Update DLLs to Tesseract 5.2

Author: Methuselah96

src/Tesseract.Net48Tests/Tesseract.Net48Tests.csproj

@@ -194,13 +194,13 @@
 	<None Include="..\Tesseract\x64\leptonica-1.82.0.dll" Link="x64\leptonica-1.82.0.dll">
 		<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
 	</None>
-	<None Include="..\Tesseract\x64\tesseract50.dll" Link="x64\tesseract50.dll">
+	<None Include="..\Tesseract\x64\tesseract52.dll" Link="x64\tesseract52.dll">
 		<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
 	</None>
 	<None Include="..\Tesseract\x86\leptonica-1.82.0.dll" Link="x86\leptonica-1.82.0.dll">
 		<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
 	</None>
-	<None Include="..\Tesseract\x86\tesseract50.dll" Link="x86\tesseract50.dll">
+	<None Include="..\Tesseract\x86\tesseract52.dll" Link="x86\tesseract52.dll">
 		<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
 	</None>
   </ItemGroup>

src/Tesseract.NetCore31Tests/Tesseract.NetCore31Tests.csproj

@@ -192,13 +192,13 @@
     <None Include="..\Tesseract\x64\leptonica-1.82.0.dll" Link="x64\leptonica-1.82.0.dll">
       <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
     </None>
-    <None Include="..\Tesseract\x64\tesseract50.dll" Link="x64\tesseract50.dll">
+    <None Include="..\Tesseract\x64\tesseract52.dll" Link="x64\tesseract52.dll">
       <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
     </None>
     <None Include="..\Tesseract\x86\leptonica-1.82.0.dll" Link="x86\leptonica-1.82.0.dll">
       <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
     </None>
-    <None Include="..\Tesseract\x86\tesseract50.dll" Link="x86\tesseract50.dll">
+    <None Include="..\Tesseract\x86\tesseract52.dll" Link="x86\tesseract52.dll">
       <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
     </None>
   </ItemGroup>

src/Tesseract.Tests/BaseApiTests.cs

@@ -11,7 +11,7 @@ public class BaseApiTests
         public void CanGetVersion()
         {
             var version = Interop.TessApi.BaseApiGetVersion();
-            Assert.That(version, Does.StartWith("5.0.0"));
+            Assert.That(version, Does.StartWith("5.2.0"));
         }
     }
 }

src/Tesseract.Tests/EngineTests.cs

@@ -1,4 +1,4 @@
-using NUnit.Framework;
+using NUnit.Framework;
 using System;
 using System.Collections.Generic;
 using System.Drawing;
@@ -20,7 +20,7 @@ public void CanGetVersion()
         {
             using (var engine = CreateEngine())
             {
-                Assert.That(engine.Version, Does.StartWith("5.0.0"));
+                Assert.That(engine.Version, Does.StartWith("5.2.0"));
             }
         }
 
@@ -71,7 +71,7 @@ public void CanParseMultipageTifOneByOne()
         [TestCase(PageSegMode.SingleColumn, "This is a lot of 12 point text to test the")]
         [TestCase(PageSegMode.SingleLine, "This is a lot of 12 point text to test the")]
         [TestCase(PageSegMode.SingleWord, "This")]
-        [TestCase(PageSegMode.SingleChar, "T")]
+        [TestCase(PageSegMode.SingleChar, "hl")]
         [TestCase(PageSegMode.SingleBlockVertText, "A line of text", Ignore = "#490")]
         public void CanParseText_UsingMode(PageSegMode mode, String expectedText)
         {
@@ -135,7 +135,7 @@ public void CanProcessBitmap()
                         var text = page.GetText();
 
                         const string expectedText =
-                            "This is a lot of 12 point text to test the\nocr code and see if it works on all types\nof file format.\n\nThe quick brown dog jumped over the\nlazy fox. The quick brown dog jumped\nover the lazy fox. The quick brown dog\njumped over the lazy fox. The quick\nbrown dog jumped over the lazy fox.\n";
+                            "This is a lot of 12 point text to test the\nocr code and see if it works on all types\nof file format.\n\nThe quick brown dog jumped over the\n\nlazy fox. The quick brown dog jumped\nover the lazy fox. The quick brown dog\njumped over the lazy fox. The quick\nbrown dog jumped over the lazy fox.\n\n";
 
