OCR Android

1. OCR là gì ?

Là viết tắt của Optical Character Recognition(Nhận dạng ký tự quang học). Nếu bạn nhìn thấy một bức ảnh nào đấy chứa nhiều ký tự hay những câu chữ ý nghĩa mà bạn muốn lấy chúng ra khỏi bức ảnh mà không phải ngồi gõ từng ký tự một thì OCR sẻ giúp bạn tách những chữ bên trong hình ảnh ra chỉ trong nháy mắt. Bạn có thể dịch, có thể tìm kiếm, hay làm bất cứ thứ gì bạn mốn với đoạn text mà bạn có thông qua OCR.

2. CODE DEMO

  • AndroidManifest.xml Bổ sung
<uses-feature
        android:name="android.hardware.camera"
        android:required="true"/>
    <uses-permission
        android:name="android.permission.WRITE_EXTERNAL_STORAGE"/>
  • build.gradle Thêm compile 'com.google.android.gms:play-services-vision:9.8.0' vào dependencies

  • Lớp MainActivity.java

    private static final int PHOTO_REQUEST = 0;
    private TextView scanResults;
    private Uri imageUri ;
    private TextRecognizer detector;
    private static final int REQUEST_WRITE_PERMISSION = 1;
    private static final String SAVED_INSTANCE_URI = "uri";
    private static final String SAVED_INSTANCE_RESULT = "result";

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_main);
        Button button = (Button) findViewById(R.id.button);
        scanResults = (TextView) findViewById(R.id.results);
        if (savedInstanceState != null) {
            imageUri = Uri.parse(savedInstanceState.getString(SAVED_INSTANCE_URI));
            scanResults.setText(savedInstanceState.getString(SAVED_INSTANCE_RESULT));
        }
        detector = new TextRecognizer.Builder(getApplicationContext()).build();
        button.setOnClickListener(new View.OnClickListener() {
            @Override
            public void onClick(View view) {
                ActivityCompat.requestPermissions(MainActivity.this, new
                        String[]{Manifest.permission.WRITE_EXTERNAL_STORAGE}, REQUEST_WRITE_PERMISSION);
            }
        });
    }

    @Override
    public void onRequestPermissionsResult(int requestCode, @NonNull String[] permissions, @NonNull int[] grantResults) {
        super.onRequestPermissionsResult(requestCode, permissions, grantResults);
        switch (requestCode) {
            case REQUEST_WRITE_PERMISSION:
                if (grantResults.length > 0 && grantResults[0] == PackageManager.PERMISSION_GRANTED) {
                    takePicture();
                } else {
                    Toast.makeText(MainActivity.this, "Permission Denied!", Toast.LENGTH_SHORT).show();
                }
        }
    }

    @Override
    protected void onActivityResult(int requestCode, int resultCode, Intent data) {
        if (requestCode == PHOTO_REQUEST && resultCode == RESULT_OK) {
            launchMediaScanIntent();
            try {
                Bitmap bitmap = decodeBitmapUri(this, imageUri);
                if (detector.isOperational() && bitmap != null) {
                    Frame frame = new Frame.Builder().setBitmap(bitmap).build();
                    SparseArray<TextBlock> textBlocks = detector.detect(frame);
                    String blocks = "";
                    for (int index = 0; index < textBlocks.size(); index++) {
                        TextBlock tBlock = textBlocks.valueAt(index);
                        blocks = blocks + tBlock.getValue() + "\n" + "\n";
                    }
                    if (textBlocks.size() == 0) {
                        scanResults.setText("Scan Failed: Found nothing to scan");
                    } else {
                        scanResults.setText(scanResults.getText() + blocks + "\n");
                    }
                } else {
                    scanResults.setText("Could not set up the detector!");
                }
            } catch (Exception e) {
                Toast.makeText(this, "Failed to load Image", Toast.LENGTH_SHORT)
                        .show();
            }
        }
    }

    private void takePicture() {
        Intent intent = new Intent(MediaStore.ACTION_IMAGE_CAPTURE);
        File photo = new File(Environment.getExternalStorageDirectory(), "picture.jpg");
        imageUri = Uri.fromFile(photo);
        intent.putExtra(MediaStore.EXTRA_OUTPUT, imageUri);
        startActivityForResult(intent, PHOTO_REQUEST);
    }

