添加PaddleOcrAll.BytesPerPixel，像素内存分别支持3通道BGR、4通道BGRA

examples/SystemDrawing.WinForms/MainForm.cs

@@ -1,3 +1,4 @@
+using Sdcb.SimdPaddleOCR;
 using System;
 using System.Diagnostics;
 using System.Drawing;
@@ -7,7 +8,7 @@
 using System.Runtime.InteropServices;
 using System.Threading.Tasks;
 using System.Windows.Forms;
-using Sdcb.SimdPaddleOCR;
+using System.Xml.Linq;
 
 namespace SystemDrawing.WinForms;
 
@@ -71,6 +72,10 @@ private void BuildLayout()
         AddPathRow(3, "REC 模型", _recPath, "模型|*.onnx|所有文件|*.*", false);
         AddPathRow(4, "字典", _dictPath, "字典|*.txt|所有文件|*.*", false);
 
+        CheckBox bppCheckBox = new() { Text = "颜色通道数(默认选中为3通道BGR, 不选为4通道BGRA)", Checked = true, Size = new Size(400, 30), Anchor = AnchorStyles.Left, Margin = new Padding(0, 7, 6, 4) };
+        bppCheckBox.CheckedChanged += (_, _) => PaddleOcrAll.BytesPerPixel = bppCheckBox.Checked ? 3 : 4;
+        _paths.Controls.Add(bppCheckBox, 1, 5);
+
         TableLayoutPanel root = new() { Dock = DockStyle.Fill, Padding = new Padding(12), RowCount = 3, ColumnCount = 1 };
         root.RowStyles.Add(new RowStyle(SizeType.AutoSize)); root.RowStyles.Add(new RowStyle(SizeType.Percent, 100)); root.RowStyles.Add(new RowStyle(SizeType.Absolute, 34));
         root.Controls.Add(_paths, 0, 0);
@@ -145,15 +150,33 @@ private async Task RunOcrAsync()
         finally { _run.Enabled = _ocr is not null; _paths.Enabled = true; }
     }
 
-    private OcrResult RunPipeline(string imagePath)
+    unsafe private OcrResult RunPipeline(string imagePath)
     {
+        //改用直接访问内存，提升性能
         using Bitmap bitmap = new(imagePath);
-        byte[] bgr = ToBgr(bitmap, out int stride); PaddleOcrResult result = _ocr!.Run(bgr, bitmap.Width, bitmap.Height, stride); Bitmap annotated = new(bitmap);
-        using Graphics graphics = Graphics.FromImage(annotated); using Pen pen = new(Color.LimeGreen, 3); using Brush brush = new SolidBrush(Color.Red);
+        var w = bitmap.Width;
+        var h = bitmap.Height;
+        var stride = w * PaddleOcrAll.BytesPerPixel;
+        var data = bitmap.LockBits(
+            new Rectangle(0, 0, w, h),
+            ImageLockMode.ReadOnly,
+            PaddleOcrAll.BytesPerPixel == 4 ? PixelFormat.Format32bppArgb : PixelFormat.Format24bppRgb);
+        PaddleOcrResult result = _ocr!.Run(new ReadOnlySpan<byte>((void*)data.Scan0, stride * h), w, h, stride);
+        bitmap.UnlockBits(data);
+
+        Bitmap annotated = new(bitmap);
+        using Graphics graphics = Graphics.FromImage(annotated);
+        using Pen pen = new(Color.LimeGreen, 3);
+        using Brush brush = new SolidBrush(Color.Red);
         foreach (PaddleOcrLine line in result.Lines)
         {
-            Point[] points = [new((int)line.Box.X1, (int)line.Box.Y1), new((int)line.Box.X2, (int)line.Box.Y2), new((int)line.Box.X3, (int)line.Box.Y3), new((int)line.Box.X4, (int)line.Box.Y4)];
-            graphics.DrawPolygon(pen, points); graphics.DrawString(line.Text, Font, brush, points[0]);
+            Point[] points = [
+                new((int)line.Box.X1,(int)line.Box.Y1),
+                new((int)line.Box.X2, (int)line.Box.Y2),
+                new((int)line.Box.X3, (int)line.Box.Y3),
+                new((int)line.Box.X4, (int)line.Box.Y4)];
+            graphics.DrawPolygon(pen, points);
+            //graphics.DrawString(line.Text, Font, brush, points[0]);
         }
         return new OcrResult(string.Join(Environment.NewLine, result.Lines.Select(line => line.Text)), result.DetectedCount, annotated);
     }
@@ -162,10 +185,19 @@ private OcrResult RunPipeline(string imagePath)
 
