Related
I've been experimenting with the image bicubic resampling algorithm present in the AForge framework with the idea of introducing something similar into my image processing solution. See the original algorithm here and interpolation kernel here
Unfortunately I've hit a wall. It looks to me like somehow I am calculating the sample destination position incorrectly, probably due to the algorithm being designed for Format24bppRgb images where as I am using a Format32bppPArgb format.
Here's my code:
public Bitmap Resize(Bitmap source, int width, int height)
{
int sourceWidth = source.Width;
int sourceHeight = source.Height;
Bitmap destination = new Bitmap(width, height, PixelFormat.Format32bppPArgb);
destination.SetResolution(source.HorizontalResolution, source.VerticalResolution);
using (FastBitmap sourceBitmap = new FastBitmap(source))
{
using (FastBitmap destinationBitmap = new FastBitmap(destination))
{
double heightFactor = sourceWidth / (double)width;
double widthFactor = sourceHeight / (double)height;
// Coordinates of source points
double ox, oy, dx, dy, k1, k2;
int ox1, oy1, ox2, oy2;
// Width and height decreased by 1
int maxHeight = height - 1;
int maxWidth = width - 1;
for (int y = 0; y < height; y++)
{
// Y coordinates
oy = (y * widthFactor) - 0.5;
oy1 = (int)oy;
dy = oy - oy1;
for (int x = 0; x < width; x++)
{
// X coordinates
ox = (x * heightFactor) - 0.5f;
ox1 = (int)ox;
dx = ox - ox1;
// Destination color components
double r = 0;
double g = 0;
double b = 0;
double a = 0;
for (int n = -1; n < 3; n++)
{
// Get Y cooefficient
k1 = Interpolation.BiCubicKernel(dy - n);
oy2 = oy1 + n;
if (oy2 < 0)
{
oy2 = 0;
}
if (oy2 > maxHeight)
{
oy2 = maxHeight;
}
for (int m = -1; m < 3; m++)
{
// Get X cooefficient
k2 = k1 * Interpolation.BiCubicKernel(m - dx);
ox2 = ox1 + m;
if (ox2 < 0)
{
ox2 = 0;
}
if (ox2 > maxWidth)
{
ox2 = maxWidth;
}
Color color = sourceBitmap.GetPixel(ox2, oy2);
r += k2 * color.R;
g += k2 * color.G;
b += k2 * color.B;
a += k2 * color.A;
}
}
destinationBitmap.SetPixel(
x,
y,
Color.FromArgb(a.ToByte(), r.ToByte(), g.ToByte(), b.ToByte()));
}
}
}
}
source.Dispose();
return destination;
}
And the kernel which should represent the given equation on Wikipedia
public static double BiCubicKernel(double x)
{
if (x < 0)
{
x = -x;
}
double bicubicCoef = 0;
if (x <= 1)
{
bicubicCoef = (1.5 * x - 2.5) * x * x + 1;
}
else if (x < 2)
{
bicubicCoef = ((-0.5 * x + 2.5) * x - 4) * x + 2;
}
return bicubicCoef;
}
Here's the original image at 500px x 667px.
And the image resized to 400px x 543px.
Visually it appears that the image is over reduced and then the same pixels are repeatedly applied once we hit a particular point.
Can anyone give me some pointers here to solve this?
Note FastBitmap is a wrapper for Bitmap that uses LockBits to manipulate pixels in memory. It works well with everything else I apply it to.
Edit
As per request here's the methods involved in ToByte
public static byte ToByte(this double value)
{
return Convert.ToByte(ImageMaths.Clamp(value, 0, 255));
}
public static T Clamp<T>(T value, T min, T max) where T : IComparable<T>
{
if (value.CompareTo(min) < 0)
{
return min;
}
if (value.CompareTo(max) > 0)
{
return max;
}
return value;
}
You are limiting your ox2 and oy2 to destination image dimensions, instead of source dimensions.
Change this:
// Width and height decreased by 1
int maxHeight = height - 1;
int maxWidth = width - 1;
to this:
// Width and height decreased by 1
int maxHeight = sourceHeight - 1;
int maxWidth = sourceWidth - 1;
Well, I've met a very strange thing, which might be or might be not a souce of the problem.
I've started to try implementing convolution matrix by myself and encountered strange behaviour. I was testing code on a small image 4x4 pixels. The code is following:
var source = Bitmap.FromFile(#"C:\Users\Public\Pictures\Sample Pictures\Безымянный.png");
using (FastBitmap sourceBitmap = new FastBitmap(source))
{
for (int TY = 0; TY < 4; TY++)
{
for (int TX = 0; TX < 4; TX++)
{
Color color = sourceBitmap.GetPixel(TX, TY);
Console.Write(color.B.ToString().PadLeft(5));
}
Console.WriteLine();
}
}
Althought I'm printing out only blue channel value, it's still clearly incorrect.
On the other hand, your solution partitially works, what makes the thing I've found kind of irrelevant. One more guess I have: what is your system's DPI?
From what I have found helpfull, here are some links:
C++ implementation of bicubic interpolation on
matrix
C# implemetation of bicubic interpolation, lacking the part about rescaling
Thread on gamedev.net which has almost working solution
That's my answer so far, but I will try further.
I'm trying to scan 2 images (32bppArgb format), identify when there is a difference and store the difference block's bounds in a list of rectangles.
Suppose these are the images:
second:
I want to get the different rectangle bounds (the opened directory window in our case).
This is what I've done:
private unsafe List<Rectangle> CodeImage(Bitmap bmp, Bitmap bmp2)
{
List<Rectangle> rec = new List<Rectangle>();
bmData = bmp.LockBits(new System.Drawing.Rectangle(0, 0, 1920, 1080), System.Drawing.Imaging.ImageLockMode.ReadOnly, bmp.PixelFormat);
bmData2 = bmp2.LockBits(new System.Drawing.Rectangle(0, 0, 1920, 1080), System.Drawing.Imaging.ImageLockMode.ReadOnly, bmp2.PixelFormat);
IntPtr scan0 = bmData.Scan0;
IntPtr scan02 = bmData2.Scan0;
int stride = bmData.Stride;
int stride2 = bmData2.Stride;
int nWidth = bmp.Width;
int nHeight = bmp.Height;
int minX = int.MaxValue;;
int minY = int.MaxValue;
int maxX = 0;
bool found = false;
for (int y = 0; y < nHeight; y++)
{
byte* p = (byte*)scan0.ToPointer();
p += y * stride;
byte* p2 = (byte*)scan02.ToPointer();
p2 += y * stride2;
for (int x = 0; x < nWidth; x++)
{
if (p[0] != p2[0] || p[1] != p2[1] || p[2] != p2[2] || p[3] != p2[3]) //found differences-began to store positions.
