最近工作有点闲，有时间就玩点有意思的东西------SURF 图像识别(WIKI地址)，懂了图像识别，真的有很多东西可以玩。。。。。先看看本文实现的效果：
左图不是相同的指纹，右图为相同的指纹
ShapeContext算法中典型的实验图片。。。借来用用而已。。。
本文修改后的代码可以到这里:http://download.csdn.net/source/2515577下载，本文的代码改自GoogleCode的OpenSource。
网上已经有很多封装好的SURF算法，这里我挑OpenSURF.OpenSURF在GoogleCode的地址
http://code.google.com/p/opensurf1/，在【Source】 Tab里有C++版和C#版，C++版依赖Opencv，C#版不依赖OpenCV，我选择了C#版裸奔SURF。。。。在使用OpenSURF的C#版发现两个问题：
1。没有Match模块，所以这个就得自己写了；
2。OpenSURF for C#竟然大量使用GetPixel() ...... -. -||| ......做过图像处理的兄弟都应该知道GetPixel()的效率...........这个也得自己改改。
解决问题1：C++版包含了Match模块，所以我就参考C++版的，写成C#。。。。。以下是我自己添加的Match代码：
view plaincopy to clipboardprint?
using System;
using System.Collections.Generic;
using System.Text;
using OpenSURFcs;
class Utils
{
private const float FLT_MAX = 3.402823466e+38F; /* max value */
public static List<IPoint>[] getMatches(List<IPoint> ipts1, List<IPoint> ipts2)
{
double dist;
double d1, d2;
IPoint match = new IPoint();
List<IPoint>[] matches = new List<IPoint>[2];
matches[0] = new List<IPoint>();
matches[1] = new List<IPoint>();
for (int i = 0; i < ipts1.Count; i++)
{
d1 = d2 = FLT_MAX;
for (int j = 0; j < ipts2.Count; j++)
{
dist = GetDistance(ipts1[i], ipts2[j]);
if (dist < d1) // if this feature matches better than current best
{
d2 = d1;
d1 = dist;
match = ipts2[j];
}
else if (dist < d2) // this feature matches better than second best
{
d2 = dist;
}
}
// If match has a d1:d2 ratio < 0.65 ipoints are a match
if (d1 / d2 < 0.77) //越小Match点越少
{
matches[0].Add(ipts1[i]);
matches[1].Add(match);
}
}
return matches;
}
private static double GetDistance(IPoint ip1, IPoint ip2)
{
float sum = 0.0f;
for (int i = 0; i < 64; ++i)
sum += (ip1.descriptor[i] - ip2.descriptor[i]) * (ip1.descriptor[i] - ip2.descriptor[i]);
return Math.Sqrt(sum);
}
}
using System;
using System.Collections.Generic;
using System.Text;
using OpenSURFcs;
class Utils
{
private const float FLT_MAX = 3.402823466e+38F; /* max value */
public static List<IPoint>[] getMatches(List<IPoint> ipts1, List<IPoint> ipts2)
{
double dist;
double d1, d2;
IPoint match = new IPoint();
List<IPoint>[] matches = new List<IPoint>[2];
matches[0] = new List<IPoint>();
matches[1] = new List<IPoint>();
for (int i = 0; i < ipts1.Count; i++)
{
d1 = d2 = FLT_MAX;
for (int j = 0; j < ipts2.Count; j++)
{
dist = GetDistance(ipts1[i], ipts2[j]);
if (dist < d1) // if this feature matches better than current best
{
d2 = d1;
d1 = dist;
match = ipts2[j];
}
else if (dist < d2) // this feature matches better than second best
{
d2 = dist;
}
}
// If match has a d1:d2 ratio < 0.65 ipoints are a match
if (d1 / d2 < 0.77) //越小Match点越少
{
matches[0].Add(ipts1[i]);
matches[1].Add(match);
}
}
return matches;
}
private static double GetDistance(IPoint ip1, IPoint ip2)
{
float sum = 0.0f;
for (int i = 0; i < 64; ++i)
sum += (ip1.descriptor[i] - ip2.descriptor[i]) * (ip1.descriptor[i] - ip2.descriptor[i]);
return Math.Sqrt(sum);
}
}
解决问题2：参考网上的代码，把IntegralImage.cs的FromImage(Bitmap image)函数改成：
view plaincopy to clipboardprint?
