/// <summary>
/// Compute a classmap that maps a set of possibly sparse classes onto a dense
/// list of new classes and vice versa
/// </summary>
public static void ClassMap(Intarray out_class_to_index, Intarray out_index_to_class, Intarray classes)
{
int nclasses = NarrayUtil.Max(classes) + 1;
Intarray hist = new Intarray(nclasses);
hist.Fill(0);
for (int i = 0; i < classes.Length(); i++)
{
if (classes[i] == -1) continue;
hist[classes[i]]++;
}
int count = 0;
for (int i = 0; i < hist.Length(); i++)
if (hist[i] > 0) count++;
out_class_to_index.Resize(nclasses);
out_class_to_index.Fill(-1);
out_index_to_class.Resize(count);
out_index_to_class.Fill(-1);
int index = 0;
for (int i = 0; i < hist.Length(); i++)
{
if (hist[i] > 0)
{
out_class_to_index[i] = index;
out_index_to_class[index] = i;
index++;
}
}
CHECK_ARG(out_class_to_index.Length() == nclasses, "class_to_index.Length() == nclasses");
CHECK_ARG(out_index_to_class.Length() == NarrayUtil.Max(out_class_to_index) + 1,
"index_to_class.Length() == Max(class_to_index)+1");
CHECK_ARG(out_index_to_class.Length() <= out_class_to_index.Length(),
"index_to_class.Length() <= class_to_index.Length()");
}
Intarray heapback; // heap[heapback[node]] == node; -1 if not in the heap
#endregion Fields
#region Constructors
/// <summary>
/// Constructor.
/// Create a heap storing node indices from 0 to n - 1.
/// </summary>
public Heap(int n)
{
heap = new Intarray();
heapback = new Intarray(n);
heapback.Fill(-1);
costs = new Floatarray();
}
/// <summary>
/// Merge segments from start to end.
/// </summary>
/// <param name="cseg">Output</param>
/// <param name="rseg">Input</param>
/// <param name="start">start merge position</param>
/// <param name="end">end merge position</param>
public static void rseg_to_cseg(Intarray cseg, Intarray rseg, int start, int end)
{
int maxSegNum = NarrayUtil.Max(rseg);
if (start > end)
{
throw new Exception("segmentation encoded in IDs looks seriously broken!");
}
if (start > maxSegNum || end > maxSegNum)
{
throw new Exception("segmentation encoded in IDs doesn't fit!");
}
Intarray map = new Intarray(maxSegNum + 1);
map.Fill(0);
int color = 1;
for (int i = 1; i <= maxSegNum; i++)
{
map[i] = color;
if (i < start || i >= end)
{
color++;
}
}
cseg.MakeLike(rseg);
for (int i = 0; i < cseg.Length1d(); i++)
{
cseg.Put1d(i, map[rseg.At1d(i)]);
}
}
Floatarray costs; // the cost of the node on the heap
/// <summary>
/// Constructor.
/// Create a heap storing node indices from 0 to n - 1.
/// </summary>
public Heap(int n)
{
heap = new Intarray();
heapback = new Intarray(n);
heapback.Fill(-1);
costs = new Floatarray();
}
public static void rseg_to_cseg(Intarray cseg, Intarray rseg, Intarray ids)
{
Intarray map = new Intarray(NarrayUtil.Max(rseg) + 1);
map.Fill(0);
int color = 0;
for (int i = 0; i < ids.Length(); i++)
{
if (ids[i] == 0)
{
continue;
}
color++;
int start = ids[i] >> 16;
int end = ids[i] & 0xFFFF;
if (start > end)
{
throw new Exception("segmentation encoded in IDs looks seriously broken!");
}
if (start >= map.Length() || end >= map.Length())
{
throw new Exception("segmentation encoded in IDs doesn't fit!");
}
for (int j = start; j <= end; j++)
{
map[j] = color;
}
}
cseg.MakeLike(rseg);
for (int i = 0; i < cseg.Length1d(); i++)
{
cseg.Put1d(i, map[rseg.At1d(i)]);
}
}
public static void segmentation_correspondences(Narray<Intarray> outsegments, Intarray seg, Intarray cseg)
{
if (NarrayUtil.Max(seg) >= 10000)
throw new Exception("CHECK_ARG: (max(seg)<10000)");
if (NarrayUtil.Max(cseg) >= 10000)
throw new Exception("CHECK_ARG: (max(cseg)<10000)");
int nseg = NarrayUtil.Max(seg) + 1;
int ncseg = NarrayUtil.Max(cseg) + 1;
Intarray overlaps = new Intarray(nseg, ncseg);
overlaps.Fill(0);
if (seg.Length() != cseg.Length())
throw new Exception("CHECK_ARG: (seg.Length()==cseg.Length())");
for (int i = 0; i < seg.Length(); i++)
overlaps[seg.At1d(i), cseg.At1d(i)]++;
outsegments.Clear();
outsegments.Resize(ncseg);
for (int i = 0; i < nseg; i++)
{
int j = NarrayRowUtil.RowArgMax(overlaps, i);
if (!(j >= 0 && j < ncseg))
throw new Exception("ASSERT: (j>=0 && j<ncseg)");
if (outsegments[j] == null)
outsegments[j] = new Intarray();
outsegments[j].Push(i);
}
}
public void Clear()
{
_keys.Fill(0);
_keys.Clear();
_values.Fill(0f);
_values.Clear();
_len = 0;
}
/// <summary>
/// Remove segments from start to end.
