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 void rescale(Floatarray outv, Floatarray sub)
{
if (sub.Rank() != 2)
{
throw new Exception("CHECK_ARG: sub.Rank()==2");
}
int csize = PGeti("csize");
int indent = PGeti("indent");
float s = Math.Max(sub.Dim(0), sub.Dim(1)) / (float)(csize - indent - indent);
if (PGeti("noupscale") > 0 && s < 1.0f)
{
s = 1.0f;
}
float sig = s * PGetf("aa");
float dx = (csize * s - sub.Dim(0)) / 2;
float dy = (csize * s - sub.Dim(1)) / 2;
if (sig > 1e-3f)
{
Gauss.Gauss2d(sub, sig, sig);
}
outv.Resize(csize, csize);
outv.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);
outv[i, j] = value;
}
}
/*Global.Debugf("fe", "{0} {1} ({2}) -> {3} {4} ({5})\n",
* sub.Dim(0), sub.Dim(1), NarrayUtil.Max(sub),
* outv.Dim(0), outv.Dim(1), NarrayUtil.Max(outv));*/
}
public static void scale_to(Floatarray v, Floatarray sub, int csize, float noupscale = 1.0f, float aa = 1.0f)
{
// compute the scale factor
float s = Math.Max(sub.Dim(0), sub.Dim(1)) / (float)csize;
// don't upscale if that's prohibited
if (s < noupscale)
{
s = 1.0f;
}
// compute the offset to keep the input centered in the output
float dx = (csize * s - sub.Dim(0)) / 2;
float dy = (csize * s - sub.Dim(1)) / 2;
// antialiasing via Gaussian convolution
float sig = s * aa;
if (sig > 1e-3f)
{
Gauss.Gauss2d(sub, sig, sig);
}
// now compute the output image via bilinear interpolation
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;
}
}
}
private static string Upload(string img, bool useImgur)
{
string imgUrl;
if (useImgur)
{
CliOutput.WriteInfo("Using Imgur for image upload");
var imgur = new Imgur();
imgUrl = imgur.Upload(img);
}
else
{
CliOutput.WriteInfo("Using ImgOps for image upload (2 hour cache)");
var imgOps = new ImgOps();
imgUrl = imgOps.UploadTempImage(img, out _);
}
return(imgUrl);
}
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));*/
}
