public override void Charseg(ref Intarray outimage, Bytearray inimage)
{
int swidth = PGeti("swidth");
int sheight = PGeti("sheight");
Bytearray image = new Bytearray();
image.Copy(inimage);
OcrRoutine.binarize_simple(image);
OcrRoutine.Invert(image);
outimage.Copy(image);
if (swidth > 0 || sheight > 0)
{
Morph.binary_close_rect(image, swidth, sheight);
}
Intarray labels = new Intarray();
labels.Copy(image);
ImgLabels.label_components(ref labels);
for (int i = 0; i < outimage.Length1d(); i++)
{
if (outimage.At1d(i) > 0)
{
outimage.Put1d(i, SegmRoutine.cseg_pixel(labels.At1d(i)));
}
}
SegmRoutine.make_line_segmentation_white(outimage);
SegmRoutine.check_line_segmentation(outimage);
}
protected void CorrectOutputsNull(int vertex)
{
if (m_outputs[vertex] == null)
{
m_outputs[vertex] = new Intarray();
}
}
public static void write_image_packed(string path, Intarray image)
{
Bitmap bitmap = ImgRoutine.NarrayToRgbBitmap(image);
bitmap.Save(path);
bitmap.Dispose();
}
/// <summary>
/// Compute a classmap that maps a set of possibly sparse classes onto a dense
/// list of new classes and vice versa
/// </summary>
public static void ClassMap(Intarray out_class_to_index, Intarray out_index_to_class, Intarray classes)
{
int nclasses = NarrayUtil.Max(classes) + 1;
Intarray hist = new Intarray(nclasses);
hist.Fill(0);
for (int i = 0; i < classes.Length(); i++)
{
if (classes[i] == -1) continue;
hist[classes[i]]++;
}
int count = 0;
for (int i = 0; i < hist.Length(); i++)
if (hist[i] > 0) count++;
out_class_to_index.Resize(nclasses);
out_class_to_index.Fill(-1);
out_index_to_class.Resize(count);
out_index_to_class.Fill(-1);
int index = 0;
for (int i = 0; i < hist.Length(); i++)
{
if (hist[i] > 0)
{
out_class_to_index[i] = index;
out_index_to_class[index] = i;
index++;
}
}
CHECK_ARG(out_class_to_index.Length() == nclasses, "class_to_index.Length() == nclasses");
CHECK_ARG(out_index_to_class.Length() == NarrayUtil.Max(out_class_to_index) + 1,
"index_to_class.Length() == Max(class_to_index)+1");
CHECK_ARG(out_index_to_class.Length() <= out_class_to_index.Length(),
"index_to_class.Length() <= class_to_index.Length()");
}
public static bool a_star_in_composition(Intarray inputs,
Intarray vertices1,
Intarray vertices2,
Intarray outputs,
Floatarray costs,
OcroFST fst1,
OcroFST fst2)
{
CompositionFst composition = FstFactory.MakeCompositionFst(fst1, fst2);
bool result;
try
{
//Floatarray g1 = new Floatarray();
//Floatarray g2 = new Floatarray();
fst1.CalculateHeuristics();
fst2.CalculateHeuristics();
result = a_star2_internal(inputs, vertices1, vertices2, outputs,
costs, fst1, fst2,
fst1.Heuristics(),
fst2.Heuristics(), composition);
}
catch (Exception ex)
{
composition.Move1();
composition.Move2();
throw ex;
}
composition.Move1();
composition.Move2();
return(result);
}
public OutputVector()
{
_len = 0;
_keys = new Intarray();
_values = new Floatarray();
_result = null;
}
/// <summary>
/// Randomly sample an FST, assuming any input.
/// </summary>
/// <param name="result">The array of output symbols, excluding epsilons.</param>
/// <param name="fst">The FST.</param>
/// <param name="max">The maximum length of the result.</param>
/// <returns>total cost</returns>
public static double fst_sample(Intarray result, IGenericFst fst, int max = 1000)
{
double total_cost = 0;
int current = fst.GetStart();
for (int counter = 0; counter < max; counter++)
{
Intarray inputs = new Intarray();
Intarray outputs = new Intarray();
Intarray targets = new Intarray();
Floatarray costs = new Floatarray();
fst.Arcs(inputs, targets, outputs, costs, current);
// now we need to deal with the costs uniformly, so:
costs.Push(fst.GetAcceptCost(current));
int choice = sample_by_costs(costs);
if (choice == costs.Length() - 1)
{
break;
}
result.Push(outputs[choice]);
total_cost += costs[choice];
current = targets[choice];
}
return(total_cost + fst.GetAcceptCost(current));
}
public void GetLineSegmentation(Intarray image, int page, int line, string variant = null)
{
string v = "rseg";
if (!String.IsNullOrEmpty(variant)) { v += "."; v += variant; }
GetLine(image, page, line, v);
SegmRoutine.make_line_segmentation_black(image);
}
/// <summary>
/// Copy one FST to another.
