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 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);
}
public void SetLine(Bytearray image)
{
CHECK_ARG(image.Dim(1) < PGeti("maxheight"), "image.Dim(1) < PGeti(\"maxheight\")");
// run the segmenter
/*Narray<Rect> bboxes = new Narray<Rect>();
* Intarray iar = new Intarray();
* iar.Copy(image);
* ImgLabels.bounding_boxes(ref bboxes, iar);*/
//Console.WriteLine("IMG SETLINE: imin:{0} imax:{1}", NarrayUtil.ArgMin(iar), NarrayUtil.ArgMax(iar));
//Console.WriteLine("INDEX_BLACK:{0} {1} {2} {3}", bboxes[0].x0, bboxes[0].y0, bboxes[0].x1, bboxes[0].y1);
//ImgIo.write_image_gray("image.png", image);
OcrRoutine.binarize_simple(binarized, image);
segmenter.Object.Charseg(ref segmentation, binarized);
/*Intarray segm = new Intarray();
* segm.Copy(segmentation);
* ImgLabels.simple_recolor(segm);
* ImgIo.write_image_packed("segm_image.png", segm);*/
//NarrayUtil.Sub(255, binarized);
SegmRoutine.make_line_segmentation_black(segmentation);
SegmRoutine.remove_small_components(segmentation, 3, 3); // i add this line
ImgLabels.renumber_labels(segmentation, 1);
// set up the grouper
grouper.Object.SetSegmentation(segmentation);
}
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);
}
public override void FindBestCuts()
{
unchecked
{
for (int i = 0; i < cutcosts.Length(); i++)
{
NarrayUtil.ExtPut(dimage, i, (int)(cutcosts[i] + 10), 0xff0000);
}
for (int i = 0; i < cutcosts.Length(); i++)
{
NarrayUtil.ExtPut(dimage, i, (int)(min_thresh + 10), 0x800000);
}
}
Floatarray temp = new Floatarray();
Gauss.Gauss1d(temp, cutcosts, 3.0f);
cutcosts.Move(temp);
SegmRoutine.local_minima(ref bestcuts, cutcosts, min_range, min_thresh);
for (int i = 0; i < bestcuts.Length(); i++)
{
Narray <Point> cut = cuts[bestcuts[i]];
for (int j = 0; j < cut.Length(); j++)
{
Point p = cut[j];
NarrayUtil.ExtPut(dimage, p.X, p.Y, 0x00ff00);
}
}
///-if(debug.Length > 0) write_image_packed(debug, dimage);
// dshow1d(cutcosts,"Y");
//dshow(dimage,"Y");
}
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(" ", ""));
}
public override void Charseg(ref Intarray outimage, Bytearray inarray)
{
Bytearray image = new Bytearray();
image.Copy(inarray);
OcrRoutine.binarize_simple(image);
OcrRoutine.Invert(image);
outimage.Copy(image);
Intarray labels = new Intarray();
labels.Copy(image);
ImgLabels.label_components(ref labels);
Narray <Rect> boxes = new Narray <Rect>();
ImgLabels.bounding_boxes(ref boxes, labels);
Intarray equiv = new Intarray(boxes.Length());
for (int i = 0; i < boxes.Length(); i++)
{
equiv[i] = i;
}
for (int i = 1; i < boxes.Length(); i++)
{
Rect p = boxes[i];
for (int j = 1; j < boxes.Length(); j++)
{
if (i == j)
{
continue;
}
Rect q = boxes[j];
int x0 = Math.Max(p.x0, q.x0);
int x1 = Math.Min(p.x1, q.x1);
int iw = x1 - x0;
if (iw <= 0)
{
continue; // no overlap
}
int ow = Math.Min(p.Width(), q.Width());
float frac = iw / (float)(ow);
if (frac < 0.5f)
{
continue; // insufficient overlap
}
// printf("%d %d : %d %d : %g\n",i,j,iw,ow,frac);
equiv.Put1d(Math.Max(i, j), Math.Min(i, j));
}
}
for (int i = 0; i < labels.Length(); i++)
{
