1  <dependencies>
 2
 3       <dependency>
 4         <groupId>net.java.dev.jna</groupId>
 5         <artifactId>jna</artifactId>
 6         <version>4.2.1</version>
 7     </dependency>
 8
 9       <dependency>
10         <groupId>net.sourceforge.tess4j</groupId>
11         <artifactId>tess4j</artifactId>
12         <version>2.0.1</version>
13         <exclusions>
14             <exclusion>
15                 <groupId>com.sun.jna</groupId>
16                 <artifactId>jna</artifactId>
17             </exclusion>
18         </exclusions>
19     </dependency>
20
21   </dependencies>

 1 package com.sinosoft.ocr;
 2
 3 import java.awt.image.BufferedImage;
 4 import java.io.File;
 5 import java.io.FileInputStream;
 6 import java.io.IOException;
 7 import java.io.InputStream;
 8
 9 import javax.imageio.ImageIO;
10
11 import net.sourceforge.tess4j.ITesseract;
12 import net.sourceforge.tess4j.Tesseract;
13 import net.sourceforge.tess4j.TesseractException;
14 import net.sourceforge.tess4j.util.ImageHelper;
15
16 public class OcrTest {
17
18      public static void main(String[] args) {
19             File imageFile = new File("E:\\valimg\\fx\\fx.tif");
20             ITesseract instance = new Tesseract();  // JNA Interface Mapping
21
22             try {
23                 //读取一个文件夹下的所有图片并验证
24                 /*    String[] filelist = imageFile.list();
25                 for (int i = 0; i < filelist.length; i++) {
26                         File readfile = new File("E:\\valimg" + "\\" + filelist[i]);
27                         if (!readfile.isDirectory()) {
28                                 System.out.println("path=" + readfile.getPath());
29                                 System.out.println("absolutepath="
30                                                 + readfile.getAbsolutePath());
31                                 System.out.println("name=" + readfile.getName());
32
33                                 String result = instance.doOCR(readfile);
34                                 //String result = instance.doOCR(change(readfile));
35                                 System.err.println(readfile.getName() +" result："+  result);
36                      }
37                 }*/
38                  instance.setLanguage("chi_sim"); //加载语言包
39                  String result = instance.doOCR(imageFile);
40
41                  System.err.println(imageFile.getName() +" result："+  result);
42
43             } catch (TesseractException e) {
44                 System.err.println(e.getMessage());
45             }
46      }
47
48      public static BufferedImage change(File file){
49
50             // 读取图片字节数组
51              BufferedImage textImage = null;
52             try {
53                  InputStream in = new FileInputStream(file);
54                  BufferedImage image = ImageIO.read(in);
55                  textImage = ImageHelper.convertImageToGrayscale(ImageHelper.getSubImage(image, 0, 0, image.getWidth(), image.getHeight()));  //对图片进行处理
56                  textImage = ImageHelper.getScaledInstance(image, image.getWidth() * 5, image.getHeight() * 5);  //将图片扩大5倍
57
58             } catch (IOException e) {
59                 e.printStackTrace();
60             }
61
62             return textImage;
63      }
64 }