public static int average_on_border(Bytearray a)
{
int sum = 0;
int right = a.Dim(0) - 1;
int top = a.Dim(1) - 1;
for (int x = 0; x < a.Dim(0); x++)
{
sum += a[x, 0];
}
for (int x = 0; x < a.Dim(0); x++)
{
sum += a[x, top];
}
for (int y = 1; y < top; y++)
{
sum += a[0, y];
}
for (int y = 1; y < top; y++)
{
sum += a[right, y];
}
// If average border intensity is between 127-128, inverting the
// image does not work correctly
float average_border_intensity = sum / ((right + top) * 2.0f);
if (!(average_border_intensity <= 127 || average_border_intensity >= 128))
{
Console.WriteLine("average border intensity is between 127-128, inverting the image does not work correctly");
}
return(sum / ((right + top) * 2));
}
public static void binary_and(Bytearray image, Bytearray image2, int dx, int dy)
{
int w = image.Dim(0);
int h = image.Dim(1);
for (int i = 0; i < w; i++)
for (int j = 0; j < h; j++)
image[i, j] = Math.Min(image[i, j], NarrayUtil.Ext(image2, i - dx, j - dy));
}
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 static void Thin(ref Bytearray uci)
{
int w = uci.Dim(0) - 1;
int h = uci.Dim(1) - 1;
for (int i = 0, n = uci.Length1d(); i < n; i++)
{
if (uci.At1d(i) > 0)
uci.Put1d(i, ON);
else
uci.Put1d(i, OFF);
}
bool flag;
do
{
flag = false;
for (int j = 0; j < 8; j += 2)
{
for (int x = 1; x < w; x++)
for (int y = 1; y < h; y++)
{
if (uci[x, y] != ON)
continue;
if (uci[x + nx[j], y + ny[j]] != OFF)
continue;
int b = 0;
for (int i = 7; i >= 0; i--)
{
b <<= 1;
b |= (uci[x + nx[i], y + ny[i]] != OFF ? 1 : 0);
}
if (ttable[b] > 0)
uci[x, y] = SKEL;
else
{
uci[x, y] = DEL;
flag = true;
}
}
if (!flag)
continue;
for (int x = 1; x < w; x++)
for (int y = 1; y < h; y++)
if (uci[x, y] == DEL)
uci[x, y] = OFF;
}
} while (flag);
for (int i = 0, n = uci.Length1d(); i < n; i++)
{
if (uci.At1d(i) == SKEL)
uci.Put1d(i, 255);
else
uci.Put1d(i, 0);
}
}
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 static void binary_or(Bytearray image, Bytearray image2, int dx, int dy)
{
int w = image.Dim(0);
int h = image.Dim(1);
for (int i = 0; i < w; i++)
{
for (int j = 0; j < h; j++)
{
image[i, j] = Math.Max(image[i, j], NarrayUtil.Ext(image2, i - dx, j - dy));
}
}
}
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 void RunTest()
{
IBookStore bstore = new SmartBookStore();
bstore.SetPrefix(@"data2");
Console.WriteLine("Pages in bookstore: {0}", bstore.NumberOfPages());
Console.WriteLine("List pages..");
for (int i = 0; i < bstore.NumberOfPages(); i++)
{
Console.WriteLine("page {0:0000}\t->\t{1,6} lines", i, bstore.LinesOnPage(i));
}
Bytearray line = new Bytearray();
bstore.GetLine(line, 1, 5);
Console.WriteLine("line{0} [{1},{2}]", 5, line.Dim(0), line.Dim(1));
Intarray cline = new Intarray();
bstore.GetCharSegmentation(cline, 1, 5);
Console.WriteLine("line{0}.cseg [{1},{2}]", 5, cline.Dim(0), cline.Dim(1));
}
/// <summary>
/// Remove singular points over image.