labels.Put1d(i, equiv.At1d(labels.At1d(i)));
}
ImgLabels.renumber_labels(labels, 1);
outimage.Move(labels);
SegmRoutine.make_line_segmentation_white(outimage);
SegmRoutine.check_line_segmentation(outimage);
}
public void SetImage(Bytearray image_)
{
Bytearray image = new Bytearray();
//image = image_;
image.Copy(image_);
dimage.Copy(image);
if (PGeti("fill_holes") > 0)
{
Bytearray holes = new Bytearray();
SegmRoutine.extract_holes(ref holes, image);
for (int i = 0; i < image.Length(); i++)
{
if (holes.At1d(i) > 0)
{
image.Put1d(i, 255);
}
}
}
int w = image.Dim(0), h = image.Dim(1);
wimage.Resize(w, h);
wimage.Fill(0);
float s1 = 0.0f, sy = 0.0f;
for (int i = 1; i < w; i++)
{
for (int j = 0; j < h; j++)
{
if (image[i, j] > 0)
{
s1++; sy += j;
}
if (image[i, j] > 0)
{
wimage[i, j] = inside_weight;
}
else
{
wimage[i, j] = outside_weight;
}
}
}
if (s1 == 0)
{
where = image.Dim(1) / 2;
}
else
{
where = (int)(sy / s1);
}
for (int i = 0; i < dimage.Dim(0); i++)
{
dimage[i, where] = 0x008000;
}
}
public void GetCharSegmentation(Intarray image, int page, int line, string variant = null)
{
string v = "cseg";
if (!String.IsNullOrEmpty(variant))
{
v += "."; v += variant;
}
GetLine(image, page, line, v);
SegmRoutine.make_line_segmentation_black(image);
}
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 void PutCharSegmentation(Intarray image, int page, int line, string variant = null)
{
string v = "cseg";
if (!String.IsNullOrEmpty(variant))
{
v += "."; v += variant;
}
Intarray simage = new Intarray();
simage.Copy(image);
SegmRoutine.make_line_segmentation_white(simage);
PutLine(simage, page, line, v);
}
/// <summary>
/// Set a character segmentation.
/// </summary>
public override void SetCSegmentation(Intarray segmentation)
{
maxrange = 1;
maxdist = 2;
labels.Copy(segmentation);
SegmRoutine.make_line_segmentation_black(labels);
GrouperRoutine.check_approximately_sorted(labels);
boxes.Dealloc();
segments.Dealloc();
class_outputs.Dealloc();
class_costs.Dealloc();
spaces.Dealloc();
computeGroups();
}
public override void Charseg(ref Intarray segmentation, Bytearray inraw)
{
Logger.Default.Image("segmenting", inraw);
OcrRoutine.optional_check_background_is_lighter(inraw);
Bytearray image = new Bytearray();
image.Copy(inraw);
OcrRoutine.binarize_simple(image);
OcrRoutine.Invert(image);
segmenter.SetImage(image);
segmenter.FindAllCuts();
segmenter.FindBestCuts();
Intarray seg = new Intarray();
seg.Copy(image);
for (int r = 0; r < segmenter.bestcuts.Length(); r++)
{
int w = seg.Dim(0);
int c = segmenter.bestcuts[r];
Narray <Point> cut = segmenter.cuts[c];
for (int y = 0; y < image.Dim(1); y++)
{
for (int i = -1; i <= 1; i++)
{
int x = cut[y].X;
if (x < 1 || x >= w - 1)
{
continue;
}
seg[x + i, y] = 0;
}
}
}
ImgLabels.label_components(ref seg);
// dshowr(seg,"YY"); dwait();
segmentation.Copy(image);
ImgLabels.propagate_labels_to(ref segmentation, seg);
SegmRoutine.line_segmentation_merge_small_components(ref segmentation, small_merge_threshold);
SegmRoutine.line_segmentation_sort_x(segmentation);
SegmRoutine.make_line_segmentation_white(segmentation);