/// </summary>
/// <param name="dst">The destination. Will be cleared before copying.</param>
/// <param name="src">The FST to copy.</param>
public static void fst_copy(IGenericFst dst, IGenericFst src)
{
dst.Clear();
int n = src.nStates();
for (int i = 0; i < n; i++)
{
dst.NewState();
}
dst.SetStart(src.GetStart());
for (int i = 0; i < n; i++)
{
dst.SetAccept(i, src.GetAcceptCost(i));
Intarray targets = new Intarray(), outputs = new Intarray(), inputs = new Intarray();
Floatarray costs = new Floatarray();
src.Arcs(inputs, targets, outputs, costs, i);
int inlen = inputs.Length();
if (inlen != targets.Length())
{
throw new Exception("ASSERT: inputs.length() == targets.length()");
}
if (inlen != outputs.Length())
{
throw new Exception("ASSERT: inputs.length() == outputs.length()");
}
if (inlen != costs.Length())
{
throw new Exception("ASSERT: inputs.length() == costs.length()");
}
for (int j = 0; j < inputs.Length(); j++)
{
dst.AddTransition(i, targets.At1d(j), outputs.At1d(j), costs.At1d(j), inputs.At1d(j));
}
}
}
private void ProcessSegmentationMethod(object sender, RoutedEventArgs e)
{
string strSermenterName = (sender as Control).Tag.ToString();
ISegmentLine segmenter = ComponentCreator.MakeComponent <ISegmentLine>(strSermenterName);
if (segmenter == null || currBookLine == null)
{
return;
}
// приведем к чернобелому
Bytearray image = currBookLine.ImageBytearray;
//IBinarize binarizer = new BinarizeByOtsu();
//binarizer.Binarize(image, image);
OcrRoutine.binarize_simple(image, image);
// сегментация
Intarray charseg = new Intarray();
segmenter.Charseg(ref charseg, image);
// фон равен 0
SegmRoutine.make_line_segmentation_black(charseg);
// удалим маленькие сегменты
SegmRoutine.remove_small_components(charseg, 3, 3);
ImgLabels.renumber_labels(charseg, 1);
currBookLine.CharsegIntarray = charseg;
CurrSegmentsCount = NarrayUtil.Max(charseg);
// Show segmented image
ShowCharsegImage(charseg,
(currBookLine.HaveTranscript && CurrSegmentsCount == currBookLine.Transcript.Length) ?
currBookLine.Transcript : "");
// to enable save button
EnableCharsegCmdButtons();
}
public static Bitmap read_image_packed(Intarray image, string path)
{
Bitmap bitmap = LoadBitmapFromFile(path);
image.Resize(bitmap.Width, bitmap.Height);
ImgRoutine.NarrayFromBitmap(image, bitmap);
return bitmap;
}
public static void check_approximately_sorted(Intarray labels)
{
for (int i = 0; i < labels.Length1d(); i++)
{
if (labels.At1d(i) > 100000)
{
throw new Exception("labels out of range");
}
}
Narray <Rect> rboxes = new Narray <Rect>();
ImgLabels.bounding_boxes(ref rboxes, labels);
#if false
// TODO/tmb disabling check until the overseg issue is fixed --tmb
for (int i = 1; i < rboxes.Length(); i++)
{
if (rboxes[i].Right < rboxes[i - 1].Left)
{
/*errors_log("bad segmentation", labels);
* errors_log.recolor("bad segmentation (recolored)", labels);
* throw_fmt("boxes aren't approximately sorted: "
* "box %d is to the left from box %d", i, i-1);*/
}
}
#endif
}
public OutputVector()
{
_len = 0;
_keys = new Intarray();
_values = new Floatarray();
_result = null;
}
public void InitData(IDataset ds, int nhidden, Intarray newc2i = null, Intarray newi2c = null)
{
CHECK_ARG(nhidden > 1 && nhidden < 1000000, "nhidden > 1 && nhidden < 1000000");
int ninput = ds.nFeatures();
int noutput = ds.nClasses();
w1.Resize(nhidden, ninput);
b1.Resize(nhidden);
w2.Resize(noutput, nhidden);
b2.Resize(noutput);
Intarray indexes = new Intarray();
NarrayUtil.RPermutation(indexes, ds.nSamples());
Floatarray v = new Floatarray();
for (int i = 0; i < w1.Dim(0); i++)
{
int row = indexes[i];
ds.Input1d(v, row);
float normv = (float)NarrayUtil.Norm2(v);
v /= normv * normv;
NarrayRowUtil.RowPut(w1, i, v);
}
ClassifierUtil.fill_random(b1, -1e-6f, 1e-6f);
ClassifierUtil.fill_random(w2, -1.0f / nhidden, 1.0f / nhidden);
ClassifierUtil.fill_random(b2, -1e-6f, 1e-6f);
if (newc2i != null)
{
c2i.Copy(newc2i);
}
if (newi2c != null)
{
i2c.Copy(newi2c);
}
}
public static bool Equals(Intarray a, Intarray b)
{
if (a.Length() != b.Length()) return false;
for (int i = 0; i < a.Length(); i++)
if (a.UnsafeAt1d(i) != b.UnsafeAt1d(i)) return false;
return true;
}
public static void segmentation_correspondences(Narray<Intarray> outsegments, Intarray seg, Intarray cseg)
{
if (NarrayUtil.Max(seg) >= 10000)
throw new Exception("CHECK_ARG: (max(seg)<10000)");
if (NarrayUtil.Max(cseg) >= 10000)
