Java Android:如何改善tesseract ocr检索到的图像中的数字?
我用android制作了一个简单的应用程序,可以读取图像并以文本形式检索数字图像。但问题是,准确率只有60%左右,一些不必要的噪声也会显示出来。我确实认为准确率不可能达到100%,但是,我相信一定有办法改进它。但是,因为我是个业余爱好者,我觉得很难。我在谷歌搜索过,但无法获得可靠的信息 我想读一张东方幸运票上的数字596、00和012345,如下图所示Java Android:如何改善tesseract ocr检索到的图像中的数字?,java,android,ocr,tesseract,Java,Android,Ocr,Tesseract,我用android制作了一个简单的应用程序,可以读取图像并以文本形式检索数字图像。但问题是,准确率只有60%左右,一些不必要的噪声也会显示出来。我确实认为准确率不可能达到100%,但是,我相信一定有办法改进它。但是,因为我是个业余爱好者,我觉得很难。我在谷歌搜索过,但无法获得可靠的信息 我想读一张东方幸运票上的数字596、00和012345,如下图所示 Tesseract ocr最适用于符合以下标准的字符图像: 输入图像应至少具有300 dpi 输入图像应该是黑白的 输入图像中的噪声应最小(即
Tesseract ocr最适用于符合以下标准的字符图像:
- 输入图像应至少具有300 dpi
- 输入图像应该是黑白的
- 输入图像中的噪声应最小(即文本应与背景清晰区分)
- 文本行应该是直的
- 图像应围绕要检测的文本居中
MainActivity.java
导入android.app.AlertDialog;
导入android.content.ContentValues;
导入android.content.Intent;
导入android.graphics.Bitmap;
导入android.graphics.BitmapFactory;
导入android.net.Uri;
导入android.provider.MediaStore;
导入android.support.v7.app.AppActivity;
导入android.os.Bundle;
导入android.text.method.ScrollingMovementMethod;
导入android.util.DisplayMetrics;
导入android.util.Log;
导入android.util.SparseArray;
导入android.view.view;
导入android.widget.TextView;
导入com.google.android.gms.vision.Frame;
导入com.google.android.gms.vision.text.TextBlock;
导入com.google.android.gms.vision.text.TextRecognizer;
导入java.io.FileNotFoundException;
导入java.io.IOException;
导入java.io.InputStream;
导入java.util.ArrayList;
导入java.util.Collections;
导入java.util.Comparator;
导入java.util.List;
公共类MainActivity扩展了AppCompatActivity{
私有静态最终整数请求\u GALLERY=0;
专用静态最终int请求\u摄像机=1;
私有静态最终字符串标记=MainActivity.class.getSimpleName();
私有Uri-imageUri;
私有文本视图检测到文本视图;
@凌驾
创建时受保护的void(Bundle savedInstanceState){
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
findViewById(R.id.choose_from_gallery).setOnClickListener(new View.OnClickListener()){
@凌驾
公共void onClick(视图v){
意图=新意图();
intent.setType(“image/*”);
intent.setAction(intent.ACTION\u GET\u CONTENT);
startActivityForResult(意向、请求);
}
});
findviewbyd(R.id.take_a_photo).setOnClickListener(newview.OnClickListener()){
@凌驾
公共void onClick(视图v){
字符串文件名=System.currentTimeMillis()+“.jpg”;
ContentValues=新的ContentValues();
value.put(MediaStore.Images.Media.TITLE,文件名);
value.put(MediaStore.Images.Media.MIME_类型,“image/jpeg”);
imageUri=getContentResolver().insert(MediaStore.Images.Media.EXTERNAL\u CONTENT\u URI,值);
意图=新意图();
intent.setAction(MediaStore.ACTION\u IMAGE\u CAPTURE);
intent.putExtra(MediaStore.EXTRA_输出,imageUri);
startActivityForResult(意图、请求和摄像头);
}
});
detectedTextView=(TextView)findViewById(R.id.detected\u text);
detectedTextView.setMovementMethod(新的ScrollingMovementMethod());
}
私有void inspectFromBitmap(位图位图){
TextRecognizer TextRecognizer=新的TextRecognizer.Builder(this.build();
试一试{
如果(!textRecognitor.isOperational()){
新建警报对话框。
建筑商(这个)。
setMessage(“无法在设备上设置文本识别器”).show();
返回;
}
Frame Frame=new Frame.Builder().setbit映射(位图).build();
SparseArray origTextBlocks=文本识别器。检测(帧);
List textBlocks=new ArrayList();
对于(int i=0;iyou can use Vision for text detection.
