private double[] process(Bitmap bmp, int n, string method)
{
double[,] features2D = BitmapFeatures.Intensity(bmp);
switch (method)
{
case "merge":
double[] features = FeatureReduction.Flatten(features2D);
return(FeatureReduction.Merge(features, n));
case "grid":
return(FeatureReduction.GridwiseMerge(features2D, n));
}
return(FeatureReduction.Flatten(features2D));
//double[] features = FeatureReduction.Flatten(features2D);
//features = FeatureReduction.RowColSums(features2D);
//features = FeatureReduction.LDA(features2D, 4);
//features = FeatureReduction.PCA(features2D, 4);
//features = FeatureReduction.SVD(features2D);
//features = FeatureReduction.FHT(features2D);
//features = FeatureReduction.Sort(features);
//features = FeatureReduction.Covariance(features2D);
//features = FeatureReduction.Merge(features, n);
//features = FeatureReduction.Binarize(features);
//double[] features = FeatureReduction.GridwiseMerge(features2D, n);
//features = FeatureReduction.Discretize(features, 100);
//features = FeatureReduction.Binarize(features);
//return features;
}
/// <summary>
/// Classifies the specified test instance.
/// </summary>
/// <param name="test">The test instance.</param>
/// <returns></returns>
/// <remarks></remarks>
public override Result Classify(Instance test)
{
string maxClass = "?";
double maxProb = float.MinValue;
double[] features = FeatureReduction.Discretize(test.Features, 10);
foreach (KeyValuePair <string, double> pair in Classes)
{
double score = Math.Log(pair.Value / TotalExamples);
for (int i = 0; i < features.Length; i++)
{
score += Math.Log(Count(pair.Key, i, features[i]) / pair.Value);
}
if (score > maxProb)
{
maxProb = score;
maxClass = pair.Key;
}
}
return(new Result(maxClass, maxProb));
}
/// <summary>
/// Trains the classifier on the specified training instances.
/// </summary>
/// <param name="trainingInstances">The training instances.</param>
/// <remarks></remarks>
public override void Train(List <Instance> trainingInstances)
{
Model = new Dictionary <string, double>();
Classes = new Dictionary <string, double>();
TotalExamples = trainingInstances.Count;
foreach (Instance train in trainingInstances)
{
double[] features = FeatureReduction.Discretize(train.Features, 3);
for (int i = 0; i < features.Length; i++)
{
string c = train.Class + "|" + i + "|" + features[i];
if (Model.ContainsKey(c))
{
Model[c] += 1;
}
else
{
Model[c] = 1;
}
}
if (Classes.ContainsKey(train.Class))
{
Classes[train.Class] += 1;
}
else
{
Classes[train.Class] = 1;
}
}
}
/// <summary>
/// Extracts intensity features from the bitmap, and uses grid merge feature reduction.
/// </summary>
/// <param name="bmp">The BMP.</param>
/// <returns></returns>
/// <remarks></remarks>
private double[] BitmapFeatureExtract(Bitmap bmp)
{
double[,] features2D = BitmapFeatures.Intensity(bmp);
double[] features = FeatureReduction.GridwiseMerge(features2D, 64);
return(features);
}
