集美大学教务处验证码识别（二）

    public static int isWhite(int colorInt) {  
        Color color = new Color(colorInt);  
        if (color.getGreen()>=200) {  
            return 1;  
        }  
        return 0;  
    } 

    public void photo(File imgfile) throws IOException{
         File file = imgfile;//图片地址 
         String newFile = "testdata"+"/new"+imgfile.getName();
         BufferedImage img = getPic(file);
         int width = img.getWidth();  
         int height = img.getHeight();
         for (int x = 0; x < width; ++x) {  
                for (int y = 0; y < height; ++y) {  
                    if (isWhite(img.getRGB(x, y)) == 1) {  
                        img.setRGB(x, y, Color.WHITE.getRGB());  
                    } else {  
                        img.setRGB(x, y, Color.BLACK.getRGB());  
                    }  
                }  
            }  
         saveImg(img,newFile);
    }

package step2;

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");  
    /** 
     *  tesseract 安装目录
     */  
    private String tessPath = "D:/备份/桌面/教务处验证码识别/tesseract-ocr-setup-3.01-1/";  
  
    /** 
     * @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,String photoName) throws Exception  
    {  
        /** 
         * 设置输出文件的保存的文件目录 
         */  
        File outputFile = new File(imageFile.getParentFile(), photoName);  
        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("wss");  //调优后的文件
  
        ProcessBuilder pb = new ProcessBuilder();  
        /** 
         *Sets this process builder‘s working directory. 
         */  
        pb.directory(imageFile.getParentFile());  
        //System.out.println(imageFile.toString());
        cmd.set(1, imageFile.getName());  
        pb.command(cmd);  
        pb.redirectErrorStream(true);
        //System.out.println("cmd:"+cmd.toString());  
        //System.out.println("photoName:"+imageFile.getName());
        Process process = pb.start();  
        /** 
         * the exit value of the process. By convention, 0 indicates normal 
         * termination. 
         */  
     
        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*", "");  
    }  
}  

public class WssOcr {
    
    /** 验证码识别*/
    public static void main(String[] args) throws IOException {
        String photoName = "2.jpg"; 
        WssOcr wss =  new WssOcr();
        String valid = wss.photoOcr(photoName);
        System.out.println(valid);
    }
    
    
    
    /**
     * @param photoFile 验证码图片地址
     * @param file 旧的图片地址 
    */
    public String photoOcr(String photoName)  {
        try {
            String photoFile = "validPhoto/"+photoName;
            File file = new File(photoFile);
            PhotoDeal pd = new PhotoDeal();
            pd.photo(file);//
            
            String newFile = "testdata"+"/new"+file.getName();
            File dataFile = new File(newFile);
            String recognizeText = new OCRHelper().recognizeText(dataFile,photoName); 
            File outputFile = new File("validPhoto/"+photoName+".txt");  
            if(file.exists()) file.delete(); //删除验证码
            if(dataFile.exists()) dataFile.delete(); //删除二值化验证码
            if(outputFile.exists()) dataFile.delete();
            return recognizeText;
        } catch (IOException e) {
            e.printStackTrace();
        }catch (Exception e) {
            e.printStackTrace();
        }
        return "";
        
    }
    
    
}