最近工作需要做了一下圖檔驗證碼自動識别的功能。但是網上對于初始圖檔的處理方法有去噪點、灰階化等,唯獨難搜到去除幹擾線的方法。于是根據網上搜來的代碼,自己嘗試寫了一段,親測有效,可以比較幹淨地去除幹擾線,提高OCR識别的準确率。
- 以下代碼除“去除幹擾線條“”一小段為原創,其他均為網上搜尋所得,但是很抱歉我忘記了來源網址,以後如果能找到再補上。在此先謝過慷慨分享原始代碼的前輩!
demo如下:
import java.awt.Color;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;
import javax.imageio.ImageIO;
public class CopyOfCleanLines {
public static void main(String[] args) throws IOException
{
File testDataDir = new File("imgWithLines");
final String destDir = testDataDir.getAbsolutePath()+"/tmp";
for (File file : testDataDir.listFiles())
{
cleanLinesInImage(file, destDir);
cleanLinesInImage(file, destDir);
cleanLinesInImage(file, destDir);
}
}
/**
*
* @param sfile
* 需要去噪的圖像
* @param destDir
* 去噪後的圖像儲存位址
* @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();
// 灰階化
int[][] gray = new int[w][h];
for (int x = ; x < w; x++)
{
for (int y = ; y < h; y++)
{
int argb = bufferedImage.getRGB(x, y);
// 圖像加亮(調整亮度識别率非常高)
int r = (int) (((argb >> ) & ) * + );
int g = (int) (((argb >> ) & ) * + );
int b = (int) (((argb >> ) & ) * + );
if (r >= )
{
r = ;
}
if (g >= )
{
g = ;
}
if (b >= )
{
b = ;
}
gray[x][y] = (int) Math
.pow((Math.pow(r, ) * + Math.pow(g, )
* + Math.pow(b, ) * ), / );
}
}
// 二值化
int threshold = ostu(gray, w, h);
BufferedImage binaryBufferedImage = new BufferedImage(w, h, BufferedImage.TYPE_BYTE_BINARY);
for (int x = ; x < w; x++)
{
for (int y = ; y < h; y++)
{
if (gray[x][y] > threshold)
{
gray[x][y] |= ;
} else
{
gray[x][y] &= ;
}
binaryBufferedImage.setRGB(x, y, gray[x][y]);
}
}
//去除幹擾線條
for(int y = ; y < h-; y++){
for(int x = ; x < w-; x++){
boolean flag = false ;
if(isBlack(binaryBufferedImage.getRGB(x, y))){
//左右均為空時,去掉此點
if(isWhite(binaryBufferedImage.getRGB(x-, y)) && isWhite(binaryBufferedImage.getRGB(x+, y))){
flag = true;
}
//上下均為空時,去掉此點
if(isWhite(binaryBufferedImage.getRGB(x, y+)) && isWhite(binaryBufferedImage.getRGB(x, y-))){
flag = true;
}
//斜上下為空時,去掉此點
if(isWhite(binaryBufferedImage.getRGB(x-, y+)) && isWhite(binaryBufferedImage.getRGB(x+, y-))){
flag = true;
}
if(isWhite(binaryBufferedImage.getRGB(x+, y+)) && isWhite(binaryBufferedImage.getRGB(x-, y-))){
flag = true;
}
if(flag){
binaryBufferedImage.setRGB(x,y,-);
}
}
}
}
// 矩陣列印
for (int y = ; y < h; y++)
{
for (int x = ; 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() <= )
{
return true;
}
return false;
}
public static boolean isWhite(int colorInt)
{
Color color = new Color(colorInt);
if (color.getRed() + color.getGreen() + color.getBlue() > )
{
return true;
}
return false;
}
public static int isBlackOrWhite(int colorInt)
{
if (getColorBright(colorInt) < || getColorBright(colorInt) > )
{
return ;
}
return ;
}
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 = ; x < w; x++)
{
for (int y = ; y < h; y++)
{
int red = & gray[x][y];
histData[red]++;
}
}
// Total number of pixels
int total = w * h;
float sum = ;
for (int t = ; t < ; t++)
sum += t * histData[t];
float sumB = ;
int wB = ;
int wF = ;
float varMax = ;
int threshold = ;
for (int t = ; t < ; t++)
{
wB += histData[t]; // Weight Background
if (wB == )
continue;
wF = total - wB; // Weight Foreground
if (wF == )
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;
}
}