Android 上的 OCR 扫描问题
Issue with OCR Scan on Android
我正在尝试使用 tessract/tess-two 库创建带有 OCR 扫描仪的应用程序，我已成功访问 Phone 相机，我可以进行手动对焦，但是当我拍照出现以下错误：
07-18 19:07:06.335 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.MainActivity: Picture taken
07-18 19:07:06.335 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.MainActivity: Got null data
07-18 19:07:06.405 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.MainActivity: Picture taken
07-18 19:07:06.426 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.MainActivity: Got bitmap
07-18 19:07:06.427 2585-11599/com.fastnetserv.myapp E/DBG_com.fastnetserv.myapp.TessAsyncEngine: Error passing parameter to execute(context, bitmap)
07-18 19:07:14.111 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.CameraUtils: CameraEngine Stopped
这里是 CameraFragment 代码：
package com.fastnetserv.myapp;
import android.content.Context;
import android.graphics.Bitmap;
import android.hardware.Camera;
import android.net.Uri;
import android.os.AsyncTask;
import android.os.Bundle;
import android.support.v4.app.Fragment;
import android.util.Log;
import android.view.LayoutInflater;
import android.view.SurfaceHolder;
import android.view.SurfaceView;
import android.view.View;
import android.view.ViewGroup;
import android.widget.Button;
import com.googlecode.tesseract.android.TessBaseAPI;
/**
* A simple {@link Fragment} subclass.
* Activities that contain this fragment must implement the
* {@link //CameraFragment.//OnFragmentInteractionListener} interface
* to handle interaction events.
* Use the {@link CameraFragment#newInstance} factory method to
* create an instance of this fragment.
*/
public class CameraFragment extends Fragment implements SurfaceHolder.Callback, View.OnClickListener,
Camera.PictureCallback, Camera.ShutterCallback {
static final String TAG = "DBG_" + MainActivity.class.getName();
Button shutterButton;
Button focusButton;
FocusBoxView focusBox;
SurfaceView cameraFrame;
CameraEngine cameraEngine;
// TODO: Rename parameter arguments, choose names that match
// the fragment initialization parameters, e.g. ARG_ITEM_NUMBER
private static final String ARG_PARAM1 = "param1";
private static final String ARG_PARAM2 = "param2";
// TODO: Rename and change types of parameters
private String mParam1;
private String mParam2;
private OnFragmentInteractionListener mListener;
public CameraFragment() {
// Required empty public constructor
}
/**
* Use this factory method to create a new instance of
* this fragment using the provided parameters.
*
* @param param1 Parameter 1.
* @param param2 Parameter 2.
* @return A new instance of fragment CameraFragment.
*/
// TODO: Rename and change types and number of parameters
public static CameraFragment newInstance(String param1, String param2) {
CameraFragment fragment = new CameraFragment();
Bundle args = new Bundle();
args.putString(ARG_PARAM1, param1);
args.putString(ARG_PARAM2, param2);
fragment.setArguments(args);
return fragment;
}
@Override
public void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
if (getArguments() != null) {
mParam1 = getArguments().getString(ARG_PARAM1);
mParam2 = getArguments().getString(ARG_PARAM2);
}
}
@Override
public View onCreateView(LayoutInflater inflater, ViewGroup container,
Bundle savedInstanceState) {
// Inflate the layout for this fragment
return inflater.inflate(R.layout.fragment_camera, container, false);
}
// TODO: Rename method, update argument and hook method into UI event
public void onButtonPressed(Uri uri) {
if (mListener != null) {
