/// <summary>
/// Set a segmentation.
/// </summary>
public override void SetSegmentation(Intarray segmentation)
{
maxrange = PGeti("maxrange");
maxdist = PGeti("maxdist");
fullheight = PGetb("fullheight");
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 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 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]);
}
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]);
}
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 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 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);
}
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 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 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);
}
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 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 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;
}
}
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;
}
}
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 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 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);
}
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 void EstimateSpaceSize()
{
Intarray labels = new Intarray();
labels.Copy(segmentation);
ImgLabels.label_components(ref labels);
Narray <Rect> boxes = new Narray <Rect>();
ImgLabels.bounding_boxes(ref boxes, labels);
Floatarray distances = new Floatarray();
distances.Resize(boxes.Length());
distances.Fill(99999f);
for (int i = 1; i < boxes.Length(); i++)
{
Rect b = boxes[i];
for (int j = 1; j < boxes.Length(); j++)
{
Rect n = boxes[j];
int delta = n.x0 - b.x1;
if (delta < 0)
{
continue;
}
if (delta >= distances[i])
{
continue;
}
distances[i] = delta;
}
}
float interchar = NarrayUtil.Fractile(distances, PGetf("space_fractile"));
space_threshold = interchar * PGetf("space_multiplier");
// impose some reasonable upper and lower bounds
float xheight = 10.0f; // FIXME
space_threshold = Math.Max(space_threshold, PGetf("space_min") * xheight);
space_threshold = Math.Min(space_threshold, PGetf("space_max") * xheight);
}
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);
}
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 static void remove_small_components <T>(Narray <T> bimage, int mw, int mh)
{
Intarray image = new Intarray();
image.Copy(bimage);
ImgLabels.label_components(ref image);
Narray <Rect> rects = new Narray <Rect>();
ImgLabels.bounding_boxes(ref rects, image);
Bytearray good = new Bytearray(rects.Length());
for (int i = 0; i < good.Length(); i++)
{
good[i] = 1;
}
for (int i = 0; i < rects.Length(); i++)
{
if (rects[i].Width() < mw && rects[i].Height() < mh)
{
// printf("*** %d %d %d\n",i,rects[i].width(),rects[i].height());
good[i] = 0;
}
}
for (int i = 0; i < image.Length1d(); i++)
{
if (good[image.At1d(i)] == 0)
{
image.Put1d(i, 0);
}
}
for (int i = 0; i < image.Length1d(); i++)
{
if (image.At1d(i) == 0)
{
bimage.Put1d(i, default(T)); // default(T) - 0
}
}
}
public static void extract_holes(ref Bytearray holes, Bytearray binarized)
{
Intarray temp = new Intarray();
temp.Copy(binarized);
NarrayUtil.Sub(255, temp);
ImgLabels.label_components(ref temp);
int background = -1;
for (int i = 0; i < temp.Dim(0); i++)
{
if (temp[i, 0] != 0)
{
background = temp[i, 0];
break;
}
}
holes.MakeLike(temp);
holes.Fill((byte)0);
if (background <= 0)
{
throw new Exception("extract_holes: background must be more 0");
}
for (int i = 0; i < temp.Dim(0); i++)
{
for (int j = 0; j < temp.Dim(1); j++)
{
if (temp[i, j] > 0 && temp[i, j] != background)
{
holes[i, j] = 255;
}
}
}
/*fprintf(stderr, "segholes\n");
* dsection("segholes");
* dshow(holes, "y");*/
}
public override void SetImage(Bytearray image)
{
dimage.Copy(image);
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 - 1, j] == 0 && image[i, j] > 0)
{
wimage[i, j] = boundary_weight;
}
else if (image[i, j] > 0)
{
wimage[i, j] = inside_weight;
}
else
{
wimage[i, j] = outside_weight;
}
}
}
where = (int)(sy / s1);
for (int i = 0; i < dimage.Dim(0); i++)
{
dimage[i, where] = 0x008000;
}
}
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);
}
/// <summary>
/// Return a list of all segments
/// </summary>