throw new Exception("CHECK_ARG: (max(cseg)<10000)");
int nseg = NarrayUtil.Max(seg) + 1;
int ncseg = NarrayUtil.Max(cseg) + 1;
Intarray overlaps = new Intarray(nseg, ncseg);
overlaps.Fill(0);
if (seg.Length() != cseg.Length())
throw new Exception("CHECK_ARG: (seg.Length()==cseg.Length())");
for (int i = 0; i < seg.Length(); i++)
overlaps[seg.At1d(i), cseg.At1d(i)]++;
outsegments.Clear();
outsegments.Resize(ncseg);
for (int i = 0; i < nseg; i++)
{
int j = NarrayRowUtil.RowArgMax(overlaps, i);
if (!(j >= 0 && j < ncseg))
throw new Exception("ASSERT: (j>=0 && j<ncseg)");
if (outsegments[j] == null)
outsegments[j] = new Intarray();
outsegments[j].Push(i);
}
}
protected override void Train(IDataset ds)
{
if (!(ds.nSamples() > 0))
{
throw new Exception("nSamples of IDataset must be > 0");
}
if (!(ds.nFeatures() > 0))
{
throw new Exception("nFeatures of IDataset must be > 0");
}
if (c2i.Length() < 1)
{
Intarray raw_classes = new Intarray();
raw_classes.ReserveTo(ds.nSamples());
for (int i = 0; i < ds.nSamples(); i++)
{
raw_classes.Push(ds.Cls(i));
}
ClassMap(c2i, i2c, raw_classes);
/*Intarray classes = new Intarray();
* ctranslate(classes, raw_classes, c2i);*/
//debugf("info","[mapped %d to %d classes]\n",c2i.length(),i2c.length());
}
TranslatedDataset mds = new TranslatedDataset(ds, c2i);
TrainDense(mds);
}
public static bool a_star_in_composition(Intarray inputs,
Intarray vertices1,
Intarray vertices2,
Intarray outputs,
Floatarray costs,
OcroFST fst1,
OcroFST fst2)
{
CompositionFst composition = FstFactory.MakeCompositionFst(fst1, fst2);
bool result;
try
{
//Floatarray g1 = new Floatarray();
//Floatarray g2 = new Floatarray();
fst1.CalculateHeuristics();
fst2.CalculateHeuristics();
result = a_star2_internal(inputs, vertices1, vertices2, outputs,
costs, fst1, fst2,
fst1.Heuristics(),
fst2.Heuristics(), composition);
}
catch (Exception ex)
{
composition.Move1();
composition.Move2();
throw ex;
}
composition.Move1();
composition.Move2();
return result;
}
public void Image(string description, Intarray a, float zoom = 100f)
{
if (verbose)
{
writer.WriteLine(String.Format("image {0} w:{1}, h:{2}", description, a.Dim(0), a.Dim(1)));
}
}
public override void SetSegmentationAndGt(Intarray segmentation, Intarray cseg, ref string text)
{
// first, set the segmentation as usual
SetSegmentation(segmentation);
// Maybe fix up the transcript (remove spaces).
gttranscript = text;
string s = text;
fixup_transcript(ref s, false);
int max_cseg = NarrayUtil.Max(cseg);
bool old_csegs = (s.Length != max_cseg);
fixup_transcript(ref gttranscript, old_csegs);
// Complain if it doesn't match.
if (gttranscript.Length != max_cseg)
{
Logger.Default.Format("transcript = '{0}'\n", gttranscript);
throw new Exception(String.Format("transcript doesn't agree with cseg (transcript {0}, cseg {1})",
gttranscript.Length, max_cseg));
}
// Now compute the correspondences between the character segmentation
// and the raw segmentation.
GrouperRoutine.segmentation_correspondences(gtsegments, segmentation, cseg);
}
Floatarray costs; // the cost of the node on the heap
/// <summary>
/// Constructor.
/// Create a heap storing node indices from 0 to n - 1.
/// </summary>
public Heap(int n)
{
heap = new Intarray();
heapback = new Intarray(n);
heapback.Fill(-1);
costs = new Floatarray();
}
/// <summary>
/// Return the segmentation-derived mask for the character.
/// This may optionally be grown by some pixels.
/// </summary>
public override void GetMask(out Rect r, ref Bytearray outmask, int index, int grow)
{
r = boxes.At1d(index).Grow(grow);
r.Intersect(new Rect(0, 0, labels.Dim(0), labels.Dim(1)));
if (fullheight)
{
r.y0 = 0;
r.y1 = labels.Dim(1);
}
int x = r.x0, y = r.y0, w = r.Width(), h = r.Height();
Intarray segs = segments.At1d(index);
outmask.Resize(w, h);
outmask.Fill(0);
for (int i = 0; i < w; i++)
{
for (int j = 0; j < h; j++)
{
int label = labels[x + i, y + j];
if (NarrayUtil.first_index_of(segs, label) >= 0)
{
outmask[i, j] = (byte)255;
}
}
}
if (grow > 0)
{
Morph.binary_dilate_circle(outmask, grow);
}
}
/// <summary>
/// Train on a text line.
/// <remarks>Usage is: call addTrainingLine with training data, then call finishTraining
/// The state of the object is undefined between calling addTrainingLine and finishTraining, and it is
/// an error to call recognizeLine before finishTraining completes. This allows both batch
/// and incemental training.
