ImageView _image;
 43 | 	protected EditText _field;
 44 | 	protected String _path;
 45 | 	protected boolean _taken;
 46 | 
 47 | 	protected static final String PHOTO_TAKEN = "photo_taken";
 48 | 
 49 | 	@Override
 50 | 	public void onCreate(Bundle savedInstanceState) {
 51 | 		super.onCreate(savedInstanceState);
 52 | 		setContentView(R.layout.main);
 53 | 
 54 | 		String[] paths = new String[] { DATA_PATH, DATA_PATH + "tessdata/" };
 55 | 
 56 | 		for (String path : paths) {
 57 | 			File dir = new File(path);
 58 | 			if (!dir.exists()) {
 59 | 				if (!dir.mkdirs()) {
 60 | 					Log.v(TAG, "ERROR: Creation of directory " + path + " on sdcard failed");
 61 | 					return;
 62 | 				} else {
 63 | 					Log.v(TAG, "Created directory " + path + " on sdcard");
 64 | 				}
 65 | 			}
 66 | 
 67 | 		}
 68 | 		
 69 | 		// lang.traineddata file with the app (in assets folder)
 70 | 		// You can get them at:
 71 | 		// http://code.google.com/p/tesseract-ocr/downloads/list
 72 | 		// This area needs work and optimization
 73 | 		if (!(new File(DATA_PATH + "tessdata/" + lang + ".traineddata")).exists()) {
 74 | 			try {
 75 | 
 76 | 				AssetManager assetManager = getAssets();
 77 | 				InputStream in = assetManager.open("tessdata/" + lang + ".traineddata");
 78 | 				//GZIPInputStream gin = new GZIPInputStream(in);
 79 | 				OutputStream out = new FileOutputStream(DATA_PATH
 80 | 						+ "tessdata/" + lang + ".traineddata");
 81 | 
 82 | 				// Transfer bytes from in to out
 83 | 				byte[] buf = new byte[1024];
 84 | 				int len;
 85 | 				//while ((lenf = gin.read(buff)) > 0) {
 86 | 				while ((len = in.read(buf)) > 0) {
 87 | 					out.write(buf, 0, len);
 88 | 				}
 89 | 				in.close();
 90 | 				//gin.close();
 91 | 				out.close();
 92 | 				
 93 | 				Log.v(TAG, "Copied " + lang + " traineddata");
 94 | 			} catch (IOException e) {
 95 | 				Log.e(TAG, "Was unable to copy " + lang + " traineddata " + e.toString());
 96 | 			}
 97 | 		}
 98 | 
 99 | 		
100 | 
101 | 		// _image = (ImageView) findViewById(R.id.image);
102 | 		_field = (EditText) findViewById(R.id.field);
103 | 		_button = (Button) findViewById(R.id.button);
104 | 		_button.setOnClickListener(new ButtonClickHandler());
105 | 
106 | 		_path = DATA_PATH + "/ocr.jpg";
107 | 	}
108 | 
109 | 	public class ButtonClickHandler implements View.OnClickListener {
110 | 		public void onClick(View view) {
111 | 			Log.v(TAG, "Starting Camera app");
112 | 			startCameraActivity();
113 | 		}
114 | 	}
115 | 
116 | 	// Simple android photo capture:
117 | 	// http://labs.makemachine.net/2010/03/simple-android-photo-capture/
118 | 
119 | 	protected void startCameraActivity() {
120 | 		File file = new File(_path);
121 | 		Uri outputFileUri = Uri.fromFile(file);
122 | 
123 | 		final Intent intent = new Intent(MediaStore.ACTION_IMAGE_CAPTURE);
124 | 		intent.putExtra(MediaStore.EXTRA_OUTPUT, outputFileUri);
125 | 
126 | 		startActivityForResult(intent, 0);
127 | 	}
128 | 
129 | 	@Override
130 | 	protected void onActivityResult(int requestCode, int resultCode, Intent data) {
131 | 
132 | 		Log.i(TAG, "resultCode: " + resultCode);
133 | 
134 | 		if (resultCode == -1) {
135 | 			onPhotoTaken();
136 | 		} else {
137 | 			Log.v(TAG, "User cancelled");
138 | 		}
139 | 	}
140 | 
141 | 	@Override
