JAVA识别复杂验证码+图像处理
先对验证码进行简单的处理噪点和纯色
例未曾处理的图片
public static void main(String[] args) throws Exception {
//源文件
String picName = "C:\\Users\\syxy101\\Desktop\\6.jpg";
File filepic=new File(picName);
//去噪点 并处理为纯色
BufferedImage bufferedImage = removeBackgroud(picName);
//处理后图片地址
File w2 = new File("C:\\Users\\syxy101\\Desktop\\5.png");//可以是jpg,png格式
ImageIO.write(bufferedImage, "jpg", w2);//不管输出什么格式图片，此处不需改动
｝
//去除图片噪点 并将彩色转为纯色(黑色)
public static BufferedImage removeBackgroud(String picFile)
throws Exception {
BufferedImage img = ImageIO.read(new File(picFile));
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());
}
}
}
return img;
}
//设置颜色阀值
public static int isWhite(int colorInt) {
Color color = new Color(colorInt);
if (color.getRed() + color.getGreen() + color.getBlue() > 200 && color.getRed() + color.getGreen() + color.getBlue()<500) {
return 0;
}
return 1;
}处理后
可以看到已经清晰了不少 当然现在还是无法识别的
一下步 强加黑色 处理掉横线斜线 噪点
package com.adc.da.sync.web;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.HttpStatus;
import org.apache.commons.httpclient.methods.GetMethod;
import org.apache.commons.io.IOUtils;
import javax.imageio.ImageIO;
import java.awt.Color;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
/**
* //TODO 添加类/接口功能描述
*
* @author zhangsj
* @date 2018-12-13
*/
public class ImagePreProcess4 {
public static void main(String[] args) throws IOException
{
//源文件
File testDataDir = new File("C:\\Users\\syxy101\\Desktop\\5.png");
//处理后路径
final String destDir = "C:\\Users\\syxy101\\Desktop\\ss";
cleanLinesInImage(testDataDir, 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(isWhite(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);
}
}
}
}
// 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, "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;
}
}
已经去掉多余的横线和噪点了
这时候识别度已经很高了
为了达到识别度百分之80
需要把每个字母隔开 分开识别
public static void main(String[] args) throws Exception {
int x=6;
for(int i=0;i<4;i++){
if(i==0){
x=6;
}else if(i==1){
x=22;
}else if(i==2){
x=36;
}else if(i==3){
x=52;
}
imageCut(x,0,15,30,picName,"D:\\ccccc"+i+".jpg");
}
｝
/**
* 图片剪裁
* @param x 距离左上角的x轴距离
* @param y 距离左上角的y轴距离
* @param width 宽度
* @param height 高度
* @param sourcePath 图片源
* @param descpath 目标位置
*/
public static void imageCut(int x, int y, int width, int height, String sourcePath, String descpath) {
FileInputStream is = null;
ImageInputStream iis = null;
try {
is = new FileInputStream(sourcePath);
String fileSuffix = sourcePath.substring(sourcePath.lastIndexOf(".") + 1);
Iterator it = ImageIO.getImageReadersByFormatName(fileSuffix);
ImageReader reader = it.next();
iis = ImageIO.createImageInputStream(is);
reader.setInput(iis, true);
ImageReadParam param = reader.getDefaultReadParam();
Rectangle rect = new Rectangle(x, y, width, height);
param.setSourceRegion(rect);
BufferedImage bi = reader.read(0, param);
ImageIO.write(bi, fileSuffix, new File(descpath));
} catch (Exception ex) {
ex.printStackTrace();
} finally {
if (is != null) {
try {
is.close();
} catch (IOException e) {
e.printStackTrace();
}
is = null;
}
if (iis != null) {
try {
iis.close();
} catch (IOException e) {
e.printStackTrace();
}
iis = null;
}
}
} 
换了个验证码剪辑
这时候识别度已经到百分之90了