mListener.onFragmentInteraction(uri);
}
}
@Override
public void onAttach(Context context) {
super.onAttach(context);
try {
mListener = (OnFragmentInteractionListener) context;
} catch (ClassCastException e) {
throw new ClassCastException(context.toString()
+ " must implement OnFragmentInteractionListener");
}
}
@Override
public void onDetach() {
super.onDetach();
mListener = null;
}
// Camera Code
public String detectText(Bitmap bitmap) {
TessDataManager.initTessTrainedData(getActivity());
TessBaseAPI tessBaseAPI = new TessBaseAPI();
String path = "/mnt/sdcard/com.fastnetserv.myapp/tessdata/ita.traineddata";
Log.d(TAG, "Check data path: " + path);
tessBaseAPI.setDebug(true);
tessBaseAPI.init(path, "ita"); //Init the Tess with the trained data file, with english language
//For example if we want to only detect numbers
tessBaseAPI.setVariable(TessBaseAPI.VAR_CHAR_WHITELIST, "1234567890");
tessBaseAPI.setVariable(TessBaseAPI.VAR_CHAR_BLACKLIST, "!@#$%^&*()_+=-qwertyuiop[]}{POIU" +
"YTREWQasdASDfghFGHjklJKLl;L:'\"\|~`xcvXCVbnmBNM,./<>?");
tessBaseAPI.setImage(bitmap);
String text = tessBaseAPI.getUTF8Text();
//Log.d(TAG, "Got data: " + result);
tessBaseAPI.end();
return text;
}
@Override
public void surfaceCreated(SurfaceHolder holder) {
Log.d(TAG, "Surface Created - starting camera");
if (cameraEngine != null && !cameraEngine.isOn()) {
cameraEngine.start();
}
if (cameraEngine != null && cameraEngine.isOn()) {
Log.d(TAG, "Camera engine already on");
return;
}
cameraEngine = CameraEngine.New(holder);
cameraEngine.start();
Log.d(TAG, "Camera engine started");
}
@Override
public void surfaceChanged(SurfaceHolder holder, int format, int width, int height) {
}
@Override
public void surfaceDestroyed(SurfaceHolder holder) {
}
@Override
public void onResume() {
super.onResume();
cameraFrame = (SurfaceView) getActivity().findViewById(R.id.camera_frame);
shutterButton = (Button) getActivity().findViewById(R.id.shutter_button);
focusBox = (FocusBoxView) getActivity().findViewById(R.id.focus_box);
focusButton = (Button) getActivity().findViewById(R.id.focus_button);
shutterButton.setOnClickListener(this);
focusButton.setOnClickListener(this);
SurfaceHolder surfaceHolder = cameraFrame.getHolder();
surfaceHolder.addCallback(this);
surfaceHolder.setType(SurfaceHolder.SURFACE_TYPE_PUSH_BUFFERS);
cameraFrame.setOnClickListener(this);
}
@Override
public void onPause() {
super.onPause();
if (cameraEngine != null && cameraEngine.isOn()) {
cameraEngine.stop();
}
SurfaceHolder surfaceHolder = cameraFrame.getHolder();
surfaceHolder.removeCallback(this);
}
@Override
public void onClick(View v) {
if(v == shutterButton){
if(cameraEngine != null && cameraEngine.isOn()){
cameraEngine.takeShot(this, this, this);
}
}
if(v == focusButton){
if(cameraEngine!=null && cameraEngine.isOn()){
cameraEngine.requestFocus();
}
}
}
@Override
public void onPictureTaken(byte[] data, Camera camera) {
Log.d(TAG, "Picture taken");
if (data == null) {
Log.d(TAG, "Got null data");
return;
}
Bitmap bmp = Tools.getFocusedBitmap(getActivity(), camera, data, focusBox.getBox());
Log.d(TAG, "Got bitmap");
new TessAsyncEngine().executeOnExecutor(AsyncTask.SERIAL_EXECUTOR, this, bmp);
}
@Override
public void onShutter() {
}
}
这里是 TessAsyncEngine：
package com.fastnetserv.myapp;
import android.app.Activity;
import android.graphics.Bitmap;
import android.os.AsyncTask;
import android.util.Log;
import com.fastnetserv.myapp.ImageDialog;
import com.fastnetserv.myapp.Tools;
/**
* Created by Fadi on 6/11/2014.
