public IEnumerable <(string Prediction, float Score, TextBlock Block)> Classify(Page page, IWordExtractor wordExtractor, IPageSegmenter pageSegmenter)
{
var words = wordExtractor.GetWords(page.Letters);
var blocks = pageSegmenter.GetBlocks(words);
foreach (var block in blocks)
{
var letters = block.TextLines.SelectMany(li => li.Words).SelectMany(w => w.Letters);
var paths = FeatureHelper.GetPathsInside(block.BoundingBox, page.ExperimentalAccess.Paths);
var images = FeatureHelper.GetImagesInside(block.BoundingBox, page.GetImages());
var features = FeatureHelper.GetFeatures(page, block.BoundingBox, letters, paths, images);
BlockFeatures blockFeatures = new BlockFeatures()
{
CharsCount = features[0],
PctNumericChars = features[1],
PctAlphabeticalChars = features[2],
PctSymbolicChars = features[3],
PctBulletChars = features[4],
DeltaToHeight = features[5],
PathsCount = features[6],
PctBezierPaths = features[7],
PctHorPaths = features[8],
PctVertPaths = features[9],
PctOblPaths = features[10],
ImagesCount = features[11],
ImageAvgProportion = features[12]
};
var result = predEngine.Predict(blockFeatures);
yield return(FeatureHelper.Categories[(int)result.Prediction], result.Score.Max(), block);
}
}
public IEnumerable <(string Prediction, float Score, TextBlock Block)> Classify(Page page, IWordExtractor wordExtractor,
IPageSegmenter pageSegmenter, Bookmarks bookmarks = null)
{
List <DocumentBookmarkNode> bookmarksNodes = bookmarks?.GetNodes()
.Where(b => b is DocumentBookmarkNode)
.Select(b => b as DocumentBookmarkNode)
.Cast <DocumentBookmarkNode>()
.Where(b => b.PageNumber == page.Number).ToList();
var avgPageFontHeight = page.Letters.Select(l => l.GlyphRectangle.Height).Average();
var words = wordExtractor.GetWords(page.Letters);
var blocks = pageSegmenter.GetBlocks(words);
foreach (var block in blocks)
{
var letters = block.TextLines.SelectMany(li => li.Words).SelectMany(w => w.Letters);
var paths = FeatureHelper.GetPathsInside(block.BoundingBox, page.ExperimentalAccess.Paths);
var images = FeatureHelper.GetImagesInside(block.BoundingBox, page.GetImages());
var features = FeatureHelper.GetFeatures(
block, paths,
images, avgPageFontHeight,
block.BoundingBox.Area,
bookmarksNodes);
BlockFeatures blockFeatures = new BlockFeatures()
{
BlockAspectRatio = features[0],
CharsCount = features[1],
WordsCount = features[2],
LinesCount = features[3],
PctNumericChars = features[4],
PctAlphabeticalChars = features[5],
PctSymbolicChars = features[6],
PctBulletChars = features[7],
DeltaToHeight = features[8],
PathsCount = features[9],
PctBezierPaths = features[10],
PctHorPaths = features[11],
PctVertPaths = features[12],
PctOblPaths = features[13],
ImagesCount = features[14],
ImageAvgProportion = features[15],
BestNormEditDistance = features[16],
};
var result = predEngine.Predict(blockFeatures);
yield return(FeatureHelper.Categories[(int)result.Prediction], result.Score.Max(), block);
}
}
public (string Prediction, float Score) Classify(TextBlock textBlock, IEnumerable <PdfPath> paths, IEnumerable <IPdfImage> images,
double averagePageFontHeight, List <DocumentBookmarkNode> pageBookmarksNodes)
{
double bboxArea = textBlock.BoundingBox.Area;
var letters = textBlock.TextLines.SelectMany(li => li.Words).SelectMany(w => w.Letters);
var features = FeatureHelper.GetFeatures(
textBlock, paths,
images, averagePageFontHeight,
textBlock.BoundingBox.Area,
pageBookmarksNodes);
BlockFeatures blockFeatures = new BlockFeatures()
{
BlockAspectRatio = features[0],
CharsCount = features[1],
WordsCount = features[2],
LinesCount = features[3],
PctNumericChars = features[4],
PctAlphabeticalChars = features[5],
PctSymbolicChars = features[6],
PctBulletChars = features[7],
DeltaToHeight = features[8],
PathsCount = features[9],
PctBezierPaths = features[10],
PctHorPaths = features[11],
PctVertPaths = features[12],
PctOblPaths = features[13],
ImagesCount = features[14],
ImageAvgProportion = features[15],
BestNormEditDistance = features[16],
};
var result = predEngine.Predict(blockFeatures);
return(FeatureHelper.Categories[(int)result.Prediction], result.Score.Max());
}