     private static byte[] ToBgr(Bitmap bitmap, out int stride)
     {
-        stride = checked(bitmap.Width * 3); byte[] bgr = new byte[checked(stride * bitmap.Height)]; Rectangle rectangle = new(0, 0, bitmap.Width, bitmap.Height);
+        stride = checked(bitmap.Width * 3);
+        byte[] bgr = new byte[checked(stride * bitmap.Height)];
+        Rectangle rectangle = new(0, 0, bitmap.Width, bitmap.Height);
         BitmapData data = bitmap.LockBits(rectangle, ImageLockMode.ReadOnly, PixelFormat.Format24bppRgb);
-        try { for (int y = 0; y < bitmap.Height; y++) Marshal.Copy(new IntPtr(data.Scan0.ToInt64() + y * (long)data.Stride), bgr, y * stride, stride); }
-        finally { bitmap.UnlockBits(data); }
+        try
+        {
+            for (int y = 0; y < bitmap.Height; y++)
+                Marshal.Copy(new IntPtr(data.Scan0.ToInt64() + y * (long)data.Stride), bgr, y * stride, stride);
+        }
+        finally
+        {
+            bitmap.UnlockBits(data);
+        }
         return bgr;
     }
 
@@ -201,6 +233,8 @@ private static string FindRepositoryRoot()
     private sealed class OcrResult
     {
         public OcrResult(string text, int count, Bitmap annotated) { Text = text; Count = count; Annotated = annotated; }
-        public string Text { get; } public int Count { get; } public Bitmap Annotated { get; }
+        public string Text { get; }
+        public int Count { get; }
+        public Bitmap Annotated { get; }
     }
 }