/// uses in skeleton segmenter
/// </summary>
public static void remove_singular_points(ref Bytearray image, int d)
{
for (int i = d; i < image.Dim(0) - d - 1; i++)
{
for (int j = d; j < image.Dim(1) - d - 1; j++)
{
if (is_singular(image, i, j))
{
for (int k = -d; k <= d; k++)
{
for (int l = -d; l <= d; l++)
{
image[i + k, j + l] = 0;
}
}
}
}
}
}
public static int average_on_border(Bytearray a)
{
int sum = 0;
int right = a.Dim(0) - 1;
int top = a.Dim(1) - 1;
for(int x = 0; x < a.Dim(0); x++)
sum += a[x, 0];
for(int x = 0; x < a.Dim(0); x++)
sum += a[x, top];
for(int y = 1; y < top; y++)
sum += a[0, y];
for(int y = 1; y < top; y++)
sum += a[right, y];
// If average border intensity is between 127-128, inverting the
// image does not work correctly
float average_border_intensity = sum / ((right + top) * 2.0f);
if (!(average_border_intensity <= 127 || average_border_intensity >= 128))
Console.WriteLine("average border intensity is between 127-128, inverting the image does not work correctly");
return sum / ((right + top) * 2);
}
public void RunTest()
{
IBookStore bstore = new SmartBookStore();
bstore.SetPrefix(@"data2");
Console.WriteLine("Pages in bookstore: {0}", bstore.NumberOfPages());
Console.WriteLine("List pages..");
for (int i = 0; i < bstore.NumberOfPages(); i++)
{
Console.WriteLine("page {0:0000}\t->\t{1,6} lines", i, bstore.LinesOnPage(i));
}
Bytearray line = new Bytearray();
bstore.GetLine(line, 1, 5);
Console.WriteLine("line{0} [{1},{2}]", 5, line.Dim(0), line.Dim(1));
Intarray cline = new Intarray();
bstore.GetCharSegmentation(cline, 1, 5);
Console.WriteLine("line{0}.cseg [{1},{2}]", 5, cline.Dim(0), cline.Dim(1));
}
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 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)
{
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 static int neighbors(Bytearray image, int i, int j)
{
if (i < 1 || i >= image.Dim(0) - 1 || j < 1 || j > image.Dim(1) - 1)
{
return(0);
}
if (image[i, j] == 0)
{
return(0);
}
int count = -1;
for (int k = -1; k <= 1; k++)
{
for (int l = -1; l <= 1; l++)
{
if (image[i + k, j + l] > 0)
{
count++;
}
}
}
return(count);
}
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)
{
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);
}
/// <summary>
/// Train on a text line, given a segmentation.
/// <remarks>This is analogous to addTrainingLine(bytearray,nustring) except that
/// it takes the "ground truth" line segmentation.</remarks>
/// </summary>
public override bool AddTrainingLine(Intarray cseg, Bytearray image_grayscale, string tr)
{
Bytearray image = new Bytearray();
image.Copy(image_grayscale);
if (String.IsNullOrEmpty(tr))
{
Global.Debugf("error", "input transcript is empty");
return false;
}
if (image.Dim(0) < PGeti("minheight"))
{
Global.Debugf("error", "input line too small ({0} x {1})", image.Dim(0), image.Dim(1));
return false;
}
if (image.Dim(1) > PGeti("maxheight"))
{
Global.Debugf("error", "input line too high ({0} x {1})", image.Dim(0), image.Dim(1));
return false;
}
if (image.Dim(1) * 1.0 / image.Dim(0) > PGetf("maxaspect"))
{
