public IEnumerable <SimilarityResult> FindSimilar(IBagOfWords bag)
{
logger.LogDebug("Searching for similar documents");
var vector = encoder.GetFullVector(bag.Words.Select(item => item.Text).ToArray());
var distanceTable = new Dictionary <IBagOfWords, double?>();
foreach (var existing in vectorTable)
{
distanceTable[existing.Key] = null;
}
Parallel.ForEach(vectorTable.Keys.ToArray(),
existingDocument =>
{
var existing = vectorTable[existingDocument];
if (existing == null)
{
existing = encoder.GetFullVector(existingDocument.Words.Select(item => item.Text).ToArray());
vectorTable[existingDocument] = existing;
}
var distance = distanceMeasurer.Measure(vector, existing);
distanceTable[existingDocument] = distance;
});
return(distanceTable.OrderByDescending(item => item.Value)
.Where(item => item.Value.HasValue)
.Select(item => new SimilarityResult(item.Key, item.Value.Value)));
}
public ContextManager(IContextBuilder contextBuilder, IRepositoryManager repositoryManager,
ITagger tagger, IBagOfWords bagOfWords)
{
this.contextBuilder = contextBuilder;
this.repositoryManager = repositoryManager;
this.tagger = tagger;
this.bagOfWords = bagOfWords;
}
private static void CreateBoW()
{
var numberOfWords = 36;
foreach (var file in Directory.EnumerateFiles(@"C:\Temp\TLLCamerasTestData\37_Training", "*.jpg"))
{
var trainingImage = (Bitmap)Bitmap.FromFile(file);
trainingImages.Add(file, trainingImage);
}
foreach (var file in Directory.EnumerateFiles(@"C:\Temp\TLLCamerasTestData\37_Testing", "*.jpg"))
{
var testImage = (Bitmap)Bitmap.FromFile(file);
testingImages.Add(file, testImage);
}
// We will use SURF, so we can use a standard clustering
// algorithm that is based on Euclidean distances. A good
// algorithm for clustering codewords is the Binary Split
// variant of the K-Means algorithm.
// Create a Binary-Split clustering algorithm
BinarySplit binarySplit = new BinarySplit(numberOfWords);
// Create bag-of-words (BoW) with the given algorithm
BagOfVisualWords surfBow = new BagOfVisualWords(binarySplit);
// Compute the BoW codebook using training images only
IBagOfWords <Bitmap> bow = surfBow.Learn(trainingImages.Values.ToArray());
// now that we've created the bow we need to use it to create a representation of each training and test image
foreach (var trainingImage in trainingImages.Keys)
{
var asBitmap = trainingImages[trainingImage] as Bitmap;
var featureVector = (bow as ITransform <Bitmap, double[]>).Transform(asBitmap);
var featureString = featureVector.ToString(DefaultArrayFormatProvider.InvariantCulture);
trainingFeatures.Add(trainingImage, featureVector);
}
foreach (var testingImage in testingImages.Keys)
{
var asBitmap = testingImages[testingImage] as Bitmap;
var featureVector = (bow as ITransform <Bitmap, double[]>).Transform(asBitmap);
var featureString = featureVector.ToString(DefaultArrayFormatProvider.InvariantCulture);
testingFeatures.Add(testingImage, featureVector);
}
}
public void Register(IBagOfWords bag)
{
if (bag == null)
{
throw new ArgumentNullException(nameof(bag));
}
foreach (var bagWord in bag.Words)
{
encoder.AddWord(bagWord.Text);
}
vectorTable[bag] = null;
}
public SimilarityResult(IBagOfWords document, double similarity)
{
Document = document ?? throw new ArgumentNullException(nameof(document));
Similarity = similarity;
}
private double[] GetData(Bitmap bitmap, IBagOfWords <Bitmap> bow) => (bow as ITransform <Bitmap, double[]>).Transform(bitmap);