// set_line_number(segmentation, 1);
Logger.Default.Image("resulting segmentation", segmentation);
}
public void PutPageSegmentation(Intarray image, int page, string variant = null)
{
string v = "pseg";
if (!String.IsNullOrEmpty(variant))
{
v += "."; v += variant;
}
Intarray simage = new Intarray();
simage.Copy(image);
SegmRoutine.check_page_segmentation(simage);
SegmRoutine.make_page_segmentation_white(simage);
PutPage(simage, page, v);
}
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 override void Charseg(ref Intarray result_segmentation, Bytearray orig_image)
{
Bytearray image = new Bytearray();
image.Copy(orig_image);
OcrRoutine.optional_check_background_is_lighter(image);
OcrRoutine.binarize_simple(image);
OcrRoutine.Invert(image);
Intarray ccseg = new Intarray();
ccseg.Copy(image);
ImgLabels.label_components(ref ccseg);
base.Charseg(ref result_segmentation, orig_image);
SegmRoutine.combine_segmentations(ref result_segmentation, ccseg);
}
public static Bitmap ConvertCharsegToBitmapRecolor(Intarray charseg, string trans = "")
{
Intarray cseg = new Intarray();
cseg.Copy(charseg);
Narray <Rect> bboxes = new Narray <Rect>();
//SegmRoutine.make_line_segmentation_black(cseg);
ImgLabels.bounding_boxes(ref bboxes, cseg);
SegmRoutine.make_line_segmentation_white(cseg);
ImgLabels.simple_recolor(cseg);
return(DrawSegmentTranscript(
DrawSegmentNumbers(
ImgRoutine.NarrayToRgbBitmap(cseg),
bboxes),
bboxes,
trans));
}
public override void Charseg(ref Intarray segmentation, Bytearray image)
{
Bytearray timage = new Bytearray();
timage.Copy(image);
//for (int i = 0; i < image.Length(); i++) image[i] = (byte)(image[i] > 0 ? 0 : 1);
OcrRoutine.binarize_simple(timage);
OcrRoutine.Invert(image);
Skeleton.Thin(ref timage);
//ImgIo.write_image_gray("_thinned.png", timage);
ImgMisc.remove_singular_points(ref timage, 2);
//ImgIo.write_image_gray("_segmented.png", timage);
Intarray tsegmentation = new Intarray();
tsegmentation.Copy(timage);
ImgLabels.label_components(ref tsegmentation);
SegmRoutine.remove_small_components(tsegmentation, 4, 4);
//ImgIo.write_image_packed("_labeled.png", tsegmentation);
segmentation.Copy(image);
ImgLabels.propagate_labels_to(ref segmentation, tsegmentation);
//ImgIo.write_image_packed("_propagated.png", segmentation);
}
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 void FindBestCuts()
{
/*Intarray segm = new Intarray();
* segm.Copy(dimage);
* ImgLabels.simple_recolor(segm);
* ImgIo.write_image_packed("debug1.png", segm);*/
unchecked
{
for (int i = 0; i < cutcosts.Length(); i++)
{
NarrayUtil.ExtPut(dimage, i, (int)(cutcosts[i] + 10), 0xff0000);
}
for (int i = 0; i < cutcosts.Length(); i++)
{
NarrayUtil.ExtPut(dimage, i, (int)(min_thresh + 10), 0x800000);
}
}
Floatarray temp = new Floatarray();
Gauss.Gauss1d(temp, cutcosts, cost_smooth);
cutcosts.Move(temp);
SegmRoutine.local_minima(ref bestcuts, cutcosts, min_range, min_thresh);
for (int i = 0; i < bestcuts.Length(); i++)
{
Narray <Point> cut = cuts[bestcuts[i]];
for (int j = 0; j < cut.Length(); j++)
{
Point p = cut[j];
NarrayUtil.ExtPut(dimage, p.X, p.Y, 0x00ff00);
}
}
/*segm.Copy(dimage);