/// NB: you might train on length 1 strings for single character training
/// and might train on words if line alignment is not working
/// (well, for some training data)</remarks>
/// </summary>
public void AddTrainingLine(Intarray cseg, string tr)
{
Bytearray gimage = new Bytearray();
ClassifierUtil.segmentation_as_bitmap(gimage, cseg);
AddTrainingLine(cseg, gimage, tr);
}
public static bool a_star_in_composition(Intarray inputs,
Intarray vertices1,
Intarray vertices2,
Intarray outputs,
Floatarray costs,
OcroFST fst1,
Floatarray g1,
OcroFST fst2,
Floatarray g2)
{
CompositionFst composition = FstFactory.MakeCompositionFst(fst1, fst2);
bool result;
try
{
result = a_star2_internal(inputs, vertices1, vertices2, outputs,
costs, fst1, fst2,
g1,
g2, composition);
}
catch (Exception ex)
{
composition.Move1();
composition.Move2();
throw ex;
}
composition.Move1();
composition.Move2();
return(result);
}
public void Get(Intarray r_vertices1,
Intarray r_vertices2,
Intarray r_inputs,
Intarray r_outputs,
Floatarray r_costs,
int id)
{
Intarray t_v1 = new Intarray(); // vertices
Intarray t_v2 = new Intarray(); // vertices
Intarray t_i = new Intarray(); // inputs
Intarray t_o = new Intarray(); // outputs
Floatarray t_c = new Floatarray(); // costs
int current = id;
while (current != -1)
{
t_v1.Push(v1[current]);
t_v2.Push(v2[current]);
t_i.Push(inputs[current]);
t_o.Push(outputs[current]);
t_c.Push(costs[current]);
current = parents[current];
}
NarrayUtil.Reverse(r_vertices1, t_v1);
NarrayUtil.Reverse(r_vertices2, t_v2);
NarrayUtil.Reverse(r_inputs, t_i);
NarrayUtil.Reverse(r_outputs, t_o);
NarrayUtil.Reverse(r_costs, t_c);
}
public override void Charseg(ref Intarray result_segmentation, Bytearray orig_image)
{
Logger.Default.Image("segmenting", orig_image);
int PADDING = 3;
OcrRoutine.optional_check_background_is_lighter(orig_image);
Bytearray image = new Bytearray();
Narray <byte> bimage = image;
image.Copy(orig_image);
OcrRoutine.binarize_simple(image);
OcrRoutine.Invert(image);
ImgOps.pad_by(ref bimage, PADDING, PADDING);
// pass image to segmenter
segmenter.SetImage(image);
// find all cuts in the image
segmenter.FindAllCuts();
// choose the best of all cuts
segmenter.FindBestCuts();
Intarray segmentation = new Intarray();
segmentation.Resize(image.Dim(0), image.Dim(1));
for (int i = 0; i < image.Dim(0); i++)
{
for (int j = 0; j < image.Dim(1); j++)
{
segmentation[i, j] = image[i, j] > 0 ? 1 : 0;
}
}
for (int r = 0; r < segmenter.bestcuts.Length(); r++)
{
int c = segmenter.bestcuts[r];
Narray <Point> cut = segmenter.cuts[c];
for (int y = 0; y < image.Dim(1); y++)
{
for (int x = cut[y].X; x < image.Dim(0); x++)
{
if (segmentation[x, y] > 0)
{
segmentation[x, y]++;
}
}
}
}
ImgOps.extract_subimage(result_segmentation, segmentation, PADDING, PADDING,
segmentation.Dim(0) - PADDING, segmentation.Dim(1) - PADDING);
if (small_merge_threshold > 0)
{
SegmRoutine.line_segmentation_merge_small_components(ref result_segmentation, small_merge_threshold);
SegmRoutine.line_segmentation_sort_x(result_segmentation);
}
SegmRoutine.make_line_segmentation_white(result_segmentation);
// set_line_number(segmentation, 1);
Logger.Default.Image("resulting segmentation", result_segmentation);
}
protected virtual void GetLinesOfPage(Intarray lines, int ipage)
{
lines.Clear();
string dirName = String.Format("{0}{1}{2:0000}", prefix, Path.DirectorySeparatorChar, ipage);
DirPattern dpattern = new DirPattern(dirName, @"([0-9][0-9][0-9][0-9])\.png");
if (dpattern.Length > 0)
{
lines.ReserveTo(dpattern.Length);
}
List <int> llist = new List <int>(dpattern.Length);
for (int i = 0; i < dpattern.Length; i++)
{
int k = int.Parse(dpattern[i]);
llist.Add(k);
//lines.Push(k);
}
IEnumerable <int> query = llist.OrderBy(i => i);
foreach (int iline in query)
{
lines.Push(iline);
}
}
public void Get(Intarray r_vertices1,
Intarray r_vertices2,
Intarray r_inputs,
Intarray r_outputs,
Floatarray r_costs,
int id)
{
Intarray t_v1 = new Intarray(); // vertices
Intarray t_v2 = new Intarray(); // vertices
Intarray t_i = new Intarray(); // inputs
Intarray t_o = new Intarray(); // outputs
Floatarray t_c = new Floatarray(); // costs
int current = id;
while (current != -1)
{
t_v1.Push(v1[current]);
t_v2.Push(v2[current]);
t_i.Push(inputs[current]);
t_o.Push(outputs[current]);
t_c.Push(costs[current]);
current = parents[current];
}
NarrayUtil.Reverse(r_vertices1, t_v1);
NarrayUtil.Reverse(r_vertices2, t_v2);
NarrayUtil.Reverse(r_inputs, t_i);
NarrayUtil.Reverse(r_outputs, t_o);
NarrayUtil.Reverse(r_costs, t_c);
}
/// <summary>
/// Merge segments from start to end.