{
found = true;
if (x < minX)
minX = x;
if (x > maxX)
maxX = x;
if (y < minY)
minY = y;
}
else
{
if (found)
{
int height = getBlockHeight(stride, scan0, maxX, minY, scan02, stride2);
found = false;
Rectangle temp = new Rectangle(minX, minY, maxX - minX, height);
rec.Add(temp);
//x += minX;
y += height;
minX = int.MaxValue;
minY = int.MaxValue;
maxX = 0;
}
}
p += 4;
p2 += 4;
}
}
return rec;
}
public unsafe int getBlockHeight(int stride, IntPtr scan, int x, int y1, IntPtr scan02, int stride2) //a function to get an existing block height.
{
int height = 0;;
for (int y = y1; y < 1080; y++) //only for example- in our case its 1080 height.
{
byte* p = (byte*)scan.ToPointer();
p += (y * stride) + (x * 4); //set the pointer to a specific potential point.
byte* p2 = (byte*)scan02.ToPointer();
p2 += (y * stride2) + (x * 4); //set the pointer to a specific potential point.
if (p[0] != p2[0] || p[1] != p2[1] || p[2] != p2[2] || p[3] != p2[3]) //still change on the height in the increasing **y** of the block.
height++;
}
return height;
}
This is actually how I call the method:
Bitmap a = Image.FromFile(#"C:\Users\itapi\Desktop\1.png") as Bitmap;//generates a 32bppRgba bitmap;
Bitmap b = Image.FromFile(#"C:\Users\itapi\Desktop\2.png") as Bitmap;//
List<Rectangle> l1 = CodeImage(a, b);
int i = 0;
foreach (Rectangle rec in l1)
{
i++;
Bitmap tmp = b.Clone(rec, a.PixelFormat);
tmp.Save(i.ToString() + ".png");
}
But I'm not getting the exact rectangle.. I'm getting only half of that and sometimes even worse. I think something in the code's logic is wrong.
Code for #nico
private unsafe List<Rectangle> CodeImage(Bitmap bmp, Bitmap bmp2)
{
List<Rectangle> rec = new List<Rectangle>();
var bmData1 = bmp.LockBits(new System.Drawing.Rectangle(0, 0, bmp.Width, bmp.Height), System.Drawing.Imaging.ImageLockMode.ReadOnly, bmp.PixelFormat);
var bmData2 = bmp2.LockBits(new System.Drawing.Rectangle(0, 0, bmp.Width, bmp.Height), System.Drawing.Imaging.ImageLockMode.ReadOnly, bmp2.PixelFormat);
int bytesPerPixel = 3;
IntPtr scan01 = bmData1.Scan0;
IntPtr scan02 = bmData2.Scan0;
int stride1 = bmData1.Stride;
int stride2 = bmData2.Stride;
int nWidth = bmp.Width;
int nHeight = bmp.Height;
bool[] visited = new bool[nWidth * nHeight];
byte* base1 = (byte*)scan01.ToPointer();
byte* base2 = (byte*)scan02.ToPointer();
for (int y = 0; y < nHeight; y += 5)
{
byte* p1 = base1;
byte* p2 = base2;
for (int x = 0; x < nWidth; x += 5)
{
if (!ArePixelsEqual(p1, p2, bytesPerPixel) && !(visited[x + nWidth * y]))
{
// fill the different area
int minX = x;
int maxX = x;
int minY = y;
int maxY = y;
var pt = new Point(x, y);
Stack<Point> toBeProcessed = new Stack<Point> ();
visited[x + nWidth * y] = true;
toBeProcessed.Push(pt);
while (toBeProcessed.Count > 0)
{
var process = toBeProcessed.Pop();
var ptr1 = (byte*)scan01.ToPointer() + process.Y * stride1 + process.X * bytesPerPixel;
var ptr2 = (byte*) scan02.ToPointer() + process.Y * stride2 + process.X * bytesPerPixel;
//Check pixel equality
if (ArePixelsEqual(ptr1, ptr2, bytesPerPixel))
continue;
//This pixel is different
//Update the rectangle
if (process.X < minX) minX = process.X;
if (process.X > maxX) maxX = process.X;
if (process.Y < minY) minY = process.Y;
if (process.Y > maxY) maxY = process.Y;
Point n;
int idx;
//Put neighbors in stack
if (process.X - 1 >= 0)
{
n = new Point(process.X - 1, process.Y);
idx = n.X + nWidth * n.Y;
if (!visited[idx])
{
visited[idx] = true;
toBeProcessed.Push(n);
}
}
if (process.X + 1 < nWidth)
{
n = new Point(process.X + 1, process.Y);
idx = n.X + nWidth * n.Y;
if (!visited[idx])
{
visited[idx] = true;
toBeProcessed.Push(n);
}
}
if (process.Y - 1 >= 0)
{
n = new Point(process.X, process.Y - 1);
idx = n.X + nWidth * n.Y;
if (!visited[idx])
{
visited[idx] = true;
toBeProcessed.Push(n);
}
}
if (process.Y + 1 < nHeight)
{
n = new Point(process.X, process.Y + 1);
idx = n.X + nWidth * n.Y;
if (!visited[idx])
{
visited[idx] = true;
toBeProcessed.Push(n);
}
}
}
if (((maxX - minX + 1) > 5) & ((maxY - minY + 1) > 5))
rec.Add(new Rectangle(minX, minY, maxX - minX + 1, maxY - minY + 1));
}
p1 += 5 * bytesPerPixel;
p2 += 5 * bytesPerPixel;
}
base1 += 5 * stride1;
base2 += 5 * stride2;
}
bmp.UnlockBits(bmData1);
bmp2.UnlockBits(bmData2);
return rec;
}
I see a couple of problems with your code. If I understand it correctly, you
find a pixel that's different between the two images.
then you continue to scan from there to the right, until you find a position where both images are identical again.
then you scan from the last "different" pixel to the bottom, until you find a position where both images are identical again.
then you store that rectangle and start at the next line below it
Am I right so far?
Two obvious things can go wrong here:
If two rectangles have overlapping y-ranges, you're in trouble: You'll find the first rectangle fine, then skip to the bottom Y-coordinate, ignoring all the pixels left or right of the rectangle you just found.
Even if there is only one rectangle, you assume that every pixel on the rectangle's border is different, and all the other pixels are identical. If that assumption isn't valid, you'll stop searching too early, and only find parts of rectangles.
If your images come from a scanner or digital camera, or if they contain lossy compression (jpeg) artifacts, the second assumption will almost certainly be wrong. To illustrate this, here's what I get when I mark every identical pixel the two jpg images you linked black, and every different pixel white:
What you see is not a rectangle. Instead, a lot of pixels around the rectangles you're looking for are different:
That's because of jpeg compression artifacts. But even if you used lossless source images, pixels at the borders might not form perfect rectangles, because of antialiasing or because the background just happens to have a similar color in that region.
You could try to improve your algorithm, but if you look at that border, you will find all kinds of ugly counterexamples to any geometric assumptions you'll make.
It would probably be better to implement this "the right way". Meaning:
Either implement a flood fill algorithm that erases different pixels (e.g. by setting them to identical or by storing a flag in a separate mask), then recursively checks if the 4 neighbor pixels.
