have any one code in c# for money recognition

Question

1.50/5 (5 votes)

See more:

all details and problem about my project
my project is money recognition by mobile (android)
the mobile (client )is capture image and send it to computer (server)
in server i used open cv library (C#) the SURF algorithm
this is algorithm input to image (modelimage,observableimage) and it is searching
modelimage at observableimage
now my problem is
i have 10 image (modelimage) i want ((condition)) if first modelimage not found in observableimage return false and try with second modelimage and do this until find modelimage(any one ) in observableimage and return true
after that send number image (1,2,3.....) to mobile for say 10,50,100,.....
please noted all processes do on computer(server)
this is my code

XML

//extract features from the object image
      modelKeyPoints = surfCPU.DetectKeyPointsRaw(modelImage, null);
      Matrix<float> modelDescriptors = surfCPU.ComputeDescriptorsRaw(modelImage, null, modelKeyPoints);

      watch = Stopwatch.StartNew();

      // extract features from the observed image
      observedKeyPoints = surfCPU.DetectKeyPointsRaw(observedImage, null);
      Matrix<float> observedDescriptors = surfCPU.ComputeDescriptorsRaw(observedImage, null, observedKeyPoints);
      BruteForceMatcher<float> matcher = new BruteForceMatcher<float>(DistanceType.L2);
      matcher.Add(modelDescriptors);

      indices = new Matrix<int>(observedDescriptors.Rows, k);
      using (Matrix<float> dist = new Matrix<float>(observedDescriptors.Rows, k))
      {
         matcher.KnnMatch(observedDescriptors, indices, dist, k, null);
         mask = new Matrix<byte>(dist.Rows, 1);
         mask.SetValue(255);
         Features2DToolbox.VoteForUniqueness(dist, uniquenessThreshold, mask);
      }

      int nonZeroCount = CvInvoke.cvCountNonZero(mask);
      if (nonZeroCount >= 4)
      {
         nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints, indices, mask, 1.5, 20);
         if (nonZeroCount >= 4)
            homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints, observedKeyPoints, indices, mask, 2);
      }

      watch.Stop();
   }

   //Draw the matched keypoints
   Image<Bgr, Byte> result = Features2DToolbox.DrawMatches(modelImage, modelKeyPoints, observedImage, observedKeyPoints,
      indices, new Bgr(255, 255, 255), new Bgr(255, 255, 255), mask, Features2DToolbox.KeypointDrawType.DEFAULT);

   #region draw the projected region on the image
   if (homography != null)
   {  //draw a rectangle along the projected model
      Rectangle rect = modelImage.ROI;
      PointF[] pts = new PointF[] {
         new PointF(rect.Left, rect.Bottom),
         new PointF(rect.Right, rect.Bottom),
         new PointF(rect.Right, rect.Top),
         new PointF(rect.Left, rect.Top)};
      homography.ProjectPoints(pts);

      result.DrawPolyline(Array.ConvertAll<PointF, Point>(pts, Point.Round), true, new Bgr(Color.Red), 5);
   }
   #endregion

   matchTime = watch.ElapsedMilliseconds;

   return result;
}

Posted 17-Apr-14 20:24pm

Member 10757783

Updated 21-Apr-14 4:13am

v5

Add a Solution

Comments

Member 10757783 18-Apr-14 2:26am

i read question about money bill recognition but i did not find any thing useful for my
i use object detection not OCR
and thank you again

Tadit Dash (ତଡିତ୍ କୁମାର ଦାଶ) 18-Apr-14 3:45am

First of all, you need to explain what techniques or algorithms you have tried already. That would give us some idea about your problems. So, please Improve your Question and add more information.

Member 10757783 20-Apr-14 5:02am

okI use open cv library with c#
and the algorithm name is surf for detect object
and now i stopped on one thing
tomorrow i will put here my code program and my problem and all details
thank you very much

Tadit Dash (ତଡିତ୍ କୁମାର ଦାଶ) 20-Apr-14 5:10am

Ok.

Member 10757783 21-Apr-14 9:24am

all details and problem about my project
my project is money recognition by mobile (android)
the mobile (client )is capture image and send it to computer (server)
in server i used open cv library (C#) the SURF algorithm
this is algorithm input to image (modelimage,observableimage) and it is searching
modelimage at observableimage
now my problem is
i have 10 image (modelimage) i want ((condition)) if first modelimage not found in observableimage return false and try with second modelimage and do this until find modelimage(any one ) in observableimage and return true
after that send number image (1,2,3.....) to mobile for say 10,50,100,.....
please noted all processes do on computer(server)

Tadit Dash (ତଡିତ୍ କୁମାର ଦାଶ) 21-Apr-14 9:36am

Please add this to the Question by clicking on "Improve Question" link.

