private void DoTestRecognize(LenetClassifier classifier)
{
OutputVector ov = new OutputVector();
Floatarray v = new Floatarray();
Bytearray ba = new Bytearray(1, 1);
ImgIo.read_image_gray(ba, testPngFileName);
NarrayUtil.Sub(255, ba);
v.Copy(ba);
v /= 255.0;
classifier.XOutputs(ov, v);
Console.WriteLine("Featured output class '{0}', score '{1}'", (char)ov.Key(ov.BestIndex), ov.Value(ov.BestIndex));
}
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");*/
}
/// <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>
/// 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);
}