Or implement a connected component labeling algorithm, that marks each different pixel with a temporary integer label, using clever data structures to keep track which temporary labels are connected. If you're only interested in a bounding box, you don't even have to merge the temporary labels, just merge the bounding boxes of adjacent labeled areas.
Connected component labeling is in general a bit faster, but is a bit trickier to get right than flood fill.
One last advice: I would rethink your "no 3rd party libraries" policy if I were you. Even if your final product will contain no 3rd party libraries, development might by a lot faster if you used well-documented, well-tested, useful building blocks from a library, then replaced them one by one with your own code. (And who knows, you might even find an open source library with a suitable license that's so much faster than your own code that you'll stick with it in the end...)
ADD: In case you want to rethink your "no libraries" position: Here's a quick and simple implementation using AForge (which has a more permissive library than emgucv):
private static void ProcessImages()
{
(* load images *)
var img1 = AForge.Imaging.Image.FromFile(#"compare1.jpg");
var img2 = AForge.Imaging.Image.FromFile(#"compare2.jpg");
(* calculate absolute difference *)
var difference = new AForge.Imaging.Filters.ThresholdedDifference(15)
{OverlayImage = img1}
.Apply(img2);
(* create and initialize the blob counter *)
var bc = new AForge.Imaging.BlobCounter();
bc.FilterBlobs = true;
bc.MinWidth = 5;
bc.MinHeight = 5;
(* find blobs *)
bc.ProcessImage(difference);
(* draw result *)
BitmapData data = img2.LockBits(
new Rectangle(0, 0, img2.Width, img2.Height),
ImageLockMode.ReadWrite, img2.PixelFormat);
foreach (var rc in bc.GetObjectsRectangles())
AForge.Imaging.Drawing.FillRectangle(data, rc, Color.FromArgb(128,Color.Red));
img2.UnlockBits(data);
img2.Save(#"compareResult.jpg");
}
The actual difference + blob detection part (without loading and result display) takes about 43ms, for the second run (this first time takes longer of course, due to JITting, cache, etc.)
Result (the rectangle is larger due to jpeg artifacts):
Here is a flood-fill based version of your code. It checks every pixel for difference. If it finds a different pixel, it runs an exploration to find the entire different area.
The code is only meant as an illustration. There are certainly some points that could be improved.
unsafe bool ArePixelsEqual(byte* p1, byte* p2, int bytesPerPixel)
{
for (int i = 0; i < bytesPerPixel; ++i)
if (p1[i] != p2[i])
return false;
return true;
}
private static unsafe List<Rectangle> CodeImage(Bitmap bmp, Bitmap bmp2)
{
if (bmp.PixelFormat != bmp2.PixelFormat || bmp.Width != bmp2.Width || bmp.Height != bmp2.Height)
throw new ArgumentException();
List<Rectangle> rec = new List<Rectangle>();
var bmData1 = bmp.LockBits(new System.Drawing.Rectangle(0, 0, bmp.Width, bmp.Height), System.Drawing.Imaging.ImageLockMode.ReadOnly, bmp.PixelFormat);
var bmData2 = bmp2.LockBits(new System.Drawing.Rectangle(0, 0, bmp.Width, bmp.Height), System.Drawing.Imaging.ImageLockMode.ReadOnly, bmp2.PixelFormat);
int bytesPerPixel = Image.GetPixelFormatSize(bmp.PixelFormat) / 8;
IntPtr scan01 = bmData1.Scan0;
IntPtr scan02 = bmData2.Scan0;
int stride1 = bmData1.Stride;
int stride2 = bmData2.Stride;
int nWidth = bmp.Width;
int nHeight = bmp.Height;
bool[] visited = new bool[nWidth * nHeight];
byte* base1 = (byte*)scan01.ToPointer();
byte* base2 = (byte*)scan02.ToPointer();
for (int y = 0; y < nHeight; y++)
{
byte* p1 = base1;
byte* p2 = base2;
for (int x = 0; x < nWidth; ++x)
{
if (!ArePixelsEqual(p1, p2, bytesPerPixel) && !(visited[x + nWidth * y]))
{
// fill the different area
int minX = x;
int maxX = x;
int minY = y;
int maxY = y;
var pt = new Point(x, y);
Stack<Point> toBeProcessed = new Stack<Point>();
visited[x + nWidth * y] = true;
toBeProcessed.Push(pt);
while (toBeProcessed.Count > 0)
{
var process = toBeProcessed.Pop();
var ptr1 = (byte*)scan01.ToPointer() + process.Y * stride1 + process.X * bytesPerPixel;
var ptr2 = (byte*)scan02.ToPointer() + process.Y * stride2 + process.X * bytesPerPixel;
//Check pixel equality
if (ArePixelsEqual(ptr1, ptr2, bytesPerPixel))
continue;
//This pixel is different
//Update the rectangle
if (process.X < minX) minX = process.X;
if (process.X > maxX) maxX = process.X;
if (process.Y < minY) minY = process.Y;
if (process.Y > maxY) maxY = process.Y;
Point n; int idx;
//Put neighbors in stack
if (process.X - 1 >= 0)
{
n = new Point(process.X - 1, process.Y); idx = n.X + nWidth * n.Y;
if (!visited[idx]) { visited[idx] = true; toBeProcessed.Push(n); }
}
if (process.X + 1 < nWidth)
{
n = new Point(process.X + 1, process.Y); idx = n.X + nWidth * n.Y;
if (!visited[idx]) { visited[idx] = true; toBeProcessed.Push(n); }
}
if (process.Y - 1 >= 0)
{
n = new Point(process.X, process.Y - 1); idx = n.X + nWidth * n.Y;
if (!visited[idx]) { visited[idx] = true; toBeProcessed.Push(n); }
}
if (process.Y + 1 < nHeight)
{
n = new Point(process.X, process.Y + 1); idx = n.X + nWidth * n.Y;
if (!visited[idx]) { visited[idx] = true; toBeProcessed.Push(n); }
}
}
rec.Add(new Rectangle(minX, minY, maxX - minX + 1, maxY - minY + 1));
}
p1 += bytesPerPixel;
p2 += bytesPerPixel;
}
base1 += stride1;
base2 += stride2;
}
bmp.UnlockBits(bmData1);
bmp2.UnlockBits(bmData2);
return rec;
}
You can achieve this easily using a flood fill segmentation algorithm.