*/
public class TessAsyncEngine extends AsyncTask<Object, Void, String> {
static final String TAG = "DBG_" + TessAsyncEngine.class.getName();
private Bitmap bmp;
private Activity context;
@Override
protected String doInBackground(Object... params) {
try {
if(params.length < 2) {
Log.e(TAG, "Error passing parameter to execute - missing params");
return null;
}
if(!(params[0] instanceof Activity) || !(params[1] instanceof Bitmap)) {
Log.e(TAG, "Error passing parameter to execute(context, bitmap)");
return null;
}
context = (Activity)params[0];
bmp = (Bitmap)params[1];
if(context == null || bmp == null) {
Log.e(TAG, "Error passed null parameter to execute(context, bitmap)");
return null;
}
int rotate = 0;
if(params.length == 3 && params[2]!= null && params[2] instanceof Integer){
rotate = (Integer) params[2];
}
if(rotate >= -180 && rotate <= 180 && rotate != 0)
{
bmp = Tools.preRotateBitmap(bmp, rotate);
Log.d(TAG, "Rotated OCR bitmap " + rotate + " degrees");
}
TessEngine tessEngine = TessEngine.Generate(context);
bmp = bmp.copy(Bitmap.Config.ARGB_8888, true);
String result = tessEngine.detectText(bmp);
Log.d(TAG, result);
return result;
} catch (Exception ex) {
Log.d(TAG, "Error: " + ex + "\n" + ex.getMessage());
}
return null;
}
@Override
protected void onPostExecute(String s) {
if(s == null || bmp == null || context == null)
return;
ImageDialog.New()
.addBitmap(bmp)
.addTitle(s)
.show(context.getFragmentManager(), TAG);
super.onPostExecute(s);
}
}
我遵循了本教程 (http://www.codeproject.com/Tips/840623/Android-Character-Recognition)，但可能由于我对 Android
缺乏了解而忘记了一些东西
不需要 if(context == null || bmp == null)，因为您已经用 instanceof.
测试了这些值
但我猜你的主要问题是从 Fragment 中将 this 作为 Activity 参数传递，而事实并非如此。
修复.. 我总体上会尽量不要乱扔 Activity 指针，因为它们在 android 上的生命周期非常有限。我有一个带有 tess-two 的应用程序，我不记得曾经需要 Activity 来初始化它（尽管通常我从原生 C++ 初始化它，所以 YMMV）。
不只是那个电话需要 Context 吗？如果是，我建议改用 getApplicationContext() 值。我认为这也可以从 Fragment 直接或间接访问。
很抱歉没有尝试你的代码，但这是你可以很容易调试的东西。
关于 android 和 tesseract 用法的更多说明。什么是 Tools.getFocusedBitmap？会合理裁剪图片吗？如果它保持全尺寸，并且您的相机设置为全尺寸，那么您将扔掉大约 5-10+MP 位图，这在 Android 中意味着几乎立即发生内存不足 (OOM)。要么将相机设置为合理的低分辨率，要么尽快剪掉照片的设计部分并丢弃整个图像，理想情况下作为处理的第一步。
另外，您可能想重新考虑一下 tess-two 的全部内容，并尝试来自 Google 播放服务的官方 Google 文本 API。
https://developers.google.com/android/reference/com/google/android/gms/vision/text/Text
这是全新的添加，我猜它会使用第二代 Tesseract 引擎进行最新改进，因此很可能会比 tess-two 获得更好的结果和更快的速度。
我认为它只能从 Android 4.4 访问，并且只能在具有 Google Play 服务的设备上访问，而且跨平台很烂，所以我在我的项目中继续使用 tess-two - 作为我也必须支持 iOS 和 Windows Phone.