Global.Debugf("warn", "input line has bad aspect ratio ({0} x {1})", image.Dim(0), image.Dim(1));
return false;
}
CHECK_ARG(image.Dim(0) == cseg.Dim(0) && image.Dim(1) == cseg.Dim(1),
"image.Dim(0) == cseg.Dim(0) && image.Dim(1) == cseg.Dim(1)");
bool use_reject = PGetb("use_reject") && !DisableJunk;
// check and set the transcript
transcript = tr;
SetLine(image_grayscale);
if (PGeti("invert") > 0)
NarrayUtil.Sub(NarrayUtil.Max(image), image);
for (int i = 0; i < transcript.Length; i++)
CHECK_ARG((int)transcript[i] >= 32, "(int)transcript[i] >= 32");
// compute correspondences between actual segmentation and
// ground truth segmentation
Narray<Intarray> segments = new Narray<Intarray>();
GrouperRoutine.segmentation_correspondences(segments, segmentation, cseg);
// now iterate through all the hypothesis segments and
// train the classifier with them
int total = 0;
int junk = 0;
for (int i = 0; i < grouper.Object.Length(); i++)
{
Intarray segs = new Intarray();
grouper.Object.GetSegments(segs, i);
// see whether this is a ground truth segment
int match = -1;
for (int j = 0; j < segments.Length(); j++)
{
if (GrouperRoutine.Equals(segments[j], segs))
{
match = j;
break;
}
}
match -= 1; // segments are numbered starting at 1
int c = reject_class;
if (match >= 0)
{
if (match >= transcript.Length)
{
Global.Debugf("error", "mismatch between transcript and cseg: {0}", transcript);
continue;
}
else
{
c = (int)transcript[match];
Global.Debugf("debugmismatch", "index {0} position {1} char {2} [{3}]", i, match, (char)c, c);
}
}
if (c == reject_class)
junk++;
// extract the character and add it to the classifier
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);
Floatarray v = new Floatarray();
v.Copy(cv);
v /= 255.0;
Global.Debugf("cdim", "character dimensions ({0},{1})", v.Dim(0), v.Dim(1));
total++;
if (use_reject)
{
classifier.Object.XAdd(v, c);
}
else
{
if (c != reject_class)
classifier.Object.XAdd(v, c);
}
if (c != reject_class)
IncClass(c);
ntrained++;
}
Global.Debugf("detail", "AddTrainingLine trained {0} chars, {1} junk", total - junk, junk);
return true;
}
public override void Binarize(Bytearray bin_image, Bytearray gray_image)
{
w = PGeti("w");
k = (float)PGetf("k");
whalf = w >> 1;
// fprintf(stderr,"[sauvola %g %d]\n",k,w);
if (k < 0.001 || k > 0.999)
{
throw new Exception("Binarize: CHECK_ARG(k>=0.001 && k<=0.999)");
}
if (w == 0 || k >= 1000)
{
throw new Exception("Binarize: CHECK_ARG(w>0 && k<1000)");
}
if (bin_image.Length1d() != gray_image.Length1d())
{
bin_image.MakeLike(gray_image);
}
if (NarrayUtil.contains_only(gray_image, (byte)0, (byte)255))
{
bin_image.Copy(gray_image);
return;
}
int image_width = gray_image.Dim(0);
int image_height = gray_image.Dim(1);
whalf = w >> 1;
// Calculate the integral image, and integral of the squared image
Narray <long> integral_image = new Narray <long>(), rowsum_image = new Narray <long>();
Narray <long> integral_sqimg = new Narray <long>(), rowsum_sqimg = new Narray <long>();
integral_image.MakeLike(gray_image);
rowsum_image.MakeLike(gray_image);
integral_sqimg.MakeLike(gray_image);