First an utility class to make fast bitmap access easier. This will help to encapsulate the complex pointer-logic and make the code more readable:
class BitmapWithAccess
{
public Bitmap Bitmap { get; private set; }
public System.Drawing.Imaging.BitmapData BitmapData { get; private set; }
public BitmapWithAccess(Bitmap bitmap, System.Drawing.Imaging.ImageLockMode lockMode)
{
Bitmap = bitmap;
BitmapData = bitmap.LockBits(new Rectangle(Point.Empty, bitmap.Size), lockMode, System.Drawing.Imaging.PixelFormat.Format32bppArgb);
}
public Color GetPixel(int x, int y)
{
unsafe
{
byte* dataPointer = MovePointer((byte*)BitmapData.Scan0, x, y);
return Color.FromArgb(dataPointer[3], dataPointer[2], dataPointer[1], dataPointer[0]);
}
}
public void SetPixel(int x, int y, Color color)
{
unsafe
{
byte* dataPointer = MovePointer((byte*)BitmapData.Scan0, x, y);
dataPointer[3] = color.A;
dataPointer[2] = color.R;
dataPointer[1] = color.G;
dataPointer[0] = color.B;
}
}
public void Release()
{
Bitmap.UnlockBits(BitmapData);
BitmapData = null;
}
private unsafe byte* MovePointer(byte* pointer, int x, int y)
{
return pointer + x * 4 + y * BitmapData.Stride;
}
}
Then a class representing a rectangle containing different pixels, to mark them in the resulting image. In general this class can also contain a list of Point instances (or a byte[,] map) to make indicating individual pixels in the resulting image possible:
class Segment
{
public int Left { get; set; }
public int Top { get; set; }
public int Right { get; set; }
public int Bottom { get; set; }
public Bitmap Bitmap { get; set; }
public Segment()
{
Left = int.MaxValue;
Right = int.MinValue;
Top = int.MaxValue;
Bottom = int.MinValue;
}
};
Then the steps of a simple algorithm are as follows:
find different pixels
use a flood-fill algorithm to find segments on the difference image
draw bounding rectangles for the segments found
The first step is the easiest one:
static Bitmap FindDifferentPixels(Bitmap i1, Bitmap i2)
{
var result = new Bitmap(i1.Width, i2.Height, System.Drawing.Imaging.PixelFormat.Format32bppArgb);
var ia1 = new BitmapWithAccess(i1, System.Drawing.Imaging.ImageLockMode.ReadOnly);
var ia2 = new BitmapWithAccess(i2, System.Drawing.Imaging.ImageLockMode.ReadOnly);
var ra = new BitmapWithAccess(result, System.Drawing.Imaging.ImageLockMode.ReadWrite);
for (int x = 0; x < i1.Width; ++x)
for (int y = 0; y < i1.Height; ++y)
{
var different = ia1.GetPixel(x, y) != ia2.GetPixel(x, y);
ra.SetPixel(x, y, different ? Color.White : Color.FromArgb(0, 0, 0, 0));
}
ia1.Release();
ia2.Release();
ra.Release();
return result;
}
And the second and the third steps are covered with the following three functions:
static List<Segment> Segmentize(Bitmap blackAndWhite)
{
var bawa = new BitmapWithAccess(blackAndWhite, System.Drawing.Imaging.ImageLockMode.ReadOnly);
var result = new List<Segment>();
HashSet<Point> queue = new HashSet<Point>();
bool[,] visitedPoints = new bool[blackAndWhite.Width, blackAndWhite.Height];
for (int x = 0;x < blackAndWhite.Width;++x)
for (int y = 0;y < blackAndWhite.Height;++y)
{
if (bawa.GetPixel(x, y).A != 0
&& !visitedPoints[x, y])
{
result.Add(BuildSegment(new Point(x, y), bawa, visitedPoints));
}
}
bawa.Release();
return result;
}
static Segment BuildSegment(Point startingPoint, BitmapWithAccess bawa, bool[,] visitedPoints)
{
var result = new Segment();
List<Point> toProcess = new List<Point>();
toProcess.Add(startingPoint);
while (toProcess.Count > 0)
{
Point p = toProcess.First();
toProcess.RemoveAt(0);
ProcessPoint(result, p, bawa, toProcess, visitedPoints);
}
return result;
}
static void ProcessPoint(Segment segment, Point point, BitmapWithAccess bawa, List<Point> toProcess, bool[,] visitedPoints)
{
for (int i = -1; i <= 1; ++i)
{
for (int j = -1; j <= 1; ++j)
{
int x = point.X + i;
int y = point.Y + j;
if (x < 0 || y < 0 || x >= bawa.Bitmap.Width || y >= bawa.Bitmap.Height)
continue;
if (bawa.GetPixel(x, y).A != 0 && !visitedPoints[x, y])
{
segment.Left = Math.Min(segment.Left, x);
segment.Right = Math.Max(segment.Right, x);
segment.Top = Math.Min(segment.Top, y);
segment.Bottom = Math.Max(segment.Bottom, y);
toProcess.Add(new Point(x, y));
visitedPoints[x, y] = true;
}
}
}
}
And the following program given your two images as arguments:
static void Main(string[] args)
{
Image ai1 = Image.FromFile(args[0]);
Image ai2 = Image.FromFile(args[1]);
Bitmap i1 = new Bitmap(ai1.Width, ai1.Height, System.Drawing.Imaging.PixelFormat.Format32bppArgb);
Bitmap i2 = new Bitmap(ai2.Width, ai2.Height, System.Drawing.Imaging.PixelFormat.Format32bppArgb);
using (var g1 = Graphics.FromImage(i1))
using (var g2 = Graphics.FromImage(i2))
{
g1.DrawImage(ai1, Point.Empty);
g2.DrawImage(ai2, Point.Empty);
}
var difference = FindDifferentPixels(i1, i2);
var segments = Segmentize(difference);
using (var g1 = Graphics.FromImage(i1))
{
foreach (var segment in segments)
{
g1.DrawRectangle(Pens.Red, new Rectangle(segment.Left, segment.Top, segment.Right - segment.Left, segment.Bottom - segment.Top));
}
}
i1.Save("result.png");
Console.WriteLine("Done.");
Console.ReadKey();
}
produces the following result:
As you can see there are more differences between the given images. You can filter the resulting segments with regard to their size for example to drop the small artefacts. Also there is of course much work to do in terms of error checking, design and performance.
One idea is to proceed as follows:
1) Rescale images to a smaller size (downsample)
2) Run the above algorithm on smaller images
3) Run the above algorithm on original images, but restricting yourself only to rectangles found in step 2)
This can be of course extended to a multi-level hierarchical approach (using more different image sizes, increasing accuracy with each step).
Ah an algorithm challenge. Like! :-)
There are other answers here using f.ex. floodfill that will work just fine. I just noticed that you wanted something fast, so let me propose a different idea. Unlike the other people, I haven't tested it; it shouldn't be too hard and should be quite fast, but I simply don't have the time at the moment to test it myself. If you do, please share the results. Also, note that it's not a standard algorithm, so there are probably some bugs here and there in my explanation (and no patents).
My idea is derived from the idea of mean adaptive thresholding but with a lot of important differences. I cannot find the link from wikipedia anymore or my code, so I'll do this from the top of my mind. Basically you create a new (64-bit) buffer for both images and fill it with:
f(x,y) = colorvalue + f(x-1, y) + f(x, y-1) - f(x-1, y-1)
f(x,0) = colorvalue + f(x-1, 0)
f(0,y) = colorvalue + f(0, y-1)
The main trick is that you can calculate the sum value of a portion of the image fast, namely by:
g(x1,y1,x2,y2) = f(x2,y2)-f(x1-1,y2)-f(x2,y1-1)+f(x1-1,y1-1)
In other words, this will give the same result as:
result = 0;
for (x=x1; x<=x2; ++x)
for (y=y1; y<=y2; ++y)
result += f(x,y)
In our case this means that with only 4 integer operations this will get you some unique number of the block in question. I'd say that's pretty awesome.
