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 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 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 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 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 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 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 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);
}
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));*/
}
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);
}