而且我一般不相信没有源码的东西，没有源码的软件就是僵尸，你用的时候已经死了（最多30-50年就死了），而且是浪费那些程序员的时间和技能。
我正在尝试使用 tessract/tess-two 库创建带有 OCR 扫描仪的应用程序，我已成功访问 Phone 相机，我可以进行手动对焦，但是当我拍照出现以下错误：
07-18 19:07:06.335 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.MainActivity: Picture taken
07-18 19:07:06.335 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.MainActivity: Got null data
07-18 19:07:06.405 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.MainActivity: Picture taken
07-18 19:07:06.426 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.MainActivity: Got bitmap
07-18 19:07:06.427 2585-11599/com.fastnetserv.myapp E/DBG_com.fastnetserv.myapp.TessAsyncEngine: Error passing parameter to execute(context, bitmap)
07-18 19:07:14.111 2585-2585/com.fastnetserv.myapp D/DBG_com.fastnetserv.myapp.CameraUtils: CameraEngine Stopped
这里是 CameraFragment 代码：
package com.fastnetserv.myapp;
import android.content.Context;
import android.graphics.Bitmap;
import android.hardware.Camera;
import android.net.Uri;
import android.os.AsyncTask;
import android.os.Bundle;
import android.support.v4.app.Fragment;
import android.util.Log;
import android.view.LayoutInflater;
import android.view.SurfaceHolder;
import android.view.SurfaceView;
import android.view.View;
import android.view.ViewGroup;
import android.widget.Button;
import com.googlecode.tesseract.android.TessBaseAPI;
/**
* A simple {@link Fragment} subclass.
* Activities that contain this fragment must implement the
* {@link //CameraFragment.//OnFragmentInteractionListener} interface
* to handle interaction events.
* Use the {@link CameraFragment#newInstance} factory method to
* create an instance of this fragment.
*/
public class CameraFragment extends Fragment implements SurfaceHolder.Callback, View.OnClickListener,
Camera.PictureCallback, Camera.ShutterCallback {
static final String TAG = "DBG_" + MainActivity.class.getName();
Button shutterButton;
Button focusButton;
FocusBoxView focusBox;
SurfaceView cameraFrame;
CameraEngine cameraEngine;
// TODO: Rename parameter arguments, choose names that match
// the fragment initialization parameters, e.g. ARG_ITEM_NUMBER
private static final String ARG_PARAM1 = "param1";
private static final String ARG_PARAM2 = "param2";
// TODO: Rename and change types of parameters
private String mParam1;
private String mParam2;
private OnFragmentInteractionListener mListener;
public CameraFragment() {
// Required empty public constructor
}
/**
* Use this factory method to create a new instance of
* this fragment using the provided parameters.
*
* @param param1 Parameter 1.
* @param param2 Parameter 2.
* @return A new instance of fragment CameraFragment.
*/
// TODO: Rename and change types and number of parameters
public static CameraFragment newInstance(String param1, String param2) {
CameraFragment fragment = new CameraFragment();
Bundle args = new Bundle();
args.putString(ARG_PARAM1, param1);
args.putString(ARG_PARAM2, param2);
fragment.setArguments(args);
return fragment;
}
@Override
public void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
if (getArguments() != null) {
mParam1 = getArguments().getString(ARG_PARAM1);
mParam2 = getArguments().getString(ARG_PARAM2);
}
}
@Override
public View onCreateView(LayoutInflater inflater, ViewGroup container,
Bundle savedInstanceState) {
// Inflate the layout for this fragment
return inflater.inflate(R.layout.fragment_camera, container, false);
}
// TODO: Rename method, update argument and hook method into UI event
public void onButtonPressed(Uri uri) {