/// </summary>
/// <param name="cseg">Output</param>
/// <param name="rseg">Input</param>
/// <param name="start">start remove position</param>
/// <param name="end">end remove position</param>
public static void rseg_to_cseg_remove(Intarray cseg, Intarray rseg,
Bytearray outimg, Bytearray img, int start, int end)
{
int maxSegNum = NarrayUtil.Max(rseg);
if (start > end)
{
throw new Exception("segmentation encoded in IDs looks seriously broken!");
}
if (start > maxSegNum || end > maxSegNum)
{
throw new Exception("segmentation encoded in IDs doesn't fit!");
}
if (rseg.Length1d() != img.Length1d())
{
throw new Exception("rseg and img must have same a dimension!");
}
Intarray map = new Intarray(maxSegNum + 1);
map.Fill(0);
int color = 1;
for (int i = 1; i <= maxSegNum; i++)
{
map[i] = color;
if (i < start || i > end)
{
color++;
}
else
{
map[i] = 0;
}
}
cseg.MakeLike(rseg);
outimg.Copy(img);
for (int i = 0; i < cseg.Length1d(); i++)
{
int val = rseg.At1d(i);
cseg.Put1d(i, map[val]);
if (val > 0 && map[val] == 0)
{
outimg.Put1d(i, 255);
}
}
}
/// <summary>
/// Compute a classmap that maps a set of possibly sparse classes onto a dense
/// list of new classes and vice versa
/// </summary>
public static void ClassMap(Intarray out_class_to_index, Intarray out_index_to_class, Intarray classes)
{
int nclasses = NarrayUtil.Max(classes) + 1;
Intarray hist = new Intarray(nclasses);
hist.Fill(0);
for (int i = 0; i < classes.Length(); i++)
{
if (classes[i] == -1)
{
continue;
}
hist[classes[i]]++;
}
int count = 0;
for (int i = 0; i < hist.Length(); i++)
{
if (hist[i] > 0)
{
count++;
}
}
out_class_to_index.Resize(nclasses);
out_class_to_index.Fill(-1);
out_index_to_class.Resize(count);
out_index_to_class.Fill(-1);
int index = 0;
for (int i = 0; i < hist.Length(); i++)
{
if (hist[i] > 0)
{
out_class_to_index[i] = index;
out_index_to_class[index] = i;
index++;
}
}
CHECK_ARG(out_class_to_index.Length() == nclasses, "class_to_index.Length() == nclasses");
CHECK_ARG(out_index_to_class.Length() == NarrayUtil.Max(out_class_to_index) + 1,
"index_to_class.Length() == Max(class_to_index)+1");
CHECK_ARG(out_index_to_class.Length() <= out_class_to_index.Length(),
"index_to_class.Length() <= class_to_index.Length()");
}
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 static void segmentation_correspondences(Narray <Intarray> outsegments, Intarray seg, Intarray cseg)
{
if (NarrayUtil.Max(seg) >= 10000)
{
throw new Exception("CHECK_ARG: (max(seg)<10000)");
}
if (NarrayUtil.Max(cseg) >= 10000)
{
throw new Exception("CHECK_ARG: (max(cseg)<10000)");
}
int nseg = NarrayUtil.Max(seg) + 1;
int ncseg = NarrayUtil.Max(cseg) + 1;
Intarray overlaps = new Intarray(nseg, ncseg);
overlaps.Fill(0);
if (seg.Length() != cseg.Length())
{
throw new Exception("CHECK_ARG: (seg.Length()==cseg.Length())");
}
for (int i = 0; i < seg.Length(); i++)
{
overlaps[seg.At1d(i), cseg.At1d(i)]++;
}
outsegments.Clear();
outsegments.Resize(ncseg);
for (int i = 0; i < nseg; i++)
{
int j = NarrayRowUtil.RowArgMax(overlaps, i);
if (!(j >= 0 && j < ncseg))
{
throw new Exception("ASSERT: (j>=0 && j<ncseg)");
}
if (outsegments[j] == null)
{
outsegments[j] = new Intarray();
}
outsegments[j].Push(i);
}
}
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 FindAllCuts()
{
int w = wimage.Dim(0), h = wimage.Dim(1);
// initialize dimensions of cuts, costs etc
cuts.Resize(w);
cutcosts.Resize(w);
costs.Resize(w, h);