                         Assert.That(text, Is.EqualTo(expectedText));
                     }

src/Tesseract.Tests/Results/EngineTests/CanPrintVariables.txt

@@ -339,7 +339,7 @@ tessedit_train_from_boxes	0	Generate training data from boxed chars
 tessedit_make_boxes_from_boxes	0	Generate more boxes from boxed chars
 tessedit_train_line_recognizer	0	Break input into lines and remap boxes if present
 tessedit_dump_pageseg_images	0	Dump intermediate images made during page segmentation
-tessedit_do_invert	1	Try inverting the image in `LSTMRecognizeWord`
+tessedit_do_invert	1	Try inverted line image if necessary (deprecated, will be removed in release 6, use the 'invert_threshold' parameter instead)
 thresholding_debug	0	Debug the thresholding process
 tessedit_ambigs_training	0	Perform training for ambiguities
 tessedit_adaption_debug	0	Generate and print debug information for adaption
@@ -488,7 +488,6 @@ matcher_avg_noise_size	12	Avg. noise blob length
 matcher_clustering_max_angle_delta	0.015	Maximum angle delta for prototype clustering
 classify_misfit_junk_penalty	0	Penalty to apply when a non-alnum is vertically out of its expected textline position
 rating_scale	1.5	Rating scaling factor
-certainty_scale	20	Certainty scaling factor
 tessedit_class_miss_scale	0.00390625	Scale factor for features not used
 classify_adapted_pruning_factor	2.5	Prune poor adapted results this much worse than best result
 classify_adapted_pruning_threshold	-1	Threshold at which classify_adapted_pruning_factor starts
@@ -531,11 +530,12 @@ language_model_penalty_chartype	0.3	Penalty for inconsistent character type
 language_model_penalty_font	0	Penalty for inconsistent font
 language_model_penalty_spacing	0.05	Penalty for inconsistent spacing
 language_model_penalty_increment	0.01	Penalty increment
-thresholding_window_size	0.33	Window size for measuring local statistics (to be multiplied by image DPI). This parameter is used by the Sauvola thresolding method
-thresholding_kfactor	0.34	Factor for reducing threshold due to variance. This parameter is used by the Sauvola thresolding method. Normal range: 0.2-0.5
-thresholding_tile_size	0.33	Desired tile size (to be multiplied by image DPI). This parameter is used by the LeptonicaOtsu thresolding method
-thresholding_smooth_kernel_size	0	Size of convolution kernel applied to threshold array (to be multiplied by image DPI). Use 0 for no smoothing. This parameter is used by the LeptonicaOtsu thresolding method
-thresholding_score_fraction	0.1	Fraction of the max Otsu score. This parameter is used by the LeptonicaOtsu thresolding method. For standard Otsu use 0.0, otherwise 0.1 is recommended
+invert_threshold	0.7	For lines with a mean confidence below this value, OCR is also tried with an inverted image
+thresholding_window_size	0.33	Window size for measuring local statistics (to be multiplied by image DPI). This parameter is used by the Sauvola thresholding method
+thresholding_kfactor	0.34	Factor for reducing threshold due to variance. This parameter is used by the Sauvola thresholding method. Normal range: 0.2-0.5
+thresholding_tile_size	0.33	Desired tile size (to be multiplied by image DPI). This parameter is used by the LeptonicaOtsu thresholding method
+thresholding_smooth_kernel_size	0	Size of convolution kernel applied to threshold array (to be multiplied by image DPI). Use 0 for no smoothing. This parameter is used by the LeptonicaOtsu thresholding method
+thresholding_score_fraction	0.1	Fraction of the max Otsu score. This parameter is used by the LeptonicaOtsu thresholding method. For standard Otsu use 0.0, otherwise 0.1 is recommended
 noise_cert_basechar	-8	Hingepoint for base char certainty
 noise_cert_disjoint	-1	Hingepoint for disjoint certainty
 noise_cert_punc	-3	Threshold for new punc char certainty

src/Tesseract/Interop/Constants.cs

@@ -8,7 +8,7 @@ namespace Tesseract.Interop
     internal static class Constants
     {
         public const string LeptonicaDllName = "leptonica-1.82.0";
-        public const string TesseractDllName = "tesseract50";
+        public const string TesseractDllName = "tesseract52";
 
         // tesseract uses an int to represent true false values.
         public const int TRUE = 1;