Java OCR tesseract 圖像智能字符識別技術 Java代碼實現

接著上一篇OCR所說的，上一篇給大家介紹了tesseract 在命令行的簡單用法，當然了要繼承到我們的程序中，還是需要代碼實現的，下面給大家分享下java實現的例子。

拿代碼掃描上面的圖片，然后輸出結果。主要思想就是利用Java調用系統任務。

下面是核心代碼：

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，項目同一路徑
     */
    private String tessPath = new File("tesseract").getAbsolutePath();

    /**
     * @param imageFile
     *            傳入的圖像文件
     * @param imageFormat
     *            傳入的圖像格式
     * @return 識別后的字符串
     */
    public String recognizeText(File imageFile) throws Exception
    {
        /**
         * 設置輸出文件的保存的文件目錄
         */
        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();
        /**
         *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*", "");
    }
}

代碼很簡單，中間那部分ProcessBuilder其實就類似Runtime.getRuntime().exec("tesseract.exe 1.jpg 1 -l chi_sim")，大家不習慣的可以使用Runtime。

測試代碼：

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();
        }

    }
}

輸出結果：

對比第一張圖片，是不是很完美~哈哈 ，當然了如果你只需要實現驗證碼的讀寫，那么上面就足夠了。下面繼續普及圖像處理的知識。

-------------------------------------------------------------------我的分割線--------------------------------------------------------------------

當然了，有時候圖片被扭曲或者模糊的很厲害，很不容易識別，所以下面我給大家介紹一個去噪的輔助類，絕對碉堡了，先看下效果圖。

來張特寫：

一個類，不依賴任何jar，把圖像中的干擾線消滅了，是不是很給力，然后再拿這樣的圖片去識別，會不會效果更好呢，嘿嘿，大家自己實驗~

代碼：

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
     *            需要去噪的圖像
     * @param destDir
     *            去噪后的圖像保存地址
     * @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 < w; x++)
        {
            for (int y = 0; y < h; y++)
            {
                int argb = bufferedImage.getRGB(x, y);
                // 圖像加亮（調整亮度識別率非常高）
                int r = (int) (((argb >> 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 < w; x++)
        {
            for (int y = 0; y < h; y++)
            {
                if (gray[x][y] > threshold)
                {
                    gray[x][y] |= 0x00FFFF;
                } else
                {
                    gray[x][y] &= 0xFF0000;
                }
                binaryBufferedImage.setRGB(x, y, gray[x][y]);
            }
        }

        // 矩陣打印
        for (int y = 0; y < h; y++)
        {
            for (int x = 0; x < w; x++)
            {
                if (isBlack(binaryBufferedImage.getRGB(x, y)))
                {
                    System.out.print("*");
                } else
                {
                    System.out.print(" ");
                }
            }
            System.out.println();
        }

        ImageIO.write(binaryBufferedImage, "jpg", new File(destDir, sfile
                .getName()));
    }

    public static boolean isBlack(int colorInt)
    {
        Color color = new Color(colorInt);
        if (color.getRed() + color.getGreen() + color.getBlue() <= 300)
        {
            return true;
        }
        return false;
    }

    public static boolean isWhite(int colorInt)
    {
        Color color = new Color(colorInt);
        if (color.getRed() + color.getGreen() + color.getBlue() > 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 < w; x++)
        {
            for (int y = 0; y < h; y++)
            {
                int red = 0xFF & gray[x][y];
                histData[red]++;
            }
        }

        // Total number of pixels
        int total = w * h;

        float sum = 0;
        for (int t = 0; t < 256; t++)
            sum += t * histData[t];

        float sumB = 0;
        int wB = 0;
        int wF = 0;

        float varMax = 0;
        int threshold = 0;

        for (int t = 0; t < 256; t++)
        {
            wB += histData[t]; // Weight Background
            if (wB == 0)
                continue;

            wF = total - wB; // Weight Foreground
            if (wF == 0)
                break;

            sumB += (float) (t * histData[t]);

            float mB = sumB / wB; // Mean Background
            float mF = (sum - sumB) / wF; // Mean Foreground

            // Calculate Between Class Variance
            float varBetween = (float) wB * (float) wF * (mB - mF) * (mB - mF);

            // Check if new maximum found
            if (varBetween > varMax)
            {
                varMax = varBetween;
                threshold = t;
            }
        }

        return threshold;
    }
}

好了，就到這里。如果這篇文章對你有用，贊一個吧~

來自： http://blog.csdn.net//lmj623565791/article/details/23960391