rowsum_sqimg.MakeLike(gray_image);
int xmin, ymin, xmax, ymax;
double diagsum, idiagsum, diff, sqdiagsum, sqidiagsum, sqdiff, area;
double mean, std, threshold;
for (int j = 0; j < image_height; j++)
{
rowsum_image[0, j] = gray_image[0, j];
rowsum_sqimg[0, j] = gray_image[0, j] * gray_image[0, j];
}
for (int i = 1; i < image_width; i++)
{
for (int j = 0; j < image_height; j++)
{
rowsum_image[i, j] = rowsum_image[i - 1, j] + gray_image[i, j];
rowsum_sqimg[i, j] = rowsum_sqimg[i - 1, j] + gray_image[i, j] * gray_image[i, j];
}
}
for (int i = 0; i < image_width; i++)
{
integral_image[i, 0] = rowsum_image[i, 0];
integral_sqimg[i, 0] = rowsum_sqimg[i, 0];
}
for (int i = 0; i < image_width; i++)
{
for (int j = 1; j < image_height; j++)
{
integral_image[i, j] = integral_image[i, j - 1] + rowsum_image[i, j];
integral_sqimg[i, j] = integral_sqimg[i, j - 1] + rowsum_sqimg[i, j];
}
}
//Calculate the mean and standard deviation using the integral image
for (int i = 0; i < image_width; i++)
{
for (int j = 0; j < image_height; j++)
{
xmin = Math.Max(0, i - whalf);
ymin = Math.Max(0, j - whalf);
xmax = Math.Min(image_width - 1, i + whalf);
ymax = Math.Min(image_height - 1, j + whalf);
area = (xmax - xmin + 1) * (ymax - ymin + 1);
// area can't be 0 here
// proof (assuming whalf >= 0):
// we'll prove that (xmax-xmin+1) > 0,
// (ymax-ymin+1) is analogous
// It's the same as to prove: xmax >= xmin
// image_width - 1 >= 0 since image_width > i >= 0
// i + whalf >= 0 since i >= 0, whalf >= 0
// i + whalf >= i - whalf since whalf >= 0
// image_width - 1 >= i - whalf since image_width > i
// --IM
if (area <= 0)
{
throw new Exception("Binarize: area can't be 0 here");
}
if (xmin == 0 && ymin == 0)
{ // Point at origin
diff = integral_image[xmax, ymax];
sqdiff = integral_sqimg[xmax, ymax];
}
else if (xmin == 0 && ymin > 0)
{ // first column
diff = integral_image[xmax, ymax] - integral_image[xmax, ymin - 1];
sqdiff = integral_sqimg[xmax, ymax] - integral_sqimg[xmax, ymin - 1];
}
else if (xmin > 0 && ymin == 0)
{ // first row
diff = integral_image[xmax, ymax] - integral_image[xmin - 1, ymax];
sqdiff = integral_sqimg[xmax, ymax] - integral_sqimg[xmin - 1, ymax];
}
else
{ // rest of the image
diagsum = integral_image[xmax, ymax] + integral_image[xmin - 1, ymin - 1];
idiagsum = integral_image[xmax, ymin - 1] + integral_image[xmin - 1, ymax];
diff = diagsum - idiagsum;
sqdiagsum = integral_sqimg[xmax, ymax] + integral_sqimg[xmin - 1, ymin - 1];
sqidiagsum = integral_sqimg[xmax, ymin - 1] + integral_sqimg[xmin - 1, ymax];
sqdiff = sqdiagsum - sqidiagsum;
}
mean = diff / area;
std = Math.Sqrt((sqdiff - diff * diff / area) / (area - 1));
threshold = mean * (1 + k * ((std / 128) - 1));
if (gray_image[i, j] < threshold)
{
bin_image[i, j] = 0;
}
else
{
bin_image[i, j] = (byte)(MAXVAL - 1);
}
}
}
if (PGeti("debug_binarize") > 0)
{
ImgIo.write_image_gray("debug_binarize.png", bin_image);
}
}
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 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 override void Binarize(Bytearray bin_image, Bytearray gray_image)
{