sources.Resize(w, h);
costs.Fill(1000000000);
for (int i = 0; i < w; i++)
{
costs[i, 0] = 0;
}
sources.Fill(-1);
limit = where;
direction = 1;
Step(0, w, 0);
for (int x = 0; x < w; x++)
{
cutcosts[x] = costs[x, where];
cuts[x] = new Narray <Point>();
cuts[x].Clear();
// bottom should probably be initialized with 2*where instead of
// h, because where cannot be assumed to be h/2. In the most extreme
// case, the cut could go through 2 pixels in each row
Narray <Point> bottom = new Narray <Point>();
int i = x, j = where;
while (j >= 0)
{
bottom.Push(new Point(i, j));
i = sources[i, j];
j--;
}
//cuts(x).resize(h);
for (i = bottom.Length() - 1; i >= 0; i--)
{
cuts[x].Push(bottom[i]);
}
}
costs.Fill(1000000000);
for (int i = 0; i < w; i++)
{
costs[i, h - 1] = 0;
}
sources.Fill(-1);
limit = where;
direction = -1;
Step(0, w, h - 1);
for (int x = 0; x < w; x++)
{
cutcosts[x] += costs[x, where];
// top should probably be initialized with 2*(h-where) instead of
// h, because where cannot be assumed to be h/2. In the most extreme
// case, the cut could go through 2 pixels in each row
Narray <Point> top = new Narray <Point>();
int i = x, j = where;
while (j < h)
{
if (j > where)
{
top.Push(new Point(i, j));
}
i = sources[i, j];
j++;
}
for (i = 0; i < top.Length(); i++)
{
cuts[x].Push(top[i]);
}
}
// add costs for line "where"
for (int x = 0; x < w; x++)
{
cutcosts[x] += wimage[x, where];
}
}
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 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));*/
}
/// <summary>
/// Output the segmentation into a segmentation graph.
/// Construct a state for each of the segments, then
/// add transitions between states (segments)
/// from min(segments[i]) to max(segments[i])+1.
/// </summary>
public override void GetLattice(IGenericFst fst)
{
fst.Clear();
int final = NarrayUtil.Max(labels) + 1;
Intarray states = new Intarray(final + 1);
states.Fill(-1);
for (int i = 1; i < states.Length(); i++)
{
states[i] = fst.NewState();
}
fst.SetStart(states[1]);
fst.SetAccept(states[final]);
for (int i = 0; i < boxes.Length(); i++)
{
int start = NarrayUtil.Min(segments.At1d(i));
int end = NarrayUtil.Max(segments.At1d(i));
int id = (start << 16) + end;
if (segments.At1d(i).Length() == 0)
{
id = 0;
}
float yes = spaces[i, 0];
float no = spaces[i, 1];
// if no space is set, assume no space is present
if (yes == float.PositiveInfinity && no == float.PositiveInfinity)
{
no = 0.0f;
}
for (int j = 0; j < class_costs[i].Length(); j++)
{
float cost = class_costs[i][j];
string str = class_outputs[i][j];
int n = str.Length;
int last = start;
for (int k = 0; k < n; k++)
{
int c = (int)str[k];
if (k < n - 1)
{
// add intermediate states/transitions for all but the last character
states.Push(fst.NewState());
fst.AddTransition(states[last], states.Last(), c, 0.0f, 0);
last = states.Length() - 1;
}
else
{
// for the last character, handle the spaces as well
if (no < 1000.0f)
{
// add the last character as a direct transition with no space
fst.AddTransition(states[last], states[end + 1], c, cost + no, id);
}
if (yes < 1000.0f)
{
// insert another state to handle spaces
states.Push(fst.NewState());
int space_state = states.Last();
fst.AddTransition(states[start], space_state, c, cost, id);
fst.AddTransition(space_state, states[end + 1], (int)' ', yes, 0);
}
}
} // for k
} // for j
} // for i
}
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));*/
}