examples/SystemDrawing.WinForms/MainForm.resx

@@ -0,0 +1,120 @@
+<?xml version="1.0" encoding="utf-8"?>
+<root>
+  <!-- 
+    Microsoft ResX Schema 
+
+    Version 2.0
+
+    The primary goals of this format is to allow a simple XML format 
+    that is mostly human readable. The generation and parsing of the 
+    various data types are done through the TypeConverter classes 
+    associated with the data types.
+
+    Example:
+
+    ... ado.net/XML headers & schema ...
+    <resheader name="resmimetype">text/microsoft-resx</resheader>
+    <resheader name="version">2.0</resheader>
+    <resheader name="reader">System.Resources.ResXResourceReader, System.Windows.Forms, ...</resheader>
+    <resheader name="writer">System.Resources.ResXResourceWriter, System.Windows.Forms, ...</resheader>
+    <data name="Name1"><value>this is my long string</value><comment>this is a comment</comment></data>
+    <data name="Color1" type="System.Drawing.Color, System.Drawing">Blue</data>
+    <data name="Bitmap1" mimetype="application/x-microsoft.net.object.binary.base64">
+        <value>[base64 mime encoded serialized .NET Framework object]</value>
+    </data>
+    <data name="Icon1" type="System.Drawing.Icon, System.Drawing" mimetype="application/x-microsoft.net.object.bytearray.base64">
+        <value>[base64 mime encoded string representing a byte array form of the .NET Framework object]</value>
+        <comment>This is a comment</comment>
+    </data>
+
+    There are any number of "resheader" rows that contain simple 
+    name/value pairs.
+
+    Each data row contains a name, and value. The row also contains a 
+    type or mimetype. Type corresponds to a .NET class that support 
+    text/value conversion through the TypeConverter architecture. 
+    Classes that don't support this are serialized and stored with the 
+    mimetype set.
+
+    The mimetype is used for serialized objects, and tells the 
+    ResXResourceReader how to depersist the object. This is currently not 
+    extensible. For a given mimetype the value must be set accordingly:
+
+    Note - application/x-microsoft.net.object.binary.base64 is the format 
+    that the ResXResourceWriter will generate, however the reader can 
+    read any of the formats listed below.
+
+    mimetype: application/x-microsoft.net.object.binary.base64
+    value   : The object must be serialized with 
+            : System.Runtime.Serialization.Formatters.Binary.BinaryFormatter
+            : and then encoded with base64 encoding.
+
+    mimetype: application/x-microsoft.net.object.soap.base64
+    value   : The object must be serialized with 
+            : System.Runtime.Serialization.Formatters.Soap.SoapFormatter
+            : and then encoded with base64 encoding.
+
+    mimetype: application/x-microsoft.net.object.bytearray.base64
+    value   : The object must be serialized into a byte array 
+            : using a System.ComponentModel.TypeConverter
+            : and then encoded with base64 encoding.
+    -->
+  <xsd:schema id="root" xmlns="" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:msdata="urn:schemas-microsoft-com:xml-msdata">
+    <xsd:import namespace="http://www.w3.org/XML/1998/namespace" />
+    <xsd:element name="root" msdata:IsDataSet="true">
+      <xsd:complexType>
+        <xsd:choice maxOccurs="unbounded">
+          <xsd:element name="metadata">
+            <xsd:complexType>
+              <xsd:sequence>
+                <xsd:element name="value" type="xsd:string" minOccurs="0" />
+              </xsd:sequence>
+              <xsd:attribute name="name" use="required" type="xsd:string" />
+              <xsd:attribute name="type" type="xsd:string" />
+              <xsd:attribute name="mimetype" type="xsd:string" />
+              <xsd:attribute ref="xml:space" />
+            </xsd:complexType>
+          </xsd:element>
+          <xsd:element name="assembly">
+            <xsd:complexType>
+              <xsd:attribute name="alias" type="xsd:string" />
+              <xsd:attribute name="name" type="xsd:string" />
+            </xsd:complexType>
+          </xsd:element>
+          <xsd:element name="data">
+            <xsd:complexType>
+              <xsd:sequence>
+                <xsd:element name="value" type="xsd:string" minOccurs="0" msdata:Ordinal="1" />
+                <xsd:element name="comment" type="xsd:string" minOccurs="0" msdata:Ordinal="2" />
+              </xsd:sequence>
+              <xsd:attribute name="name" type="xsd:string" use="required" msdata:Ordinal="1" />
+              <xsd:attribute name="type" type="xsd:string" msdata:Ordinal="3" />
+              <xsd:attribute name="mimetype" type="xsd:string" msdata:Ordinal="4" />
+              <xsd:attribute ref="xml:space" />
+            </xsd:complexType>
+          </xsd:element>
+          <xsd:element name="resheader">
+            <xsd:complexType>
+              <xsd:sequence>
+                <xsd:element name="value" type="xsd:string" minOccurs="0" msdata:Ordinal="1" />
+              </xsd:sequence>
+              <xsd:attribute name="name" type="xsd:string" use="required" />
+            </xsd:complexType>
+          </xsd:element>
+        </xsd:choice>
+      </xsd:complexType>
+    </xsd:element>
+  </xsd:schema>
+  <resheader name="resmimetype">
+    <value>text/microsoft-resx</value>
+  </resheader>
+  <resheader name="version">
+    <value>2.0</value>
+  </resheader>
+  <resheader name="reader">
+    <value>System.Resources.ResXResourceReader, System.Windows.Forms, Version=4.0.0.0, Culture=neutral, PublicKeyToken=b77a5c561934e089</value>
+  </resheader>
+  <resheader name="writer">
+    <value>System.Resources.ResXResourceWriter, System.Windows.Forms, Version=4.0.0.0, Culture=neutral, PublicKeyToken=b77a5c561934e089</value>
+  </resheader>
+</root>

examples/SystemDrawing.WinForms/SystemDrawing.WinForms.csproj

@@ -10,6 +10,7 @@
     <AutoGenerateBindingRedirects Condition="'$(TargetFramework)' == 'net48'">true</AutoGenerateBindingRedirects>
     <ApplicationManifest Condition="'$(TargetFramework)' == 'net48'">app.manifest</ApplicationManifest>
     <PlatformTarget>x64</PlatformTarget>
+    <AllowUnsafeBlocks>True</AllowUnsafeBlocks>
   </PropertyGroup>
   <ItemGroup>
     <ProjectReference Include="..\..\src\Sdcb.SimdPaddleOCR\Sdcb.SimdPaddleOCR.csproj" />