if (mListener != null) {
mListener.onFragmentInteraction(uri);
}
}
@Override
public void onAttach(Context context) {
super.onAttach(context);
try {
mListener = (OnFragmentInteractionListener) context;
} catch (ClassCastException e) {
throw new ClassCastException(context.toString()
+ " must implement OnFragmentInteractionListener");
}
}
@Override
public void onDetach() {
super.onDetach();
mListener = null;
}
// Camera Code
public String detectText(Bitmap bitmap) {
TessDataManager.initTessTrainedData(getActivity());
TessBaseAPI tessBaseAPI = new TessBaseAPI();
String path = "/mnt/sdcard/com.fastnetserv.myapp/tessdata/ita.traineddata";
Log.d(TAG, "Check data path: " + path);
tessBaseAPI.setDebug(true);
tessBaseAPI.init(path, "ita"); //Init the Tess with the trained data file, with english language
//For example if we want to only detect numbers
tessBaseAPI.setVariable(TessBaseAPI.VAR_CHAR_WHITELIST, "1234567890");
tessBaseAPI.setVariable(TessBaseAPI.VAR_CHAR_BLACKLIST, "!@#$%^&*()_+=-qwertyuiop[]}{POIU" +
"YTREWQasdASDfghFGHjklJKLl;L:'\"\|~`xcvXCVbnmBNM,./<>?");
tessBaseAPI.setImage(bitmap);
String text = tessBaseAPI.getUTF8Text();
//Log.d(TAG, "Got data: " + result);
tessBaseAPI.end();
return text;
}
@Override
public void surfaceCreated(SurfaceHolder holder) {
Log.d(TAG, "Surface Created - starting camera");
if (cameraEngine != null && !cameraEngine.isOn()) {
cameraEngine.start();
}
if (cameraEngine != null && cameraEngine.isOn()) {
Log.d(TAG, "Camera engine already on");
return;
}
cameraEngine = CameraEngine.New(holder);
cameraEngine.start();
Log.d(TAG, "Camera engine started");
}
@Override
public void surfaceChanged(SurfaceHolder holder, int format, int width, int height) {
}
@Override
public void surfaceDestroyed(SurfaceHolder holder) {
}
@Override
public void onResume() {
super.onResume();
cameraFrame = (SurfaceView) getActivity().findViewById(R.id.camera_frame);
shutterButton = (Button) getActivity().findViewById(R.id.shutter_button);
focusBox = (FocusBoxView) getActivity().findViewById(R.id.focus_box);
focusButton = (Button) getActivity().findViewById(R.id.focus_button);
shutterButton.setOnClickListener(this);
focusButton.setOnClickListener(this);
SurfaceHolder surfaceHolder = cameraFrame.getHolder();
surfaceHolder.addCallback(this);
surfaceHolder.setType(SurfaceHolder.SURFACE_TYPE_PUSH_BUFFERS);
cameraFrame.setOnClickListener(this);
}
@Override
public void onPause() {
super.onPause();
if (cameraEngine != null && cameraEngine.isOn()) {
cameraEngine.stop();
}
SurfaceHolder surfaceHolder = cameraFrame.getHolder();
surfaceHolder.removeCallback(this);
}
@Override
public void onClick(View v) {
if(v == shutterButton){
if(cameraEngine != null && cameraEngine.isOn()){
cameraEngine.takeShot(this, this, this);
}
}
if(v == focusButton){
if(cameraEngine!=null && cameraEngine.isOn()){
cameraEngine.requestFocus();
}
}
}
@Override
public void onPictureTaken(byte[] data, Camera camera) {
Log.d(TAG, "Picture taken");
if (data == null) {
Log.d(TAG, "Got null data");
return;
}
Bitmap bmp = Tools.getFocusedBitmap(getActivity(), camera, data, focusBox.getBox());
Log.d(TAG, "Got bitmap");
new TessAsyncEngine().executeOnExecutor(AsyncTask.SERIAL_EXECUTOR, this, bmp);
}
@Override
public void onShutter() {
}
}
这里是 TessAsyncEngine：
package com.fastnetserv.myapp;
import android.app.Activity;
import android.graphics.Bitmap;
import android.os.AsyncTask;
import android.util.Log;
import com.fastnetserv.myapp.ImageDialog;
import com.fastnetserv.myapp.Tools;
/**
* Created by Fadi on 6/11/2014.
