【发布时间】:2016-12-19 21:03:23
【问题描述】:
我正在为 Tesseract Ocr 编写一个 .Net 包装器,如果我使用灰度图像而不是 rgb 图像作为它的输入文件,那么结果会非常好。
所以我在网上搜索将 Rgb 图像转换为灰度图像的 C# 解决方案,我found this code。
这会执行 3 次操作以提高 tesseract 的准确性。
- 调整图片大小
- 然后转换成灰度图,去除图像中的噪点
现在这个转换后的图像可以提供几乎 90% 的准确结果。
//Resize
public Bitmap Resize(Bitmap bmp, int newWidth, int newHeight)
{
Bitmap temp = (Bitmap)bmp;
Bitmap bmap = new Bitmap(newWidth, newHeight, temp.PixelFormat);
double nWidthFactor = (double)temp.Width / (double)newWidth;
double nHeightFactor = (double)temp.Height / (double)newHeight;
double fx, fy, nx, ny;
int cx, cy, fr_x, fr_y;
Color color1 = new Color();
Color color2 = new Color();
Color color3 = new Color();
Color color4 = new Color();
byte nRed, nGreen, nBlue;
byte bp1, bp2;
for (int x = 0; x < bmap.Width; ++x)
{
for (int y = 0; y < bmap.Height; ++y)
{
fr_x = (int)Math.Floor(x * nWidthFactor);
fr_y = (int)Math.Floor(y * nHeightFactor);
cx = fr_x + 1;
if (cx >= temp.Width)
cx = fr_x;
cy = fr_y + 1;
if (cy >= temp.Height)
cy = fr_y;
fx = x * nWidthFactor - fr_x;
fy = y * nHeightFactor - fr_y;
nx = 1.0 - fx;
ny = 1.0 - fy;
color1 = temp.GetPixel(fr_x, fr_y);
color2 = temp.GetPixel(cx, fr_y);
color3 = temp.GetPixel(fr_x, cy);
color4 = temp.GetPixel(cx, cy);
// Blue
bp1 = (byte)(nx * color1.B + fx * color2.B);
bp2 = (byte)(nx * color3.B + fx * color4.B);
nBlue = (byte)(ny * (double)(bp1) + fy * (double)(bp2));
// Green
bp1 = (byte)(nx * color1.G + fx * color2.G);
bp2 = (byte)(nx * color3.G + fx * color4.G);
nGreen = (byte)(ny * (double)(bp1) + fy * (double)(bp2));
// Red
bp1 = (byte)(nx * color1.R + fx * color2.R);
bp2 = (byte)(nx * color3.R + fx * color4.R);
nRed = (byte)(ny * (double)(bp1) + fy * (double)(bp2));
bmap.SetPixel(x, y, System.Drawing.Color.FromArgb(255, nRed, nGreen, nBlue));
}
}
//here i included the below to functions logic without the for loop to remove repetitive use of for loop but it did not work and taking the same time.
bmap = SetGrayscale(bmap);
bmap = RemoveNoise(bmap);
return bmap;
}
//SetGrayscale
public Bitmap SetGrayscale(Bitmap img)
{
Bitmap temp = (Bitmap)img;
Bitmap bmap = (Bitmap)temp.Clone();
Color c;
for (int i = 0; i < bmap.Width; i++)
{
for (int j = 0; j < bmap.Height; j++)
{
c = bmap.GetPixel(i, j);
byte gray = (byte)(.299 * c.R + .587 * c.G + .114 * c.B);
bmap.SetPixel(i, j, Color.FromArgb(gray, gray, gray));
}
}
return (Bitmap)bmap.Clone();
}
//RemoveNoise
public Bitmap RemoveNoise(Bitmap bmap)
{
for (var x = 0; x < bmap.Width; x++)
{
for (var y = 0; y < bmap.Height; y++)
{
var pixel = bmap.GetPixel(x, y);
if (pixel.R < 162 && pixel.G < 162 && pixel.B < 162)
bmap.SetPixel(x, y, Color.Black);
}
}
for (var x = 0; x < bmap.Width; x++)
{
for (var y = 0; y < bmap.Height; y++)
{
var pixel = bmap.GetPixel(x, y);
if (pixel.R > 162 && pixel.G > 162 && pixel.B > 162)
bmap.SetPixel(x, y, Color.White);
}
}
return bmap;
}
但问题是转换它需要很多时间
所以我加入了SetGrayscale(Bitmap bmap)
Resize() 方法内的RemoveNoise(Bitmap bmap) 函数逻辑,以消除对 for 循环的重复使用
但这并没有解决我的问题。
【问题讨论】:
-
为什么要调整图片大小?
-
如果我使用 newsize=oldSize*2 会提高 20% 的准确率