compile 'com.google.android.gms:play-services-vision:10.0.0'
<meta-data
android:name="com.google.android.gms.vision.DEPENDENCIES"
android:value="ocr" />
import android.app.AlertDialog;
import android.content.ContentValues;
import android.content.Intent;
import android.graphics.Bitmap;
import android.graphics.BitmapFactory;
import android.net.Uri;
import android.provider.MediaStore;
import android.support.v7.app.AppCompatActivity;
import android.os.Bundle;
import android.text.method.ScrollingMovementMethod;
import android.util.DisplayMetrics;
import android.util.Log;
import android.util.SparseArray;
import android.view.View;
import android.widget.TextView;
import com.google.android.gms.vision.Frame;
import com.google.android.gms.vision.text.TextBlock;
import com.google.android.gms.vision.text.TextRecognizer;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.List;
public class MainActivity extends AppCompatActivity {
private static final int REQUEST_GALLERY = 0;
private static final int REQUEST_CAMERA = 1;
private static final String TAG = MainActivity.class.getSimpleName();
private Uri imageUri;
private TextView detectedTextView;
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
findViewById(R.id.choose_from_gallery).setOnClickListener(new View.OnClickListener() {
@Override
public void onClick(View v) {
Intent intent = new Intent();
intent.setType("image/*");
intent.setAction(Intent.ACTION_GET_CONTENT);
startActivityForResult(intent, REQUEST_GALLERY);
}
});
findViewById(R.id.take_a_photo).setOnClickListener(new View.OnClickListener() {
@Override
public void onClick(View v) {
String filename = System.currentTimeMillis() + ".jpg";
ContentValues values = new ContentValues();
values.put(MediaStore.Images.Media.TITLE, filename);
values.put(MediaStore.Images.Media.MIME_TYPE, "image/jpeg");
imageUri = getContentResolver().insert(MediaStore.Images.Media.EXTERNAL_CONTENT_URI, values);
Intent intent = new Intent();
intent.setAction(MediaStore.ACTION_IMAGE_CAPTURE);
intent.putExtra(MediaStore.EXTRA_OUTPUT, imageUri);
startActivityForResult(intent, REQUEST_CAMERA);
}
});
detectedTextView = (TextView) findViewById(R.id.detected_text);
detectedTextView.setMovementMethod(new ScrollingMovementMethod());
}
private void inspectFromBitmap(Bitmap bitmap) {
TextRecognizer textRecognizer = new TextRecognizer.Builder(this).build();
try {
if (!textRecognizer.isOperational()) {
new AlertDialog.
Builder(this).
setMessage("Text recognizer could not be set up on your device").show();
return;
}
Frame frame = new Frame.Builder().setBitmap(bitmap).build();
SparseArray<TextBlock> origTextBlocks = textRecognizer.detect(frame);
List<TextBlock> textBlocks = new ArrayList<>();
for (int i = 0; i < origTextBlocks.size(); i++) {
TextBlock textBlock = origTextBlocks.valueAt(i);
textBlocks.add(textBlock);
}
Collections.sort(textBlocks, new Comparator<TextBlock>() {
@Override
public int compare(TextBlock o1, TextBlock o2) {
int diffOfTops = o1.getBoundingBox().top - o2.getBoundingBox().top;
int diffOfLefts = o1.getBoundingBox().left - o2.getBoundingBox().left;
if (diffOfTops != 0) {
return diffOfTops;
}
return diffOfLefts;
}
});
StringBuilder detectedText = new StringBuilder();
for (TextBlock textBlock : textBlocks) {
if (textBlock != null && textBlock.getValue() != null) {
detectedText.append(textBlock.getValue());
detectedText.append("\n");
}
}
detectedTextView.setText(detectedText);
}
finally {
textRecognizer.release();
}
}
private void inspect(Uri uri) {
InputStream is = null;
Bitmap bitmap = null;
try {
is = getContentResolver().openInputStream(uri);
BitmapFactory.Options options = new BitmapFactory.Options();
options.inPreferredConfig = Bitmap.Config.ARGB_8888;
options.inSampleSize = 2;
options.inScreenDensity = DisplayMetrics.DENSITY_LOW;
bitmap = BitmapFactory.decodeStream(is, null, options);
inspectFromBitmap(bitmap);
} catch (FileNotFoundException e) {
Log.w(TAG, "Failed to find the file: " + uri, e);
} finally {
if (bitmap != null) {
bitmap.recycle();
}
if (is != null) {
try {
is.close();
} catch (IOException e) {
Log.w(TAG, "Failed to close InputStream", e);
}
}
}
}
@Override
protected void onActivityResult(int requestCode, int resultCode, Intent data) {
switch (requestCode) {
case REQUEST_GALLERY:
if (resultCode == RESULT_OK) {
inspect(data.getData());
}
break;
case REQUEST_CAMERA:
if (resultCode == RESULT_OK) {
if (imageUri != null) {
inspect(imageUri);
}
}
break;
default:
super.onActivityResult(requestCode, resultCode, data);
break;
}
}
}
<?xml version="1.0" encoding="utf-8"?>
<RelativeLayout xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:tools="http://schemas.android.com/tools"
android:id="@+id/activity_main"
android:layout_width="match_parent"
android:layout_height="match_parent"
android:paddingBottom="@dimen/activity_vertical_margin"
android:paddingLeft="@dimen/activity_horizontal_margin"
android:paddingRight="@dimen/activity_horizontal_margin"
android:paddingTop="@dimen/activity_vertical_margin"
tools:context="org.komamitsu.android_ocrsample.MainActivity">
<Button
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:text="@string/choose_from_gallery"
android:id="@+id/choose_from_gallery"
tools:context=".MainActivity"
android:layout_marginTop="23dp"
android:layout_alignParentTop="true"
android:layout_centerHorizontal="true" />
<Button
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:text="@string/take_a_photo"
android:id="@+id/take_a_photo"
tools:context=".MainActivity"
android:layout_marginTop="11dp"
android:layout_below="@+id/choose_from_gallery"
android:layout_centerHorizontal="true" />
<TextView
android:text=""
android:layout_width="match_parent"
android:layout_height="match_parent"
android:id="@+id/detected_text"
android:layout_alignParentBottom="true"
android:layout_below="@+id/take_a_photo"
android:layout_margin="25dp"
android:layout_centerHorizontal="true"
android:background="#EEEEEE"
android:scrollbars="vertical" />
</RelativeLayout>