if(bin_image.Length1d() != gray_image.Length1d())
bin_image.MakeLike(gray_image);
if(NarrayUtil.contains_only(gray_image, (byte)0, (byte)255))
{
bin_image.Copy(gray_image);
return;
}
int image_width = gray_image.Dim(0);
int image_height = gray_image.Dim(1);
int[] hist = new int[MAXVAL];
double[] pdf = new double[MAXVAL]; //probability distribution
double[] cdf = new double[MAXVAL]; //cumulative probability distribution
double[] myu = new double[MAXVAL]; // mean value for separation
double max_sigma;
double[] sigma = new double[MAXVAL]; // inter-class variance
/* Histogram generation */
for(int i=0; i<MAXVAL; i++){
hist[i] = 0;
}
for(int x=0; x<image_width; x++){
for(int y=0; y<image_height; y++){
hist[gray_image[x,y]]++;
}
}
/* calculation of probability density */
for(int i=0; i<MAXVAL; i++){
pdf[i] = (double)hist[i] / (image_width * image_height);
}
/* cdf & myu generation */
cdf[0] = pdf[0];
myu[0] = 0.0; /* 0.0 times prob[0] equals zero */
for(int i=1; i<MAXVAL; i++){
cdf[i] = cdf[i-1] + pdf[i];
myu[i] = myu[i-1] + i*pdf[i];
}
/* sigma maximization
sigma stands for inter-class variance
and determines optimal threshold value */
int threshold = 0;
max_sigma = 0.0;
for(int i=0; i<MAXVAL-1; i++){
if(cdf[i] != 0.0 && cdf[i] != 1.0){
double p1p2 = cdf[i]*(1.0 - cdf[i]);
double mu1mu2diff = myu[MAXVAL-1]*cdf[i]-myu[i];
sigma[i] = mu1mu2diff * mu1mu2diff / p1p2;
}
else
sigma[i] = 0.0;
if(sigma[i] > max_sigma){
max_sigma = sigma[i];
threshold = i;
}
}
for(int x=0; x<image_width; x++){
for(int y=0; y<image_height; y++){
if (gray_image[x,y] > threshold)
bin_image[x,y] = (byte)(MAXVAL-1);
else
bin_image[x,y] = 0;
}
}
if(PGeti("debug_otsu") > 0) {
Logger.Default.Format("Otsu threshold value = {0}\n", threshold);
//ImgIo.write_image_gray("debug_otsu.png", bin_image);
}
}
public void Image(string description, Bytearray a, float zoom = 100f)
{
if (verbose)
{
writer.WriteLine(String.Format("image {0} w:{1}, h:{2}", description, a.Dim(0), a.Dim(1)));
}
}
public void Image(string description, Bytearray a, float zoom = 100f)
{
if (verbose)
writer.WriteLine(String.Format("image {0} w:{1}, h:{2}", description, a.Dim(0), a.Dim(1)));
}
public static void Thin(ref Bytearray uci)
{
int w = uci.Dim(0) - 1;
int h = uci.Dim(1) - 1;
for (int i = 0, n = uci.Length1d(); i < n; i++)
{
if (uci.At1d(i) > 0)
{
uci.Put1d(i, ON);
}
else
{
uci.Put1d(i, OFF);
}
}
bool flag;
do
{
flag = false;
for (int j = 0; j < 8; j += 2)
{
for (int x = 1; x < w; x++)
{
for (int y = 1; y < h; y++)
{
if (uci[x, y] != ON)
{
continue;
}
if (uci[x + nx[j], y + ny[j]] != OFF)
{
continue;
}
int b = 0;
for (int i = 7; i >= 0; i--)
{
b <<= 1;
b |= (uci[x + nx[i], y + ny[i]] != OFF ? 1 : 0);
}
if (ttable[b] > 0)
{
uci[x, y] = SKEL;
}
else
{
uci[x, y] = DEL;
flag = true;
}
}
}
if (!flag)
{
continue;
}
for (int x = 1; x < w; x++)
{
for (int y = 1; y < h; y++)
{
if (uci[x, y] == DEL)
{
uci[x, y] = OFF;
}
}
}
}
} while (flag);
for (int i = 0, n = uci.Length1d(); i < n; i++)
{
if (uci.At1d(i) == SKEL)
{
uci.Put1d(i, 255);
}
else
{
uci.Put1d(i, 0);
}
}
}
/// <summary>
/// Train on a text line, given a segmentation.
