JavaOCRtesseract图像智能文字字符识别技术实例代码

package com.zhy.test; 
 
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 OCRHelper 
{ 
 private final String LANG_OPTION = "-l"; 
 private final String EOL = System.getProperty("line.separator"); 
 /** 
  * 文件位置我防止在，项目同一路径 
  */ 
 private String tessPath = new File("tesseract").getAbsolutePath(); 
 
 /** 
  * @param imageFile 
  *   传入的图像文件 
  * @param imageFormat 
  *   传入的图像格式 
  * @return 识别后的字符串 
  */ 
 public String recognizeText(File imageFile) throws Exception 
 { 
  /** 
   * 设置输出文件的保存的文件目录 
   */ 
  File outputFile = new File(imageFile.getParentFile(), "output"); 
 
  StringBuffer strB = new StringBuffer(); 
  List cmd = new ArrayList(); 
  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(); 
  /** 
   *Sets this process builder's working directory. 
   */ 
  pb.directory(imageFile.getParentFile()); 
  cmd.set(1, imageFile.getName()); 
  pb.command(cmd); 
  pb.redirectErrorStream(true); 
  Process process = pb.start(); 
  // tesseract.exe 1.jpg 1 -l chi_sim 
  // Runtime.getRuntime().exec("tesseract.exe 1.jpg 1 -l chi_sim"); 
  /** 
   * the exit value of the process. By convention, 0 indicates normal 
   * termination. 
   */ 
//  System.out.println(cmd.toString()); 
  int w = process.waitFor(); 
  if (w == 0)// 0代表正常退出 
  { 
   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 recognize the image or its selected region."; 
    break; 
   case 31: 
    msg = "Unsupported image format."; 
    break; 
   default: 
    msg = "Errors occurred."; 
   } 
   throw new RuntimeException(msg); 
  } 
  new File(outputFile.getAbsolutePath() + ".txt").delete(); 
  return strB.toString().replaceAll("\\s*", ""); 
 } 
} 

package com.zhy.test; 
 
import java.io.File; 
 
public class Test 
{ 
 public static void main(String[] args) 
 { 
  try 
  { 
    
   File testDataDir = new File("testdata"); 
   System.out.println(testDataDir.listFiles().length); 
   int i = 0 ; 
   for(File file :testDataDir.listFiles()) 
   { 
    i++ ; 
    String recognizeText = new OCRHelper().recognizeText(file); 
    System.out.print(recognizeText+"\t"); 
 
    if( i % 5 == 0 ) 
    { 
     System.out.println(); 
    } 
   } 
    
  } catch (Exception e) 
  { 
   e.printStackTrace(); 
  } 
 
 } 
} 

package com.zhy.test; 
 
import java.awt.Color; 
import java.awt.image.BufferedImage; 
import java.io.File; 
import java.io.IOException; 
 
import javax.imageio.ImageIO; 
 
public class ClearImageHelper 
{ 
 
 public static void main(String[] args) throws IOException 
 { 
 
   
  File testDataDir = new File("testdata"); 
  final String destDir = testDataDir.getAbsolutePath()+"/tmp"; 
  for (File file : testDataDir.listFiles()) 
  { 
   cleanImage(file, destDir); 
  } 
 
 } 
 
 /** 
  * 
  * @param sfile 
  *   需要去噪的图像 
  * @param destDir 
  *   去噪后的图像保存地址 
  * @throws IOException 
  */ 
 public static void cleanImage(File sfile, String destDir) 
   throws IOException 
 { 
  File destF = new File(destDir); 
  if (!destF.exists()) 
  { 
   destF.mkdirs(); 
  } 
 
  BufferedImage bufferedImage = ImageIO.read(sfile); 
  int h = bufferedImage.getHeight(); 
  int w = bufferedImage.getWidth(); 
 
  // 灰度化 
  int[][] gray = new int[w][h]; 
  for (int x = 0; x > 16) & 0xFF) * 1.1 + 30); 
    int g = (int) (((argb >> 8) & 0xFF) * 1.1 + 30); 
    int b = (int) (((argb >> 0) & 0xFF) * 1.1 + 30); 
    if (r >= 255) 
    { 
     r = 255; 
    } 
    if (g >= 255) 
    { 
     g = 255; 
    } 
    if (b >= 255) 
    { 
     b = 255; 
    } 
    gray[x][y] = (int) Math 
      .pow((Math.pow(r, 2.2) * 0.2973 + Math.pow(g, 2.2) 
        * 0.6274 + Math.pow(b, 2.2) * 0.0753), 1 / 2.2); 
   } 
  } 
 
  // 二值化 
  int threshold = ostu(gray, w, h); 
  BufferedImage binaryBufferedImage = new BufferedImage(w, h, 
    BufferedImage.TYPE_BYTE_BINARY); 
  for (int x = 0; x  threshold) 
    { 
     gray[x][y] |= 0x00FFFF; 
    } else 
    { 
     gray[x][y] &= 0xFF0000; 
    } 
    binaryBufferedImage.setRGB(x, y, gray[x][y]); 
   } 
  } 
 
  // 矩阵打印 
  for (int y = 0; y  300) 
  { 
   return true; 
  } 
  return false; 
 } 
 
 public static int isBlackOrWhite(int colorInt) 
 { 
  if (getColorBright(colorInt) <30 || getColorBright(colorInt) > 730) 
  { 
   return 1; 
  } 
  return 0; 
 } 
 
 public static int getColorBright(int colorInt) 
 { 
  Color color = new Color(colorInt); 
  return color.getRed() + color.getGreen() + color.getBlue(); 
 } 
 
 public static int ostu(int[][] gray, int w, int h) 
 { 
  int[] histData = new int[w * h]; 
  // Calculate histogram 
  for (int x = 0; x  varMax) 
   { 
    varMax = varBetween; 
    threshold = t; 
   } 
  } 
 
  return threshold; 
 } 
}