* ImgLabels.simple_recolor(segm);
* ImgIo.write_image_packed("debug2.png", segm);*/
}
public override void Extract(Narray <Floatarray> outarrays, Floatarray inarray)
{
outarrays.Clear();
Floatarray input = new Floatarray();
input.Copy(inarray);
int w = input.Dim(0), h = input.Dim(1);
Floatarray a = new Floatarray(); // working array
int csize = PGeti("csize");
// get rid of small components
SegmRoutine.erase_small_components(input, PGetf("minsize"), PGetf("threshold"));
// compute a thresholded version for morphological operations
Bytearray thresholded = new Bytearray();
OcrRoutine.threshold_frac(thresholded, input, PGetf("threshold"));
// compute a smoothed version of the input for gradient computations
float sigma = PGetf("gradsigma");
Floatarray smoothed = new Floatarray();
smoothed.Copy(input);
Gauss.Gauss2d(smoothed, sigma, sigma);
// x gradient
a.Resize(w, h);
for (int j = 0; j < h; j++)
{
for (int i = 0; i < w; i++)
{
float delta;
if (i == 0)
{
delta = 0f;
}
else
{
delta = smoothed[i, j] - smoothed[i - 1, j];
}
a[i, j] = delta;
}
}
Floatarray xgrad = outarrays.Push(new Floatarray());
OcrRoutine.scale_to(xgrad, a, csize, PGetf("noupscale"), PGetf("aa"));
for (int j = 0; j < csize; j++)
{
for (int i = 0; i < csize; i++)
{
if (j % 2 == 0)
{
xgrad[i, j] = Math.Max(xgrad[i, j], 0f);
}
else
{
xgrad[i, j] = Math.Min(xgrad[i, j], 0f);
}
}
}
// y gradient
a.Resize(w, h);
for (int i = 0; i < w; i++)
{
for (int j = 0; j < h; j++)
{
float delta;
if (j == 0)
{
delta = 0f;
}
else
{
delta = smoothed[i, j] - smoothed[i, j - 1];
}
a[i, j] = delta;
}
}
Floatarray ygrad = outarrays.Push(new Floatarray());
OcrRoutine.scale_to(ygrad, a, csize, PGetf("noupscale"), PGetf("aa"));
for (int i = 0; i < csize; i++)
{
for (int j = 0; j < csize; j++)
{
if (i % 2 == 0)
{
ygrad[i, j] = Math.Max(ygrad[i, j], 0f);
}
else
{
ygrad[i, j] = Math.Min(ygrad[i, j], 0f);
}
}
}
// junctions, endpoints, and holes
Floatarray junctions = new Floatarray();
Floatarray endpoints = new Floatarray();
Floatarray holes = new Floatarray();
Bytearray junctions1 = new Bytearray();
Bytearray endpoints1 = new Bytearray();
Bytearray holes1 = new Bytearray();
Bytearray dilated = new Bytearray();
Bytearray binary = new Bytearray();
junctions.MakeLike(input, 0f);
endpoints.MakeLike(input, 0f);
holes.MakeLike(input, 0f);
int n = PGeti("n");
float step = PGetf("step");
int bs = PGeti("binsmooth");
for (int i = 0; i < n; i++)
{
sigma = step * i;
if (bs > 0)
{
OcrRoutine.binsmooth(binary, input, sigma);
}
else
{
binary.Copy(thresholded);
Morph.binary_dilate_circle(binary, (int)(sigma));
}
OcrRoutine.skeletal_features(endpoints1, junctions1, binary, 0.0f, 0.0f);
NarrayUtil.Greater(junctions1, (byte)0, (byte)0, (byte)1);
junctions.Copy(junctions1);
NarrayUtil.Greater(endpoints1, (byte)0, (byte)0, (byte)1);
endpoints.Copy(endpoints1);
SegmRoutine.extract_holes(ref holes1, binary);
NarrayUtil.Greater(holes1, (byte)0, (byte)0, (byte)1);
holes.Copy(holes1);
}
junctions *= 1.0f / (float)n;
endpoints *= 1.0f / (float)n;
holes *= 1.0f / (float)n;
OcrRoutine.scale_to(outarrays.Push(new Floatarray()), junctions, csize, PGetf("noupscale"), PGetf("aa"));
