概述
Tesseract是一个OCR（Optical Character Recognition，光学字符识别）引擎，在这里我用来开发Android上能识别一张图片上的股票代码APP功能。
Github地址
这个库非常庞大，反正我是看不出怎么使用在Android开发上，于是我找了另一个库，https://github.com/rmtheis/tess-two ，应该是基于前面的库制作的。
添加依赖
dependencies {
compile 'com.rmtheis:tess-two:8.0.0'
}
布局
布局非常简单，只有右上角一个导入按钮：
布局
xml
<?xml version="1.0" encoding="utf-8"?>
<RelativeLayout xmlns:android="http://schemas.android.com/apk/res/android"
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">
<!--显示识别结果-->
<TextView
android:id="@+id/text"
android:layout_width="wrap_content"
android:layout_height="wrap_content"/>
<!--识别过程中的进度条-->
<ProgressBar
android:id="@+id/progressBar"
android:layout_width="match_parent"
android:layout_height="wrap_content"
android:indeterminate="true"
android:visibility="gone"
android:layout_centerInParent="true"/>
<!--显示识别图片前处理过后的图片-->
<ImageView
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:layout_alignParentRight="true"
android:layout_alignParentEnd="true"
android:id="@+id/imageView" />
</RelativeLayout>
导入识别库
先去这里下载识别库，少了这个识别库没有使用的，而且不同的识别库识别准确率也是不一样的，当你发现准确率低是可以尝试换一个识别库或许会改善，里面有很多语言的识别库，其他语言的不需要关心，我们只需要记住开头chi_sim的是简体中文，chi_tra是繁体中文，eng是英语，eus应该是美式英语。我使用的是eus.traineddata。
先在项目里新建assert目录-tessdata目录-eus.traineddata。
image.png
可以编写代码了
直接看代码
public class MainActivity extends AppCompatActivity {
private static final String TAG = MainActivity.class.getSimpleName();
private static final int REQUEST_PICK_PHOTO = 1;
private TessBaseAPI tessBaseAPI;
private static final String lang = "eus";//识别库
//private static final String lang = "chi_sim";
private static final String DATA_PATH = Environment.getExternalStorageDirectory().toString() + "/Tesseract/";
private static final String TESSDATA = "tessdata";
String result = "empty";
private TextView text;
private ProgressBar progressBar;
private ImageView imageView;
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
Toolbar toolbar = (Toolbar) findViewById(R.id.toolbar);
setSupportActionBar(toolbar);
text = (TextView) findViewById(R.id.text);
progressBar = (ProgressBar) findViewById(R.id.progressBar);
imageView = (ImageView) findViewById(R.id.imageView);
}
@Override
public boolean onCreateOptionsMenu(Menu menu) {
getMenuInflater().inflate(R.menu.menu_main, menu);
return true;
}
@Override
public boolean onOptionsItemSelected(MenuItem item) {
int id = item.getItemId();
if (id == R.id.dao_ru) {
//打开图库选择图片
pickPhoto();
}
return super.onOptionsItemSelected(item);
}
private void pickPhoto() {
Intent intent = new Intent(Intent.ACTION_PICK, android.provider.MediaStore.Images.Media.EXTERNAL_CONTENT_URI);
startActivityForResult(intent, REQUEST_PICK_PHOTO);
}
@Override
protected void onActivityResult(int requestCode, int resultCode, Intent data) {
super.onActivityResult(requestCode,resultCode,data);
if (requestCode == REQUEST_PICK_PHOTO && resultCode == RESULT_OK) {
//首先需要把assert目录中的识别库拷贝到手机中
prepareTesseract();
Uri uri = data.getData();
BitmapFactory.Options options = new BitmapFactory.Options();
options.inSampleSize = 1;
Bitmap bitmap = BitmapFactory.decodeFile(getRealImageFilePath(this,uri));
//把图片处理成黑白的，有利于识别
bitmap = toHeibai(bitmap);
//识别耗时，放在异步处理
new MyAsyckTask().execute( bitmap);
}
}
public static String getRealImageFilePath( Context context,Uri uri) {
if( uri == null ) {
return null;
}
String[] filePathColumn = {MediaStore.Images.Media.DATA};
Cursor cursor = context.getContentResolver().query(uri, filePathColumn, null, null, null);
if (cursor!=null){
if (cursor.moveToFirst()) {
int columnIndex = cursor.getColumnIndex(filePathColumn[0]);
String yourRealPath = cursor.getString(columnIndex);
return yourRealPath;
}
cursor.close();
}
return uri.getPath();
}
//在手机中新建目录
private void prepareDirectory(String path) {
File dir = new File(path);
if (!dir.exists()) {
if (!dir.mkdirs()) {
Log.e(TAG, "ERROR: Creation of directory " + path + " failed, check does Android Manifest have permission to write to external storage.");
}
} else {
Log.i(TAG, "Created directory " + path);
}
}
private void prepareTesseract() {