/// <remarks>This is analogous to addTrainingLine(bytearray,nustring) except that
/// it takes the "ground truth" line segmentation.</remarks>
/// </summary>
public override bool AddTrainingLine(Intarray cseg, Bytearray image_grayscale, string tr)
{
Bytearray image = new Bytearray();
image.Copy(image_grayscale);
if (String.IsNullOrEmpty(tr))
{
Global.Debugf("error", "input transcript is empty");
return(false);
}
if (image.Dim(0) < PGeti("minheight"))
{
Global.Debugf("error", "input line too small ({0} x {1})", image.Dim(0), image.Dim(1));
return(false);
}
if (image.Dim(1) > PGeti("maxheight"))
{
Global.Debugf("error", "input line too high ({0} x {1})", image.Dim(0), image.Dim(1));
return(false);
}
if (image.Dim(1) * 1.0 / image.Dim(0) > PGetf("maxaspect"))
{
Global.Debugf("warn", "input line has bad aspect ratio ({0} x {1})", image.Dim(0), image.Dim(1));
return(false);
}
CHECK_ARG(image.Dim(0) == cseg.Dim(0) && image.Dim(1) == cseg.Dim(1),
"image.Dim(0) == cseg.Dim(0) && image.Dim(1) == cseg.Dim(1)");
bool use_reject = PGetb("use_reject") && !DisableJunk;
// check and set the transcript
transcript = tr;
SetLine(image_grayscale);
if (PGeti("invert") > 0)
{
NarrayUtil.Sub(NarrayUtil.Max(image), image);
}
for (int i = 0; i < transcript.Length; i++)
{
CHECK_ARG((int)transcript[i] >= 32, "(int)transcript[i] >= 32");
}
// compute correspondences between actual segmentation and
// ground truth segmentation
Narray <Intarray> segments = new Narray <Intarray>();
GrouperRoutine.segmentation_correspondences(segments, segmentation, cseg);
// now iterate through all the hypothesis segments and
// train the classifier with them
int total = 0;
int junk = 0;
for (int i = 0; i < grouper.Object.Length(); i++)
{
Intarray segs = new Intarray();
grouper.Object.GetSegments(segs, i);
// see whether this is a ground truth segment
int match = -1;
for (int j = 0; j < segments.Length(); j++)
{
if (GrouperRoutine.Equals(segments[j], segs))
{
match = j;
break;
}
}
match -= 1; // segments are numbered starting at 1
int c = reject_class;
if (match >= 0)
{
if (match >= transcript.Length)
{
Global.Debugf("error", "mismatch between transcript and cseg: {0}", transcript);
continue;
}
else
{
c = (int)transcript[match];
Global.Debugf("debugmismatch", "index {0} position {1} char {2} [{3}]", i, match, (char)c, c);
}
}
if (c == reject_class)
{
junk++;
}
// extract the character and add it to the classifier
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);
Floatarray v = new Floatarray();
v.Copy(cv);
v /= 255.0;
Global.Debugf("cdim", "character dimensions ({0},{1})", v.Dim(0), v.Dim(1));
total++;
if (use_reject)
{
classifier.Object.XAdd(v, c);
}
else
{
if (c != reject_class)
{
classifier.Object.XAdd(v, c);
}
}
if (c != reject_class)
{
IncClass(c);
}
ntrained++;
}
Global.Debugf("detail", "AddTrainingLine trained {0} chars, {1} junk", total - junk, junk);
return(true);
}
/// <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);
}