Now, in our case, we don't really care about the average value; we just care about some sort-of unique number. If the image changes, it should change - simple as that. As for colorvalue, usually some gray scale number is used for thresholding - instead, we'll be using the complete 24-bit RGB value. Because there are only so few compares, we can simply scan until we find a block that doesn't match.
The basic algorithm that I propose works as follows:
for (y=0; y<height;++y)
for (x=0; x<width; ++x)
if (src[x,y] != dst[x,y])
if (!IntersectsWith(x, y, foundBlocks))
FindBlock(foundBlocks);
Now, IntersectsWith can be something like a quad tree of if there are only a few blocks, you can simply iterate through the blocks and check if they are within the bounds of the block. You can also update the x variable accordingly (I would). You can even balance things by re-building the buffer for f(x,y) if you have too many blocks (more precise: merge found blocks back from dst into src, then rebuild the buffer).
FindBlocks is where it gets interesting. Using the formula for g that's now pretty easy:
int x1 = x-1; int y1 = y-1; int x2 = x; int y2 = y;
while (changes)
{
while (g(srcimage,x1-1,y1,x1,y2) == g(dstimage,x1-1,y1,x1,y2)) { --x1; }
while (g(srcimage,x1,y1-1,x1,y2) == g(dstimage,x1,y1-1,x1,y2)) { --y1; }
while (g(srcimage,x1,y1,x1+1,y2) == g(dstimage,x1,y1,x1+1,y2)) { ++x1; }
while (g(srcimage,x1,y1,x1,y2+1) == g(dstimage,x1,y1,x1,y2+1)) { ++y1; }
}
That's it. Note that the complexity of the FindBlocks algorithm is O(x + y), which is pretty awesome for finding a 2D block IMO. :-)
As I said, let me know how it turns out.
I've got torubles with appling gaussian blur to image in frequency domain.
For unknown reasons (probably I've dont something wrong) I recieve wired image instead of blurred one.
There's what i do step by step:
Load the image.
Split image into separate channels.
private static Bitmap[] separateColorChannels(Bitmap source, int channelCount)
{
if (channelCount != 3 && channelCount != 4)
{
throw new NotSupportedException("Bitmap[] FFTServices.separateColorChannels(Bitmap, int): Only 3 and 4 channels are supported.");
}
Bitmap[] result = new Bitmap[channelCount];
LockBitmap[] locks = new LockBitmap[channelCount];
LockBitmap sourceLock = new LockBitmap(source);
sourceLock.LockBits();
for (int i = 0; i < channelCount; ++i)
{
result[i] = new Bitmap(source.Width, source.Height, PixelFormat.Format8bppIndexed);
locks[i] = new LockBitmap(result[i]);
locks[i].LockBits();
}
for (int x = 0; x < source.Width; x++)
{
for (int y = 0; y < source.Height; y++)
{
switch (channelCount)
{
case 3:
locks[0].SetPixel(x, y, Color.FromArgb(sourceLock.GetPixel(x, y).R));
locks[1].SetPixel(x, y, Color.FromArgb(sourceLock.GetPixel(x, y).G));
locks[2].SetPixel(x, y, Color.FromArgb(sourceLock.GetPixel(x, y).B));
break;
case 4:
locks[0].SetPixel(x, y, Color.FromArgb(sourceLock.GetPixel(x, y).A));
locks[1].SetPixel(x, y, Color.FromArgb(sourceLock.GetPixel(x, y).R));
locks[2].SetPixel(x, y, Color.FromArgb(sourceLock.GetPixel(x, y).G));
locks[3].SetPixel(x, y, Color.FromArgb(sourceLock.GetPixel(x, y).B));
break;
default:
break;
}
}
}
for (int i = 0; i < channelCount; ++i)
{
locks[i].UnlockBits();
}
sourceLock.UnlockBits();
}
Convert every channel into complex images (with AForge.NET).
public static AForge.Imaging.ComplexImage[] convertColorChannelsToComplex(Emgu.CV.Image<Emgu.CV.Structure.Gray, Byte>[] channels)
{
AForge.Imaging.ComplexImage[] result = new AForge.Imaging.ComplexImage[channels.Length];
for (int i = 0; i < channels.Length; ++i)
{
result[i] = AForge.Imaging.ComplexImage.FromBitmap(channels[i].Bitmap);
}
return result;
}
Apply Gaussian blur.
First i create the kernel (For testing purposes kernel size is equal to image size, tho only center part of it is calculated with gaussian function, rest of kernel is equal to re=1 im=0).
private ComplexImage makeGaussKernel(int side, double min, double max, double step, double std)
{
// get value at top left corner
double _0x0 = gauss2d(min, min, std);
// top left corner should be 1, so making scaler for rest of the values
double scaler = 1 / _0x0;
int pow2 = SizeServices.getNextNearestPowerOf2(side);
Bitmap bitmap = new Bitmap(pow2, pow2, PixelFormat.Format8bppIndexed);
var result = AForge.Imaging.ComplexImage.FromBitmap(bitmap);
// For test purposes my kernel is size of image, so first, filling with 1 only.
for (int i = 0; i < result.Data.GetLength(0); ++i)
{
for (int j = 0; j < result.Data.GetLength(0); ++j)
{
result.Data[i, j].Re = 1;
result.Data[i, j].Im = 0;
}
}
// The real kernel's size.
int count = (int)((Math.Abs(max) + Math.Abs(min)) / step);
double h = min;
// Calculating kernel's values and storing them somewhere in the center of kernel.
for (int i = result.Data.GetLength(0) / 2 - count / 2; i < result.Data.GetLength(0) / 2 + count / 2; ++i)
{
double w = min;
for (int j = result.Data.GetLength(1) / 2 - count / 2; j < result.Data.GetLength(1) / 2 + count / 2; ++j)
{
result.Data[i, j].Re = (scaler * gauss2d(w, h, std)) * 255;
w += step;
}
h += step;
}
return result;
}
// The gauss function
private double gauss2d(double x, double y, double std)
{
return ((1.0 / (2 * Math.PI * std * std)) * Math.Exp(-((x * x + y * y) / (2 * std * std))));
}
Apply FFT to every channel and kernel.