try {
prepareDirectory(DATA_PATH + TESSDATA);
} catch (Exception e) {
e.printStackTrace();
}
copyTessDataFiles(TESSDATA);
}
//拷贝识别库到手机
private void copyTessDataFiles(String path) {
try {
String fileList[] = getAssets().list(path);
for (String fileName : fileList) {
// open file within the assets folder
// if it is not already there copy it to the sdcard
String pathToDataFile = DATA_PATH + path + "/" + fileName;
if (!(new File(pathToDataFile)).exists()) {
InputStream in = getAssets().open(path + "/" + fileName);
OutputStream out = new FileOutputStream(pathToDataFile);
// Transfer bytes from in to out
byte[] buf = new byte[1024];
int len;
while ((len = in.read(buf)) > 0) {
out.write(buf, 0, len);
}
in.close();
out.close();
Log.d(TAG, "Copied " + fileName + "to tessdata");
}
}
} catch (IOException e) {
Log.e(TAG, "Unable to copy files to tessdata " + e.toString());
}
}
//真正从图片提取内容的方法
private String extractText(Bitmap bitmap) {
try {
tessBaseAPI = new TessBaseAPI();
} catch (Exception e) {
Log.e(TAG, e.getMessage());
if (tessBaseAPI == null) {
Log.e(TAG, "TessBaseAPI is null. TessFactory not returning tess object.");
}
}
tessBaseAPI.init(DATA_PATH, lang);
// //EXTRA SETTINGS 提取设置
// //For example if we only want to detect numbers 白名单
tessBaseAPI.setVariable(TessBaseAPI.VAR_CHAR_WHITELIST, "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_");
//tessBaseAPI.setVariable(TessBaseAPI.VAR_CHAR_WHITELIST, "0123456789");
//
// //blackList Example 黑名单
// tessBaseAPI.setVariable(TessBaseAPI.VAR_CHAR_BLACKLIST, "!@#$%^&*()_+=-qwertyuiop[]}{POIU" +
// "YTRWQasdASDfghFGHjklJKLl;L:'\"\\|~`xcvXCVbnmBNM,./<>?");
Log.d(TAG, "Training file loaded");
tessBaseAPI.setImage(bitmap);
String extractedText = "empty result";
try {
extractedText = tessBaseAPI.getUTF8Text();
} catch (Exception e) {
Log.e(TAG, "Error in recognizing text.");
}
tessBaseAPI.end();
return extractedText;
}
//提取图片内容采用异步执行
private class MyAsyckTask extends AsyncTask<Bitmap,Void,String>{
@Override
protected void onPreExecute() {
progressBar.setVisibility(View.VISIBLE);
super.onPreExecute();
}
@Override
protected String doInBackground(final Bitmap... params) {
runOnUiThread(new Runnable() {
@Override
public void run() {
imageView.setImageBitmap(params[0]);
}
});
return extractText(params[0]);
}
@Override
protected void onPostExecute(String s) {
progressBar.setVisibility(View.GONE);
// String pattern = "\\d{5,6}\\b|\\b[A-Z_]+\\b";//正则表达式过滤
String pattern = "\\d{5,6}\\b";//正则表达式过滤
Pattern p = Pattern.compile(pattern);
Matcher m = p.matcher(s);
StringBuilder formatStringBuilder = new StringBuilder();
while (m.find()) {
formatStringBuilder.append(m.group()).append("\n");
// Log.i(TAG,"formatStringBuilder---------"+formatStringBuilder.toString());
}
text.setText(formatStringBuilder);
}
}
//转换成黑白照片，更利于识别图片
public static Bitmap toHeibai(Bitmap mBitmap) {
int mBitmapWidth = 0;
int mBitmapHeight = 0;
//截取图片宽度的3分之一
mBitmapWidth = mBitmap.getWidth() / 3;
mBitmapHeight = mBitmap.getHeight();
Bitmap bmpReturn = Bitmap.createBitmap(mBitmapWidth, mBitmapHeight,
Bitmap.Config.ARGB_8888);
Bitmap resizeBmp;
int iPixel = 0;
int wTime = 0;//用于判断是白色背景的图片
int bTime = 0;//用于判断是黑色背景的图片
for (int i = 0; i < mBitmapWidth; i++) {
for (int j = 0; j < mBitmapHeight; j++) {
int curr_color = mBitmap.getPixel(i, j);
int avg = (Color.red(curr_color) + Color.green(curr_color) + Color
.blue(curr_color)) / 3;
if (avg >= 190)//修改这个值会影响字体颜色的深浅，这个项目的截图的股票代码字体比较暗，设置成190有利于识别，
{
iPixel = 255;
wTime++;
} else if (avg < 190 && avg > 100) {
if (wTime > bTime) {//当为白色的背景图片时
iPixel = 0;
} else {
iPixel = 255;
}
} else {
iPixel = 0;
bTime++;
}
int modif_color = Color.argb(255, iPixel, iPixel, iPixel);
bmpReturn.setPixel(i, j, modif_color);
}
}
if (mBitmap != null) {
mBitmap.recycle();
mBitmap = null;
}
resizeBmp = ThumbnailUtils.extractThumbnail(bmpReturn, mBitmapWidth, mBitmapHeight);
return resizeBmp;
}
}
相信注释已经很明白。来看图（不知道用什么工具制作效果图，有小伙伴知道告诉我一声）
选择图片
识别结果和处理过后的图片
会出现一些识别错误的东西，但是没有关系，可以完善正则去匹配，也可以完善功能让用户选择需要的。
网友评论