tesseract图片文字识别 - 滤波 降噪 灰度 二值化 去除文本边框 去除验证码干扰线

版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/qq_28114645/article/details/81328039
import org.apache.xmlgraphics.image.codec.tiff.TIFFEncodeParam;
import org.apache.xmlgraphics.image.codec.util.ImageEncoder;

import javax.imageio.ImageIO;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.util.ArrayList;
import java.util.List;

public class ImageUtil {

    public static void main(String[] args) throws IOException {
        File testDataDir = new File("pic");
        final String destDir = "picimages";
        for (File file : testDataDir.listFiles()) {
            cleanLinesInImage(file, destDir);
            cleanLinesInImage(file, destDir);
            cleanLinesInImage(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 cleanLinesInImage(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);
                // 图像加亮(调整亮度识别率非常高)
                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]);
            }
        }

        //去除干扰线条
//        for(int y = 1; y < h-1; y++){
//            for(int x = 1; x < w-1; x++){
//                boolean flag = false ;
//                if(isBlack(binaryBufferedImage.getRGB(x, y))){
//                    //左右均为空时,去掉此点
//                    if((binaryBufferedImage.getRGB(x-1, y)) && isWhite(binaryBufferedImage.getRGB(x+1, y))){
//                        flag = true;
//                    }
//                    //上下均为空时,去掉此点
//                    if(isWhite(binaryBufferedImage.getRGB(x, y+1)) && isWhite(binaryBufferedImage.getRGB(x, y-1))){
//                        flag = true;
//                    }
//                    //斜上下为空时,去掉此点
//                    if(isWhite(binaryBufferedImage.getRGB(x-1, y+1)) && isWhite(binaryBufferedImage.getRGB(x+1, y-1))){
//                        flag = true;
//                    }
//                    if(isWhite(binaryBufferedImage.getRGB(x+1, y+1)) && isWhite(binaryBufferedImage.getRGB(x-1, y-1))){
//                        flag = true;
//                    }
//                    if(flag){
//                        binaryBufferedImage.setRGB(x,y,-1);
//                    }
//                }
//            }
//        }
        //去除边框线
        for (int y = 1; y < h; y++) {
            for (int x = 1; x < w; x++) {
                boolean flag = true;
                int px = 15;
                if (isBlack(binaryBufferedImage.getRGB(x, y))) {
                    if (x < w - px) {
                        for (int i = 1; i <= px; i++) {
                            //右15像素均为空时,去掉此行
                            if (isWhite(binaryBufferedImage.getRGB(x + i, y))) {
                                flag = false;
                                if (!flag) {
                                    break;
                                }
                            }
                        }
                    }
                    for (int i = x; i < w; i++) {
                        if (flag) {
                            if (isBlack(binaryBufferedImage.getRGB(i, y))) {
                                binaryBufferedImage.setRGB(i, y, -1);
                            } else {
                                break;
                            }
                        }
                    }
                    flag = true;
                    if (y < h - px) {
                        for (int i = 1; i <= px; i++) {
                            //下15像素均为空时,去掉此列
                            if (isWhite(binaryBufferedImage.getRGB(x, y + i))) {
                                flag = false;
                                if (!flag) {
                                    break;
                                }
                            }
                        }
                    }
                    for (int i = y; i <= h; i++) {
                        if (flag) {
                            if (isBlack(binaryBufferedImage.getRGB(x, i))) {
                                binaryBufferedImage.setRGB(x, i, -1);
                            } else {
                                break;
                            }
                        }
                    }
                }
            }
        }


        // 矩阵打印
        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, "tif", 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;
    }
}

原图

这里写图片描述

处理后图片

这里写图片描述

Demo下载地址

猜你喜欢

转载自blog.csdn.net/qq_28114645/article/details/81328039