public override void GetSegments(Intarray result, int index)
{
result.Copy(segments[index]);
}
public void EstimateSpaceSize()
{
Intarray labels = new Intarray();
labels.Copy(segmentation);
ImgLabels.label_components(ref labels);
Narray<Rect> boxes = new Narray<Rect>();
ImgLabels.bounding_boxes(ref boxes, labels);
Floatarray distances = new Floatarray();
distances.Resize(boxes.Length());
distances.Fill(99999f);
for (int i = 1; i < boxes.Length(); i++)
{
Rect b = boxes[i];
for (int j = 1; j < boxes.Length(); j++)
{
Rect n = boxes[j];
int delta = n.x0 - b.x1;
if (delta < 0) continue;
if (delta >= distances[i]) continue;
distances[i] = delta;
}
}
float interchar = NarrayUtil.Fractile(distances, PGetf("space_fractile"));
space_threshold = interchar * PGetf("space_multiplier");
// impose some reasonable upper and lower bounds
float xheight = 10.0f; // FIXME
space_threshold = Math.Max(space_threshold, PGetf("space_min") * xheight);
space_threshold = Math.Min(space_threshold, PGetf("space_max") * xheight);
}
/// <summary>
/// This is a weird, optional method that exposes character segmentation
/// for those line recognizers that have it segmentation contains colored pixels,
/// and a transition in the transducer of the form * --- 1/eps --> * --- 2/a --> *
/// means that pixels with color 1 and 2 together form the letter "a"
/// </summary>
public override double RecognizeLine(Intarray segmentation_, IGenericFst result, Bytearray image_)
{
double rate = 0.0;
CHECK_ARG(image_.Dim(1) < PGeti("maxheight"),
String.Format("input line too high ({0} x {1})", image_.Dim(0), image_.Dim(1)));
CHECK_ARG(image_.Dim(1) * 1.0 / image_.Dim(0) < PGetf("maxaspect"),
String.Format("input line has bad aspect ratio ({0} x {1})", image_.Dim(0), image_.Dim(1)));
bool use_reject = PGetb("use_reject") && !DisableJunk;
//Console.WriteLine("IMG: imin:{0} imax:{1}", NarrayUtil.ArgMin(image_), NarrayUtil.ArgMax(image_));
Bytearray image = new Bytearray();
image.Copy(image_);
SetLine(image_);
if (PGeti("invert") > 0)
NarrayUtil.Sub(NarrayUtil.Max(image), image);
segmentation_.Copy(segmentation);
Bytearray available = new Bytearray();
Floatarray cp = new Floatarray();
Floatarray ccosts = new Floatarray();
Floatarray props = new Floatarray();
OutputVector p = new OutputVector();
int ncomponents = grouper.Object.Length();
int minclass = PGeti("minclass");
float minprob = PGetf("minprob");
float space_yes = PGetf("space_yes");
float space_no = PGetf("space_no");
float maxcost = PGetf("maxcost");
// compute priors if possible; fall back on
// using no priors if no counts are available
Floatarray priors = new Floatarray();
bool use_priors = PGeti("use_priors") > 0;
if (use_priors)
{
if (counts.Length() > 0)
{
priors.Copy(counts);
priors /= NarrayUtil.Sum(priors);
}
else
{
if (!counts_warned)
Global.Debugf("warn", "use_priors specified but priors unavailable (old model)");
use_priors = false;
counts_warned = true;
}
}
EstimateSpaceSize();
for (int i = 0; i < ncomponents; i++)
{
Rect b;
Bytearray mask = new Bytearray();
grouper.Object.GetMask(out b, ref mask, i, 0);
Bytearray cv = new Bytearray();
grouper.Object.ExtractWithMask(cv, mask, image, i, 0);
//ImgIo.write_image_gray("extrmask_image.png", cv);
Floatarray v = new Floatarray();
v.Copy(cv);
v /= 255.0f;
float ccost = classifier.Object.XOutputs(p, v);
if (use_reject && classifier.Object.HigherOutputIsBetter)
{
ccost = 0;
float total = p.Sum();
if (total > 1e-11f)
{
//p /= total;
}
else
p.Values.Fill(0.0f);
}
int count = 0;
Global.Debugf("dcost", "output {0}", p.Keys.Length());
for (int index = 0; index < p.Keys.Length(); index++)
{
int j = p.Keys[index];
if (j < minclass) continue;
if (j == reject_class) continue;
float value = p.Values[index];
if (value <= 0.0f) continue;
if (value < minprob) continue;
float pcost = classifier.Object.HigherOutputIsBetter ? (float)-Math.Log(value) : value;
Global.Debugf("dcost", "{0} {1} {2}", j, pcost + ccost, (j > 32 ? (char)j : '_'));
float total_cost = pcost + ccost;
if (total_cost < maxcost)
{
if (use_priors)
{
total_cost -= (float)-Math.Log(priors[j]);
}
grouper.Object.SetClass(i, j, total_cost);
count++;
}
}
Global.Debugf("dcost", "");
if (count == 0)
{
float xheight = 10.0f;
if (b.Height() < xheight / 2 && b.Width() < xheight / 2)
{