src/Sdcb.SimdPaddleOCR/Kernels/Warp.Avx.cs

@@ -69,7 +69,7 @@ private static unsafe void SampleCubicAvx(byte* source, int stride,
         Vector256<double> wy = CubicWeightVectorAvx(ty);
         Vector256<double> wx0 = Avx2.Permute4x64(wx, 0x00), wx1 = Avx2.Permute4x64(wx, 0x55);
         Vector256<double> wx2 = Avx2.Permute4x64(wx, 0xAA), wx3 = Avx2.Permute4x64(wx, 0xFF);
-        byte* row = source + (yBase - 1) * stride + (xBase - 1) * 3;
+        byte* row = source + (yBase - 1) * stride + (xBase - 1) * PaddleOcrAll.BytesPerPixel;
         Vector256<double> acc = AccumulateRowAvx(row, wx0, wx1, wx2, wx3,
             Avx2.Permute4x64(wy, 0x00), Vector256<double>.Zero);
         acc = AccumulateRowAvx(row + stride, wx0, wx1, wx2, wx3, Avx2.Permute4x64(wy, 0x55), acc);
@@ -84,10 +84,11 @@ private static unsafe Vector256<double> AccumulateRowAvx(byte* row,
         Vector256<double> wx0, Vector256<double> wx1, Vector256<double> wx2, Vector256<double> wx3,
         Vector256<double> wy, Vector256<double> acc)
     {
+        int bpp = PaddleOcrAll.BytesPerPixel;
         acc = Avx.Add(acc, Avx.Multiply(Avx.Multiply(LoadPixelAvx(row), wx0), wy));
-        acc = Avx.Add(acc, Avx.Multiply(Avx.Multiply(LoadPixelAvx(row + 3), wx1), wy));
-        acc = Avx.Add(acc, Avx.Multiply(Avx.Multiply(LoadPixelAvx(row + 6), wx2), wy));
-        acc = Avx.Add(acc, Avx.Multiply(Avx.Multiply(LoadPixelAvx(row + 9), wx3), wy));
+        acc = Avx.Add(acc, Avx.Multiply(Avx.Multiply(LoadPixelAvx(row + bpp), wx1), wy));
+        acc = Avx.Add(acc, Avx.Multiply(Avx.Multiply(LoadPixelAvx(row + 2 * bpp), wx2), wy));
+        acc = Avx.Add(acc, Avx.Multiply(Avx.Multiply(LoadPixelAvx(row + 3 * bpp), wx3), wy));
         return acc;
     }
 

src/Sdcb.SimdPaddleOCR/Kernels/Warp.Avx512.cs

@@ -74,7 +74,7 @@ private static unsafe void SampleCubicAvx512(byte* source, int stride,
         Vector512<double> wx1 = Vector512.Create(wx.GetElement(1));
         Vector512<double> wx2 = Vector512.Create(wx.GetElement(2));
         Vector512<double> wx3 = Vector512.Create(wx.GetElement(3));
-        byte* row = source + (yBase - 1) * stride + (xBase - 1) * 3;
+        byte* row = source + (yBase - 1) * stride + (xBase - 1) * PaddleOcrAll.BytesPerPixel;
         Vector512<double> acc = AccumulateRowAvx512(row, wx0, wx1, wx2, wx3,
             Vector512.Create(wy.GetElement(0)), Vector512<double>.Zero);
         acc = AccumulateRowAvx512(row + stride, wx0, wx1, wx2, wx3, Vector512.Create(wy.GetElement(1)), acc);
@@ -89,10 +89,11 @@ private static unsafe Vector512<double> AccumulateRowAvx512(byte* row,
         Vector512<double> wx0, Vector512<double> wx1, Vector512<double> wx2, Vector512<double> wx3,
         Vector512<double> wy, Vector512<double> acc)
     {
+        int bpp = PaddleOcrAll.BytesPerPixel;
         acc = Avx512F.Add(acc, Avx512F.Multiply(Avx512F.Multiply(LoadPixelAvx512(row), wx0), wy));
-        acc = Avx512F.Add(acc, Avx512F.Multiply(Avx512F.Multiply(LoadPixelAvx512(row + 3), wx1), wy));
-        acc = Avx512F.Add(acc, Avx512F.Multiply(Avx512F.Multiply(LoadPixelAvx512(row + 6), wx2), wy));
-        acc = Avx512F.Add(acc, Avx512F.Multiply(Avx512F.Multiply(LoadPixelAvx512(row + 9), wx3), wy));
+        acc = Avx512F.Add(acc, Avx512F.Multiply(Avx512F.Multiply(LoadPixelAvx512(row + bpp), wx1), wy));
+        acc = Avx512F.Add(acc, Avx512F.Multiply(Avx512F.Multiply(LoadPixelAvx512(row + 2 * bpp), wx2), wy));
+        acc = Avx512F.Add(acc, Avx512F.Multiply(Avx512F.Multiply(LoadPixelAvx512(row + 3 * bpp), wx3), wy));
         return acc;
     }
 

