Android: How to improve the numbers within the ima

2019-04-05 03:47发布

站内文章 / Java
27 0 0

问题:

I made a simple app that reads images and retrieves the number image as text with android. But the problem is that the accuracy is only about 60% and some unwanted noise also shows as well. I do perceive that the accuracy cannot be good as 100%,however, I believe that there must be a way to improve it. But, since I'm an amateur, I find it difficult. I've searched around google but was unable to gain a solid information.

I want to read the numbers 596 , 00 , and 012345 from a oriental lucky tickets like the image below.

回答1:

Tesseract-ocr works best on images of characters which meet the following criteria:

  • The input image should have atleast 300 dpi

  • The input image should be black and white

  • There should be minimal noise in the input image (i.e. the text should be clearly distinguishable from the background)

  • Text lines should be straight

  • The image should be centered around the text to be detected

(See the tesseract-ocr wiki for further details)

For a given input image, tesseract will try to pre-process and clean the image to meet these criteria, but to maximise your detection accuracy, it is best to do the pre-processing yourself.

Based on the input image you provided, the main problem is that there is too much background noise. To remove the background noise from the text in the image, I have found that applying the Stroke Width Transform (SWT) algorithm with a threshold value to remove noise gives promising results. A fast implementation of SWT with many configurable parameters is provided in the libCCV library. How well it cleans the image depends on a number of factors including image size, uniformity of stroke width and other input parameters to the algorithm. A list of the configurable parameters is provided here.

You then pass the output of SWT to tesseract to obtain the text values of characters in the image.

If the image passed to tesseract still contains some noise, it may return some false detections such as punctuation characters. Given that the image you are processing is likely to only contain letters and numbers a-z A-Z 0-9, you can simply apply a regex to the output to remove any final false detections.



回答2:

you can use Vision for text detection.

Add dependency in app gradle

compile 'com.google.android.gms:play-services-vision:10.0.0'

Add in Manifest.xml

<meta-data
        android:name="com.google.android.gms.vision.DEPENDENCIES"
        android:value="ocr" />

MainActivity.java

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;
        }
    }
}

activity_main.xml

<?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>


标签： java android ocr tesseract
举报

收藏的人(0)

Ta的文章 更多文章
登录 后发表评论
0条评论
还没有人评论过~