grouper.Object.SetClass(i, (int)'~', high_cost / 2);
}
else
{
grouper.Object.SetClass(i, (int)'#', (b.Width() / xheight) * high_cost);
}
}
if (grouper.Object.PixelSpace(i) > space_threshold)
{
Global.Debugf("spaces", "space {0}", grouper.Object.PixelSpace(i));
grouper.Object.SetSpaceCost(i, space_yes, space_no);
}
}
grouper.Object.GetLattice(result);
return rate;
}
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 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);
}
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);
}
/// <summary>
/// This is a weird, optional method that exposes character segmentation
/// for those line recognizers that have it segmentation contains colored pixels,
/// and a transition in the transducer of the form * --- 1/eps --> * --- 2/a --> *
/// means that pixels with color 1 and 2 together form the letter "a"
/// </summary>
public override double RecognizeLine(Intarray segmentation_, IGenericFst result, Bytearray image_)
{
double rate = 0.0;
CHECK_ARG(image_.Dim(1) < PGeti("maxheight"),
String.Format("input line too high ({0} x {1})", image_.Dim(0), image_.Dim(1)));
CHECK_ARG(image_.Dim(1) * 1.0 / image_.Dim(0) < PGetf("maxaspect"),
String.Format("input line has bad aspect ratio ({0} x {1})", image_.Dim(0), image_.Dim(1)));
bool use_reject = PGetb("use_reject") && !DisableJunk;
//Console.WriteLine("IMG: imin:{0} imax:{1}", NarrayUtil.ArgMin(image_), NarrayUtil.ArgMax(image_));
Bytearray image = new Bytearray();
image.Copy(image_);
SetLine(image_);
if (PGeti("invert") > 0)
{
NarrayUtil.Sub(NarrayUtil.Max(image), image);
}
segmentation_.Copy(segmentation);
Bytearray available = new Bytearray();
Floatarray cp = new Floatarray();
Floatarray ccosts = new Floatarray();
Floatarray props = new Floatarray();
OutputVector p = new OutputVector();
int ncomponents = grouper.Object.Length();
int minclass = PGeti("minclass");
float minprob = PGetf("minprob");
float space_yes = PGetf("space_yes");
float space_no = PGetf("space_no");
float maxcost = PGetf("maxcost");
// compute priors if possible; fall back on
// using no priors if no counts are available
Floatarray priors = new Floatarray();
bool use_priors = PGeti("use_priors") > 0;
if (use_priors)
{
if (counts.Length() > 0)
{
priors.Copy(counts);
priors /= NarrayUtil.Sum(priors);
}
else
{
if (!counts_warned)
{
Global.Debugf("warn", "use_priors specified but priors unavailable (old model)");
}
use_priors = false;
counts_warned = true;
}
}
EstimateSpaceSize();
for (int i = 0; i < ncomponents; i++)
{
Rect b;
Bytearray mask = new Bytearray();
grouper.Object.GetMask(out b, ref mask, i, 0);
Bytearray cv = new Bytearray();
grouper.Object.ExtractWithMask(cv, mask, image, i, 0);
//ImgIo.write_image_gray("extrmask_image.png", cv);
Floatarray v = new Floatarray();
v.Copy(cv);
v /= 255.0f;
float ccost = classifier.Object.XOutputs(p, v);
if (use_reject && classifier.Object.HigherOutputIsBetter)
{
ccost = 0;
float total = p.Sum();
if (total > 1e-11f)
{
//p /= total;
}
else
{
p.Values.Fill(0.0f);
}
}
int count = 0;
Global.Debugf("dcost", "output {0}", p.Keys.Length());
for (int index = 0; index < p.Keys.Length(); index++)
{
int j = p.Keys[index];
if (j < minclass)
{
continue;
}
if (j == reject_class)
{
continue;
}
float value = p.Values[index];
if (value <= 0.0f)
{
continue;
}
if (value < minprob)
{
continue;
}
float pcost = classifier.Object.HigherOutputIsBetter ? (float)-Math.Log(value) : value;
Global.Debugf("dcost", "{0} {1} {2}", j, pcost + ccost, (j > 32 ? (char)j : '_'));
float total_cost = pcost + ccost;
if (total_cost < maxcost)
{
if (use_priors)
{
total_cost -= (float)-Math.Log(priors[j]);
}
grouper.Object.SetClass(i, j, total_cost);
count++;
}
}
Global.Debugf("dcost", "");
if (count == 0)
{
float xheight = 10.0f;
if (b.Height() < xheight / 2 && b.Width() < xheight / 2)
{
grouper.Object.SetClass(i, (int)'~', high_cost / 2);
}
else
{
grouper.Object.SetClass(i, (int)'#', (b.Width() / xheight) * high_cost);
}
}
if (grouper.Object.PixelSpace(i) > space_threshold)
{
Global.Debugf("spaces", "space {0}", grouper.Object.PixelSpace(i));
grouper.Object.SetSpaceCost(i, space_yes, space_no);
}
}
grouper.Object.GetLattice(result);
return(rate);
}
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);
}