/// <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 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 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 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 override void Binarize(Bytearray bin_image, Bytearray gray_image)
{
if (bin_image.Length1d() != gray_image.Length1d())
{
bin_image.MakeLike(gray_image);
}
if (NarrayUtil.contains_only(gray_image, (byte)0, (byte)255))
{
bin_image.Copy(gray_image);
return;
}
int image_width = gray_image.Dim(0);
int image_height = gray_image.Dim(1);
int[] hist = new int[MAXVAL];
double[] pdf = new double[MAXVAL]; //probability distribution
double[] cdf = new double[MAXVAL]; //cumulative probability distribution
double[] myu = new double[MAXVAL]; // mean value for separation
double max_sigma;
double[] sigma = new double[MAXVAL]; // inter-class variance
/* Histogram generation */
for (int i = 0; i < MAXVAL; i++)
{
hist[i] = 0;
}
for (int x = 0; x < image_width; x++)
{
for (int y = 0; y < image_height; y++)
{
hist[gray_image[x, y]]++;
}
}
/* calculation of probability density */
for (int i = 0; i < MAXVAL; i++)
{
pdf[i] = (double)hist[i] / (image_width * image_height);
}
/* cdf & myu generation */
cdf[0] = pdf[0];
myu[0] = 0.0; /* 0.0 times prob[0] equals zero */
for (int i = 1; i < MAXVAL; i++)
{
cdf[i] = cdf[i - 1] + pdf[i];
myu[i] = myu[i - 1] + i * pdf[i];
}
/* sigma maximization
* sigma stands for inter-class variance
* and determines optimal threshold value */
int threshold = 0;
max_sigma = 0.0;
for (int i = 0; i < MAXVAL - 1; i++)
{
if (cdf[i] != 0.0 && cdf[i] != 1.0)
{
double p1p2 = cdf[i] * (1.0 - cdf[i]);
double mu1mu2diff = myu[MAXVAL - 1] * cdf[i] - myu[i];
sigma[i] = mu1mu2diff * mu1mu2diff / p1p2;
}
else
{
sigma[i] = 0.0;
}
if (sigma[i] > max_sigma)
{
max_sigma = sigma[i];
threshold = i;
}
}
for (int x = 0; x < image_width; x++)
{
for (int y = 0; y < image_height; y++)
{
if (gray_image[x, y] > threshold)
{
bin_image[x, y] = (byte)(MAXVAL - 1);
}
else
{
bin_image[x, y] = 0;
}
}
}
if (PGeti("debug_otsu") > 0)
{
Logger.Default.Format("Otsu threshold value = {0}\n", threshold);
//ImgIo.write_image_gray("debug_otsu.png", bin_image);
}
}
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 Binarize(Bytearray bin_image, Bytearray gray_image)
{
w = PGeti("w");
k = (float)PGetf("k");
whalf = w >> 1;
// fprintf(stderr,"[sauvola %g %d]\n",k,w);
if(k<0.001 || k>0.999)
throw new Exception("Binarize: CHECK_ARG(k>=0.001 && k<=0.999)");
if(w==0 || k>=1000)
throw new Exception("Binarize: CHECK_ARG(w>0 && k<1000)");
if(bin_image.Length1d() != gray_image.Length1d())
bin_image.MakeLike(gray_image);
if(NarrayUtil.contains_only(gray_image, (byte)0, (byte)255))
{
bin_image.Copy(gray_image);
return;
}
int image_width = gray_image.Dim(0);
int image_height = gray_image.Dim(1);
whalf = w >> 1;
// Calculate the integral image, and integral of the squared image
Narray<long> integral_image = new Narray<long>(), rowsum_image = new Narray<long>();
