kmenshikov/GSS2Rework
1
0
Fork 0
forked from amkovkov/GranuSightSoftware2
Code Pull Requests Activity

feat: some analysis changes

Browse Source
This commit is contained in:
amkovkov
2026-06-08 07:37:38 +03:00
parent f1a840b23b
commit 226d35f5d5
1 changed files with 87 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
GSS2.Core/Analysis/AmineContent/AnalyzerService.cs
+86 -27
View File
@@ -20,14 +20,14 @@ public partial class AnalyzerService
public const int SEPARATOR_ROI_THRESHOLD = 5; public const int SEPARATOR_ROI_THRESHOLD = 5;
public const float CONTOUR_MAX_SIZE = 100; public const float CONTOUR_MAX_SIZE = 100;
public const float CONTOUR_MAX_AREA = (float)Math.PI * (CONTOUR_MAX_SIZE * CONTOUR_MAX_SIZE) / 4.0f; public const float CONTOUR_MAX_AREA = (float)Math.PI * (CONTOUR_MAX_SIZE * CONTOUR_MAX_SIZE) / 5.0f;
public const float CONTOUR_MIN_SIZE = 12; public const float CONTOUR_MIN_SIZE = 10;
public const float CONTOUR_MIN_AREA = (float)Math.PI * (CONTOUR_MIN_SIZE * CONTOUR_MIN_SIZE) / 4.0f / 4.0f; public const float CONTOUR_MIN_AREA = (float)Math.PI * (CONTOUR_MIN_SIZE * CONTOUR_MIN_SIZE) / 5.0f / 5.0f;
public const int SEPARATOR_X = 519; public const int SEPARATOR_X = 519;
public const int SEPARATOR_Y = 17; public const int SEPARATOR_Y = 17;
public const int SEPARATOR_WIDTH = 2989; public const int SEPARATOR_WIDTH = 2969;
public const int SEPARATOR_HEIGHT = 2985; public const int SEPARATOR_HEIGHT = 2965;
private class ClusterizationData private class ClusterizationData
{ {
@@ -143,6 +143,8 @@ public partial class AnalyzerService
Features = r.Values Features = r.Values
}) })
.ToList(); .ToList();
trainDataSet = trainDataSet.Shuffle().ToList();
_logger.LogInformation("Записей для обучения: {}", trainDataSet.Count());
var trainData = _ml.Data.LoadFromEnumerable(trainDataSet); var trainData = _ml.Data.LoadFromEnumerable(trainDataSet);
cancellationToken.ThrowIfCancellationRequested(); cancellationToken.ThrowIfCancellationRequested();
@@ -160,10 +162,9 @@ public partial class AnalyzerService
if (_ml is null) if (_ml is null)
throw new InvalidOperationException(); throw new InvalidOperationException();
cancellationToken.ThrowIfCancellationRequested();
_logger.LogInformation("Создание конвейера"); _logger.LogInformation("Создание конвейера");
var pipeline = _ml.Regression.Trainers.Sdca();
var pipeline = _ml.Regression.Trainers.FastTree();
cancellationToken.ThrowIfCancellationRequested(); cancellationToken.ThrowIfCancellationRequested();
@@ -184,13 +185,14 @@ public partial class AnalyzerService
Features = r.Values Features = r.Values
}) })
.ToList(); .ToList();
trainDataSet = trainDataSet.Shuffle().ToList();
_logger.LogInformation("Записей для обучения: {}", trainDataSet.Count());
var trainData = _ml.Data.LoadFromEnumerable(trainDataSet); var trainData = _ml.Data.LoadFromEnumerable(trainDataSet);
cancellationToken.ThrowIfCancellationRequested(); cancellationToken.ThrowIfCancellationRequested();
_logger.LogInformation("Обучение модели"); _logger.LogInformation("Обучение модели");
var model = pipeline.Fit(trainData); var model = pipeline.Fit(trainData);
_regressionEngine = _ml.Model.CreatePredictionEngine<RegressionData, RegressionPrediction>(model); _regressionEngine = _ml.Model.CreatePredictionEngine<RegressionData, RegressionPrediction>(model);
model.Dispose(); model.Dispose();
@@ -230,7 +232,7 @@ public partial class AnalyzerService
for (var row = 0; row < ANALYSIS_IMAGE_SIZE; row++) for (var row = 0; row < ANALYSIS_IMAGE_SIZE; row++)
for (var col = 0; col < ANALYSIS_IMAGE_SIZE; col++) for (var col = 0; col < ANALYSIS_IMAGE_SIZE; col++)
{ {
if (mask.At<byte>(row, col) != 255) if (mask.At<byte>(row, col) == 0)
continue; continue;
var vector = new float[FEATURES_LENGTH]; var vector = new float[FEATURES_LENGTH];