Member 10757783 21-Apr-14 10:08am

ok sorry and thank you

Tadit Dash (ତଡିତ୍ କୁମାର ଦାଶ) 22-Apr-14 0:24am

Welcome. :)

cigwork 18-Apr-14 5:11am

What about colour analysis? In the UK and those European countries using the Euro the currency notes are of different colours. So one possible solution might be to take the bitmap containing the image of the note and work out its average colour (most non white pixels of a specific colour of all colours found perhaps?) and compare the value with previously determined reference values. If you want to cope with multiple currencies then if reference colour values are grouped by locale it should be possible to offer the most likely identification of a note based on current locale in the case where notes from different countries have the same reference colour.

Something as crude as this should work reasonably quickly without needing a round-trip to the server. You could fall back to a server to request an update of reference colour values should you encounter an average colour value not held locally.

Alternatively you could provide the application with a training mode. Present it with a series of notes and let it work out the reference values for each note for itself. This would take account of vagaries in the image quality of individual device cameras and allow a user (with help from a sighted friend) to set up the app. for any currencies that he or she commonly uses. The application then becomes self supporting.

Of course none of this will work for coins nor for currencies like the U.S. dollar which have notes of a uniform colour.

Member 10757783 20-Apr-14 5:03am

first thing thank you for answer my question
then i am use the open CV library in C# SURF algorithm
i write code to extraction the feature from image (small image)
and search it in big image (main image)
but my problem is .
i have 10 key point vector
i want ((condition)), if first key point vector not found it in big image (main image)
return false and try again with second key point vector and do this until return true
and return money name (100,50,.....)
if you want my code tell my to put it here

thatraja 21-Apr-14 8:04am

Update your question with more details like code, etc.,

Member 10757783 21-Apr-14 10:09am

//extract features from the object image
modelKeyPoints = surfCPU.DetectKeyPointsRaw(modelImage, null);
Matrix<float> modelDescriptors = surfCPU.ComputeDescriptorsRaw(modelImage, null, modelKeyPoints);

watch = Stopwatch.StartNew();

// extract features from the observed image
observedKeyPoints = surfCPU.DetectKeyPointsRaw(observedImage, null);
Matrix<float> observedDescriptors = surfCPU.ComputeDescriptorsRaw(observedImage, null, observedKeyPoints);
BruteForceMatcher<float> matcher = new BruteForceMatcher<float>(DistanceType.L2);
matcher.Add(modelDescriptors);

indices = new Matrix<int>(observedDescriptors.Rows, k);
using (Matrix<float> dist = new Matrix<float>(observedDescriptors.Rows, k))
{
matcher.KnnMatch(observedDescriptors, indices, dist, k, null);
mask = new Matrix<byte>(dist.Rows, 1);
mask.SetValue(255);
Features2DToolbox.VoteForUniqueness(dist, uniquenessThreshold, mask);
}

int nonZeroCount = CvInvoke.cvCountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints, indices, mask, 1.5, 20);
if (nonZeroCount >= 4)
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints, observedKeyPoints, indices, mask, 2);
}

watch.Stop();
}

//Draw the matched keypoints
Image<bgr, byte=""> result = Features2DToolbox.DrawMatches(modelImage, modelKeyPoints, observedImage, observedKeyPoints,
indices, new Bgr(255, 255, 255), new Bgr(255, 255, 255), mask, Features2DToolbox.KeypointDrawType.DEFAULT);

#region draw the projected region on the image
if (homography != null)
{ //draw a rectangle along the projected model
Rectangle rect = modelImage.ROI;
PointF[] pts = new PointF[] {
new PointF(rect.Left, rect.Bottom),
new PointF(rect.Right, rect.Bottom),
new PointF(rect.Right, rect.Top),
new PointF(rect.Left, rect.Top)};
homography.ProjectPoints(pts);

result.DrawPolyline(Array.ConvertAll<PointF, Point>(pts, Point.Round), true, new Bgr(Color.Red), 5);
}
#endregion

matchTime = watch.ElapsedMilliseconds;

return result;
}

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)