*/
public class TessAsyncEngine extends AsyncTask<Object, Void, String> {
static final String TAG = "DBG_" + TessAsyncEngine.class.getName();
private Bitmap bmp;
private Activity context;
@Override
protected String doInBackground(Object... params) {
try {
if(params.length < 2) {
Log.e(TAG, "Error passing parameter to execute - missing params");
return null;
}
if(!(params[0] instanceof Activity) || !(params[1] instanceof Bitmap)) {
Log.e(TAG, "Error passing parameter to execute(context, bitmap)");
return null;
}
context = (Activity)params[0];
bmp = (Bitmap)params[1];
if(context == null || bmp == null) {
Log.e(TAG, "Error passed null parameter to execute(context, bitmap)");
return null;
}
int rotate = 0;
if(params.length == 3 && params[2]!= null && params[2] instanceof Integer){
rotate = (Integer) params[2];
}
if(rotate >= -180 && rotate <= 180 && rotate != 0)
{
bmp = Tools.preRotateBitmap(bmp, rotate);
Log.d(TAG, "Rotated OCR bitmap " + rotate + " degrees");
}
TessEngine tessEngine = TessEngine.Generate(context);
bmp = bmp.copy(Bitmap.Config.ARGB_8888, true);
String result = tessEngine.detectText(bmp);
Log.d(TAG, result);
return result;
} catch (Exception ex) {
Log.d(TAG, "Error: " + ex + "\n" + ex.getMessage());
}
return null;
}
@Override
protected void onPostExecute(String s) {
if(s == null || bmp == null || context == null)
return;
ImageDialog.New()
.addBitmap(bmp)
.addTitle(s)
.show(context.getFragmentManager(), TAG);
super.onPostExecute(s);
}
}
我遵循了本教程 (http://www.codeproject.com/Tips/840623/Android-Character-Recognition)，但可能由于我对 Android
缺乏了解而忘记了一些东西不需要 if(context == null || bmp == null)，因为您已经用 instanceof.
但我猜你的主要问题是从 Fragment 中将 this 作为 Activity 参数传递，而事实并非如此。
修复.. 我总体上会尽量不要乱扔 Activity 指针，因为它们在 android 上的生命周期非常有限。我有一个带有 tess-two 的应用程序，我不记得曾经需要 Activity 来初始化它（尽管通常我从原生 C++ 初始化它，所以 YMMV）。
不只是那个电话需要 Context 吗？如果是，我建议改用 getApplicationContext() 值。我认为这也可以从 Fragment 直接或间接访问。
很抱歉没有尝试你的代码，但这是你可以很容易调试的东西。
关于 android 和 tesseract 用法的更多说明。什么是 Tools.getFocusedBitmap？会合理裁剪图片吗？如果它保持全尺寸，并且您的相机设置为全尺寸，那么您将扔掉大约 5-10+MP 位图，这在 Android 中意味着几乎立即发生内存不足 (OOM)。要么将相机设置为合理的低分辨率，要么尽快剪掉照片的设计部分并丢弃整个图像，理想情况下作为处理的第一步。
另外，您可能想重新考虑一下 tess-two 的全部内容，并尝试来自 Google 播放服务的官方 Google 文本 API。
https://developers.google.com/android/reference/com/google/android/gms/vision/text/Text
这是全新的添加，我猜它会使用第二代 Tesseract 引擎进行最新改进，因此很可能会比 tess-two 获得更好的结果和更快的速度。
我认为它只能从 Android 4.4 访问，并且只能在具有 Google Play 服务的设备上访问，而且跨平台很烂，所以我在我的项目中继续使用 tess-two - 作为我也必须支持 iOS 和 Windows Phone.
而且我一般不相信没有源码的东西，没有源码的软件就是僵尸，你用的时候已经死了（最多30-50年就死了），而且是浪费那些程序员的时间和技能。