Automatically trim a bitmap to minimum size?

Question

Suppose I have a System.Drawing.Bitmap in 32bpp ARGB mode. It's a large bitmap, but it's mostly fully transparent pixels with a relatively small image somewhere in the middle.

What is a fast algorithm to detect the borders of the "real" image, so I can crop away all the transparent pixels from around it?

Alternatively, is there a function already in .Net that I can use for this?

Answer 1

The basic idea is to check every pixel of the image to find the top, left, right and bottom bounds of the image. To do this efficiently, don't use the GetPixel method, which is pretty slow. Use LockBits instead.

Here's the implementation I came up with:

static Bitmap TrimBitmap(Bitmap source)
{
    Rectangle srcRect = default(Rectangle);
    BitmapData data = null;
    try
    {
        data = source.LockBits(new Rectangle(0, 0, source.Width, source.Height), ImageLockMode.ReadOnly, PixelFormat.Format32bppArgb);
        byte[] buffer = new byte[data.Height * data.Stride];
        Marshal.Copy(data.Scan0, buffer, 0, buffer.Length);
        int xMin = int.MaxValue;
        int xMax = 0;
        int yMin = int.MaxValue;
        int yMax = 0;
        for (int y = 0; y < data.Height; y++)
        {
            for (int x = 0; x < data.Width; x++)
            {
                byte alpha = buffer[y * data.Stride + 4 * x + 3];
                if (alpha != 0)
                {
                    if (x < xMin) xMin = x;
                    if (x > xMax) xMax = x;
                    if (y < yMin) yMin = y;
                    if (y > yMax) yMax = y;
                }
            }
        }
        if (xMax < xMin || yMax < yMin)
        {
            // Image is empty...
            return null;
        }
        srcRect = Rectangle.FromLTRB(xMin, yMin, xMax, yMax);
    }
    finally
    {
        if (data != null)
            source.UnlockBits(data);
    }

    Bitmap dest = new Bitmap(srcRect.Width, srcRect.Height);
    Rectangle destRect = new Rectangle(0, 0, srcRect.Width, srcRect.Height);
    using (Graphics graphics = Graphics.FromImage(dest))
    {
        graphics.DrawImage(source, destRect, srcRect, GraphicsUnit.Pixel);
    }
    return dest;
}

It can probably be optimized, but I'm not a GDI+ expert, so it's the best I can do without further research...

---

EDIT: actually, there's a simple way to optimize it, by not scanning some parts of the image :

1. scan left to right until you find a non-transparent pixel; store (x, y) into (xMin, yMin)
2. scan top to bottom until you find a non-transparent pixel (only for x >= xMin); store y into yMin
3. scan right to left until you find a non-transparent pixel (only for y >= yMin); store x into xMax
4. scan bottom to top until you find a non-transparent pixel (only for xMin <= x <= xMax); store y into yMax

---

EDIT2: here's an implementation of the approach above:

static Bitmap TrimBitmap(Bitmap source)
{
    Rectangle srcRect = default(Rectangle);
    BitmapData data = null;
    try
    {
        data = source.LockBits(new Rectangle(0, 0, source.Width, source.Height), ImageLockMode.ReadOnly, PixelFormat.Format32bppArgb);
        byte[] buffer = new byte[data.Height * data.Stride];
        Marshal.Copy(data.Scan0, buffer, 0, buffer.Length);

        int xMin = int.MaxValue,
            xMax = int.MinValue,
            yMin = int.MaxValue,
            yMax = int.MinValue;

        bool foundPixel = false;

        // Find xMin
        for (int x = 0; x < data.Width; x++)
        {
            bool stop = false;
            for (int y = 0; y < data.Height; y++)
            {
                byte alpha = buffer[y * data.Stride + 4 * x + 3];
                if (alpha != 0)
                {
                    xMin = x;
                    stop = true;
                    foundPixel = true;
                    break;
                }
            }
            if (stop)
                break;
        }

        // Image is empty...
        if (!foundPixel)
            return null;

        // Find yMin
        for (int y = 0; y < data.Height; y++)
        {
            bool stop = false;
            for (int x = xMin; x < data.Width; x++)
            {
                byte alpha = buffer[y * data.Stride + 4 * x + 3];
                if (alpha != 0)
                {
                    yMin = y;
                    stop = true;
                    break;
                }
            }
            if (stop)
                break;
        }

        // Find xMax
        for (int x = data.Width - 1; x >= xMin; x--)
        {
            bool stop = false;
            for (int y = yMin; y < data.Height; y++)
            {
                byte alpha = buffer[y * data.Stride + 4 * x + 3];
                if (alpha != 0)
                {
                    xMax = x;
                    stop = true;
                    break;
                }
            }
            if (stop)
                break;
        }

        // Find yMax
        for (int y = data.Height - 1; y >= yMin; y--)
        {
            bool stop = false;
            for (int x = xMin; x <= xMax; x++)
            {
                byte alpha = buffer[y * data.Stride + 4 * x + 3];
                if (alpha != 0)
                {
                    yMax = y;
                    stop = true;
                    break;
                }
            }
            if (stop)
                break;
        }

        srcRect = Rectangle.FromLTRB(xMin, yMin, xMax, yMax);
    }
    finally
    {
        if (data != null)
            source.UnlockBits(data);
    }

    Bitmap dest = new Bitmap(srcRect.Width, srcRect.Height);
    Rectangle destRect = new Rectangle(0, 0, srcRect.Width, srcRect.Height);
    using (Graphics graphics = Graphics.FromImage(dest))
    {
        graphics.DrawImage(source, destRect, srcRect, GraphicsUnit.Pixel);
    }
    return dest;
}

There won't be a significant gain if the non-transparent part is small of course, since it will still scan most of the pixels. But if it's big, only the rectangles around the non-transparent part will be scanned.

Answer 2

I would like to suggest a divide & conquer approach:

1. split the image in the middle (e.g. vertically)
2. check if there are non-transparent pixels on the cut line (if so, remember min/max for bounding box)
3. split left half again vertically
4. if cut line contains non-transparent pixels -> update bounding box
5. if not, you can probably discard the leftmost half (I don't know the pictures)
6. continue with the left-right half (you stated that the image is somewhere in the middle) until you find the leftmost bound of the image
7. do the same for the right half