Multiply center part of every channel by kernel.
void applyFilter(/*shortened*/)
{
// Image's size is 512x512 that's why 512 is hardcoded here
// min = -2.0; max = 2.0; step = 0.33; std = 11
ComplexImage filter = makeGaussKernel(512, min, max, step, std);
// Applies FFT (with AForge.NET) to every channel and filter
applyFFT(complexImage);
applyFFT(filter);
for (int i = 0; i < 3; ++i)
{
applyGauss(complexImage[i], filter, side);
}
// Applies IFFT to every channel
applyIFFT(complexImage);
}
private void applyGauss(ComplexImage complexImage, ComplexImage filter, int side)
{
int width = complexImage.Data.GetLength(1);
int height = complexImage.Data.GetLength(0);
for(int i = 0; i < height; ++i)
{
for(int j = 0; j < width; ++j)
{
complexImage.Data[i, j] = AForge.Math.Complex.Multiply(complexImage.Data[i, j], filter.Data[i, j]);
}
}
}
Apply IFFT to every channel.
Convert every channel back to bitmaps (with AForge.NET).
public static System.Drawing.Bitmap[] convertComplexColorChannelsToBitmap(AForge.Imaging.ComplexImage[] channels)
{
System.Drawing.Bitmap[] result = new System.Drawing.Bitmap[channels.Length];
for (int i = 0; i < channels.Length; ++i)
{
result[i] = channels[i].ToBitmap();
}
return result;
}
Merge bitmaps into single bitmap
public static Bitmap mergeColorChannels(Bitmap[] channels)
{
Bitmap result = null;
switch (channels.Length)
{
case 1:
return channels[0];
case 3:
result = new Bitmap(channels[0].Width, channels[0].Height, PixelFormat.Format24bppRgb);
break;
case 4:
result = new Bitmap(channels[0].Width, channels[0].Height, PixelFormat.Format32bppArgb);
break;
default:
throw new NotSupportedException("Bitmap FFTServices.mergeColorChannels(Bitmap[]): Only 1, 3 and 4 channels are supported.");
}
LockBitmap resultLock = new LockBitmap(result);
resultLock.LockBits();
LockBitmap red = new LockBitmap(channels[0]);
LockBitmap green = new LockBitmap(channels[1]);
LockBitmap blue = new LockBitmap(channels[2]);
red.LockBits();
green.LockBits();
blue.LockBits();
for (int y = 0; y < result.Height; y++)
{
for (int x = 0; x < result.Width; x++)
{
resultLock.SetPixel(x, y, Color.FromArgb((int)red.GetPixel(x, y).R, (int)green.GetPixel(x, y).G, (int)blue.GetPixel(x, y).B));
}
}
red.UnlockBits();
green.UnlockBits();
blue.UnlockBits();
resultLock.UnlockBits();
return result;
}
As a result I've got shifted, red-colored blurred version of image: link.
#edit - Updated the question with several changes to the code.
I figured it out with some help at DSP stackexchange... and some cheating but it works. The main problem was kernel generation and applying FFT to it. Also important thing is that AForge.NET divides image pixels by 255 during conversion to ComplexImage and multiplies by 255 during conversion from ComplexImage to Bitmap (thanks Olli Niemitalo # DSP SE).
How I solved this:
I've found how kernel should look like after FFT (see below).
Looked up colors of that image.
Calculated gauss2d for x = -2; y = -2; std = 1.
Calculated the prescaler to receive color value from value calculated in pt. 3 (see wolfram).
Generated kernel with scaled values with perscaler from pt. 4.
However I cant use FFT on generated filter, because generated filter looks like filter after FFT already. It works - the output image is blurred without artifacts so I think that's not too bad.
The images (I cant post more than 2 links, and images are farily big):
Input image
Generated filter (without FFT!)
Parameters for below function:
std = 1.0
size = 8.0
width = height = 512
Result image
The final code:
private ComplexImage makeGaussKernel(double size, double std, int imgWidth, int imgHeight)
{
double scale = 2000.0;
double hsize = size / 2.0;
Bitmap bmp = new Bitmap(imgWidth, imgHeight, PixelFormat.Format8bppIndexed);
LockBitmap lbmp = new LockBitmap(bmp);
lbmp.LockBits();
double y = -hsize;
double yStep = hsize / (lbmp.Height / 2.0);
double xStep = hsize / (lbmp.Width / 2.0);
for (int i = 0; i < lbmp.Height; ++i)
{
double x = -hsize;
for (int j = 0; j < lbmp.Width; ++j)
{
double g = gauss2d(x, y, std) * scale;
g = g < 0.0 ? 0.0 : g;
g = g > 255.0 ? 255.0 : g;
lbmp.SetPixel(j, i, Color.FromArgb((int)g));
x += xStep;
}
y += yStep;
}
lbmp.UnlockBits();
return ComplexImage.FromBitmap(bmp);
}
private double gauss2d(double x, double y, double std)
{
return (1.0 / (2 * Math.PI * std * std)) * Math.Exp(-(((x * x) + (y * y)) / (2 * std * std)));
}
private void applyGaussToImage(ComplexImage complexImage, ComplexImage filter)
{
for (int i = 0; i < complexImage.Height; ++i)
{
for (int j = 0; j < complexImage.Width; ++j)
{
complexImage.Data[i, j] = AForge.Math.Complex.Multiply(complexImage.Data[i, j], filter.Data[i, j]);
}
}
}
I'm looking for a fast, professionally looking and customizable waveform display component in C#.
I'm wanting to display mainly real-time audio waveforms (fast!) in both time and frequency domain. I would like the ability to zoom, change axis settings, display multiple channels, customize the feel and colors etc...
Anybody knows of anything, whether commercial or not?
Thank you!
Diego
I bumped into a code project awhile ago that was doing this.
Check out http://www.codeproject.com/KB/miscctrl/GraphComponents.aspx it may be what you are looking for to do real-time graphing in .net
as far as i know, national instrument has some cool control, but it's not free.
http://sine.ni.com/psp/app/doc/p/id/psp-317
free ones:
http://www.codeproject.com/KB/audio-video/wavecontrol.aspx
Based on Illaya's code:
public void CreateWaveForm(string audioFilePath, string audioWaveFormFilePath)
{
try
{
int bytesPerSample = 0;
using (NAudio.Wave.Mp3FileReader reader = new NAudio.Wave.Mp3FileReader(audioFilePath, wf => new NAudio.FileFormats.Mp3.DmoMp3FrameDecompressor(wf)))
{
using (NAudio.Wave.WaveChannel32 channelStream = new NAudio.Wave.WaveChannel32(reader))
{
bytesPerSample = (reader.WaveFormat.BitsPerSample / 8) * channelStream.WaveFormat.Channels;
//Give a size to the bitmap; either a fixed size, or something based on the length of the audio
using (Bitmap bitmap = new Bitmap((int)Math.Round(reader.TotalTime.TotalSeconds * 40), 200))
{
int width = bitmap.Width;
int height = bitmap.Height;
using (Graphics graphics = Graphics.FromImage(bitmap))
{
graphics.Clear(Color.White);
Pen bluePen = new Pen(Color.Blue);
int samplesPerPixel = (int)(reader.Length / (double)(width * bytesPerSample));
int bytesPerPixel = bytesPerSample * samplesPerPixel;
int bytesRead;
byte[] waveData = new byte[bytesPerPixel];
for (float x = 0; x < width; x++)
{
bytesRead = reader.Read(waveData, 0, bytesPerPixel);
if (bytesRead == 0)
break;
short low = 0;
short high = 0;
for (int n = 0; n < bytesRead; n += 2)
{
short sample = BitConverter.ToInt16(waveData, n);
if (sample < low) low = sample;
if (sample > high) high = sample;
}
float lowPercent = ((((float)low) - short.MinValue) / ushort.MaxValue);
float highPercent = ((((float)high) - short.MinValue) / ushort.MaxValue);
float lowValue = height * lowPercent;
float highValue = height * highPercent;
graphics.DrawLine(bluePen, x, lowValue, x, highValue);
}
}
bitmap.Save(audioWaveFormFilePath);
}
}
}
}
catch
{
}
}
That is a wave flow displayer
http://www.codeproject.com/KB/audio-video/wavecontrol.aspx
Check out Zedgraph. It's a free graphing library that works great. There are lots of code samples on their website that allow you to do what you're asking. Zedgraph Downloads Their website seems to be having issues right now, but the download session works and contains all of their sample files.