OcrRoutine.scale_to(outarrays.Push(new Floatarray()), endpoints, csize, PGetf("noupscale"), PGetf("aa"));
OcrRoutine.scale_to(outarrays.Push(new Floatarray()), holes, csize, PGetf("noupscale"), PGetf("aa"));
}
public override void Charseg(ref Intarray segmentation, Bytearray inraw)
{
setParams();
//Logger.Default.Image("segmenting", inraw);
int PADDING = 3;
OcrRoutine.optional_check_background_is_lighter(inraw);
Bytearray image = new Bytearray();
image.Copy(inraw);
OcrRoutine.binarize_simple(image);
OcrRoutine.Invert(image);
SetImage(image);
FindAllCuts();
FindBestCuts();
Intarray seg = new Intarray();
seg.MakeLike(image);
seg.Fill(255);
for (int r = 0; r < bestcuts.Length(); r++)
{
int w = seg.Dim(0);
int c = bestcuts[r];
Narray <Point> cut = cuts[c];
for (int y = 0; y < image.Dim(1); y++)
{
for (int i = -1; i <= 1; i++)
{
int x = cut[y].X;
if (x < 1 || x >= w - 1)
{
continue;
}
seg[x + i, y] = 0;
}
}
}
ImgLabels.label_components(ref seg);
// dshowr(seg,"YY"); dwait();
segmentation.Copy(image);
for (int i = 0; i < seg.Length1d(); i++)
{
if (segmentation.At1d(i) == 0)
{
seg.Put1d(i, 0);
}
}
ImgLabels.propagate_labels_to(ref segmentation, seg);
if (PGeti("component_segmentation") > 0)
{
Intarray ccseg = new Intarray();
ccseg.Copy(image);
ImgLabels.label_components(ref ccseg);
SegmRoutine.combine_segmentations(ref segmentation, ccseg);
if (PGeti("fix_diacritics") > 0)
{
SegmRoutine.fix_diacritics(segmentation);
}
}
#if false
SegmRoutine.line_segmentation_merge_small_components(ref segmentation, small_merge_threshold);
SegmRoutine.line_segmentation_sort_x(segmentation);
#endif
SegmRoutine.make_line_segmentation_white(segmentation);
// set_line_number(segmentation, 1);
//Logger.Default.Image("resulting segmentation", segmentation);
}
public void TestTrainLenetCseg()
{
string bookPath = "data\\0000\\";
string netFileName = "latin-lenet.model";
Linerec.GDef("linerec", "use_reject", 1);
Linerec.GDef("lenet", "junk", 1);
Linerec.GDef("lenet", "epochs", 4);
// create Linerec
Linerec linerec;
if (File.Exists(netFileName))
{
linerec = Linerec.LoadLinerec(netFileName);
}
else
{
linerec = new Linerec("lenet");
LenetClassifier classifier = linerec.GetClassifier() as LenetClassifier;
if (classifier != null)
{
classifier.InitNumSymbLatinAlphabet();
}
}
// temporary disable junk
//linerec.DisableJunk = true;
linerec.StartTraining();
int nepochs = 10;
LineSource lines = new LineSource();
lines.Init(new string[] { "data2" });
//linerec.GetClassifier().Set("epochs", 1);
for (int epoch = 1; epoch <= nepochs; epoch++)
{
linerec.Epoch(epoch);
// load cseg samples
while (!lines.Done())
{
lines.MoveNext();
Intarray cseg = new Intarray();
//Bytearray image = new Bytearray();
string transcript = lines.GetTranscript();
//lines.GetImage(image);
if (!lines.GetCharSegmentation(cseg) && cseg.Length() == 0)
{
Global.Debugf("warn", "skipping book {0} page {1} line {2} (no or bad cseg)",
lines.CurrentBook, lines.CurrentPage, lines.Current);
continue;
}
SegmRoutine.make_line_segmentation_black(cseg);
linerec.AddTrainingLine(cseg, transcript);
}