    @Override
    protected void onSaveInstanceState(Bundle outState) {
        if (imageUri != null) {
            outState.putString(SAVED_INSTANCE_URI, imageUri.toString());
            outState.putString(SAVED_INSTANCE_RESULT, scanResults.getText().toString());
        }
        super.onSaveInstanceState(outState);
    }

    private void launchMediaScanIntent() {
        Intent mediaScanIntent = new Intent(Intent.ACTION_MEDIA_SCANNER_SCAN_FILE);
        mediaScanIntent.setData(imageUri);
        this.sendBroadcast(mediaScanIntent);
    }

    private Bitmap decodeBitmapUri(Context ctx, Uri uri) throws FileNotFoundException {
        int targetW = 600;
        int targetH = 600;
        BitmapFactory.Options bmOptions = new BitmapFactory.Options();
        bmOptions.inJustDecodeBounds = true;
        BitmapFactory.decodeStream(ctx.getContentResolver().openInputStream(uri), null, bmOptions);
        int photoW = bmOptions.outWidth;
        int photoH = bmOptions.outHeight;

        int scaleFactor = Math.min(photoW / targetW, photoH / targetH);
        bmOptions.inJustDecodeBounds = false;
        bmOptions.inSampleSize = scaleFactor;

        return BitmapFactory.decodeStream(ctx.getContentResolver()
                .openInputStream(uri), null, bmOptions);
    }
  • Tạo gia diện cho ứng dụng
 <Button
        android:id="@+id/button"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:layout_marginBottom="8dp"
        android:text="Scan Text"
        app:layout_constraintBottom_toBottomOf="parent"
        app:layout_constraintLeft_toLeftOf="parent"
        app:layout_constraintRight_toRightOf="parent"
        tools:layout_constraintLeft_creator="1"
        tools:layout_constraintRight_creator="1"
        />

    <TextView
        android:id="@+id/textView"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:text="Scan Results:"
        android:textAllCaps="false"
        android:textStyle="normal|bold"
        app:layout_constraintLeft_toLeftOf="parent"
        app:layout_constraintRight_toRightOf="parent"
        tools:layout_constraintLeft_creator="1"
        tools:layout_constraintRight_creator="1"
        tools:layout_editor_absoluteY="0dp"/>

    <ScrollView
        android:layout_width="0dp"
        android:layout_height="0dp"
        android:layout_marginTop="8dp"
        android:paddingLeft="5dp"
        android:paddingRight="5dp"
        app:layout_constraintBottom_toBottomOf="parent"
        app:layout_constraintHorizontal_bias="1.0"
        app:layout_constraintLeft_toLeftOf="parent"
        app:layout_constraintRight_toRightOf="parent"
        app:layout_constraintTop_toBottomOf="@+id/textView"
        tools:layout_constraintBottom_creator="1"
        tools:layout_constraintLeft_creator="1"
        tools:layout_constraintRight_creator="1"
        tools:layout_constraintTop_creator="1">

        <LinearLayout
            android:layout_width="match_parent"
            android:layout_height="wrap_content"
            android:orientation="vertical">

            <TextView
                android:id="@+id/results"
                android:layout_width="wrap_content"
                android:layout_height="wrap_content"
                android:layout_marginTop="8dp"
                app:layout_constraintLeft_toLeftOf="parent"
                app:layout_constraintRight_toRightOf="parent"
                tools:layout_constraintLeft_creator="1"
                tools:layout_constraintRight_creator="1"
                tools:layout_constraintTop_creator="1"/>
        </LinearLayout>
    </ScrollView>

Ok, vậy là bạn đã tạo được 1 app OCR đơn giản.