/// </summary>
/// <param name="cseg">Output</param>
/// <param name="rseg">Input</param>
/// <param name="start">start merge position</param>
/// <param name="end">end merge position</param>
public static void rseg_to_cseg(Intarray cseg, Intarray rseg, int start, int end)
{
int maxSegNum = NarrayUtil.Max(rseg);
if (start > end)
{
throw new Exception("segmentation encoded in IDs looks seriously broken!");
}
if (start > maxSegNum || end > maxSegNum)
{
throw new Exception("segmentation encoded in IDs doesn't fit!");
}
Intarray map = new Intarray(maxSegNum + 1);
map.Fill(0);
int color = 1;
for (int i = 1; i <= maxSegNum; i++)
{
map[i] = color;
if (i < start || i >= end)
{
color++;
}
}
cseg.MakeLike(rseg);
for (int i = 0; i < cseg.Length1d(); i++)
{
cseg.Put1d(i, map[rseg.At1d(i)]);
}
}
public IBatchDense()
{
c2i = new Intarray();
i2c = new Intarray();
Persist(c2i, "c2i");
Persist(i2c, "i2c");
}
public static void rseg_to_cseg(Intarray cseg, Intarray rseg, Intarray ids)
{
Intarray map = new Intarray(NarrayUtil.Max(rseg) + 1);
map.Fill(0);
int color = 0;
for (int i = 0; i < ids.Length(); i++)
{
if (ids[i] == 0)
{
continue;
}
color++;
int start = ids[i] >> 16;
int end = ids[i] & 0xFFFF;
if (start > end)
{
throw new Exception("segmentation encoded in IDs looks seriously broken!");
}
if (start >= map.Length() || end >= map.Length())
{
throw new Exception("segmentation encoded in IDs doesn't fit!");
}
for (int j = start; j <= end; j++)
{
map[j] = color;
}
}
cseg.MakeLike(rseg);
for (int i = 0; i < cseg.Length1d(); i++)
{
cseg.Put1d(i, map[rseg.At1d(i)]);
}
}
public static void remove_small_components(Intarray segmentation, int w = 5, int h = 4)
{
if (NarrayUtil.Max(segmentation) > 100000)
{
throw new Exception("remove_small_components: to many segments");
}
Narray <Rect> bboxes = new Narray <Rect>();
ImgLabels.bounding_boxes(ref bboxes, segmentation);
for (int i = 1; i < bboxes.Length(); i++)
{
Rect b = bboxes[i];
if (b.Width() < w && b.Height() < h)
{
for (int x = b.x0; x < b.x1; x++)
{
for (int y = b.y0; y < b.y1; y++)
{
if (segmentation[x, y] == i)
{
segmentation[x, y] = 0;
}
}
}
}
}
}
/// <summary>
/// A valid line segmentation may contain 0 or 0xffffff as the
/// background, and otherwise numbers components starting at 1.
/// The segmentation consists of segmented background pixels
/// (0x80xxxx) and segmented foreground pixels (0x00xxxx). The
/// segmented foreground pixels should constitute a usable
/// binarization of the original image.
/// </summary>
public static void check_line_segmentation(Intarray cseg)
{
if (cseg.Length1d() == 0)
{
return;
}
if (cseg.Rank() != 2)
{
throw new Exception("check_line_segmentation: rank must be 2");
}
for (int i = 0; i < cseg.Length1d(); i++)
{
int value = cseg.At1d(i);
if (value == 0)
{
continue;
}
if (value == 0xffffff)
{
continue;
}
if ((value & 0x800000) > 0)
{
if ((value & ~0x800000) > 100000)
{
throw new Exception("check_line_segmentation: (value & ~0x800000) > 100000");
}
}
else
if (value > 100000)
{
throw new Exception("check_line_segmentation: value > 100000");
}
}
}
public void BestPath(Intarray v1, Intarray v2, Intarray inputs,
Intarray outputs, Floatarray costs)
{
stree.Clear();
beam.Resize(1);
beamcost.Resize(1);
beam[0] = stree.Add(-1, fst1.GetStart(), fst2.GetStart(), 0, 0, 0);
beamcost[0] = 0;
best_so_far = 0;
best_cost_so_far = fst1.GetAcceptCost(fst1.GetStart()) +
fst2.GetAcceptCost(fst1.GetStart());
while (beam.Length() > 0)
{
Radiate();
}
stree.Get(v1, v2, inputs, outputs, costs, best_so_far);
costs.Push(fst1.GetAcceptCost(stree.v1[best_so_far]) +
fst2.GetAcceptCost(stree.v2[best_so_far]));
//logger("costs", costs);
}
public override void Arcs(Intarray out_inputs, Intarray out_targets, Intarray out_outputs, Floatarray out_costs, int from)
{
out_inputs.Copy(m_inputs[from]);
out_targets.Copy(m_targets[from]);
out_outputs.Copy(m_outputs[from]);
out_costs.Copy(m_costs[from]);
}
internal static bool a_star2_internal(Intarray inputs,
Intarray vertices1,
Intarray vertices2,
Intarray outputs,
Floatarray costs,
IGenericFst fst1,
IGenericFst fst2,
Floatarray g1,
Floatarray g2,
CompositionFst composition)
{
Intarray vertices = new Intarray();
AStarCompositionSearch a = new AStarCompositionSearch(g1, g2, composition);
if (!a.Loop())
{
return(false);
}
if (!a.reconstruct_vertices(vertices))
{
return(false);
}
a.reconstruct_edges(inputs, outputs, costs, vertices);
composition.SplitIndices(vertices1, vertices2, vertices);
return(true);
}
public IBatchDense()
{
c2i = new Intarray();
i2c = new Intarray();
Persist(c2i, "c2i");
Persist(i2c, "i2c");
}
public override void Arcs(Intarray out_inputs, Intarray out_targets, Intarray out_outputs, Floatarray out_costs, int from)
{
out_inputs.Copy(m_inputs[from]);
out_targets.Copy(m_targets[from]);
out_outputs.Copy(m_outputs[from]);
out_costs.Copy(m_costs[from]);
}
Intarray heapback; // heap[heapback[node]] == node; -1 if not in the heap
#endregion Fields
#region Constructors
/// <summary>
/// Constructor.
/// Create a heap storing node indices from 0 to n - 1.
/// </summary>
public Heap(int n)
{
heap = new Intarray();
heapback = new Intarray(n);
heapback.Fill(-1);
costs = new Floatarray();
}
protected void CorrectTargetsNull(int vertex)
{
if (m_targets[vertex] == null)
{
m_targets[vertex] = new Intarray();
}
}
public Linerec(string classifier1 = "latin"/*none*/, string extractor1 = "scaledfe",
string segmenter1 = "DpSegmenter", int use_reject = 1)
{
transcript = "";
//line = new Bytearray();
segmentation = new Intarray();
binarized = new Bytearray();
// component choices
PDef("classifier", classifier1, "character classifier");
PDef("extractor", extractor1, "feature extractor");
PDef("segmenter", segmenter1, "line segmenter");
PDef("grouper", "SimpleGrouper", "line grouper");
// retraining
PDef("cpreload", "none", "classifier to be loaded prior to training");
// debugging
PDef("verbose", 0, "verbose output from glinerec");
// outputs
PDef("use_priors", 0, "correct the classifier output by priors");
PDef("use_reject", use_reject, "use a reject class (use posteriors only and train on junk chars)");
PDef("maxcost", 20.0, "maximum cost of a character to be added to the output");
PDef("minclass", 32, "minimum output class to be added (default=unicode space)");
PDef("minprob", 1e-9, "minimum probability for a character to appear in the output at all");
PDef("invert", 1, "invert the input line prior to char extraction");
// segmentation
PDef("maxrange", 5, "maximum number of components that are grouped together");
// sanity limits on input
PDef("minheight", 9, "minimum height of input line");
PDef("maxheight", 300, "maximum height of input line");
PDef("maxaspect", 2.0, "maximum height/width ratio of input line");
// space estimation (FIXME factor this out eventually)
PDef("space_fractile", 0.5, "fractile for space estimation");
PDef("space_multiplier", 2.0, "multipler for space estimation");
PDef("space_min", 0.2, "minimum space threshold (in xheight)");
PDef("space_max", 1.1, "maximum space threshold (in xheight)");
PDef("space_yes", 1.0, "cost of inserting a space");
PDef("space_no", 5.0, "cost of not inserting a space");
// back compability
PDef("minsize_factor", 0.0, "");
counts = new Intarray();
segmenter = new ComponentContainerISegmentLine(ComponentCreator.MakeComponent<ISegmentLine>(PGet("segmenter")));
grouper = new ComponentContainerIGrouper(ComponentCreator.MakeComponent<IGrouper>(PGet("grouper")));
classifier = new ComponentContainerIModel(IModel.MakeModel(PGet("classifier")));
TryAttachClassifierEvent(classifier.Object);
Persist(classifier, "classifier");
Persist(counts, "counts");
Persist(segmenter, "segmenter");
Persist(grouper, "grouper");
if (!classifier.IsEmpty)
{
classifier.Object.Set("junk", PGeti("use_reject"));
classifier.Object.SetExtractor(PGet("extractor"));
}
ntrained = 0;
counts_warned = false;
}
public void TestSimple()
{
Global.SetEnv("debug", Global.GetEnv("debug") + "");
// image file name to recognize
string imgFileName = "line.png";
string imgCsegFileName = "line.cseg.png";
string imgTranscriptFileName = "line.txt";
// line recognizer
Linerec lrec = (Linerec)Linerec.LoadLinerec("default.model");
//Linerec lrec = (Linerec)Linerec.LoadLinerec("2m2-reject.cmodel");
//Linerec lrec = (Linerec)Linerec.LoadLinerec("multi3.cmodel");
//Linerec lrec = (Linerec)Linerec.LoadLinerec("latin-ascii.model");
lrec.Info();
// language model
OcroFST default_lmodel = OcroFST.MakeOcroFst();
default_lmodel.Load("default.fst");
OcroFST lmodel = default_lmodel;
// read image
Bytearray image = new Bytearray(1, 1);
ImgIo.read_image_gray(image, imgFileName);
// recognize!
OcroFST fst = OcroFST.MakeOcroFst();
Intarray rseg = new Intarray();
lrec.RecognizeLine(rseg, fst, image);
// show result 1
string resStr;
fst.BestPath(out resStr);
Console.WriteLine("Fst BestPath: {0}", resStr);
// find result 2
Intarray v1 = new Intarray();
Intarray v2 = new Intarray();
Intarray inp = new Intarray();
Intarray outp = new Intarray();
Floatarray c = new Floatarray();
BeamSearch.beam_search(v1, v2, inp, outp, c, fst, lmodel, 100);
FstUtil.remove_epsilons(out resStr, outp);
Console.WriteLine("Fst BeamSearch: {0}", resStr);
Intarray cseg = new Intarray();
SegmRoutine.rseg_to_cseg(cseg, rseg, inp);
SegmRoutine.make_line_segmentation_white(cseg);
ImgLabels.simple_recolor(cseg); // for human readable
ImgIo.write_image_packed(imgCsegFileName, cseg);
File.WriteAllText(imgTranscriptFileName, resStr.Replace(" ", ""));
}
/// <summary>
/// Return an array of arcs leading from the given node.
/// WARN_DEPRECATED
/// </summary>
public virtual void Arcs(Intarray ids,
Intarray targets,
Intarray outputs,
Floatarray costs,
int from)
{
throw new NotImplementedException("IGenericFst:Arcs: unimplemented");
}
public RowDataset8()
{
DatatypeSize = sizeof(byte); // one byte
data = new ObjList<Narray<byte>>();
classes = new Intarray();
nc = -1;
nf = -1;
}
public Dataset8()
{
DatatypeSize = sizeof(sbyte); // one byte
data = new Narray<sbyte>();
classes = new Intarray();
nc = -1;
nf = -1;
}
public void GetPageSegmentation(Intarray image, int page, string variant = null)
{
string v = "pseg";
if (!String.IsNullOrEmpty(variant)) { v += "."; v += variant; }
GetPage(image, page, v);
//SegmRoutine.check_page_segmentation(image); // dublicate!
SegmRoutine.make_page_segmentation_black(image);
}
public List<List<float>> SpaceCosts(List<Candidate> candidates, Bytearray image)
{
/*
Given a list of character recognition candidates and their
classifications, and an image of the corresponding text line,
compute a list of pairs of costs for putting/not putting a space
after each of the candidate characters.
The basic idea behind this simple algorithm is to try larger
and larger horizontal closing operations until most of the components
start having a "wide" aspect ratio; that's when characters have merged
into words. The remaining whitespace should be spaces.
This is just a simple stopgap measure; it will be replaced with
trainable space modeling.
*/
int w = image.Dim(0);
int h = image.Dim(1);
Bytearray closed = new Bytearray();
int r;
for (r = 0; r < maxrange; r++)
{
if (r > 0)
{
closed.Copy(image);
Morph.binary_close_circle(closed, r);
}
else
closed.Copy(image);
Intarray labeled = new Intarray();
labeled.Copy(closed);
ImgLabels.label_components(ref labeled);
Narray<Rect> rects = new Narray<Rect>();
ImgLabels.bounding_boxes(ref rects, labeled);
Floatarray aspects = new Floatarray();
for (int i = 0; i < rects.Length(); i++)
{
Rect rect = rects[i];
float aspect = rect.Aspect();
aspects.Push(aspect);
}
float maspect = NarrayUtil.Median(aspects);
if (maspect >= this.aspect_threshold)
break;
}
// close with a little bit of extra space
closed.Copy(image);
Morph.binary_close_circle(closed, r+1);
// compute the remaining aps
//Morph.binary_dilate_circle();
// every character box that ends near a cap gets a space appended
return null;
}
public Intarray v2; // vertices from FST 2
#endregion Fields
#region Constructors
public SearchTree()
{
parents = new Intarray();
inputs = new Intarray();
outputs = new Intarray();
v1 = new Intarray();
v2 = new Intarray();
costs = new Floatarray();
}
public RowDataset8(Narray<byte> ds, Intarray cs)
: this()
{
for (int i = 0; i < ds.Dim(0); i++)
{
RowGet(data.Push(new Narray<byte>()), ds, i);
classes.Push(cs[i]);
}
Recompute();
}
public RowDataset8(int nsamples)
{
DatatypeSize = sizeof(byte); // one byte
data = new ObjList<Narray<byte>>();
data.ReserveTo(nsamples);
classes = new Intarray();
classes.ReserveTo(nsamples);
nc = -1;
nf = -1;
}
public TestDataset()
{
classes = new int[sClasses.Length];
aclasses = new Intarray(sClasses.Length);
for (int i = 0; i < sClasses.Length; i++)
{
classes[i] = (int)sClasses[i];
aclasses.Put1d(i, classes[i]);
}
}
/// <summary>
/// constructor for a NBest data structure of size n
/// </summary>
public PriorityQueue(int n)
{
this.n = n;
ids = new Intarray();
tags = new Intarray();
values = new Floatarray();
ids.Resize(n + 1);
tags.Resize(n + 1);
values.Resize(n + 1);
Clear();
}
public static double a_star(out string result, OcroFST fst)
{
result = "";
Intarray inputs = new Intarray();
Intarray vertices = new Intarray();
Intarray outputs = new Intarray();
Floatarray costs = new Floatarray();
if (!a_star(inputs, vertices, outputs, costs, fst))
return 1e38;
FstUtil.remove_epsilons(out result, outputs);
return NarrayUtil.Sum(costs);
}
public CurvedCutSegmenterImpl()
{
wimage = new Intarray();
costs = new Intarray();
sources = new Intarray();
bestcuts = new Intarray();
dimage = new Intarray();
cuts = new Narray<Narray<Point>>();
cutcosts = new Floatarray();
//params_for_chars();
params_for_lines();
//params_from_hwrec_c();
}
public static double a_star(out string result, OcroFST fst1, OcroFST fst2)
{
result = "";
Intarray inputs = new Intarray();
Intarray v1 = new Intarray();
Intarray v2 = new Intarray();
Intarray outputs = new Intarray();
Floatarray costs = new Floatarray();
if (!a_star_in_composition(inputs, v1, v2, outputs, costs, fst1, fst2))
return 1e38;
FstUtil.remove_epsilons(out result, outputs);
return NarrayUtil.Sum(costs);
}
public override int AddLineId(int ipage, int iline)
{
if (lines.Length() <= ipage)
{
lines.Resize(ipage + 1);
for (int i = 0; i < lines.Length(); i++)
{
if (lines[i] == null)
lines[i] = new Intarray();
}
}
lines[ipage].Push(iline);
return lines[ipage].Length() - 1;
}
public static double beam_search(out string result, OcroFST fst1, OcroFST fst2,
int beam_width)
{
Intarray v1 = new Intarray();
Intarray v2 = new Intarray();
Intarray i = new Intarray();
Intarray o = new Intarray();
Floatarray c = new Floatarray();
//fprintf(stderr,"starting beam search\n");
beam_search(v1, v2, i, o, c, fst1, fst2, beam_width);
//fprintf(stderr,"finished beam search\n");
FstUtil.remove_epsilons(out result, o);
return NarrayUtil.Sum(c);
}
public override void Charseg(ref Intarray result_segmentation, Bytearray orig_image)
{
Logger.Default.Image("segmenting", orig_image);
int PADDING = 3;
OcrRoutine.optional_check_background_is_lighter(orig_image);
Bytearray image = new Bytearray();
Narray<byte> bimage = image;
image.Copy(orig_image);
OcrRoutine.binarize_simple(image);
OcrRoutine.Invert(image);
ImgOps.pad_by(ref bimage, PADDING, PADDING);
// pass image to segmenter
segmenter.SetImage(image);
// find all cuts in the image
segmenter.FindAllCuts();
// choose the best of all cuts
segmenter.FindBestCuts();
Intarray segmentation = new Intarray();
segmentation.Resize(image.Dim(0), image.Dim(1));
for (int i = 0; i < image.Dim(0); i++)
for (int j = 0; j < image.Dim(1); j++)
segmentation[i, j] = image[i, j] > 0 ? 1 : 0;
for (int r = 0; r < segmenter.bestcuts.Length(); r++)
{
int c = segmenter.bestcuts[r];
Narray<Point> cut = segmenter.cuts[c];
for (int y = 0; y < image.Dim(1); y++)
{
for (int x = cut[y].X; x < image.Dim(0); x++)
{
if (segmentation[x, y] > 0) segmentation[x, y]++;
}
}
}
ImgOps.extract_subimage(result_segmentation, segmentation, PADDING, PADDING,
segmentation.Dim(0) - PADDING, segmentation.Dim(1) - PADDING);
if (small_merge_threshold > 0)
{
SegmRoutine.line_segmentation_merge_small_components(ref result_segmentation, small_merge_threshold);
SegmRoutine.line_segmentation_sort_x(result_segmentation);
}
SegmRoutine.make_line_segmentation_white(result_segmentation);
// set_line_number(segmentation, 1);
Logger.Default.Image("resulting segmentation", result_segmentation);
}
protected override void GetLinesOfPage(Intarray lines, int ipage)
{
lines.Clear();
string dirName = String.Format("{0}{1}{2:0000}", prefix, Path.DirectorySeparatorChar, ipage);
//DirPattern dpattern = new DirPattern(dirName, @"([0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F])\.png");
DirPattern dpattern = new DirPattern(dirName, @"([0-9][0-9][0-9][0-9][0-9][0-9])\.png");
if (dpattern.Length > 0)
lines.ReserveTo(dpattern.Length);
for (int i = 0; i < dpattern.Length; i++)
{
int k = int.Parse(dpattern[i]);
lines.Push(k);
}
}
public static bool a_star(Intarray inputs,
Intarray vertices,
Intarray outputs,
Floatarray costs,
OcroFST fst)
{
AStarSearch a = new AStarSearch(fst);
if (!a.Loop())
return false;
if (!a.reconstruct_vertices(vertices))
return false;
a.reconstruct_edges(inputs, outputs, costs, vertices);
return true;
}