src/Sdcb.SimdPaddleOCR/Kernels/Warp.Scalar.cs

@@ -34,7 +34,7 @@ internal static unsafe void ProcessPixel(byte* sourcePtr, int sourceWidth, int s
             throw new InvalidDataException("Invalid perspective transform.");
         int destinationX = rotateVertical ? unrotatedHeight - 1 - y : x;
         int destinationY = rotateVertical ? x : y;
-        int destination = checked((destinationY * outputWidth + destinationX) * 3);
+        int destination = checked((destinationY * outputWidth + destinationX) * PaddleOcrAll.BytesPerPixel);
         SampleCubicScalar(sourcePtr, sourceWidth, sourceHeight, sourceStride,
             sx, sy, cropPtr, destination);
     }
@@ -58,14 +58,15 @@ internal static unsafe void SampleCubicScalar(byte* source, int width, int heigh
             CubicWeight(y - (yBase + 1)),
             CubicWeight(y - (yBase + 2)),
         ];
+        int bpp = PaddleOcrAll.BytesPerPixel;
         double value0 = 0, value1 = 0, value2 = 0;
         if (xBase >= 1 && xBase < width - 2 && yBase >= 1 && yBase < height - 2)
         {
             for (int ky = 0; ky < 4; ky++)
             {
                 double wy = yWeights[ky];
-                int sourceOffset = (yBase + ky - 1) * stride + (xBase - 1) * 3;
-                for (int kx = 0; kx < 4; kx++, sourceOffset += 3)
+                int sourceOffset = (yBase + ky - 1) * stride + (xBase - 1) * bpp;
+                for (int kx = 0; kx < 4; kx++, sourceOffset += bpp)
                 {
                     double wx = xWeights[kx];
                     value0 += source[sourceOffset] * wx * wy;
@@ -84,7 +85,7 @@ internal static unsafe void SampleCubicScalar(byte* source, int width, int heigh
                 {
                     double wx = xWeights[kx];
                     int sx = Clamp(xBase + kx - 1, width);
-                    int sourceOffset = sy * stride + sx * 3;
+                    int sourceOffset = sy * stride + sx * bpp;
                     value0 += source[sourceOffset] * wx * wy;
                     value1 += source[sourceOffset + 1] * wx * wy;
                     value2 += source[sourceOffset + 2] * wx * wy;

src/Sdcb.SimdPaddleOCR/Kernels/Warp.Vector.cs

@@ -69,7 +69,7 @@ private static unsafe void SampleCubicVector(byte* source, int stride,
         Vector<double> wy = CubicWeightVector(new Vector<double>(y) - tap);
         Vector<double> wx0 = new(wx.GetElement(0)), wx1 = new(wx.GetElement(1));
         Vector<double> wx2 = new(wx.GetElement(2)), wx3 = new(wx.GetElement(3));
-        byte* row = source + (yBase - 1) * stride + (xBase - 1) * 3;
+        byte* row = source + (yBase - 1) * stride + (xBase - 1) * PaddleOcrAll.BytesPerPixel;
         Vector<double> acc = AccumulateRowVector(row, wx0, wx1, wx2, wx3,
             new Vector<double>(wy.GetElement(0)), Vector<double>.Zero);
         acc = AccumulateRowVector(row + stride, wx0, wx1, wx2, wx3, new Vector<double>(wy.GetElement(1)), acc);
@@ -84,10 +84,11 @@ private static unsafe Vector<double> AccumulateRowVector(byte* row,
         Vector<double> wx0, Vector<double> wx1, Vector<double> wx2, Vector<double> wx3,
         Vector<double> wy, Vector<double> acc)
     {
+        int bpp = PaddleOcrAll.BytesPerPixel;
         acc += LoadPixelVector(row) * wx0 * wy;
-        acc += LoadPixelVector(row + 3) * wx1 * wy;
-        acc += LoadPixelVector(row + 6) * wx2 * wy;
-        acc += LoadPixelVector(row + 9) * wx3 * wy;
+        acc += LoadPixelVector(row + bpp) * wx1 * wy;
+        acc += LoadPixelVector(row + 2 * bpp) * wx2 * wy;
+        acc += LoadPixelVector(row + 3 * bpp) * wx3 * wy;
         return acc;
     }
 

src/Sdcb.SimdPaddleOCR/Kernels/Warp.cs

@@ -65,7 +65,7 @@ private static unsafe void SampleMappedPixel(byte* sourcePtr, int sourceWidth, i
     {
         int destinationX = rotateVertical ? unrotatedHeight - 1 - y : x;
         int destinationY = rotateVertical ? x : y;
-        int destination = checked((destinationY * outputWidth + destinationX) * 3);
+        int destination = checked((destinationY * outputWidth + destinationX) * PaddleOcrAll.BytesPerPixel);
         SampleCubic(sourcePtr, sourceWidth, sourceHeight, sourceStride,
             pixelX, pixelY, cropPtr, destination);
     }