lines.Reset();
lines.Shuffle();
// do Train and clear Dataset
linerec.FinishTraining();
// do save
if (epoch % 1 == 0)
{
linerec.Save(netFileName);
}
// recognize test line
bool bakDisJunk = linerec.DisableJunk;
linerec.DisableJunk = false;
DoTestLinerecRecognize(linerec, "data2\\", "test1.png");
linerec.DisableJunk = bakDisJunk;
}
// finnaly save
linerec.Save(netFileName);
}
/// <summary>
/// Create char segmentation (cseg) files if missing
/// </summary>
/// <param name="bookPath">path to bookstore</param>
/// <param name="modelFilename">Linerec model file</param>
/// <param name="langModel">language model file</param>
/// <param name="suffix">e.g., 'gt'</param>
public void ComputeMissingCsegForBookStore(string bookPath, string model = "default.model",
string suffix = "", bool saveRseg = false, string langModel = "default.fst")
{
// create line recognizer
Linerec linerec = Linerec.LoadLinerec(model);
// create IBookStore
IBookStore bookstore = new SmartBookStore();
bookstore.SetPrefix(bookPath);
bookstore.Info();
// language model
OcroFST lmodel = OcroFST.MakeOcroFst();
lmodel.Load(langModel);
// iterate lines of pages
for (int page = 0; page < bookstore.NumberOfPages(); page++)
{
int nlines = bookstore.LinesOnPage(page);
Console.WriteLine("Page {0} has {1} lines", page, nlines);
for (int j = 0; j < nlines; j++)
{
int line = bookstore.GetLineId(page, j);
Bytearray image = new Bytearray();
bookstore.GetLine(image, page, line);
Intarray cseg = new Intarray();
bookstore.GetCharSegmentation(cseg, page, line, suffix);
// check missing cseg file
if (cseg.Length() <= 0 && image.Length() > 0)
{
// recognize line
OcroFST fst = OcroFST.MakeOcroFst();
Intarray rseg = new Intarray();
linerec.RecognizeLine(rseg, fst, image);
// find best results
string resText;
Intarray inp = new Intarray();
Floatarray costs = new Floatarray();
double totalCost = BeamSearch.beam_search(out resText, inp, costs, fst, lmodel, 100);
Console.WriteLine(bookstore.PathFile(page, line, suffix));
Console.Write(" beam_search score: {0}", totalCost);
/*string resText2;
* fst.BestPath(out resText2);*/
// write cseg to bookstore
string trans;
bookstore.GetLine(out trans, page, line, suffix);
resText = resText.Replace(" ", "");
if (String.IsNullOrEmpty(trans))
{
bookstore.PutLine(resText, page, line, suffix);
Console.Write("; transcript saved");
}
else if (trans == resText)
{
// convert inputs and rseg to cseg
SegmRoutine.rseg_to_cseg(cseg, rseg, inp);
bookstore.PutCharSegmentation(cseg, page, line, suffix);
Console.Write("; cseg saved");
}
else if (saveRseg)
{
// convert inputs and rseg to cseg
SegmRoutine.rseg_to_cseg(cseg, rseg, inp);
//SegmRoutine.remove_small_components(cseg, 4);
/*bookstore.PutCharSegmentation(cseg, page, line, suffix);
* Console.Write("; cseg saved");*/
SegmRoutine.make_line_segmentation_white(cseg);
ImgLabels.simple_recolor(cseg);
string v = "rseg";
if (!String.IsNullOrEmpty(suffix))
{
v += "."; v += suffix;
}
string rsegpath = bookstore.PathFile(page, line, v, "png");
ImgIo.write_image_packed(rsegpath, cseg);
Console.Write("; rseg saved");
}
Console.WriteLine();
}
}
}
}