foreach (var (i, image) in images.Enumerate()) foreach (var (i, image) in images.Enumerate())
@@ -250,17 +252,72 @@ public partial class AnalyzerService
}); });
if (prediction is null) if (prediction is null)
continue; continue;
result.Set<float>(row, col, prediction.Value); if (prediction.Value >= 0)
values[row * ANALYSIS_IMAGE_SIZE + col] = prediction.Value; {
result.Set(row, col, prediction.Value);
values[row * ANALYSIS_IMAGE_SIZE + col] = prediction.Value;
}
} }
var oldMean = Cv2.Mean(result, mask).Val0; // foreach (var contour in contours)
values.Sort(); // {
float p999 = values[(int)(values.Length * 0.999)]; // var contourMask = new Mat(new Size(ANALYSIS_IMAGE_SIZE, ANALYSIS_IMAGE_SIZE), MatType.CV_8UC1, new Scalar(0));
Cv2.Threshold(result, result, p999, p999, ThresholdTypes.Trunc); // var contourDistance = new Mat(new Size(ANALYSIS_IMAGE_SIZE, ANALYSIS_IMAGE_SIZE), MatType.CV_32FC1, new Scalar(0));
var newMean = Cv2.Mean(result, mask).Val0; // Cv2.DrawContours(contourMask, [contour], -1, new Scalar(255), -1);
var scale = oldMean / newMean; // Cv2.DistanceTransform(contourMask, contourDistance, DistanceTypes.L2, DistanceTransformMasks.Mask5);
Cv2.ConvertScaleAbs(result, result, scale); // Cv2.Pow(contourDistance, 2, contourDistance);
// Cv2.MinMaxLoc(contourDistance, out double minVal, out double maxVal);
// contourDistance.ConvertTo(contourDistance, MatType.CV_32FC1, 1 / (maxVal - minVal), 1 * minVal / (maxVal - minVal));
// // Cv2.ConvertScaleAbs(contourDistance, contourDistance, -1, 1);
// Cv2.BitwiseNot(contourMask, contourMask);
// contourDistance.SetTo(new Scalar(1), contourMask);
// Cv2.Multiply(result, contourDistance, result);
// contourMask.Dispose();
// contourDistance.Dispose();
// }
// var maskDistance = new Mat();
// var resultDistance = new Mat();
// var temp = new Mat();
// Cv2.DistanceTransform(mask, maskDistance, DistanceTypes.L2, DistanceTransformMasks.Mask5);
// Cv2.MinMaxLoc(result, out double minValue, out double maxValue, out _, out _, mask);
// result.ConvertTo(temp, MatType.CV_8UC1, 255 / (maxValue - 0), 255 * 0 / (maxValue - 0));
// Cv2.DistanceTransform(temp, resultDistance, DistanceTypes.L2, DistanceTransformMasks.Mask5);
// Cv2.Multiply(maskDistance, resultDistance, temp);
// Cv2.Threshold(temp, temp, 0, 255, ThresholdTypes.Binary);
// for (var row = 0; row < ANALYSIS_IMAGE_SIZE; row++)
// for (var col = 0; col < ANALYSIS_IMAGE_SIZE; col++)
// if (mask.At<byte>(row, col) == 0)
// {
// result.Set(row, col, 0);
// mask.Set(row, col, 0);
// }
// maskDistance.Dispose();
// resultDistance.Dispose();
// temp.Dispose();
// var oldMean = Cv2.Mean(result, mask).Val0;
// float p001 = values[values.Count(v => v == 0) + 1];
// float p999 = values[(int)(values.Length * 0.999)];
// Cv2.Threshold(result, result, p999, p999, ThresholdTypes.Trunc);
// var zeroMask = result.LessThanOrEqual(0);
// result.SetTo(p001, zeroMask);
// zeroMask.Dispose();
// var newMean = Cv2.Mean(result, mask).Val0;
// var scale = oldMean / newMean;
// Cv2.ConvertScaleAbs(result, result, scale);
// Добавляем эрозию к результатм и маске, удаляющую края, и пересчитываем контура
// поскольку края грунул подсвечиваются близлежайщими гранулами и сепаратором,
// их нельзя считаль представительными
Cv2.Erode(result, result, Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(3, 3)));
Cv2.Erode(mask, mask, Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(3, 3)));
Cv2.FindContours(mask, out var newContours, out _, RetrievalModes.List, ContourApproximationModes.ApproxSimple);
return (avgImage, roi, mask, contours, result, separatorType, sampleBrand); return (avgImage, roi, mask, contours, result, separatorType, sampleBrand);
} }
catch (Exception ex) catch (Exception ex)