This will generate waveform from audio file using nAudio...
using NAudio.Wave;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.IO;
using System.Linq;
using System.Web;
using System.Web.UI;
using System.Web.UI.WebControls;
public partial class test : System.Web.UI.Page
{
protected void Page_Load(object sender, EventArgs e)
{
string strPath = Server.MapPath("audio/060.mp3");
string SongID = "2";
byte[] bytes = File.ReadAllBytes(strPath);
WriteToFile(SongID,strPath, bytes);
Response.Redirect("Main.aspx");
}
private void WriteToFile(string SongID, string strPath, byte[] Buffer)
{
try
{
int samplesPerPixel = 128;
long startPosition = 0;
//FileStream newFile = new FileStream(GeneralUtils.Get_SongFilePath() + "/" + strPath, FileMode.Create);
float[] data = FloatArrayFromByteArray(Buffer);
Bitmap bmp = new Bitmap(1170, 200);
int BORDER_WIDTH = 5;
int width = bmp.Width - (2 * BORDER_WIDTH);
int height = bmp.Height - (2 * BORDER_WIDTH);
NAudio.Wave.Mp3FileReader reader = new NAudio.Wave.Mp3FileReader(strPath, wf => new NAudio.FileFormats.Mp3.DmoMp3FrameDecompressor(wf));
NAudio.Wave.WaveChannel32 channelStream = new NAudio.Wave.WaveChannel32(reader);
int bytesPerSample = (reader.WaveFormat.BitsPerSample / 8) * channelStream.WaveFormat.Channels;
using (Graphics g = Graphics.FromImage(bmp))
{
g.Clear(Color.White);
Pen pen1 = new Pen(Color.Gray);
int size = data.Length;
string hexValue1 = "#009adf";
Color colour1 = System.Drawing.ColorTranslator.FromHtml(hexValue1);
pen1.Color = colour1;
Stream wavestream = new NAudio.Wave.Mp3FileReader(strPath, wf => new NAudio.FileFormats.Mp3.DmoMp3FrameDecompressor(wf));
wavestream.Position = 0;
int bytesRead1;
byte[] waveData1 = new byte[samplesPerPixel * bytesPerSample];
wavestream.Position = startPosition + (width * bytesPerSample * samplesPerPixel);
for (float x = 0; x < width; x++)
{
short low = 0;
short high = 0;
bytesRead1 = wavestream.Read(waveData1, 0, samplesPerPixel * bytesPerSample);
if (bytesRead1 == 0)
break;
for (int n = 0; n < bytesRead1; n += 2)
{
short sample = BitConverter.ToInt16(waveData1, n);
if (sample < low) low = sample;
if (sample > high) high = sample;
}
float lowPercent = ((((float)low) - short.MinValue) / ushort.MaxValue);
float highPercent = ((((float)high) - short.MinValue) / ushort.MaxValue);
float lowValue = height * lowPercent;
float highValue = height * highPercent;
g.DrawLine(pen1, x, lowValue, x, highValue);
}
}
string filename = Server.MapPath("image/060.png");
bmp.Save(filename);
bmp.Dispose();
}
catch (Exception e)
{
}
}
public float[] FloatArrayFromStream(System.IO.MemoryStream stream)
{
return FloatArrayFromByteArray(stream.GetBuffer());
}
public float[] FloatArrayFromByteArray(byte[] input)
{
float[] output = new float[input.Length / 4];
for (int i = 0; i < output.Length; i++)
{
output[i] = BitConverter.ToSingle(input, i * 4);
}
return output;
}
}
Is there any open source C# code or library to present a graphical waveform given a byte array?
This is as open source as it gets:
public static void DrawNormalizedAudio(ref float[] data, PictureBox pb,
Color color)
{
Bitmap bmp;
if (pb.Image == null)
{
bmp = new Bitmap(pb.Width, pb.Height);
}
else
{
bmp = (Bitmap)pb.Image;
}
int BORDER_WIDTH = 5;
int width = bmp.Width - (2 * BORDER_WIDTH);
int height = bmp.Height - (2 * BORDER_WIDTH);
using (Graphics g = Graphics.FromImage(bmp))
{
g.Clear(Color.Black);
Pen pen = new Pen(color);
int size = data.Length;
for (int iPixel = 0; iPixel < width; iPixel++)
{
// determine start and end points within WAV
int start = (int)((float)iPixel * ((float)size / (float)width));
int end = (int)((float)(iPixel + 1) * ((float)size / (float)width));
float min = float.MaxValue;
float max = float.MinValue;
for (int i = start; i < end; i++)
{
float val = data[i];
min = val < min ? val : min;
max = val > max ? val : max;
}
int yMax = BORDER_WIDTH + height - (int)((max + 1) * .5 * height);
int yMin = BORDER_WIDTH + height - (int)((min + 1) * .5 * height);
g.DrawLine(pen, iPixel + BORDER_WIDTH, yMax,
iPixel + BORDER_WIDTH, yMin);
}
}
pb.Image = bmp;
}
This function will produce something like this:
This takes an array of samples in floating-point format (where all sample values range from -1 to +1). If your original data is actually in the form of a byte[] array, you'll have to do a little bit of work to convert it to float[]. Let me know if you need that, too.
Update: since the question technically asked for something to render a byte array, here are a couple of helper methods:
public float[] FloatArrayFromStream(System.IO.MemoryStream stream)
{
return FloatArrayFromByteArray(stream.GetBuffer());
}
public float[] FloatArrayFromByteArray(byte[] input)
{
float[] output = new float[input.Length / 4];
for (int i = 0; i < output.Length; i++)
{
output[i] = BitConverter.ToSingle(input, i * 4);
}
return output;
}
Update 2: I forgot there's a better way to do this:
public float[] FloatArrayFromByteArray(byte[] input)
{
float[] output = new float[input.Length / 4];
Buffer.BlockCopy(input, 0, output, 0, input.Length);
return output;
}
I'm just so in love with for loops, I guess.
