Windows下Java调用OCR进行图片识别
这篇文章主要为大家详细介绍了Windows下Java调用OCR进行图片识别，通过Tesseract-OCR对图片进行识别，具有一定的参考价值，感兴趣的小伙伴们可以参考一下使用java语言，通过tesseract-ocr对图片进行识别。
1.tesseract-ocr
下载windows版本并安装。
2.程序如下：
a.imageiohelper类
package ocr;
import java.awt.image.bufferedimage;
import java.io.file;
import java.io.ioexception;
import java.util.iterator;
import java.util.locale;
import javax.imageio.iioimage;
import javax.imageio.imageio;
import javax.imageio.imagereader;
import javax.imageio.imagewriteparam;
import javax.imageio.imagewriter;
import javax.imageio.metadata.iiometadata;
import javax.imageio.stream.imageinputstream;
import javax.imageio.stream.imageoutputstream;
import com.sun.media.imageio.plugins.tiff.tiffimagewriteparam;
public class imageiohelper {
/**
* 图片文件转换为tif格式
* @param imagefile 文件路径
* @param imageformat 文件扩展名
* @return
*/
public static file createimage(file imagefile, string imageformat) {
file tempfile = null;
try {
iterator<imagereader> readers = imageio.getimagereadersbyformatname(imageformat);
imagereader reader = readers.next();
imageinputstream iis = imageio.createimageinputstream(imagefile);
reader.setinput(iis);
//read the stream metadata
iiometadata streammetadata = reader.getstreammetadata();
//set up the writeparam
tiffimagewriteparam tiffwriteparam = new tiffimagewriteparam(locale.chinese);
tiffwriteparam.setcompressionmode(imagewriteparam.mode_disabled);
//get tif writer and set output to file
iterator<imagewriter> writers = imageio.getimagewritersbyformatname("tiff");
imagewriter writer = writers.next();
bufferedimage bi = reader.read(0);
iioimage image = new iioimage(bi,null,reader.getimagemetadata(0));
tempfile = tempimagefile(imagefile);
imageoutputstream ios = imageio.createimageoutputstream(tempfile);
writer.setoutput(ios);
writer.write(streammetadata, image, tiffwriteparam);
ios.close();
writer.dispose();
reader.dispose();
} catch (ioexception e) {
e.printstacktrace();
}
return tempfile;
}
private static file tempimagefile(file imagefile) {
string path = imagefile.getpath();
stringbuffer strb = new stringbuffer(path);
strb.insert(path.lastindexof('.'),0);
return new file(strb.tostring().replacefirst("(?<=//.)(//w+)$", "tif"));
}
}
b.ocr核心类
package ocr;
import java.io.bufferedreader;
import java.io.file;
import java.io.fileinputstream;
import java.io.inputstreamreader;
import java.util.arraylist;
import java.util.list;
import org.jdesktop.swingx.util.os;
public class ocr {
private final string lang_option = "-l"; //英文字母小写l，并非数字1
private final string eol = system.getproperty("line.separator");
private string tesspath = "c://program files//tesseract-ocr";
//private string tesspath = new file("tesseract").getabsolutepath();
public string recognizetext(file imagefile,string imageformat)throws exception{
file tempimage = imageiohelper.createimage(imagefile,imageformat);
file outputfile = new file(imagefile.getparentfile(),"output");
stringbuffer strb = new stringbuffer();
list<string> cmd = new arraylist<string>();
if(os.iswindowsxp()){
cmd.add(tesspath+"//tesseract");
}else if(os.islinux()){
cmd.add("tesseract");
}else{
cmd.add(tesspath+"//tesseract");
}
cmd.add("");
cmd.add(outputfile.getname());
//cmd.add(lang_option);
//cmd.add("chi_sim");
//cmd.add("eng");
processbuilder pb = new processbuilder();
pb.directory(imagefile.getparentfile());
cmd.set(1, tempimage.getname());
pb.command(cmd);
pb.redirecterrorstream(true);
process process = pb.start();
//tesseract.exe 1.jpg 1 -l chi_sim
int w = process.waitfor();
//删除临时正在工作文件
tempimage.delete();
if(w==0){
bufferedreader in = new bufferedreader(new inputstreamreader(new fileinputstream(outputfile.getabsolutepath()+".txt"),"utf-8"));
string str;
while((str = in.readline())!=null){
strb.append(str).append(eol);
}
in.close();
}else{
string msg;
switch(w){
case 1:
msg = "errors accessing files.there may be spaces in your image's filename.";
break;
case 29:
msg = "cannot recongnize the image or its selected region.";
break;
case 31:
msg = "unsupported image format.";
break;
default:
msg = "errors occurred.";
}
tempimage.delete();
//throw new runtimeexception(msg);
}
new file(outputfile.getabsolutepath()+".txt").delete();
return strb.tostring();
}
}
c.main
package ocr;
import java.io.file;
import java.io.ioexception;
public class testocr {
/**
* @param args
*/
public static void main(string[] args) {
//输入图片地址
string path = "d://test//test.bmp";
try {
string valcode = new ocr().recognizetext(new file(path), "bmp");
system.out.println(valcode);
} catch (ioexception e) {
e.printstacktrace();
} catch (exception e) {
e.printstacktrace();
}
}
}
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持CodeAE代码之家。
原文链接：https://blog.csdn.net/gaokao2011/article/details/23421477
http://www.zzvips.com/article/172409.html
页:
[1]