@@ -335,7 +392,7 @@ public partial class AnalyzerService
continue; continue;
if (!keyMap.ContainsKey(prediction.Label)) if (!keyMap.ContainsKey(prediction.Label))
keyMap.Add(prediction.Label, ++lastKey); keyMap.Add(prediction.Label, ++lastKey);
result.Set<ushort>(row, col, keyMap[prediction.Label]); result.Set(row, col, keyMap[prediction.Label]);
} }
foreach (var image in images) foreach (var image in images)
@@ -344,7 +401,6 @@ public partial class AnalyzerService
var valueMap = keyMap.ToDictionary(kv => kv.Value, kv => kv.Key); var valueMap = keyMap.ToDictionary(kv => kv.Value, kv => kv.Key);
var frequency = new Dictionary<string, int>(); var frequency = new Dictionary<string, int>();
for (var row = 0; row < ANALYSIS_IMAGE_SIZE; row++) for (var row = 0; row < ANALYSIS_IMAGE_SIZE; row++)
for (var col = 0; col < ANALYSIS_IMAGE_SIZE; col++) for (var col = 0; col < ANALYSIS_IMAGE_SIZE; col++)
{ {
@@ -358,13 +414,13 @@ public partial class AnalyzerService
if (valueMap[value].StartsWith(separatorPrefix)) if (valueMap[value].StartsWith(separatorPrefix))
result.Set<ushort>(row, col, 0); result.Set<ushort>(row, col, 0);
if (valueMap[value].StartsWith(samplePrefix)) if (valueMap[value].StartsWith(samplePrefix))
result.Set<ushort>(row, col, ushort.MaxValue); result.Set(row, col, ushort.MaxValue);
} }
result.ConvertTo(result, MatType.CV_8UC1, 1 / 255.0); result.ConvertTo(result, MatType.CV_8UC1, 1 / 255.0);
Cv2.MorphologyEx(result, result, MorphTypes.Close, Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(3, 3)), iterations: 2); Cv2.MorphologyEx(result, result, MorphTypes.Close, Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(3, 3)));
Cv2.MorphologyEx(result, result, MorphTypes.Open, Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(3, 3)), iterations: 2); Cv2.MorphologyEx(result, result, MorphTypes.Open, Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(3, 3)));
Cv2.Dilate(result, result, Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(3, 3))); Cv2.Dilate(result, result, Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(3, 3)));
Cv2.GaussianBlur(result, result, new Size(5, 5), 1); Cv2.GaussianBlur(result, result, new Size(5, 5), 1);
Cv2.Threshold(result, result, 127, 255, ThresholdTypes.Binary); Cv2.Threshold(result, result, 127, 255, ThresholdTypes.Binary);
@@ -374,6 +430,9 @@ public partial class AnalyzerService
result = new Mat(new Size(ANALYSIS_IMAGE_SIZE, ANALYSIS_IMAGE_SIZE), MatType.CV_8UC1, new Scalar(0)); result = new Mat(new Size(ANALYSIS_IMAGE_SIZE, ANALYSIS_IMAGE_SIZE), MatType.CV_8UC1, new Scalar(0));
Cv2.DrawContours(result, contours.Where(ContourIsValid), -1, new Scalar(255), -1); Cv2.DrawContours(result, contours.Where(ContourIsValid), -1, new Scalar(255), -1);
_logger.LogInformation("Найдено гранул: {}", contours.Where(ContourIsValid).Count());
_logger.LogInformation("Детекторованные обекты:\n\t{}", string.Join("\n\t", frequency.Select(f => $"{f.Key}: {f.Value}")));
return ( return (
avgImage, avgImage,
roi.Value, roi.Value,
@@ -524,9 +583,9 @@ public partial class AnalyzerService
// } // }
private static bool ContourIsValid(Point[] contour) private static bool ContourIsValid(Point[] contour)
{ {
var bbox = Cv2.BoundingRect(contour); var bbox = Cv2.MinAreaRect(contour);
var area = Cv2.ContourArea(contour); var area = Cv2.ContourArea(contour);
return CONTOUR_MIN_SIZE < bbox.Width && CONTOUR_MIN_SIZE < bbox.Height && CONTOUR_MIN_AREA < area && return CONTOUR_MIN_SIZE < bbox.Size.Width && CONTOUR_MIN_SIZE < bbox.Size.Height && CONTOUR_MIN_AREA < area &&
CONTOUR_MAX_SIZE > bbox.Width && CONTOUR_MAX_SIZE > bbox.Height && CONTOUR_MAX_AREA > area; CONTOUR_MAX_SIZE > bbox.Size.Width && CONTOUR_MAX_SIZE > bbox.Size.Height && CONTOUR_MAX_AREA > area;
} }
} }