I modified MusiGenesis's solution a little bit.
This gave me a much better result, especially with house music :)
public static Bitmap DrawNormalizedAudio(List<float> data, Color foreColor, Color backColor, Size imageSize)
{
Bitmap bmp = new Bitmap(imageSize.Width, imageSize.Height);
int BORDER_WIDTH = 0;
float width = bmp.Width - (2 * BORDER_WIDTH);
float height = bmp.Height - (2 * BORDER_WIDTH);
using (Graphics g = Graphics.FromImage(bmp))
{
g.Clear(backColor);
Pen pen = new Pen(foreColor);
float size = data.Count;
for (float iPixel = 0; iPixel < width; iPixel += 1)
{
// determine start and end points within WAV
int start = (int)(iPixel * (size / width));
int end = (int)((iPixel + 1) * (size / width));
if (end > data.Count)
end = data.Count;
float posAvg, negAvg;
averages(data, start, end, out posAvg, out negAvg);
float yMax = BORDER_WIDTH + height - ((posAvg + 1) * .5f * height);
float yMin = BORDER_WIDTH + height - ((negAvg + 1) * .5f * height);
g.DrawLine(pen, iPixel + BORDER_WIDTH, yMax, iPixel + BORDER_WIDTH, yMin);
}
}
return bmp;
}
private static void averages(List<float> data, int startIndex, int endIndex, out float posAvg, out float negAvg)
{
posAvg = 0.0f;
negAvg = 0.0f;
int posCount = 0, negCount = 0;
for (int i = startIndex; i < endIndex; i++)
{
if (data[i] > 0)
{
posCount++;
posAvg += data[i];
}
else
{
negCount++;
negAvg += data[i];
}
}
posAvg /= posCount;
negAvg /= negCount;
}
with adapted code from robby and using Graphics.Fill/DrawClosedCurve with antialiasing, I get a pretty good looking result.
here's the code:
using System;
using System.Drawing;
using System.Drawing.Drawing2D;
namespace Soundfingerprinting.Audio.Services
{
public static class AudioVisualizationService
{
public class WaveVisualizationConfiguration
{
public Nullable<Color> AreaColor { get; set; }
public Nullable<Color> EdgeColor { get; set; }
public int EdgeSize { get; set; }
public Nullable<Rectangle> Bounds { get; set; }
public double Overlap { get; set; }
public int Step { get; set; }
}
public static void DrawWave(float[] data, Bitmap bitmap, WaveVisualizationConfiguration config = null)
{
Color areaColor = Color.FromArgb(0x7F87CEFA);// Color.LightSkyBlue; semi transparent
Color edgeColor = Color.DarkSlateBlue;
int edgeSize = 2;
int step = 2;
double overlap = 0.10f; // would better use a windowing function
Rectangle bounds = Rectangle.FromLTRB(0, 0, bitmap.Width, bitmap.Height);
if (config != null)
{
edgeSize = config.EdgeSize;
if (config.AreaColor.HasValue)
areaColor = config.AreaColor.GetValueOrDefault();
if (config.EdgeColor.HasValue)
edgeColor = config.EdgeColor.GetValueOrDefault();
if (config.Bounds.HasValue)
bounds = config.Bounds.GetValueOrDefault();
step = Math.Max(1, config.Step);
overlap = config.Overlap;
}
float width = bounds.Width;
float height = bounds.Height;
using (Graphics g = Graphics.FromImage(bitmap))
{
Pen edgePen = new Pen(edgeColor);
edgePen.LineJoin = LineJoin.Round;
edgePen.Width = edgeSize;
Brush areaBrush = new SolidBrush(areaColor);
float size = data.Length;
PointF[] topCurve = new PointF[(int)width / step];
PointF[] bottomCurve = new PointF[(int)width / step];
int idx = 0;
for (float iPixel = 0; iPixel < width; iPixel += step)
{
// determine start and end points within WAV
int start = (int)(iPixel * (size / width));
int end = (int)((iPixel + step) * (size / width));
int window = end - start;
start -= (int)(overlap * window);
end += (int)(overlap * window);
if (start < 0)
start = 0;
if (end > data.Length)
end = data.Length;
float posAvg, negAvg;
averages(data, start, end, out posAvg, out negAvg);
float yMax = height - ((posAvg + 1) * .5f * height);
float yMin = height - ((negAvg + 1) * .5f * height);
float xPos = iPixel + bounds.Left;
if (idx >= topCurve.Length)
idx = topCurve.Length - 1;
topCurve[idx] = new PointF(xPos, yMax);
bottomCurve[bottomCurve.Length - idx - 1] = new PointF(xPos, yMin);
idx++;
}
PointF[] curve = new PointF[topCurve.Length * 2];
Array.Copy(topCurve, curve, topCurve.Length);
Array.Copy(bottomCurve, 0, curve, topCurve.Length, bottomCurve.Length);
g.InterpolationMode = InterpolationMode.HighQualityBicubic;
g.SmoothingMode = SmoothingMode.AntiAlias;
g.FillClosedCurve(areaBrush, curve, FillMode.Winding, 0.15f);
if (edgeSize > 0)
g.DrawClosedCurve(edgePen, curve, 0.15f, FillMode.Winding);
}
}
private static void averages(float[] data, int startIndex, int endIndex, out float posAvg, out float negAvg)
{
posAvg = 0.0f;
negAvg = 0.0f;
int posCount = 0, negCount = 0;
for (int i = startIndex; i < endIndex; i++)
{
if (data[i] > 0)
{
posCount++;
posAvg += data[i];
}
else
{
negCount++;
negAvg += data[i];
}
}
if (posCount > 0)
posAvg /= posCount;
if (negCount > 0)
negAvg /= negCount;
}
}
}
In NAudio, there is code to draw audio waveforms in both WinForms and WPF. Have a look at the demo projects for examples of how to use it.
I've been a fan of ZedGraph for many years and have used it to display all kinds of data in various projects.
The following sample code graphs an array of doubles varying between -1 and 1:
void DisplayWaveGraph(ZedGraphControl graphControl, double[] waveData)
{
var pane = graphControl.GraphPane;
pane.Chart.Border.IsVisible = false;
pane.Chart.Fill.IsVisible = false;
pane.Fill.Color = Color.Black;
pane.Margin.All = 0;
pane.Title.IsVisible = false;
pane.XAxis.IsVisible = false;
pane.XAxis.Scale.Max = waveData.Length - 1;
pane.XAxis.Scale.Min = 0;
pane.YAxis.IsVisible = false;
pane.YAxis.Scale.Max = 1;
pane.YAxis.Scale.Min = -1;
var timeData = Enumerable.Range(0, waveData.Length)
.Select(i => (double) i)
.ToArray();
pane.AddCurve(null, timeData, waveData, Color.Lime, SymbolType.None);
graphControl.AxisChange();
}
The above sample mimics the style of an audio editor by suppressing the axes and changing the colors to produce the following: