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 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;
}
}
}
}
}
}
public static void threshold_frac(Bytearray thresholded, Floatarray input, float frac)
{
float minofinput = NarrayUtil.Min(input);
float theta = frac * (NarrayUtil.Max(input) - minofinput) + minofinput;
binarize_with_threshold(thresholded, input, theta);
}
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);
}
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)]);
}
}
/// <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)]);
}
}
protected void Recompute()
{
nc = NarrayUtil.Max(classes) + 1;
nf = data[0].Dim(0);
CHECK_ARG(DataMin(data) >= 0 && DataMax(data) < 256, "min(data) >= 0 && max(data) < 256");
CHECK_ARG(NarrayUtil.Min(classes) >= -1 && NarrayUtil.Max(classes) < 10000,
"min(classes)>=-1 && max(classes)<10000");
CHECK_ARG(nc > 0, "nc > 0");
CHECK_ARG(nf > 0, "nf > 0");
}
protected void Recompute()
{
nc = NarrayUtil.Max(classes) + 1;
nf = data.Dim(1);
CHECK_ARG(Min(data) > -100 && Max(data) < 100, "min(data) > -100 && max(data) < 100");
CHECK_ARG(NarrayUtil.Min(classes) >= -1 && NarrayUtil.Max(classes) < 10000,
"min(classes)>=-1 && max(classes)<10000");
CHECK_ARG(nc > 0, "nc > 0");
CHECK_ARG(nf > 0, "nf > 0");
}
public static void combine_segmentations(ref Intarray dst, Intarray src)
{
dst.SameDims(src);
int n = NarrayUtil.Max(dst) + 1;
for (int i = 0; i < dst.Length1d(); i++)
{
dst.Put1d(i, (dst.At1d(i) + src.At1d(i) * n));
}
ImgLabels.renumber_labels(dst, 1);
}
/// <summary>
/// Изменился текущий BookLine
/// </summary>
private void BookLine_CurrentChanged(object sender, EventArgs e)
{
if (listingDataView.View.CurrentItem == null)
{
return;
}
// сбросим кэш предыдущего елемента
if (currBookLine != null)
{
currBookLine.Image = null;
currBookLine.ImageBytearray = null;
currBookLine.CharsegIntarray = null;
}
// текущий елемент
BookLine bline = listingDataView.View.CurrentItem as BookLine;
currBookLine = bline;
// сбросим некоторые признаки
isCurrDeletedSegment = false;
// показать Charseg
if (bline != null && bline.HaveCharseg)
{
// загрузим с файла
Intarray charseg = bline.CharsegIntarray;
// занесем в кэш
bline.CharsegIntarray = charseg;
// номер максимального сегмента
CurrSegmentsCount = NarrayUtil.Max(charseg);
// отобразим картинку
ShowCharsegImage(charseg, bline.Transcript);
// активируем кнопки действий
EnableCharsegCmdButtons();
}
else
{
imgCharSeg.Source = null;
DisableCharsegCmdButtons();
}
// показать Transcript
if (bline != null && bline.HaveTranscript)
{
ShowTranscript(bline.Transcript);
}
else
{
ShowTranscript("");
}
// сбросим к началу номер начальног осегмента
numUpDnStart.Value = 1;
numUpDnEnd.Value = 2;
}
public static int binarize_simple(Bytearray result, Bytearray image)
{
int threshold = (NarrayUtil.Max(image) /* + NarrayUtil.Min(image)*/) / 2;
result.MakeLike(image);
for (int i = 0; i < image.Length1d(); i++)
{
result.Put1d(i, image.At1d(i) < threshold ? (byte)0 : (byte)255);
}
return(threshold);
}
public static void binsmooth(Bytearray binary, Floatarray input, float sigma)
{
Floatarray smoothed = new Floatarray();
smoothed.Copy(input);
smoothed -= NarrayUtil.Min(smoothed);
smoothed /= NarrayUtil.Max(smoothed);
if (sigma > 0)
{
Gauss.Gauss2d(smoothed, sigma, sigma);
}
binarize_with_threshold(binary, smoothed, 0.5f);
}
/// <summary>
/// Get spacing to the next component.
/// </summary>
public override int PixelSpace(int i)
{
int end = NarrayUtil.Max(segments.At1d(i));
if (end >= rboxes.Length() - 1)
{
return(-1);
}
int x0 = rboxes.At1d(end).x1;
int x1 = rboxes.At1d(end + 1).x0;
return(x1 - x0);
}
public static Bitmap read_image_binary(Bytearray image, string path)
{
Bitmap bitmap = LoadBitmapFromFile(path);
image.Resize(bitmap.Width, bitmap.Height);
ImgRoutine.NarrayFromBitmap(image, bitmap);
double threshold = (NarrayUtil.Min(image) + NarrayUtil.Max(image)) / 2.0;
for (int i = 0; i < image.Length1d(); i++)
{
image.Put1d(i, (byte)((image.At1d(i) < threshold) ? 0 : 255));
}
return(bitmap);
}
public override void Add(Floatarray v, int c)
{
CHECK_ARG(NarrayUtil.Min(v) > -1.2f && NarrayUtil.Max(v) < 1.2f, "float8: value out of range (-1.2..1.2)");
CHECK_ARG(c >= -1, "c>=-1");
if (c >= nc)
{
nc = c + 1;
}
if (nf < 0)
{
nf = v.Length();
}
RowPush(data, v);
classes.Push(c);
}
/// <summary>
/// Remove segments from start to end.
/// </summary>
/// <param name="cseg">Output</param>
/// <param name="rseg">Input</param>
/// <param name="start">start remove position</param>
/// <param name="end">end remove position</param>
public static void rseg_to_cseg_remove(Intarray cseg, Intarray rseg,
Bytearray outimg, Bytearray img, 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!");
}
if (rseg.Length1d() != img.Length1d())
{
throw new Exception("rseg and img must have same a dimension!");
}
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++;
}
else
{
map[i] = 0;
}
}
cseg.MakeLike(rseg);
outimg.Copy(img);
for (int i = 0; i < cseg.Length1d(); i++)
{
int val = rseg.At1d(i);
cseg.Put1d(i, map[val]);
if (val > 0 && map[val] == 0)
{
outimg.Put1d(i, 255);
}
}
}
private void ProcessMergeSegments(object sender, RoutedEventArgs e)
{
int start = numUpDnStart.Value ?? 1;
int end = numUpDnEnd.Value ?? 1;
start = Math.Min(start, CurrSegmentsCount);
end = Math.Min(end, CurrSegmentsCount);
SegmRoutine.rseg_to_cseg(currBookLine.CharsegIntarray, currBookLine.CharsegIntarray, start, end);
// пересчитаем число сегментов
CurrSegmentsCount = NarrayUtil.Max(currBookLine.CharsegIntarray);
// Show segmented image
ShowCharsegImage(currBookLine.CharsegIntarray,
(currBookLine.HaveTranscript && CurrSegmentsCount == currBookLine.Transcript.Length) ?
currBookLine.Transcript : "");
}
public static void line_segmentation_sort_x(Intarray segmentation)
{
if (NarrayUtil.Max(segmentation) > 100000)
{
throw new Exception("line_segmentation_merge_small_components: to many segments");
}
Narray <Rect> bboxes = new Narray <Rect>();
ImgLabels.bounding_boxes(ref bboxes, segmentation);
Floatarray x0s = new Floatarray();
unchecked
{
x0s.Push((float)-999999);
}
for (int i = 1; i < bboxes.Length(); i++)
{
if (bboxes[i].Empty())
{
x0s.Push(999999);
}
else
{
x0s.Push(bboxes[i].x0);
}
}
// dprint(x0s,1000); printf("\n");
Narray <int> permutation = new Intarray();
Narray <int> rpermutation = new Intarray();
NarrayUtil.Quicksort(permutation, x0s);
rpermutation.Resize(permutation.Length());
for (int i = 0; i < permutation.Length(); i++)
{
rpermutation[permutation[i]] = i;
}
// dprint(rpermutation,1000); printf("\n");
for (int i = 0; i < segmentation.Length1d(); i++)
{
if (segmentation.At1d(i) == 0)
{
continue;
}
segmentation.Put1d(i, rpermutation[segmentation.At1d(i)]);
}
}
public override void Info()
{
bool bak = Logger.Default.verbose;
Logger.Default.verbose = true;
Logger.Default.WriteLine("MLP");
PPrint();
Logger.Default.WriteLine(String.Format("nInput {0} nHidden {1} nOutput {2}",
w1.Dim(1), w1.Dim(0), w2.Dim(0)));
if (w1.Length() > 0 && w2.Length() > 0)
{
Logger.Default.WriteLine(String.Format("w1 [{0},{1}] b1 [{2},{3}]",
NarrayUtil.Min(w1), NarrayUtil.Max(w1), NarrayUtil.Min(b1), NarrayUtil.Max(b1)));
Logger.Default.WriteLine(String.Format("w2 [{0},{1}] b2 [{2},{3}]",
NarrayUtil.Min(w2), NarrayUtil.Max(w2), NarrayUtil.Min(b2), NarrayUtil.Max(b2)));
}
Logger.Default.verbose = bak;
}
public static void weighted_sample(Intarray samples, Floatarray weights, int n)
{
Floatarray cs = new Floatarray();
cs.Copy(weights);
for (int i = 1; i < cs.Length(); i++)
{
cs[i] += cs[i - 1];
}
cs /= NarrayUtil.Max(cs);
samples.Clear();
for (int i = 0; i < n; i++)
{
float value = (float)DRandomizer.Default.drand();
int where = Binsearch(cs, value);
samples.Push(where);
}
}
public Dataset8(Narray <sbyte> data, Intarray classes)
: this()
{
data.Copy(data);
classes.Copy(classes);
if (classes.Length() > 0)
{
nc = NarrayUtil.Max(classes) + 1;
nf = data.Dim(1);
//CHECK_ARG(NarrayUtil.Min(data) > -100 && NarrayUtil.Max(data) < 100, "min(data)>-100 && max(data)<100");
CHECK_ARG(NarrayUtil.Min(classes) >= -1 && NarrayUtil.Max(classes) < 10000, "min(classes)>=-1 && max(classes)<10000");
}
else
{
nc = 0;
nf = -1;
}
}
/// <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 void binarize_by_range(Bytearray outa, Floatarray ina, float fraction)
{
float imin = NarrayUtil.Min(ina);
float imax = NarrayUtil.Max(ina);
float thresh = (int)(imin + (imax - imin) * fraction);
outa.MakeLike(ina);
for (int i = 0; i < ina.Length1d(); i++)
{
if (ina.At1d(i) > thresh)
{
outa.Put1d(i, 255);
}
else
{
outa.Put1d(i, 0);
}
}
}
public override void Add(Floatarray v, int c)
{
CHECK_ARG(NarrayUtil.Min(v) >= 0.0f && NarrayUtil.Max(v) <= 1.0f, "float8: value out of range (0..1)");
CHECK_ARG(c >= -1, "c>=-1");
if (c >= nc)
{
nc = c + 1;
}
if (nf < 0)
{
nf = v.Length();
}
Narray <byte> newDataItem = data.Push(new Narray <byte>());
Copy(newDataItem, v);
classes.Push(c);
CHECK_ARG(nc > 0, "nc>0");
CHECK_ARG(nf > 0, "nf>0");
}
public static void erase_small_components(Floatarray input, float mins = 0.2f, float thresh = 0.25f)
{
// compute a thresholded image for component labeling
float threshold = thresh * NarrayUtil.Max(input);
Intarray components = new Intarray();
components.MakeLike(input);
components.Fill(0);
for (int i = 0; i < components.Length(); i++)
{
components[i] = (input[i] > threshold ? 1 : 0);
}
// compute the number of pixels in each component
int n = ImgLabels.label_components(ref components);
Intarray totals = new Intarray(n + 1);
totals.Fill(0);
for (int i = 0; i < components.Length(); i++)
{
totals[components[i]] = totals[components[i]] + 1;
}
totals[0] = 0;
int biggest = NarrayUtil.ArgMax(totals);
// erase small components
float minsize = mins * totals[biggest];
Bytearray keep = new Bytearray(n + 1);
float background = NarrayUtil.Min(input);
for (int i = 0; i < keep.Length(); i++)
{
keep[i] = (byte)(totals[i] > minsize ? 1 : 0);
}
for (int i = 0; i < input.Length(); i++)
{
if (keep[components[i]] == 0)
{
input[i] = background;
}
}
}
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);
}
}
/// <summary>
/// Compute the bounding boxes for the pixels in the image.
/// </summary>
public static void bounding_boxes(ref Narray <Rect> result, Intarray image)
{
result.Clear();
int n = NarrayUtil.Max(image);
if (n < 1)
{
return;
}
result.Resize(n + 1);
result.Fill(Rect.CreateEmpty());
for (int i = 0; i < image.Dim(0); i++)
{
for (int j = 0; j < image.Dim(1); j++)
{
int value = image[i, j];
Rect r = result[value];
r.Include(i, j);
result[value] = r;
//original: result(value).include(i, j);
}
}
}
private void ProcessDeleteSegment(object sender, RoutedEventArgs e)
{
int start = numUpDnStart.Value ?? 1;
start = Math.Min(start, CurrSegmentsCount);
Bytearray outgray = new Bytearray();
SegmRoutine.rseg_to_cseg_remove(
currBookLine.CharsegIntarray, currBookLine.CharsegIntarray,
outgray, currBookLine.ImageBytearray, start, start);
// пересчитаем число сегментов
CurrSegmentsCount = NarrayUtil.Max(currBookLine.CharsegIntarray);
// Show segmented image
ShowCharsegImage(currBookLine.CharsegIntarray,
(currBookLine.HaveTranscript && CurrSegmentsCount == currBookLine.Transcript.Length) ?
currBookLine.Transcript : "");
currBookLine.ImageBytearray = outgray;
currBookLine.Image = ImgRoutine.NarrayToRgbBitmap(outgray);
isCurrDeletedSegment = true;
}
public override int nClasses()
{
return(NarrayUtil.Max(_classes) + 1);
}
protected void rescale(Floatarray v, Floatarray input)
{
if (input.Rank() != 2)
{
throw new Exception("CHECK_ARG: sub.Rank()==2");
}
Floatarray sub = new Floatarray();
// find the largest connected component
// and crop to its bounding box
// (use a binary version of the character
// to compute the bounding box)
Intarray components = new Intarray();
float threshold = PGetf("threshold") * NarrayUtil.Max(input);
Global.Debugf("biggestcc", "threshold {0}", threshold);
components.MakeLike(input);
components.Fill(0);
for (int i = 0; i < components.Length(); i++)
{
components[i] = (input[i] > threshold ? 1 : 0);
}
int n = ImgLabels.label_components(ref components);
Intarray totals = new Intarray(n + 1);
totals.Fill(0);
for (int i = 0; i < components.Length(); i++)
{
totals[components[i]]++;
}
totals[0] = 0;
Narray <Rect> boxes = new Narray <Rect>();
ImgLabels.bounding_boxes(ref boxes, components);
int biggest = NarrayUtil.ArgMax(totals);
Rect r = boxes[biggest];
int pad = (int)(PGetf("pad") + 0.5f);
r.PadBy(pad, pad);
Global.Debugf("biggestcc", "({0}) {1}[{2}] :: {3} {4} {5} {6}",
n, biggest, totals[biggest],
r.x0, r.y0, r.x1, r.y1);
// now perform normal feature extraction
// (use the original grayscale input)
sub = input;
ImgMisc.Crop(sub, r);
int csize = PGeti("csize");
float s = Math.Max(sub.Dim(0), sub.Dim(1)) / (float)csize;
if (PGetf("noupscale") > 0 && s < 1.0f)
{
s = 1.0f;
}
float sig = s * PGetf("aa");
float dx = (csize * s - sub.Dim(0)) / 2f;
float dy = (csize * s - sub.Dim(1)) / 2f;
if (sig > 1e-3f)
{
Gauss.Gauss2d(sub, sig, sig);
}
v.Resize(csize, csize);
v.Fill(0f);
for (int i = 0; i < csize; i++)
{
for (int j = 0; j < csize; j++)
{
float x = i * s - dx;
float y = j * s - dy;
if (x < 0 || x >= sub.Dim(0))
{
continue;
}
if (y < 0 || y >= sub.Dim(1))
{
continue;
}
float value = ImgOps.bilin(sub, x, y);
v[i, j] = value;
}
}
/*Global.Debugf("biggestcc", "{0} {1} ({2}) -> {3} {4} ({5})",
* sub.Dim(0), sub.Dim(1), NarrayUtil.Max(sub),
* v.Dim(0), v.Dim(1), NarrayUtil.Max(v));*/
}
