我正试图从相机拍照并通过tesseract-ocr库对其进行OCR。这是我的完整代码：
清单：
<?xml version="1.0" encoding="utf-8"?>
<manifest xmlns:android="http://schemas.android.com/apk/res/android"
package="com.m.ocrapp">
<uses-permission android:name="android.permission.INTERNET"/>
<uses-permission android:name="android.permission.CAMERA"/>
<uses-feature android:name="android.hardware.camera"/>
<uses-feature android:name="android.hardware.camera.autofocus"/>
<uses-feature android:name="android.hardware.camera.front"/>
<uses-feature android:name="android.hardware.camera.front.autofocus"/>
<application
android:allowBackup="true"
android:icon="@mipmap/ic_launcher"
android:label="@string/app_name"
android:roundIcon="@mipmap/ic_launcher_round"
android:supportsRtl="true"
android:theme="@style/AppTheme">
<activity android:name=".MainActivity"
android:screenOrientation="landscape">
<intent-filter>
<action android:name="android.intent.action.MAIN" />
<category android:name="android.intent.category.LAUNCHER" />
</intent-filter>
</activity>
</application>
</manifest>
MainActivity：
package com.m.ocrapp;
public class MainActivity extends AppCompatActivity implements CameraBridgeViewBase.CvCameraViewListener2{
Scalar CONTOUR_COLOR = new Scalar(255);
private Bitmap bmp;
private Mat mIntermediateMat , mGrey, mRgba;
private JavaCameraView mOpenCvCameraView;
private BaseLoaderCallback mLoaderCallback = new BaseLoaderCallback(this) {
@Override
public void onManagerConnected(int status) {
switch (status) {
case LoaderCallbackInterface.SUCCESS: {
mOpenCvCameraView.enableView();
}
break;
default: {
super.onManagerConnected(status);
}
break;
}
}
};
@Override
public void onCameraViewStopped() {
}
@Override
public void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
getWindow().setFlags(WindowManager.LayoutParams.FLAG_FULLSCREEN, WindowManager.LayoutParams.FLAG_FULLSCREEN);
getWindow().addFlags(WindowManager.LayoutParams.FLAG_KEEP_SCREEN_ON);
//FULLSCREEN MODE
getWindow().setFlags(WindowManager.LayoutParams.FLAG_FULLSCREEN, WindowManager.LayoutParams.FLAG_FULLSCREEN);
getWindow().addFlags(WindowManager.LayoutParams.FLAG_KEEP_SCREEN_ON);
setContentView(R.layout.activity_main);
mOpenCvCameraView = findViewById(R.id.my_java_camera);
mOpenCvCameraView.setVisibility(SurfaceView.VISIBLE);
mOpenCvCameraView.setCvCameraViewListener(this);
}
public Mat onCameraFrame(CameraBridgeViewBase.CvCameraViewFrame inputFrame) {
mGrey = inputFrame.gray();
mRgba = inputFrame.rgba();
detectText();
return mRgba;
}
@Override
public void onPause() {
super.onPause();
if (mOpenCvCameraView != null)
mOpenCvCameraView.disableView();
}
@Override
public void onResume() {
super.onResume();
if (!OpenCVLoader.initDebug()) {
OpenCVLoader.initAsync(OpenCVLoader.OPENCV_VERSION_3_1_0, this, mLoaderCallback);
} else {
mLoaderCallback.onManagerConnected(LoaderCallbackInterface.SUCCESS);
}
}
public void onDestroy() {
super.onDestroy();
if (mOpenCvCameraView != null)
mOpenCvCameraView.disableView();
}
public void onCameraViewStarted(int width, int height) {
mIntermediateMat = new Mat();
mGrey = new Mat(height, width, CvType.CV_8UC4);
mRgba = new Mat(height, width, CvType.CV_8UC4);
}
private void doOCR(final Bitmap bitmap) {
String text = mTessOCR.getOCRResult(bitmap);
// String temp = mTessOCR.getOCRResult(bitmap);
}
private void detectText()
{
MatOfKeyPoint keypoint = new MatOfKeyPoint();
List<KeyPoint> listpoint;
KeyPoint kpoint;
Mat mask = Mat.zeros(mGrey.size(), CvType.CV_8UC1);
int rectanx1;
int rectany1;
int rectanx2;
int rectany2;
int imgsize = mGrey.height() * mGrey.width();
Scalar zeos = new Scalar(0, 0, 0);
List<MatOfPoint> contour2 = new ArrayList<MatOfPoint>();
Mat kernel = new Mat(1, 50, CvType.CV_8UC1, Scalar.all(255));
Mat morbyte = new Mat();
Mat hierarchy = new Mat();
Rect rectan3;
//
FeatureDetector detector = FeatureDetector
.create(FeatureDetector.MSER);
detector.detect(mGrey, keypoint);
listpoint = keypoint.toList();
//