142 | 	protected void onSaveInstanceState(Bundle outState) {
143 | 		outState.putBoolean(SimpleAndroidOCRActivity.PHOTO_TAKEN, _taken);
144 | 	}
145 | 
146 | 	@Override
147 | 	protected void onRestoreInstanceState(Bundle savedInstanceState) {
148 | 		Log.i(TAG, "onRestoreInstanceState()");
149 | 		if (savedInstanceState.getBoolean(SimpleAndroidOCRActivity.PHOTO_TAKEN)) {
150 | 			onPhotoTaken();
151 | 		}
152 | 	}
153 | 
154 | 	protected void onPhotoTaken() {
155 | 		_taken = true;
156 | 
157 | 		BitmapFactory.Options options = new BitmapFactory.Options();
158 | 		options.inSampleSize = 4;
159 | 
160 | 		Bitmap bitmap = BitmapFactory.decodeFile(_path, options);
161 | 
162 | 		try {
163 | 			ExifInterface exif = new ExifInterface(_path);
164 | 			int exifOrientation = exif.getAttributeInt(
165 | 					ExifInterface.TAG_ORIENTATION,
166 | 					ExifInterface.ORIENTATION_NORMAL);
167 | 
168 | 			Log.v(TAG, "Orient: " + exifOrientation);
169 | 
170 | 			int rotate = 0;
171 | 
172 | 			switch (exifOrientation) {
173 | 			case ExifInterface.ORIENTATION_ROTATE_90:
174 | 				rotate = 90;
175 | 				break;
176 | 			case ExifInterface.ORIENTATION_ROTATE_180:
177 | 				rotate = 180;
178 | 				break;
179 | 			case ExifInterface.ORIENTATION_ROTATE_270:
180 | 				rotate = 270;
181 | 				break;
182 | 			}
183 | 
184 | 			Log.v(TAG, "Rotation: " + rotate);
185 | 
186 | 			if (rotate != 0) {
187 | 
188 | 				// Getting width & height of the given image.
189 | 				int w = bitmap.getWidth();
190 | 				int h = bitmap.getHeight();
191 | 
192 | 				// Setting pre rotate
193 | 				Matrix mtx = new Matrix();
194 | 				mtx.preRotate(rotate);
195 | 
196 | 				// Rotating Bitmap
197 | 				bitmap = Bitmap.createBitmap(bitmap, 0, 0, w, h, mtx, false);
198 | 			}
199 | 
200 | 			// Convert to ARGB_8888, required by tess
201 | 			bitmap = bitmap.copy(Bitmap.Config.ARGB_8888, true);
202 | 
203 | 		} catch (IOException e) {
204 | 			Log.e(TAG, "Couldn't correct orientation: " + e.toString());
205 | 		}
206 | 
207 | 		// _image.setImageBitmap( bitmap );
208 | 		
209 | 		Log.v(TAG, "Before baseApi");
210 | 
211 | 		TessBaseAPI baseApi = new TessBaseAPI();
212 | 		baseApi.setDebug(true);
213 | 		baseApi.init(DATA_PATH, lang);
214 | 		baseApi.setImage(bitmap);
215 | 		
216 | 		String recognizedText = baseApi.getUTF8Text();
217 | 		
218 | 		baseApi.end();
219 | 
220 | 		// You now have the text in recognizedText var, you can do anything with it.
221 | 		// We will display a stripped out trimmed alpha-numeric version of it (if lang is eng)
222 | 		// so that garbage doesn't make it to the display.
223 | 
224 | 		Log.v(TAG, "OCRED TEXT: " + recognizedText);
225 | 
226 | 		if ( lang.equalsIgnoreCase("eng") ) {
227 | 			recognizedText = recognizedText.replaceAll("[^a-zA-Z0-9]+", " ");
228 | 		}
229 | 		
230 | 		recognizedText = recognizedText.trim();
231 | 
232 | 		if ( recognizedText.length() != 0 ) {
233 | 			_field.setText(_field.getText().toString().length() == 0 ? recognizedText : _field.getText() + " " + recognizedText);
234 | 			_field.setSelection(_field.getText().toString().length());
235 | 		}
236 | 		
237 | 		// Cycle done.
238 | 	}
239 | 	
240 | 	// www.Gaut.am was here
241 | 	// Thanks for reading!
242 | }
243 | 


--------------------------------------------------------------------------------