Narray<long> integral_sqimg = new Narray<long>(), rowsum_sqimg = new Narray<long>();
integral_image.MakeLike(gray_image);
rowsum_image.MakeLike(gray_image);
integral_sqimg.MakeLike(gray_image);
rowsum_sqimg.MakeLike(gray_image);
int xmin,ymin,xmax,ymax;
double diagsum,idiagsum,diff,sqdiagsum,sqidiagsum,sqdiff,area;
double mean,std,threshold;
for (int j = 0; j < image_height; j++)
{
rowsum_image[0, j] = gray_image[0, j];
rowsum_sqimg[0, j] = gray_image[0, j] * gray_image[0, j];
}
for (int i = 1; i < image_width; i++)
{
for (int j = 0; j < image_height; j++)
{
rowsum_image[i, j] = rowsum_image[i - 1, j] + gray_image[i, j];
rowsum_sqimg[i, j] = rowsum_sqimg[i - 1, j] + gray_image[i, j] * gray_image[i, j];
}
}
for (int i = 0; i < image_width; i++)
{
integral_image[i, 0] = rowsum_image[i, 0];
integral_sqimg[i, 0] = rowsum_sqimg[i, 0];
}
for (int i = 0; i < image_width; i++)
{
for (int j = 1; j < image_height; j++)
{
integral_image[i, j] = integral_image[i, j - 1] + rowsum_image[i, j];
integral_sqimg[i, j] = integral_sqimg[i, j - 1] + rowsum_sqimg[i, j];
}
}
//Calculate the mean and standard deviation using the integral image
for(int i=0; i<image_width; i++){
for(int j=0; j<image_height; j++){
xmin = Math.Max(0,i-whalf);
ymin = Math.Max(0, j - whalf);
xmax = Math.Min(image_width - 1, i + whalf);
ymax = Math.Min(image_height - 1, j + whalf);
area = (xmax-xmin+1)*(ymax-ymin+1);
// area can't be 0 here
// proof (assuming whalf >= 0):
// we'll prove that (xmax-xmin+1) > 0,
// (ymax-ymin+1) is analogous
// It's the same as to prove: xmax >= xmin
// image_width - 1 >= 0 since image_width > i >= 0
// i + whalf >= 0 since i >= 0, whalf >= 0
// i + whalf >= i - whalf since whalf >= 0
// image_width - 1 >= i - whalf since image_width > i
// --IM
if (area <= 0)
throw new Exception("Binarize: area can't be 0 here");
if (xmin == 0 && ymin == 0)
{ // Point at origin
diff = integral_image[xmax, ymax];
sqdiff = integral_sqimg[xmax, ymax];
}
else if (xmin == 0 && ymin > 0)
{ // first column
diff = integral_image[xmax, ymax] - integral_image[xmax, ymin - 1];
sqdiff = integral_sqimg[xmax, ymax] - integral_sqimg[xmax, ymin - 1];
}
else if (xmin > 0 && ymin == 0)
{ // first row
diff = integral_image[xmax, ymax] - integral_image[xmin - 1, ymax];
sqdiff = integral_sqimg[xmax, ymax] - integral_sqimg[xmin - 1, ymax];
}
else
{ // rest of the image
diagsum = integral_image[xmax, ymax] + integral_image[xmin - 1, ymin - 1];
idiagsum = integral_image[xmax, ymin - 1] + integral_image[xmin - 1, ymax];
diff = diagsum - idiagsum;
sqdiagsum = integral_sqimg[xmax, ymax] + integral_sqimg[xmin - 1, ymin - 1];
sqidiagsum = integral_sqimg[xmax, ymin - 1] + integral_sqimg[xmin - 1, ymax];
sqdiff = sqdiagsum - sqidiagsum;
}
mean = diff/area;
std = Math.Sqrt((sqdiff - diff*diff/area)/(area-1));
threshold = mean*(1+k*((std/128)-1));
if(gray_image[i,j] < threshold)
bin_image[i,j] = 0;
else
bin_image[i,j] = (byte)(MAXVAL-1);
}
}
if(PGeti("debug_binarize") > 0) {
ImgIo.write_image_gray("debug_binarize.png", bin_image);
}
}