for (int ind = 0; ind < listpoint.size(); ind++) {
kpoint = listpoint.get(ind);
rectanx1 = (int) (kpoint.pt.x - 0.5 * kpoint.size);
rectany1 = (int) (kpoint.pt.y - 0.5 * kpoint.size);
rectanx2 = (int) (kpoint.size);
rectany2 = (int) (kpoint.size);
if (rectanx1 <= 0)
rectanx1 = 1;
if (rectany1 <= 0)
rectany1 = 1;
if ((rectanx1 + rectanx2) > mGrey.width())
rectanx2 = mGrey.width() - rectanx1;
if ((rectany1 + rectany2) > mGrey.height())
rectany2 = mGrey.height() - rectany1;
Rect rectant = new Rect(rectanx1, rectany1, rectanx2, rectany2);
try {
Mat roi = new Mat(mask, rectant);
roi.setTo(CONTOUR_COLOR);
} catch (Exception ex) {
Log.d("mylog", "mat roi error " + ex.getMessage());
}
}
Imgproc.morphologyEx(mask, morbyte, Imgproc.MORPH_DILATE, kernel);
Imgproc.findContours(morbyte, contour2, hierarchy,
Imgproc.RETR_EXTERNAL, Imgproc.CHAIN_APPROX_NONE);
/*
for (int ind = 0; ind < contour2.size(); ind++) {
rectan3 = Imgproc.boundingRect(contour2.get(ind));
rectan3 = Imgproc.boundingRect(contour2.get(ind));
if (rectan3.area() > 0.5 * imgsize || rectan3.area() < 100
|| rectan3.width / rectan3.height < 2) {
Mat roi = new Mat(morbyte, rectan3);
roi.setTo(zeos);
} else
Imgproc.rectangle(mRgba, rectan3.br(), rectan3.tl(), CONTOUR_COLOR);
*/
for (int ind = 0; ind < contour2.size(); ind++)
{
rectan3 = Imgproc.boundingRect(contour2.get(ind));
try {
Mat croppedPart;
croppedPart = mIntermediateMat.submat(rectan3);
bmp = Bitmap.createBitmap(croppedPart.width(), croppedPart.height(), Bitmap.Config.ARGB_8888);
Utils.matToBitmap(croppedPart, bmp);
} catch (Exception e) {
// Log.d(TAG, "cropped part data error " + e.getMessage());
}
if (bmp != null) {
doOCR(bmp);
}
}
}
}
MyTessOCR：
package com.m.ocrapp;
public class MyTessOCR
{
private String datapath;
private TessBaseAPI mTess;
Context context;
public MyTessOCR(Context context)
{
datapath = Environment.getExternalStorageDirectory() + "/ocrctz/";
File dir = new File(datapath + "/tessdata/");
File file = new File(datapath + "/tessdata/" + "eng.traineddata");
if (!file.exists()) {
Log.d("mylog", "in file doesn't exist");
dir.mkdirs();
copyFile(context);
}
mTess = new TessBaseAPI();
String language = "eng";
mTess.init(datapath, language);
//Auto only mTess.setPageSegMode(TessBaseAPI.PageSegMode.PSM_AUTO_ONLY);
}
public void stopRecognition()
{
mTess.stop();
}
public String getOCRResult(Bitmap bitmap)
{
mTess.setImage(bitmap);
String result = mTess.getUTF8Text();
return result;
}
public void onDestroy()
{
if (mTess != null)
mTess.end();
}
private void copyFile(Context context)
{
AssetManager assetManager = context.getAssets();
try {
InputStream in = assetManager.open("eng.traineddata");
OutputStream out = new FileOutputStream(datapath + "/tessdata/" + "eng.traineddata");
byte[] buffer = new byte[1024];
int read = in.read(buffer);
while (read != -1)
{
out.write(buffer, 0, read);
read = in.read(buffer);
}
} catch (Exception e)
{
Log.d("mylog", "couldn't copy with the following error : " + e.toString());
}
}
// }
}
但在此行的MainActivity内：mTess.init(datapath, language);
我收到此错误消息：
java.lang.RuntimeException：无法启动活动 ComponentInfo {com.m.ocrapp / com.m.ocrapp.MainActivity}： java.lang.IllegalArgumentException：数据路径不存在！
我还必须说我已在项目的assets路径中创建了app/src/main/assets文件夹，并将eng.traineddata从https://github.com/tesseract-ocr/tessdata/blob/master/eng.traineddata复制到其中。但我认为这还不够，我应该将更多文件从tesseract复制到我的项目中？但我不知道哪些文件在哪里？
（事实上，我在网站内看到了这段代码，并按上述方式进行了尝试）
答案 0 :(得分：1)
<uses-permission android:name="android.permission.CAMERA"/>
<uses-feature android:name="android.hardware.camera"/>
<uses-feature android:name="android.hardware.camera.autofocus"/>
<uses-feature android:name="android.hardware.camera.front"/>
<uses-feature android:name="android.hardware.camera.front.autofocus"/>
缺少android权限。您尝试触摸文件存储系统时需要这些权限。
<uses-permission android:name="android.permission.READ_EXTERNAL_STORAGE" />
<uses-permission android:name="android.permission.WRITE_EXTERNAL_STORAGE" />