public static IntegralImage FromImage(Bitmap image)
{
IntegralImage pic = new IntegralImage(image.Width, image.Height);
float rowsum = 0;
/* for (int y = 0; y < image.Height; y++)
{
rowsum = 0;
for (int x = 0; x < image.Width; x++)
{
Color c = image.GetPixel(x, y);
rowsum += (cR * c.R + cG * c.G + cB * c.B) / 255f;
// integral image is rowsum + value above
if(y==0)
pic[0, x] = rowsum;
else
pic[y, x] = rowsum + pic[y - 1, x];
}
}*/
BitmapData dataIn = image.LockBits(new Rectangle(0, 0, image.Width, image.Height), ImageLockMode.ReadOnly, PixelFormat.Format24bppRgb);
unsafe
{
byte* pIn = (byte*)(dataIn.Scan0.ToPointer());
for (int y = 0; y < dataIn.Height; y++)
{
rowsum = 0;
for (int x = 0; x < dataIn.Width; x++)
{
int cb = (byte)( pIn[0]);
int cg = (byte)(pIn[1]);
int cr = (byte)(pIn[2]);
// 0 1 2代表的次序是B G R
rowsum += (cR * cr + cG * cg + cB * cb) / 255f;
// integral image is rowsum + value above
if (y == 0)
pic[0, x] = rowsum;
else
pic[y, x] = rowsum + pic[y - 1, x];
pIn += 3;
}
pIn += dataIn.Stride - dataIn.Width * 3;
}
}
image.UnlockBits(dataIn);
return pic;
}
public static IntegralImage FromImage(Bitmap image)
{
IntegralImage pic = new IntegralImage(image.Width, image.Height);
float rowsum = 0;
/* for (int y = 0; y < image.Height; y++)
{
rowsum = 0;
for (int x = 0; x < image.Width; x++)
{
Color c = image.GetPixel(x, y);
rowsum += (cR * c.R + cG * c.G + cB * c.B) / 255f;
// integral image is rowsum + value above
if(y==0)
pic[0, x] = rowsum;
else
pic[y, x] = rowsum + pic[y - 1, x];
}
}*/
BitmapData dataIn = image.LockBits(new Rectangle(0, 0, image.Width, image.Height), ImageLockMode.ReadOnly, PixelFormat.Format24bppRgb);
unsafe
{
byte* pIn = (byte*)(dataIn.Scan0.ToPointer());
for (int y = 0; y < dataIn.Height; y++)
{
rowsum = 0;
for (int x = 0; x < dataIn.Width; x++)
{
int cb = (byte)( pIn[0]);
int cg = (byte)(pIn[1]);
int cr = (byte)(pIn[2]);
// 0 1 2代表的次序是B G R
rowsum += (cR * cr + cG * cg + cB * cb) / 255f;
// integral image is rowsum + value above
if (y == 0)
pic[0, x] = rowsum;
else
pic[y, x] = rowsum + pic[y - 1, x];
pIn += 3;
}
pIn += dataIn.Stride - dataIn.Width * 3;
}
}
image.UnlockBits(dataIn);
return pic;
}
OK,解决了以上两个问题，OpenSURF的C#版功能算是跟C++差不多了。。。。当然，C#跟C++的速度还有点差距的。。。。接下来就说说如何提高识别率，有两个关键的系数要微调的：
1。FastHessian.getIpoints(0.0001f, 5, 2, iimg);的第一个参数决定了特征点的数量，越小则特征点越多；
2。在Utils.cs里面的if (d1 / d2 < 0.77) //越小匹配的点越少，但误判断点也越少；越大匹配的点越多，但误判断点也越多。
以上两个要微调的函数就要具体情况具体微调了。。。。
